CN101918958A - System and method for compressing video based on detected intraframe motion - Google Patents

Abstract

A system and method are described below for encoding interactive low-latency video using interframe coding. For example, one embodiment of a computer-implemented method for performing video compression comprises: logically subdividing each of a sequence of images into a plurality of tiles, each of the tiles having a defined position within each of the sequence of images, the defined position remaining the same between successive images; detecting motion within the sequence of images occurring at each of the positions of each of the tiles; and encoding each tile within each image of the sequence of images using a first compression format or a second compression format, wherein the frequency at which a particular tile is encoded according to the first compression format across the sequence of images is based on the detected amount of motion at the position of that tile across the sequence of images.

Description

The system and method that is used for compressed video based on the intraframe motion that detects

Related application

The application be that submitted on Dec 10th, 2002, that be entitled as " device and method (Apparatus and Method for Wireless Video Gaming) that is used for the wireless video recreation ", the 10/315th, No. 460 part continues (CIP) application, and this application has transferred the assignee of this CIP application.

Technical field

The disclosure relates generally to the field of the data handling system of the ability of improving user's operation and access audio and video medium.

Background technology

Since Thomas Edison (Thomas Edison) since the epoch, the audio frequency of record and film media have become the one side of society.Early in the twentieth century, audio frequency media of record (magnetic post and disc) and film media (jukebox and film) be distribution extensively, but two kinds of technology still are in its starting stage.In the later stage twenties 20th century, on the basis of general marketplace,, afterwards color film and audio frequency are made up film and audio frequency combination.Radio broadcasting develops into the broadcasting general marketplace audio frequency media of the form of supporting advertisement to a great extent gradually.When setting up TV (TV) broadcast standard in the mid-40 in 20th century, TV engages with the form of radio with broadcasting general marketplace medium, thereby film precedence record or live is brought in the family.

Till mid-term in 20th century, most of American family had the audio frequency media that is used to play record disc player (phonograph record player), be used to receive the wireless device of live broadcast audio, and be used to play the televisor of live broadcast audio/video (A/V) medium.Usually described 3 " media players " (disc player, wireless device and TV) is combined in the cabinet of total public loudspeaker, becomes " media center " of family.Although the medium selection is limited for consumers, medium " ecosystem " are highly stable.Most consumers is known the four corner that how to use " media player " and can enjoy its ability.Simultaneously, the publisher of medium (mostly be film and television operations chamber greatly, and music company) can give cinema and family with its media distribution, and do not suffer pirate widely or " secondary sale " (yet promptly, having used the sale again of medium).Usually, publisher can not sell from secondary and obtain income, and therefore, secondary is sold and reduced the income that publisher obtains from the buyer that can oneself use medium originally for new sale.Although 20th century interim period have the disc that used really and sell, but described sale can not have big influence to disc publisher, because be different from film or video frequency program (its watched once by the adult usually or only for several times), music track can be listened to hundreds of times or even thousands of times.Therefore, music media is more than movie/video medium " prolonged " (also promptly, for the consumer that grows up, it has lasting value).In case bought disc, if the consumer likes this music, then the consumer may keep it for a long time.

From mid-term in 20th century till now, the medium ecosystem has all experienced a series of radical changes for the interests of consumer and publisher and loss.Under the situation of the extensive introducing of audio sound-recording machine (especially having the stereosonic magnetic tape cassette of high-quality), the consumer's facility that truly has higher degree.But it also indicates the beginning of consumer's medium practice-piracy widely now.Really, many consumers for using for the purpose of the facility magnetic tape cassette to record its own disc, duplicate but the consumer who increases day by day (for example, preparing the student of access disc collection each other in the dormitory) will carry out piracy purely.And the consumer will record the music via radio play, but not buy disc or tape from publisher.

The appearance of consumer VCR causes the more consumers facility, because VCR is set to write down the TV program now, it can be watched in time after a while, and VCR also causes the foundation of video rental industry, and wherein the design of film and TV program can be at " program request " basic enterprising line access.The quick exploitation of the general marketplace home media equipment since 20th century the mid-80s has caused consumer's unprecedented selection and convenience degree, and also causes medium to publish the Rapid Expansion in market.

Now, the consumer faced multimedia and selected and crossed multimedia equipment, wherein many medium or specific publishers that are bound to particular form.The media consumer's of making earnest efforts may be connected to a heaping equipment TV and the computing machine in each room, house, causes " mouse nest formula " cable and a group Long-distance Control to one or more televisor and/or personal computer (PC).(in the application's context, term " personal computer " or " PC " refer to the computing machine that is suitable for any kind of that uses in family or office) comprises desk-top computer, Macintosh (Macintosh machine)

Or other non-Windows (form) computing machine, the equipment compatible, Unix variant, notebook etc.) with Windows.Described equipment can comprise that video game console, VCR, DVD player, Audio Loop are around sound effect processor/amplifier, satellite set top box, cable tv set-top box etc.In addition, for the consumer who makes earnest efforts, may there be the equipment of a plurality of similar functions owing to consistency problem.For example, the consumer may have HD-DVD and blue light (Blu-ray) DVD player, or Microsoft Xbox (Microsoft's home game machine)

With Sony Playstation (game station of Sony)

Video game system both.In fact and since some stride the game console version the incompatibility of recreation, the consumer may have XBox and after a while version (such as, Xbox360

) both.Frequently, the consumer is for using which video inputs and which far-end to be puzzled.Even at the video that laser disc is placed in the correct player (for example, DVD, HD-DVD, blue light, Xbox or Playstation), selects to be used for this equipment and audio input end and find that after the correct Long-distance Control, the consumer still faces technological challenge.For example, under the situation of widescreen DVD, the user may need at first to determine correct aspect ratio (for example, 4: 3, fully, amplification, wide amplification, cinema be wide etc.) and then set correct aspect ratio on its TV or monitor screen.Similarly, the user may need at first to determine that correct Audio Loop is around sound effect system form (for example, AC-3, Dolby Digital, DTS etc.) and then set correct Audio Loop around the sound effect system form.Often, the consumer do not recognize media content under its whole abilities of may not enjoying its TV or audio system (for example, watch film with wrong aspect ratio extruding, or listen to stereosonic audio frequency but not around the audio frequency of audio).

Increase ground day by day, will add in the storehouse of equipment with media device based on the internet.Similar Sonos (George Soros)

The audio frequency apparatus of digital music system makes audio frequency directly from the internet mobile (stream).Similarly, similar Slingbox ^TM(look Lingbao City ^TM) the amusement player the equipment records video and it is flowed or via flowing and go out in the internet via home network, wherein can be on PC this video of remote watching.And IPTV (IPTV) service connects via Digital Subscriber Line (DSL) or other home interconnect nets and the service of analogous cable TV is provided.Recently also make great efforts a plurality of media functions are incorporated into individual equipment (such as, Moxi (Moses)

The PC of media center and execution Windows XP media center version) in.Although each equipment in the described equipment provides a bit convenient to the function of its execution, each equipment lacks the general and simple access to most of medium.In addition, usually owing to expensive processing and/or the local needs that store make described equipment often cost make for hundreds of dollars.In addition, the consumer electronics in described modern times usually consumes a large amount of electric power, even also consumes a large amount of electric power when idle, this meaning its along with the time costliness and wasting energy more.For example, switch to the different video input end if the consumer forgets with the equipment cut-out or with it, then this equipment may continue operation.In addition, because neither one equipment is solution completely in the middle of the described equipment, so the storehouse of other equipment in itself and the family must be combined, this still stays mouse nest formula line and many Long-distance Control to the user.

In addition, when many newer equipment based on the internet were suitably worked, it provided the medium of updating currently form (comparing with the form that its script possibility is available) usually.For example, make the equipment that video flows via the internet that audio-visual-materials are flowed, and interactive " extra items " of usually following DVD flowed, as " making ", recreation or director's comment of video.This is due to the fact that interactive material often is to make with specific format, and this specific format is intended to be used at the interactive particular device of this locality processing.For example, each has the specific interactive form of himself in DVD, HD-DVD and the Blu-ray Disc.Any home media equipment or local computer (its may through exploitation to support all popular format) will need to a certain degree tip property (sophistication) and dirigibility, and it may be for consumer's operation speech costliness and complicated too.

This problem is increased the weight of, if introducing format in the future after a while, then local device may not have the hardware capabilities of supporting format, and this will mean that the consumer will buy the local media equipment of upgrading.For example, if (for example introduce the video of high-resolution or three-dimensional video-frequency on after a while date, video flowing of each eye), then local device may not have the computing power of this video of decoding, or it (for example may not have the hardware that is used for exporting this video with format, suppose by realizing stereoscopic vision with the synchronous 120fps video of shading eyeglasses (shuttered glassess), wherein 60fps is sent to each eye, if consumer's vision hardware only can be supported the 60fps video, then this option under the situation that the hardware that lacks upgrading is bought with unavailable).

When referring to most advanced and sophisticated interactive medium (especially video-game), media device problem discarded and complexity is serious problems.

Modern video games is used and is divided into four main non-portable formula hardware platform: SonyPlayStation basically

1,2 and 3 (PS1, PS2, and PS3); Microsoft Xbox

And Xbox360

And Nintendo Gamecube (Nintendo's sugar cube)

And Wii ^TMAnd based on the recreation of PC.In the described platform each is different from other persons, makes to be write with the recreation of carrying out on a platform can not carry out on another platform usually.The consistency problem that also may have generation equipment and equipment of future generation.Even most of software game developers set up the software game that is independent of particular platform and designs, in order on particular platform, to carry out particular game, also need proprietary software layer (it often is called as " development of games engine " ") to adjust recreation on particular platform, to use.Each platform is sold to the consumer with the form of " control desk " (also promptly, being attached to the off line box (standalone box) of TV or monitor/loudspeaker) or itself is PC.Usually, video-game is sold on the optical media such as blue-ray DVD, DVD-ROM or CD-ROM, and this optical media contains the video-game that is presented as most advanced and sophisticated real-time software application program.Along with family's broadband speeds increases, video-game becomes just day by day and can be used for downloading.

The real-time and the high calculation requirement of playing owing to advanced video make the realization and the singularity of the platform compatibility of video game software require extreme harshness.For example, a people from generation video-game to video-game of future generation (for example may expect, from XBox to XBox 360, or from Playstation 2 (" PS2 ") to Playstation 3 (" PS3 ")) recreation compatibility fully, as the general compatibility that has yield-power application program (for example, MicrosoftWord (Microsoft's word processor)) from a PC to another PC with faster treatment unit or core.Yet, be not to be this situation for video-game.Because when the video-game of a distribution generation, video game manufacturers is sought the high likelihood energy for given price point usually, change so often system is carried out dynamic schema, can not worked in the generation system after a while so that write with the many recreation that are used for the former generation system.For example, XBox is based on the x86 series processors, and XBox360 is based on PowerPC series.

Can utilize technology to imitate previous framework, but the supposition video-game is a real-time application, it is usually unrealistic then to reach identical behavior in imitation.This is the loss to consumer, video game console manufacturer and video game software publisher.For consumers, this means old generation video game console and new generation video game console maintenance are switched to TV so that can play the necessity of all recreation.For control desk manufacturer, this means with the imitation of new control desk to reach the relevant cost of employing more slowly.And for publisher, this means may must issue a plurality of versions of new game so that (for example contain each trade mark that all potential consumers-not only issue are used for video-game, XBox, Playstation) version, and usually distribution is used for the version of each version (for example, PS2 and PS3) of given trade mark.The independent version of " the mad rugby 08 " of the electric company limited of exploitation skill for example, (Electronic Arts) is to be used for XBox, XBox 360, PS2, PS3, Gamecube, Wii and PC platform and other platforms.

Portable set (such as, mobile phone and portable electronic device) also the game developer is challenged.Increase ground day by day, described equipment is connected to radio data network and can foradownloaded video plays.But, have multiple mobile phone and media device in the market with multiple different display resolution and computing power.And, because described equipment has power consumption, cost and weight constraints usually, so it usually lacks the advanced figure accelerating hardware that is similar to Graphics Processing Unit (" GPU ") (such as, the equipment of being made by the NVIDIA (the tall and handsome company that reaches) of the Santa Clara of California, USA).Therefore, the common exploitation of Games Software developer is used for the given game title of many dissimilar portable sets simultaneously.The user can find: given game title is not useable for its specific mobile phone or portable electronic device.

Under the situation of family's game console, hardware platform manufacturer collects the royalty that is used for the ability of issue recreation on its platform to the software game developer usually.The mobile phone wireless communications carriers is also collected to recreation publisher usually and is used for the royalty of game download to mobile phone.Under the situation of PC recreation, do not exist to be used to issue the royalty that recreation is paid, but owing to be used to support multiple PC configuration and the higher consumer of the installation question that may cause serves and bears that to make that the game developer faces usually expensive.And the piracy of the common less obstruction Games Software of PC is because it can and more easily be assigned with (for example, via the internet) more easily by piracy by the user's reprogramming of being proficient in technology and recreation at an easy rate.Therefore, for the software game developer, distribution has cost and disadvantage on game console, mobile phone and PC.

For the recreation publisher of control desk and PC software, cost more than that.In order to play via the retail channel allocation, publisher collects the wholesale price that is lower than commercial value so that the retailer has rate of profit to the retailer.Publisher also must pay the cost of making and distributing the physical medium of preserving recreation usually.The retailer often also to publisher collect " price protection expense " with contain possible accidental cost (such as, recreation can not sold, or the price of recreation reduces, or the retailer must return some or all wholesale prices and/or regain recreation from the buyer).In addition, the retailer also collects the expense that is used for helping to sell in flyer recreation to publisher usually.In addition, the retailer buys the play of migrating from the user who has played recreation with increasing day by day, and then described recreation is sold with used recreation, does not share the income of used recreation with recreation publisher usually.The following fact has increased the cost burden that imposes on recreation publisher: recreation is usually by via the Internet piracy and distribute for user's download and freely duplicate.

Along with increase of internet broadband speed and broadband connection become more extensive (more specifically, to family with to " Internet bar " of leasing the PC that is connected the internet) in the U.S. and the whole world, recreation is assigned to PC or control desk more via download.And broadband connection is used for playing many people and MMOG (both are referred to by initialism " MMOG " in the disclosure for this) more.These changes have alleviated and relevant some costs and the problem of retail distribution.Download some disadvantages that game on line has solved recreation publisher, because apportioning cost is less usually and exist less or do not have the cost of not selling medium.But the recreation of having downloaded is still by piracy, and downloads owing to its size (size usually is tens bytes) makes it may spend the very long time.In addition, a plurality of recreation can be filled the minidisk driver, for example together with portable computer or those disc drivers of selling together with video game console.Yet, need online connection so that with regard to the degree that recreation can be played, problem of piracy is alleviated, because need the user to have effective user account usually with regard to recreation or MMOG.Being different from can be by the video of camera filmed display screen or the linear media (for example, video and music) that is duplicated from the audio frequency of loudspeaker by the microphone record, and it is unique that each video-game is experienced, and can not use simple video/audio record to duplicate.Therefore, even carry out in the Copyright Law and the pirate rampant zone, also can protect MMOG to avoid, thereby can support commerce by piracy powerful.For example, successfully dispose " World of Warcraft " MMOG of Vivendi SA (Vivendi Universal Games company), and do not suffer piracy in the whole world.And many online or MMOG recreation (such as, " second life " MMOG of Linden Lab (woods steps on the laboratory)) by building the income that economic model in the recreation produces recreation operator in, wherein assets can be used online tool and bring, sell and even set up.Therefore, can use the mechanism except that traditional game software is bought or subscribed to pay as the use of game on line.

Although usually can alleviate piracy owing to the character of online or MMOG makes, game on line operator still faces all the other challenges.Many recreation need a large amount of this locality (also promptly, in the family) processing resources suitably to work for online or MMOG.If the local computer (for example, not having the computing machine of GPU, such as the low-end notebook computing machine) that the user has low performance, then it may not play this recreation.In addition, along with game console is aging, it far lags behind present state of the art and may not handle more senior recreation.Even supposition user's local PC can handle the calculation requirement of recreation, usually also exist complexity is installed.May there be driver incompatibility (for example, if download new game, the graphdriver of redaction may be installed then, it causes the previous mounted recreation that depends on the legacy version graphdriver to operate).Along with downloading more recreation, control desk may use up local disk space.When finding defective and repairing or if recreation has been carried out revising (for example, if the game developer finds that the rank of playing is too difficult and plays or play too easily), complicated recreation receives the patch (patch) of download usually as time passes from the game developer.This patch needs new download.But be not the download that all users finish all patches sometimes.Other the time, the patch of download is introduced other compatibilities or disk space consumption problem.

And, during game play, may need big data to download so that figure or behavioural information are provided to local PC or control desk.For example,, and run into scene or the personage who forms or have disabled behavior on user's local machine by graph data if the user enters in the room among the MMOG, then must that scene of download or personage's data.If Internet connection is fast inadequately, then this can cause the essence between game play session to postpone.In addition, if the scene or the personage that are run into need surpass local PC or the storage area of control desk or the storage area or the computing power of computing power, then it can produce following situation: wherein the user can not continue in recreation, or must continue with the figure that quality reduces.Therefore, online or MMOG recreation usually limits its storage and/or computation complexity requirement.In addition, it usually limits the amount that the data during the recreation transmit.Online or MMOG recreation also can make the user's that can play games market narrow down.

In addition, the user who is proficient in technology carries out reverse engineering and revises recreation so that they can practise fraud the local duplicate of recreation more and more.Cheating may with carry out equally simpler than push (for example, for shooting) very apace with the possible fireballing repeat knob of manpower.In supporting recreation in the recreation of transaction in assets, cheating can reach the swindle degree that causes bogus transaction to relate to having the assets that real economy is worth.When online or MMOG economic model during based on described transaction in assets, this can cause the harmful consequence of the essence of recreation operator.

The cost of exploitation new game can be made more and more most advanced and sophisticated recreation (for example, have figure more true to nature (such as, ray tracing in real time), and behavior more true to nature (such as, physics emulation in real time)) along with PC and control desk and increase.Early stage in video-game industry, the video-game exploitation is a very similarly process of application software exploitation; Also promptly, most of cost of development (compare with the exploitation of figure, audio frequency and behavioral primitive or " assets ") in the exploitation of software, such as those software developments that can be developed with the film that is used to have extensive special-effect.Now, the video-game development at many tips more is similar to the film exploitation that is rich in special efficacy than software development.For example, many video-games provide the emulation in the 3-D world, and produce personage, stage property and the environment of true more (also promptly, seeming and the same computer graphical true to nature of outdoor scene (live action) image of photographing and taking).In the tool challenge aspect of the development of games that photo is equally true to nature one is for creating people's face that the computing machine that can not be different from outdoor scene people face produces.The face capture technology (such as, by the Contour of the Mova exploitation of the San Francisco of California ^TM(profile ^TM) the authenticity capture systems) catch performing artist's precise geometry of face and the precise geometry of when the performing artist is in the motion, following the trail of performing artist's face with high resolving power.This technology allows to reproduce the 3D face on PC or game console, and in fact this 3D face can not be different from the outdoor scene face of being caught.Accurately catching and reproducing " photo is equally true to nature " people's face is useful in many aspects.At first, highly discernible famous person or sportsman usually are used for video-game (usually being employed by expensive), and imperfection is may be for the user apparent, thereby viewing experience (viewing experience) is divert one's attention or make us unhappy.Frequently, need high degree of detail to realize that the same sense true to nature of photo of height-need potentially reproduces a large amount of polygons and high resolving power texture (connecing at frame at polygon and/or texture on the basis of frame under the situation that moves along with face and change).

When the high polygon counting scene with detailed texture changes fast, support the PC of recreation or game console may not have enough polygons and data texturing that enough RAM store the requisite number purpose animation frame that fragment produced that is used for playing.In addition, the single optical drive or the single disc driver that can be used for usually on PC or the game console are much slower than RAM usually, and can not catch up with GPU acceptable maximum data rate in reproducing polygon and texture usually.Current recreation is loaded into most of polygons and texture among the RAM usually, this means that given scenario is in complexity and be subjected to the capacity limit of RAM on the duration to a great extent.Under the situation that for example FA Facial Animation is made, this may be limited to the low resolution face that there is no the sense of reality with PC or game console, or only is limited to and to be written in suspension of game play and is used for the more polygon of multiframe and texture (and other data) is made into animation before at a limited number of frame sense of reality face.

When PC or control desk show when being similar to the message of " being written into ... ", the process bar of watching is striden screen and is moved lentamente that to be known as by the user of now complicated video-game be latent defect.Next scene from disk (unless have ready conditions in addition, otherwise herein " disk " refers to non-volatile optical media or magnetic medium, and such as the nonmagnetic disk medium of semiconductor " flash memory " storer) delay when being written into can spend some seconds or even some minutes.This loses time and may make the game player quite dejected.As discussed previously, a large amount of or all delays may be because from time that is written into of polygon, texture or other data of disk, but also may be following situation: when the processor in PC or the control desk and/or GPU prepared to be used for the data of scene, a cost part be written into the time.For example, the Association football video-game can allow the player to select in the middle of a large amount of players, group, sports ground and weather condition.Therefore, depend on and select what particular combinations, may need to be used for different polygons, texture and other data (general designation " object ") (for example, different groups have different color and pattern on its uniform) of scene.Enumerate many or all arrangements and many or all objects in the calculating object and object stores is being used for the disk of stores games in advance in advance in the various arrangements possibly.But if the number of arranging is very big, then the required storage capacity of all objects may be excessive so that can not be installed on the disk (or too unrealistic so that can not download).Therefore, existing P C and control desk system time that is written into of on the complexity of given scenario and playing duration time, being tied usually and being grown for complex scene.

Another of the video game system of prior art and application software system significantly is limited in: its for example use more and more the big database of 3D object (such as, polygon and texture), described big database need be loaded in PC or the game console to be used for processing.As mentioned above, when being stored in disk in this locality described database, described database can spend for a long time and be written into.Yet if data base set is stored in remote location and comes access via the internet, it is much serious usually to be written into the time.Under this kind situation, download big database may spend a few minutes, several hours or even several days.In addition, described database usually produces a large amount of expenses detailed high 3D model that the mast sailing boat is arranged of film or historical record sheet (for example, be used for playing) and is intended to be used to be sold to the local terminal user.Yet in case database is downloaded to the local user, it just has by the risk of piracy.Under many situations, the user only wishes the data download storehouse for the purpose of its needs that whether are fit to the user (for example, when the user carries out specificly when mobile, whether the 3D clothes that are used for game character have satisfied outward appearance or appearance) is watched in the assessment data storehouse.For the user of assessment 3D database before buying in decision, it may be to hinder that length is written into the time.

Similar problem occurs in MMOG (more specifically, as allowing the user to utilize the personage's who customizes more recreation).For the PC or the game console that show the personage, it needs can access to have the database of 3D geometric configuration (polygon, texture etc.) and described personage's behavior (for example, if the personage has shield, then whether shield is enough by force so that lance deflection).Usually, when MMOG was played for the first time by the user, the mass data storehouse that is used for the personage was available under the initial duplicate of recreation, and the initial duplicate of recreation is available or be downloaded to disk on game optical disk in this locality.But, along with game progress, if the user run into database in this locality disabled personage or object (for example) if another user has set up a customization personage, then before can showing this personage or object, must download its database.This essence that can cause playing postpones.

The tip property of given video-game and complexity, then formerly under the technology video game console situation another challenge to video-game developer and publisher be: often cost 2 years to 3 years of exploitation video-game, cost is at tens million of dollars.Suppose new video game control desk platform roughly to introduce every the speed of twice-a-decade, then the game developer need begin the development of those recreation in the several years before the distribution of new game control desk, so that make video-game simultaneously available when the new platform of distribution.From the distribution approximately simultaneously sometimes of several control desks of competitive manufacturer (for example, each other in 1 year or in two years), but remain to be seen is the popularity (for example, which control desk will produce maximum video game software sale) of each control desk.For example, in the cycle, Microsoft XBox 360, SonyPlaystation 3 and Nintendo Wii plan to introduce in the approximately identical cardinal principle period at nearest control desk.But in the several years before described introduction, the game developer in fact must " pressure injection (place bets) " which control desk platform will be more successful than other persons, and correspondingly drop into it and exploit natural resources.Studio also must estimate the successful film of possibility and share its limited making resource based on it for a long time before film distributor.The growth degree of the investment that given video-game is required, the then game making similar film making that all the more becomes, and game making company conventionally drops into it and makes resource the estimation of the success in future of particular video frequency recreation based on it.But, being different from film company, this pressure injection is not only based on the success of making itself; But it is dependent on the success of the game console that recreation will carry out thereon.The distribution recreation can alleviate risk on a plurality of control desks simultaneously, but this extra effort increases cost, and often postpones the actual distribution of recreation.

Application software on the PC and user environment are just becoming more to calculate and are going up intensive, dynamic and interaction, not only make it visually more attract the user, and make it more useful and directly perceived.For example, new Windows Vista (form distant view) ^TMOperating system and Macintosh Both have incorporated vision animation effect into the later release of operating system.The advanced figure instrument (such as, from the Maya of Autodesk (Ou Teke) company ^TM(Mayan ^TM)) provide very most advanced and sophisticated 3D to reproduce and cartoon making ability (it has promoted the restriction of the CPU and the GPU of present state of the art).Yet the calculation requirement of these new tools has produced many practical problemss for the user of described product and software developer.

Because the Visual Display of operating system (OS) must be in multiple computing machine (comprising the former generation computing machine of not resaling but still can upgrade along with the new OS) work of going up, the OS graphics request is subjected to the minimum common ground restriction of the computing machine (it generally includes the computing machine that does not comprise GPU) that OS will be used for to a great extent.This seriously limits the graph ability of OS.In addition, battery powered portable computer (for example, notebook) restriction Visual Display ability is because the high computational activity among CPU or the GPU causes higher power consumption and shorter battery life usually.Portable computer is usually included in the unfavorable processor activity that automatically lowers during with processor to reduce the software of power consumption.In some computer model, the user can manually be lowered the processor activity.For example, the VGN-SZ280P notebook of Sony is included on the side and is labeled as " Stamina (persistence) " and (is used for low performance, longer battery life) and on the opposite side be labeled as " Speed (the speed) " interchanger of (being used for high-performance, shorter battery life).But even the OS that carries out on the portable computer must be under the situation that computing machine is carried out with the sub-fraction of its peak performance ability also land used work.Therefore, the OS graphics performance usually remains the available computing power far below present state of the art.

Often sell intensive application program (as Maya) in the high-end calculating, expect that described application program will be used for power PC.This usually produces much higher performance, and the requirement of more expensive and portable relatively poor, minimum common ground.Therefore, described application program have than general purpose O S (or general yield-power application program, similar Microsoft Office) limited many target audience and usually to sell than general purpose O S software or much lower the measuring of general purpose application program software.Potential audient is further restricted, because the user of expection is difficult to intensive application program in the described calculating on probation in advance often.For example, suppose that the student wishes to understand the potential buyer who how to use Maya or known described application program and wish Maya on probation before investing (this may relate to also buy the high-end computer that can carry out Maya) in purchase.When student or potential buyer can download the crippled version of Maya or obtain the physical medium duplicate of Maya crippled version, if whole potential that its shortage can be carried out Maya (for example, handle complicated 3D scene) computing machine, then it can not carry out the comprehensive assessment of product.This limits the audient of described high-end applications program in fact.This also makes commercial value uprise, because cost of development is usually through sharing than the much smaller purchase number of times of the purchase number of times of general purpose application program.

The high price application program also produces more to the individuality of the pirate duplicate that uses application software and commerce, and thorniness swashs.Therefore, the high-end applications program software suffers rampant pirate, although the publisher of this software has carried out making great efforts in a large number by various technology alleviating this piracy.But, even when using pirate high-end applications program, the user also can not get rid of the needs that the PC that invests expensive present state of the art carries out pirate duplicate.Therefore, although the user can use the sub-fraction of the actual retail price of software application to obtain the use of software application, the user of piracy software still needs to buy or obtain expensive PC, so that utilize this application program fully.

This user for the pirate video-game of high-performance sets up equally.Although the bootlegger can obtain recreation with the sub-fraction of the real price of playing, it still needs to buy the required expensive computing hardware (for example, GPU-in-dash computer, or the high-end video game console of similar XBox360) of suitably playing games.Suppose normally consumer's amusement of video-game, the extra cost that then is used for high-end video game system may be too expensive.This situation is even worse in the country (for example, China) of current workman's average year income quite low (with respect to current workman's average year income of the U.S.).The population of like this, much smaller number percent has high-end video game system or high-end PC.In these countries, the payable expense of user is connected to " Internet bar " of computing machine of internet with use quite general.Frequently, described Internet bar have performance characteristics (such as, the player can be played calculate the GPU that goes up intensive video-game) than old model or low side PC.This is the key factor (such as, " World of Warcraft " of Vivendi, it is highly successful in China, and normally plays in the Internet bar of China) of the recreation success carried out on low side PC.By contrast, play on the intensive more impossible PC in being installed on Chinese Internet bar of recreation (as " second life ") in the calculating.In fact described recreation is inaccessible for the user of the low performance PC in only can the access Internet bar.

Buy video-game and be ready that at first also there is obstacle in the user of the demo version of trial game by via the internet demonstration being downloaded to its family for considering.Video game presentation usually is the all-round version of recreation, and the some of them feature is stopped using, or the amount of game play is applied restriction.This may relate at the growth process (possible several hrs) that recreation can be installed on PC or the control desk and download the data of billions of bytes before carrying out on PC or the control desk.Under the situation of PC, it also may relate to calculates recreation and needs which special driver (for example, DirectX or OpenGL driver), downloads correct version, and correct version is installed, and determines then whether PC can play this recreation.Latter's step may relate to determines whether PC has enough processing (CPU and GPU) ability, enough RAM and compatible OS (for example, some recreation carry out and do not carry out) on Windows XP on Vista.Therefore, after attempting to carry out the growth process of video game presentation, video game presentation can not be played under the situation of the PC configuration that the user may find given user.Even worse ground, in case the user has downloaded new driver to be used to attempt this demonstration, these driver versions just may to be accustomed to other recreation or the application program used on PC incompatible with the user, and therefore, the installation of demonstration can cause previous exercisable recreation or application program not to operate.These obstacles not only make the user dejected, and it also sells its recreation generation obstacle to video game software publisher and video-game developer.

Cause not having another problem of economic benefit relevant with the following fact: given PC or game console are designed to adapt to the performance requirement of the specific degrees of application programs and/or recreation usually.For example, some PC have more or less RAM, more slowly or faster CPU and GPU (if it has GPU) more slowly or faster.Some recreation or application program are utilized the full computing power of given PC or control desk, and some recreation or application program are not utilized the full computing power of given PC or control desk.If the selection of user's recreation or application program does not reach the peak performance ability of local PC or control desk, then the user may waste financial resources owing to the feature of not utilizing on PC or control desk.Under the situation of control desk, control desk manufacturer may pay than subsidizing the desired cost of Duoing of control desk cost.

Be present in the sale of video-game and enjoy in another problem related to before the user implements to buy recreation and allow the user to watch other people to play games.Exist and to be used for the some prior art approach of recording of video recreation to reset in time after a while.For example, United States Patent (USP) the 5th, 558 has instructed for No. 339 during " game play " game state information (comprising the game console action) is recorded in the video-game client computer (being had by same or different user).This status information can be in time use after a while to go up the some or all of game actions of resetting at video-game client computer (for example, PC or control desk).The remarkable shortcoming of this method is: for the user who watches the recreation of having write down, the user must have the video-game client computer that can play this recreation and must have the video game application programs of carrying out on this computing machine, so that game play is identical when resetting the game state that is recorded.In addition, video game application programs must be not exist the mode of possible execution difference to write in the recreation that is recorded and between the recreation of playback.

For example, game graph connects on the frame basis at frame substantially and calculates.For many recreation, depend on that scene is whether complicated especially or do not exist slow down execution other delays (for example, on PC, another process may be carried out, so that seize cpu cycle from game application), game logic may spend sometimes that the time shorter or longer than a frame time than a frame time is calculated as next frame and the figure that shows.In this kind recreation, " threshold value " frame that calculates with the time of lacking slightly than a frame time (for example, few several cpu clock cycle) finally can occur.When using identical game state information to calculate this Same Scene once more, may spend easily than a frame time Duo several cpu clock cycle time (for example, if internal cpu bus a little with outside DRAM bus homophase not, even and do not have to come the big delay that seizes another process of several milliseconds of CPU time since game processing, it also introduces the delay of several times cpu cycle).Therefore, when playback was played, frame became with two frame times calculating but not with single frame time calculating.The frequency (for example, when recreation sampling from the input of game console time) of new frame is calculated in some behaviors based on recreation.When game replaying, this deviation that is used for the time reference of different behaviors can not influence game play, but it can cause the recreation of institute's playback to produce Different Results.For example, if the track of basketball is to calculate with stable 60fps speed, but the game console input is based on the speed of the frame of calculating and takes a sample, then when recording game, the speed of the frame that calculates may be 53fps, and when resetting recreation, the speed of the frame of calculating may be 52fps, whether this can make basketball be prevented from entering in the basket and there are differences, thereby cause Different Results.Therefore, use the recreation of game state recording of video to need very careful Games Software design, to guarantee that using same game state information to reset produces identical result.

Another prior art approach that is used for recording of video recreation is the video output of only writing down PC or video game system (for example, to VCR, a DVD register, or the video capture board to the PC).Then video can be returned down and playback, or alternatively, the video that writes down be uploaded to internet (usually after with video compress).The disadvantage of this method is: when playback 3D game sequence, the user is limited to only from watching point (sequence is watched a little from this and being recorded) to watch sequence.In other words, the immutable scene of user watches a little.

In addition, but when the compressed video of the game sequence that makes the record of on PC of family or game console, playing via the internet be other user's times spent, even video is a Real Time Compression, also can not in real time compressed video be uploaded to the internet.Its reason is to have highly asymmetric broadband connection (for example, DSL and cable modem have the dirty bandwidth more much higher than upper reaches bandwidth usually) because be connected to many families of internet in the world.Compressed high-resolution video sequence usually have than network upload the high bandwidth of bandwidth capacity, make it not upload in real time.Therefore, after the game replaying sequence (possible a few minutes or even several hours), another user on the internet can watch before this recreation, will exist significantly to postpone.Although (for example should postpone under particular condition, watch the game player's of time appearance achievement formerly) tolerable, but " resetting at once " ability when it has been eliminated the ability of watching recreation on-the-spot broadcasting (for example, the basketball championship of being played by winning player) or has broadcast live the ground game replaying.

Another prior art approach allows the beholder with television receiver to watch the video-game on-the-spot broadcasting, but only under TV programme producers' control.Some television channels in the U.S. and the other countries provide video-game to watch channel, and wherein the televiewer can watch specific video game user (for example, participate in the tournament annoying top player) on the video-game channel.This is fed to the video distribution and the treatment facility that are used for television channel by the video output with video game system (PC and/or control desk) and finishes.This situation during as the live Basketball Match of television channel broadcaster, wherein several cameras provide live from the different angles around the basketball court and present.Television channel then can utilize its video/audio to handle and effect device is operated output from various video game systems.For example, television channel can be on from the video of video-game the literal (as its literal that superposes during can live at the scene Basketball Match) of the different players' of stack indication state, and television channel can add the audio frequency of record from commentator's (it can discuss the action that occurs between match period).In addition, can be with camera (for example, showing the emotional reactions of the player) combination of the video of the actual player of video-game output and recording game to recreation.

A problem of this method is: video distribution and treatment facility that must to make described live video feed in real time be television channel can be used, so that make it have the pungency of live broadcasting.Yet as discussed previously, when video game system (especially when the part of broadcasting comprises live video from the camera of the real world videos of just catching the game player) when family carries out, this is usually impossible.In addition, under the championship situation, what paid close attention to is that the player can revise recreation and cheating in the family, as discussed previously.Owing to these reasons, described video-game broadcasting on the television channel is usually disposed and (for example is gathered in public location, at the teletorium place or in the arena) player and video game system, wherein TV making equipment can be accepted the video feed from a plurality of video game systems and potential live camera.

Although described prior art video-game television channel can be the televiewer performance that stimulates is provided very (this is similar (for example with live motion event, similar with the video gamer that presents with " sportsman ") experience, not only according to its action in the video-game world, and according to its action in real world), but these video game systems usually are limited to player's hand-to-hand situation on the health each other.In addition, because television channel is broadcasted, so each channel that is broadcasted only can show a video flowing by producer's selection of television channel.Because these restrictions and airtime, making apparatus and producer's is expensive, described television channel only shows the top player who participates in top championship usually.

In addition, the given television channel to the full screen image of whole televiewer's broadcast videos recreation only shows a video-game at every turn.This seriously limits TV viewer's selection.For example, the TV viewer may lose interest in to the recreation that show preset time.Another beholder may be not interested in the game play of the particular player of projection preset time by television channel to watching only.Under other situations, the beholder may be only interested in the specific rank of watching expert player how to handle in the recreation.Other beholders may wish control watch point (video-game is watched a little from this), this is watched and a little is different from watching a little by selections such as production groups.In brief, the TV viewer may have countless preference (even several different television channels can be used, the specific broadcasting of TV network is the described preference of incompatibility also) in watching video-game.Owing to all above-mentioned reasons, make prior art video-game television channel have remarkable restriction in the video-game presenting to the TV viewer.

Another shortcoming of prior art video game system and application software system is: they are very complicated, and suffer mistake, collapse and/or unconscious and unwanted behavior (general designation " defective ") usually.Although usually experience debug and tuning process (often are called " software quality assurance " or SQA) before distribution for recreation and application program, but almost constant is: in case recreation or application program are issued to the numerous audients in the field, defective will occur suddenly.Regrettably, the software developer is difficult to discern and track many defectives after distribution.The software developer may be difficult to recognize defective.Even when it understood defective, also may only exist it to can be used for discerning was the limited amount information what causes this defective.For example, the user can phone consumer's service hotline of game developer and stay message, and this message statement: when playing games, screen begins flicker, then becomes solid blue (solid blue) and PC and freezes.It provides useful considerably less information in following the trail of defective for SQA group.Some recreation or the application program of online connection can provide more information sometimes under particular condition.For example, can use sometimes " house dog " process monitors recreation or application program whether " collapse ".The house dog process can collect recreation or during application crash about recreation or application program status of processes (for example, the degree that memory stack user mode, recreation or application program proceed to etc.) statistics, and then via the internet with described information uploading to SQA group.But in complexity recreation or application program, this information can spend the very long time and decipher, so that determine exactly what the user carrying out when collapse.However, can not determine that also what sequence causes collapse.

The another problem that is associated with PC and game console is: it stands the service problem that makes the consumer extremely not convenient.Service problem also influences the manufacturer of PC or game console, because it usually needs to send special boxes with damaged PC or control desk of shipment safely, and thereby causes the cost (if PC or control desk were in the guarantee period) of repairing.Recreation or application software publisher also can be in loss on sale (or the online service use) influence that PC in the repairing state and/or control desk cause.

Fig. 1 explanation is such as Sony Playstation

3, Microsoft Xbox360

NintendoWii ^TM, based on the personal computer of Windows or the prior art video game system of Apple Macintosh.In the described system each comprises the CPU (central processing unit) (CPU) that is used for program code (being generally the Graphics Processing Unit (GPU) that is used to carry out the advanced figure operation), and is used for the I/O (I/O) with a plurality of forms of external unit and telex network.For the sake of simplicity, described assembly is shown as combine and is individual unit 100.The prior art video game system of Fig. 1 also is shown as and comprises optical media driver 104 (for example, DVD-ROM driver); Be used to store the hard disk drive 103 of video game program code and data; Be used to play multiplayer, be used for download games, the network of patch, demonstration or other medium connects 105; Be used to store the random-access memory (ram) 101 of the current procedure code of just carrying out by CPU/GPU100; Be used for during game play, receiving game console 106 from user's input command; And display device 102 (for example, SDTV/HDTV or computer monitor).

Shown prior art system is subjected to some restrictions among Fig. 1.At first, compare with the access speed of RAM101, optical drive 104 and Hard Disk Drive 103 often have slowly many access speeds.When directly working by RAM101, because RAM101 has much higher bandwidth usually and can not be subjected to the fact that the long relatively search of disk mechanism postpones, CPU/GPU100 can handle the much more polygon figurate number of per second of the polygon figurate number of per second possible than directly from hard disk drive 103 or optical drive 104 read routine codes and data the time in practice.But only limited amount RAM is provided in (for example, 256-512 megabyte) in these prior art system.Therefore, usually need " being written into ... " sequence, wherein RAM101 periodically is filled with the data of the next scene that is used for video-game.

Some systems being written into and game play of program code of attempting side by side to overlap, but this only can (for example carry out when having the incident of known array, if just along the driving path car, then can in steered vehicle, be written into the geometric configuration of the just approaching buildings in roadside).For complicated and/or quick scene change, the overlapping of this type is inoperative usually.For example, the user be in campaign carry out among and in the view carved at that time RAM101 be filled fully under the situation of data of indicated object, if the user is moved to the left view apace to watch the object among the current RAM101 of not being loaded in, then will cause the uncontinuity of moving, because do not exist time enough that new object is loaded among the RAM101 from hard disk drive 103 or optical media 104.

Another problem of the system of Fig. 1 is because the restriction of the storage volume of hard disk drive 103 and optical media 104 causes.Although Disk Storage Device can be manufactured into relatively large storage volume (for example, 50,000,000,000 bytes or more than 50,000,000,000 bytes), it still is not provided for enough storage volumes of the particular case that run in the current video recreation.For example, as discussed previously, the Association football video-game can allow the user to select in the middle of global many groups, player and sports ground.For each group, each player and each sports ground, need a large amount of texture and environment mappings to come characterization 3D surface (for example, each group has unique sport shirt, and each needs unique texture) in the world.

A technology that is used to solve above-mentioned latter's problem is: for recreation, in case the user has selected texture and environment mappings, just calculate texture and environment mappings in advance.This can relate to process intensive in many calculating, comprises decompressing image, 3D mapping, adds shade, organizes data structure etc.Therefore, when these calculating are carried out in video-game, may there be delay for the user.Reduce on the methodological principle of this delay and be: each arrangement of carrying out all these during initial game development and calculating-comprise group, player's register and sports ground.The release version of recreation thus will comprise be stored on the optical media 104 or the one or more servers on the internet on all are described through pretreated data, when the user makes one's options, only will be used for the selected pretreated data that given group, player's register, sports ground select and download to hard disk drive 103 via the internet.Yet as practical problems, these data that are written in advance of each possible arrangement may be the data of several terabytes (terabyte) easily in the game play, and it far surpasses the capacity of optical media equipment now.In addition, be used for the data that given group, player's register, sports ground select and be the data more than the data of several hundred million bytes or several hundred million bytes easily.(for example, 10Mbps), connecting 105 these data of download via network will be than in local computational data cost for more time under the situation of home-network linkups.

Therefore, shown prior art game structure makes the user stand remarkable delay between the changing than large scene of complexity recreation among Fig. 1.

Another problem of the prior art approach of all prior art approach as shown in Figure 1 is: in these years, video-game is tended to become more senior and is needed more CPU/GPU processing poweies.Therefore, even adopt endless RAM, the video-game hardware requirement also surpasses the peak level of processing power available in the described system.Therefore, need the user to upgrade game hardware every several years to keep synchronously (or to play than new game) than the inferior quality level.Than the consequence of the trend of more senior video-game in the past be: the machine that is used for the playing video game of domestic use is not had economic benefit usually, because its cost is determined by the requirement of its supported peak performance recreation usually.For example, may use XBox 360 to play the recreation of similar " war machine (Gears of War) ", this recreation requires the RAM of high performance CPU, GPU and several hundred million bytes, perhaps may use XBox360 to play " eating beans (Pac Man) ", it is the recreation from the seventies in 20th century, and it only needs the RAM of several kilobyte to reach the very CPU of low performance.In fact, XBox360 has enough computing powers of " eating beans " recreation of many whiles of Co-location simultaneously.

In the great majority in a week hour, close video game machine usually.According in July, 2006 Nielsen (Nelson) amusement to the research that enlivens the player more than 13 years old and 13 years old, on an average, enliven that the player spent 14 hours in one week or in the week whole hours only 12% play the control desk video-game.This means that the average video game console is idle in 88% time, this is the inefficiency use of expensive resource.Suppose that video game console usually is to be subsidized to reduce purchasing price (expect that this subsidy will earn back by the royalty of buying from following video game software) by manufacturer, then this is meaningful especially.

Video game console also causes and the relevant cost of any consumer electronics almost.For example, the electronic equipment and the mechanism of system need be contained in the shell.Manufacturer need provide service guarantees.The retailer who sells this system need collect about the sale of system and/or about the profit of the sale of video game software.All of these factors taken together adds the cost of video game console, and this cost must be subsidized, be passed to the consumer by manufacturer, perhaps subsidized by manufacturer and consumer.

In addition, piracy is the big problem of video game industry.In fact the release mechanism that is utilized on each big video game system " breaks " in these years, causes the unwarranted of video-game to duplicate.For example, the Xbox360 security system was broken and the user now can the illegal duplicate of online download in July, 2006.Downloadable recreation (for example, being used for the recreation of PC or Mac) stands piracy especially easily.In the specific region in the world (wherein pirate control is not strong), there is not the feasible market of independent vide Games Software in fact, because the user can easily buy pirate duplicate with the very little part of cost with legal duplicate is general.And, the many places in the world, the cost of game console accounts for the high number percent of income, even so that pirate controlled, also few people can afford the games system of present state of the art.

The income of video-game industry has been reduced in the market of the recreation of having used in addition.When the user becomes when recreation is weary of, it can be sold to recreation recreation is resell to other users' shop.Without permission this but general practice has significantly reduced the income of recreation publisher.Similarly, when existing platform to change every several years, about 50% sale minimizing appears usually.This be because: when the user knew the platform of forthcoming more recent version, the user stopped to buy the recreation that is used for than legacy platform (for example, when being about to issue Playstation3, the user stops to buy the Playstation2 recreation).Combine, the loss of sale reaches the adverse effect that highly significant can be arranged game developer's rentability with the cost of development of the increase that newly platform is relevant.

The new game control desk is also very expensive.Xbox360, Nintendo Wii and Sony Playstation 3 are all with hundreds of dollars of retails.The personal computer games system of high ability can spend up to.This expression user's remarkable investment specifically, considers that hardware stale and many systems after several years are the facts of buying for child.

A method of the problems referred to above is games on line, wherein manages on behalf of another games code and data host on server and is sent to client machine on request, and compressed video and audio frequency flow via digital broadband network.The current online described service that provides of some companies (such as, the G-Cluster of Finland (G-troop company), it is subsidiary company of the SOFTBANK Broadmedia (the wide matchmaker of soft silver) of Japan now).It is available in local network (such as, those networks that provide in the hotel and by DSL and cable television supplier) that similar game services becomes.The problem that the big shortcoming of these systems is time-delays, also, signal rows enters game server and from the time that game server is advanced and spent, game server is positioned in " front end " of operator usually.Quick acting video-game (being also referred to as " very fast (twitch) " video-game) needs low-down time-delay at the user carries out action by game console time and update displayed screen between the time with the result of explicit user action.Need low delay, so that the user feels that recreation " immediately " responds.The type of videogame and user's skill level and satisfy the user at interval with different delayed time.For example, for slowly unofficially for recreation (similar backgammon) or the slow motion RPG (Role-playing game), 100 milliseconds time-delay may be tolerable, but in the snap action recreation, the time-delay that surpasses 70 milliseconds or 80 milliseconds can cause user's performance more sorrily in recreation, and therefore unacceptable.For example, in the recreation that needs the fast response time,, exist the sharp of accuracy to fall when delaying time when increasing to 100 milliseconds for 50 milliseconds.

When recreation or application server are installed in the network environment of nigh controlled network environment or and/or tolerable bandwidth peak measurable to user's network path, aspect the consistance of maximum delay and time-delay, control time-delay much easier (for example, so user observe the stable motion of flowing via network) from digital video.The control of this degree can be reached following: at cable tv network front end inter-household to the cable tv user, or from the DSL central office family to the DSL subscriber, or in commercial office's Local Area Network (LAN) environment from server or user.And the point-to-point private that might obtain the particular hierarchical with guaranteed bandwidth and time-delay between the commerce connects.But game host is being managed on behalf of another in the server-centric that is connected to common interconnection network and then made compressed video flow (stream) in user's recreation or application system via broadband connection, many factors cause time-delay, cause the serious restriction in the deployment of prior art system.

In the family in typical connection broadband, the user can have DSL or the cable modem that is used for broadband service.Described broadband service causes user's family and nearly 25 milliseconds the round trip time-delay (and more sometimes) between the common interconnection network usually.In addition, exist owing to route data to the round trip time-delay that server-centric causes via the internet.The delay that data are caused when being routed based on the route that provides data and data via the time-delay of internet and changing.Except that route postpones, also, light cause round trip to delay time because passing the speed of the optical fiber that makes the interconnection of most of internets.For example, for per 1000 miles, speed and other consumptions of passing optical fiber owing to light cause about 22 milliseconds round trip time-delay.

Extra time-delay can cause owing to the data rate of the data that flow via the internet.For example, if the user has the DSL service of selling with " 6Mbps DSL service ", then in practice, the user will obtain the descending operational throughput less than 5Mbps probably at most, and may periodically see because various factors (such as, peak value be written into time durations Digital Subscriber Line Access Multiplexer (DSLAM) locate crowded) the connection degradation that produces.If via existing other places in crowded or the cable modem system network to exist crowded in the local sharing coaxial cable of neighbor's round-robin, then similar problem can occur, thereby the data rate that will be used for the cable modem of the connection of selling with " 6Mbps cable modem services " is decreased to much smaller than this data rate.Flow via described connection from server-centric with User Datagram Protoco (UDP) (UDP) form uniaxially as if the packet under the steady rate that makes 4Mbps, if all are all suitably worked, then packet will by and do not cause extra time-delay, but if exist crowded (or other obstruction) and only 3.5Mbps can be used for making streams data to arrive the user, then under typical situation, bag will be dropped, cause obliterated data, perhaps grouping will be lined up till they can be sent out at crowded some place, thereby introduce extra time-delay.Different crowded points have the different queue capacity that is used to preserve the grouping that is delayed, and therefore under some situations, can not successfully solve crowded grouping immediately and abandon.Under other situations, with the data queue of millions of bits and its transmission the most at last.But under nearly all situation, the queuing at crowded some place has capacity limit, and in case above this restriction, formation will overflow and divide into groups to be dropped.Therefore, for fear of causing extra time-delay (or even worse ground, packet loss), must avoid surpassing from recreation or application server to the user's data rate capacities.

Also owing to compressed video in server and in client device the required time of decompressed video cause time-delay.When next frame to be shown is being calculated in the video-game of carrying out, further cause time-delay on server.Current available video compression algorithm is subjected to high data rate or high time-delay.For example, the compression algorithm of motion JPEG for diminishing in the frame only, this compression algorithm is characterized as low delay.Each frame of video is independent of each other frame of video and compresses.When client device receives frame of compressed motion JPEG video, its this frame and show this frame of can decompressing immediately, thus cause low-down time-delay.But because each frame separately compresses, so algorithm can not utilize the similarity between the successive frame, and therefore only in the frame video compression algorithm be subjected to very high data rate.For example, 60fps (number of pictures per second) 640 * 480 motion JPEG videos may need the above data of 40Mbps (per second megabit) or 40Mbps (per second megabit).The described high data rate that is used for described low-resolution video window will be too expensive (and for most consumers the way it goes based on the application program of internet) in many broadband application programs.In addition, because each frame is through independent compression, so the false shadow in the frame that may produce owing to lossy compression method may come across the diverse location place in the successive frame.This can cause when decompressed video, in the visual artifacts of beholder for moving.

Other compression algorithms (such as, from the MPEG2 of Microsoft company, H.264 or VC9) when being used for the configuration of prior art, can realize the high compression ratio, but be cost with the height time-delay.Described algorithm utilizes compression in interframe compression and the frame.Periodically, described algorithm is carried out the interior compression of only frame of frame.This frame is called as key frame (so-called " I " frame).Then, this algorithm is compared with previous frame the I frame usually with successive frames.Be not to compress previous frame and successive frames independently, but algorithm determine image from the I frame to previous frame and successive frames have anything to change, and then this change is saved as: " B " frame (for the change before the I frame) and " P " frame (for the change after the I frame).This causes than only compressing much lower data rate in the frame.But it is a cost with higher time-delay usually.The I frame is usually than B frame or P frame much bigger (usually big 10 times), and therefore, spends the long time pro rata with given data rate transport.

Consider (for example) i situation: wherein the I frame is 10 times of size of B frame and P frame, and in each single I frame, has 29 B frame+30 P frame=59 interframe, or for each " frame group " (GOP) 60 frames altogether.Therefore, under 60fps, there is 1 60 frame GOP in per second.Suppose that transmission channel has the maximum data rate of 2Mbps.In order to reach the video of E.B.B. in channel, compression algorithm will produce the 2Mbps data stream, and given above-mentioned ratio, and this will produce 2 megabits of (Mb)/(59+10)=30,394 bits and 303,935 bits of every I frame in every frame.When receiving compressed video flowing,, need (for example, 60fps) decompress and show each frame at interval with rule for displaying video stably by decompression algorithm.In order to realize this result, if any frame is subjected to transmission delay, then need this time-delay at least of all frame delay, therefore the frame of situation is delayed time and will be defined for the time-delay of each frame of video worst.Because I frame maximum, so the I frame is introduced longer transmission time-delay, and the entire I frame must can decompress and show that I frame any interframe of I frame (or depend on) receives before.Suppose that channel data rates is 2Mbps, then transmits the I frame and will spend 303, the 935/2Mb=145 millisecond.

Use the inter-frame video compressibility (as mentioned above) of big number percent of the bandwidth of transmission channel to stand long delay with respect to the big size of the mean size of frame owing to the I frame.Perhaps, in other words, when previous technology interframe compression algorithm than the low average every frame data speed of compression algorithm in the frame only (is for example reached, 2Mbps is to 40Mbps) time, itself since big I frame and still suffer the every frame data speed of high peak value (for example, 303,935*60=18.2Mbps).But please remember: above-mentioned analysis supposition P frame and B frame are all much smaller than I frame.Although this sets up substantially, for the frame that has with previous frame, high motion or the incoherent hi-vision complexity of scene change, this is false.Under described situation, P frame or B frame can become and I frame generally big (if P frame or B frame become bigger than I frame, then most advanced and sophisticated compression algorithm is replaced P frame or B frame with " pressure " I frame and with the I frame usually).Therefore, the data rate peak value of I frame sign can come across in the digital video frequency flow at any time.Therefore, for compressed video, when average video data rate during near the data rate capacity of transmission channel (often be this situation, given high data rate for video requires), cause high frame time-delay from I frame or big P frame or the peak data rates of B frame.

Certainly, the only compression algorithm time-delay that produces by the big B frame among the GOP, P frame or I frame of characterization of above-mentioned argumentation.If use the B frame, then time-delay will be higher.Reason is because before can showing the B frame, must receive B frame all B frames and I frame afterwards.Therefore, in picture group (GOP) sequence, wherein before each I frame, have 5 B frames such as BBBBBIPPPPPBBBBBIPPPPP, only receive subsequently the B frame and the I frame after just can show a B frame by video decompressor.Therefore,, then before the B frame that can decompress,, receive five B frames and I frame and will spend the 16.67*6=100 millisecond, and this is the situation of 5 B frames only no matter how fast channel width is if video is flowed with 60fps (also promptly, 16.67 milliseconds/frame).Compressed video sequence with 30 B frames is quite general.In addition, under the low channel width as 2Mbps, the time-delay influence that causes owing to the size of I frame is increased to a great extent owing to wait for that the B frame arrives the time-delay that produces and influences.Therefore, on the 2Mbps channel, under the situation of a large amount of B frames, the time-delay of using the prior art video compression technology to surpass more than 500 milliseconds or 500 milliseconds is quite easy.If do not use B frame (for given quality level, to be cost), then do not cause the time-delay of B frame, but still cause the time-delay that causes owing to the peak value frame sign as described above than the low compression ratio rate.

Problem is exactly owing to the character of many video-games increases the weight of.Utilizing the video compression algorithm of gop structure as described above to be optimized to a great extent being used for uses together with the live video or the film material that will be used for passive viewing.Usually, camera (true camera, the perhaps virtual camera under the situation of the animation that produces of computing machine) and scene relatively stable, only because if camera or scene move around very much with jolting, then video or film material (a) are watched usually and are made us unhappy, and (b) if it is just viewed, when camera jolts suddenly back and forth, the beholder can not (for example closely follow this action usually, if during the child of the candle of camera on take blowing out birthday cake by disturbance and between cake, jolt back and forth suddenly, then the beholder concentrates on child and the cake usually, and ignores the unexpected brief interruption when mobile of camera).Under the situation of video talks or video conference call, can be immobilizated in camera in the fixed position and not mobile, thereby cause considerably less at all data peaks.The action video recreation by characterization (for example comes by steady motion but 3D is high, consider the 3D contest, wherein entire frame was in the rapid movement in the duration of contest, perhaps considered first person shooting game, and wherein virtual camera moves around consistently with jolting).Described video-game can produce the frame sequence with big and frequent peak value, and wherein the user may need clearly to see between this unexpected moving period what has taken place.Therefore, in the high action video recreation of 3D, compress the far not tolerable of false shadow.Therefore, the video of many video-games output (because its character) produces the compressed video flowing with very high and frequent peak value.

Time-delay has little tolerance to the user who supposes the snap action video-game for height, and given all above-mentioned time-delay reasons, has the restriction of the video-game of managing on behalf of another for the server host that video is flowed on the internet so far.In addition, if the application program that needs high interaction by Co-location on common interconnection network and video is flowed, then the user of described application program suffers similar restriction.Described service needs network configuration, wherein the Co-location server directly is arranged in front end (under the situation of cable broadband) or the central office (under the situation of Digital Subscriber Line (DSL)), or in the LAN in the business contexts (or the private of special classification connects) so that control from client device the route to server and distance to minimize time-delay and can adapt to peak value and do not cause time-delay.LAN (being rated at 100Mbps-1Gbps usually) and the leased line with enough bandwidth can support peak bandwidth to require (for example, 18Mbps peak bandwidth be 100Mbps LAN capacity sub-fraction) usually.

If carry out idioadaptation, then peak bandwidth requires also can be adapted to by dwelling house broadband architecture.For example, in the cable tv system, can be Digital Video Communication and provide dedicated bandwidth, this dedicated bandwidth can be handled the peak value such as big I frame.In addition, in the DSL system, can supply the DSL modulator-demodular unit (consideration peak value) of fair speed, maybe can supply the connection of the special classification that can handle higher data rate.But, be attached to the traditional cable modulator-demodular unit of common interconnection network and DSL architecture and for the peak bandwidth of the video that is used to compress requires, far can't stand.Therefore, online service (is managed on behalf of another video-game or application host in the server-centric of the long distance of distance client device, and then make the compressed video output streams moving via the internet via traditional dwelling house broadband connection) suffer significant time-delay and peak bandwidth requirement-especially (for example for the recreation of the low-down time-delay of needs and application program, first person shooting game and other multi-users, interactive action game, or need the application program of fast-response time).

Description of drawings

According to following detailed and can more completely understand the disclosure with reference to the accompanying drawings, yet, described accompanying drawing be not used for disclosed subject matter restricted to shown in the specific implementations, and just with laying down a definition and understanding.

Fig. 1 shows the framework of prior art video game system.

Fig. 2 a to Fig. 2 b shows the high level system architecture according to an embodiment.

Fig. 3 shows the reality of communicating by letter, the specified and required data rate that is used between client and the server.

Fig. 4 a shows host services and the client of using according to an embodiment.

Fig. 4 b show with client and host services between the relevant exemplary time-delay of communicating by letter.

Fig. 4 c shows the client device according to an embodiment.

Fig. 4 d shows the client device according to another embodiment.

Fig. 4 e shows the example block of the client device among Fig. 4 c.

Fig. 4 f shows the example block of the client device among Fig. 4 d.

Fig. 5 shows an example of the video compress that can use according to an embodiment.

Fig. 6 a shows an example of the video compress that can use in another embodiment.

Fig. 6 b shows and transmits low complex degree, hangs down the peak value in the relevant data rate of action video sequence.

Fig. 6 c shows the peak value in the data rate relevant with transmitting high complexity, high action video sequence.

Fig. 7 a to Fig. 7 b shows the instance video compress technique of using in one embodiment.

Fig. 8 shows the additional examples video compression technology of using in one embodiment.

Fig. 9 a to Fig. 9 c shows and uses in one embodiment to be used to alleviate the case technology of data rate peak value.

Figure 10 a to Figure 10 b shows the image image block is packaged in an interior embodiment of grouping effectively.

Figure 11 a to Figure 11 d shows the embodiment that uses forward error correction technique.

Figure 12 shows an embodiment who uses multinuclear heart processing unit to compress.

Figure 13 a to Figure 13 b shows according to geo-location between the host services of various embodiment and communication.

Figure 14 show with client and host services between the relevant exemplary time-delay of communicating by letter.

Figure 15 shows example host services server-centric framework.

Figure 16 shows the example screen shot of an embodiment of the user interface that comprises a plurality of live video windows.

Figure 17 shows the user interface of the Figure 16 after selecting the particular video frequency window.

Figure 18 shows the user interface of the Figure 17 after the particular video frequency window is amplified to the full screen size.

Figure 19 shows the example partner user video data on the screen that is superimposed upon multiplayer.

Figure 20 shows the game player's who is used on the host services the instance user page.

Figure 21 shows example 3D interactive type advertisement.

Figure 22 shows the case step sequence that is used for catching from the surface of live performance the image that produces the photo realistic with grain surface.

Figure 23 shows the instance user interface page that allows to select linear media content.

Figure 24 shows the time quantum that disappears before the live at the scene webpage and the curve map of connection speed.

Embodiment

Enumerated in the following description specific detail (such as, device type, system configuration, communication means etc.) so that provide to thorough understanding of the present disclosure.Yet, it be to be appreciated that those skilled in the art that generally putting into practice described described embodiment may not need these specific detail.

Fig. 2 a to Fig. 2 b provides the high level architecture of two embodiment, wherein video-game and software application (are noted by customer site 211 by host services 210 Co-locations and under subscription service, " customer site " meaning is the position anywhere that the user locatees, if use mobile device then to comprise outdoor) client device 205 located comes access via internet 206 (or other public networks or private network).The multi-purpose computer that client device 205 can be the wired or wireless connection that has to the internet, have inside or external display device 222 (such as, based on the PC of Microsoft Windows or Linux or the macintosh computer of Apple company), perhaps it can be the private client equipment such as set-top box (having the wired or wireless connection to the internet) that video and audio frequency is outputed to monitor or television machine 222, and perhaps it can be the action equipment that presumably has to the wireless connections of internet.

The user input device that in the described equipment any one can have himself (for example, keyboard, button, touch screen, tracking plate (track pad) or inertia sensing rod (inertial-sensing wand), Video Capture camera and/or motion tracking camera etc.), perhaps it can use the external input device 221 (for example, keyboard, mouse, game console, inertia sensing rod, Video Capture camera and/or motion tracking camera etc.) by wired or wireless connection.As more detailed description hereinafter, host services 210 comprises the server (comprising those servers with high ability CPU/GPU processing power) of various performance levels.During the application program on game replaying or the use host services 210, family or office's client device 205 receive from user's keyboard and/or controller input, and then it transfers to host services 210 with the controller input via internet 206, host services 210 carry out the games code in response and produce be used to play or the successive frames of the video output (sequence of video images) of application software (for example, if the user pushes the button that will guide the personage on the screen to move right, then games then will produce the sequence of video images that shows that the personage moves right).Then use the low delay video compressor to compress this sequence of video images, and host services 210 is then transmitted the low delay video flowing via internet 206.Then decode compressed video flowing and the video image through decompressing is reproduced on monitor or the TV of family or office's client device.Therefore, reduce the calculating and the graphic hardware requirement of client device 205 significantly.Client 205 only needs to have the processing power that is used for keyboard/controller input is forwarded to internet 206 and decoding and decompression 206 compressed video flowings that received from the internet, in fact now any personal computer all can carry out these (for example, the double-core CPU of Intel Company that carries out with about 2GHz can decompress and use the 720p HDTV that encodes such as the compressor reducer that H.264 reaches windows media VC9) with software on its CPU.In addition, under the situation of any client device, special chip also can than the much lower cost of universal cpu and than the power consumption of universal cpu much less (such as, modern PC is required) carry out the video decompression that is used for described standard in real time.Notably, in order to carry out the function of input of transmission controller and decompressed video, home client equipment 205 is without any need for Graphics Processing Unit (GPU), optical drive or the hard disk drive of specialization (such as, shown prior art video game system among Fig. 1).

Along with recreation and application software become more complicated and have more the photo realistic sense, it will need CPU, the GPU of superior performance, more RAM, and disc driver more greatly and faster, and the computing power at host services 210 places is constantly upgraded, but the terminal user will not need to make family or 205 upgradings of office's client platform, because will make the processing requirements of family or office's client platform 205 keep constant for display resolution and frame rate by given video decompression algorithm.Therefore, there are not being seen now hardware constraints and consistency problem in the illustrated system among Fig. 2 a to Fig. 2 b.

In addition, because recreation and application software are only carried out in the server in host services 210, so in user's family or office (unless have ready conditions in addition, otherwise " office " will comprise any non-dwelling house background as used herein, comprise (for example) classroom) in never have the duplicate (form of optical media perhaps is a downloaded software) of recreation or application software.This significantly alleviates recreation or application software by the possibility of bootlegging (piracy), and alleviates the valuable database that can be used by recreation or application software by the possibility of piracy.In fact, if (for example need specialized server, need very expensive, equipment big or that noise is arranged) play for family or office and use infeasible recreation or application software, even then obtain the pirate duplicate of recreation or application software, it also can not be operated in family or office.

In one embodiment, (it refers to software supplier, recreation or film workshop to host services 210 substantially to the design recreation of video-game or application software developer, or recreation or application software publisher) 220 provide SDK (Software Development Kit), so that it can design the recreation that can carry out on host services 210.Described instrument allows feature (described feature usually in independent PC or game console with unavailable) that the developer utilizes host services (for example, the very large database of quick access complex geometric shapes (unless have ready conditions in addition, otherwise " geometric configuration " will be used in reference to polygon, texture, rigging, illumination, behavior and other assemblies and parameter that generation limits the 3D data set in this article)).

Under this framework, different business prototype are possible.Under a model, host services 210 is collected subscription charge usefulness and is paid royalties to developer 220 from the terminal user, as shown among Fig. 2 a.In substitute implementing (shown among Fig. 2 b), developer 220 directly from the user collect subscription charge with and be used for the expense of Co-location recreation or application content to host services 210 payments.These ultimate principles are not limited to be used to any particular business model of providing game on line or application host to manage on behalf of another.

Compressed video properties

As discussed previously, the online prominent question of video-game service or application software service that provides is time-delay.70 milliseconds-80 milliseconds time-delay (from input equipment by the user activate (actuate) the time be carved into moment when on display device, showing response) for need being used to the recreation of fast-response time and the upper limit of application program.Yet, be very difficult to reach under the situation of this shown framework in Fig. 2 a and Fig. 2 b owing to a large amount of reality and physical constraint make.

As indicated among Fig. 3, when the user subscribes to Internet service, connect the demarcation maximum data rate 301 of the family or the office that are rated for the user usually.Depend on supplier's strategy and routing device ability, this maximum data rate can more or less strictly be executed, but usually owing to one in many different reasons make that actual available data rate is lower.For example, may there be multi-network communication communication at DSL central office place or on local cable modem loop, or may on cable, have noise, thus cause the grouping that abandons, or the supplier may set up the bit of every month maximum number of every user.Current, the maximum downstream data rate that is used for cable and DSL service is usually in hundreds of kilobits/second (Kbps) arrive the scope of 30Mbps.Cellular services is limited to the downlink data of hundreds of Kbps usually.Yet the user's of the speed of broadband service and subscription broadband service number will sharply increase along with the time.Current, some analysts estimate that 33% U.S. broadband user has 2Mbps or the above downstream data rate of 2Mbps.For example, some analyst's predictions: ended to 2010, the U.S. broadband user above 85% will have 2Mbps or the above data rate of 2Mbps.

As indicated among Fig. 3, actual available maximum data speed 302 can fluctuate along with the time.Therefore, under low delay, game on line or application software situation, be difficult to predict the actual available data rate that is used for particular video stream sometimes.If for the scene complexity of specified quantitative and motion under the number of pictures per second (fps) of given number with given resolution (for example, 640 * 480@60fps) keep the required data rate of given quality level 303 is higher than actual available maximum data speed 302 (as by the indication of the peak value among Fig. 3), then some problems can occur.For example, some Internet services will only abandon grouping, thus cause data of losing on user's the video screen and distortion/image lost.Other services will temporarily cushion (also promptly, queuing) additional packet and with available data rate described grouping will be provided to client, thereby cause the unacceptable result of the increase of delaying time-be for many video-games and application program.At last, some ISPs are considered as malicious attack (attacking (by computer hacker with so that network connects the known technology of stopping using) such as, the service of denying) with the increase of data rate, and will cut off user's Internet connection at special time in the cycle.Therefore, embodiment described herein manages to guarantee that the desired data speed that is used for video-game can not surpass maximum usable data rates.

The host services framework

Fig. 4 a explanation is according to the framework of the host services 210 of an embodiment.Host services 210 can be arranged in individual server in the heart, perhaps can cross over a plurality of server-centrics and disperse (to think that the user to the path at particular server center who has than other person's low delays provides low delay to connect, so that load balance to be provided, and under the out of order situation of one or more server-centric, provide redundant between the user).Host services 210 finally can comprise thousands of or even millions of servers 402, thereby serve very large user base (user base).Host services control system 401 provides the overall control to host services 210, and guides router, server, video compression system, charging and account system etc.In one embodiment, host services control system 401 is implemented on the distributed processing system based on Linux, and this disposal system is tied to the RAID array that is used to store the database that is used for user profile, server info and system statistics data.In the foregoing description, unless owing to other particular systems, otherwise the exercises of being implemented by host services 210 are by the 401 initial and controls of host services control system.

Host services 210 comprises many servers 402, such as the current described server that can obtain from Intel (intel corporation), IBM (IBM) and Hewlett Packard (Hewlett-Packard) and other persons.Perhaps, server 402 can be assembled into the customizable component configuration, can be single chip with server 402 integration so that with whole server implementation finally perhaps.Although this figure shows minority server 402 for purposes of illustration, in actual deployment, may exist few to a server 402 or reach the server of millions of or millions of above servers 402.Server 402 all can dispose in the same manner (as the example of some configuration parameters, has identical cpu type and performance; Have or do not have GPU, and, then have identical GPU type and performance if having GPU; CPU and GPU with similar number; RAM with same amount and same type/speed; And has an identical RAM configuration), or each subset of server 402 can have identical configuration, and (for example, 25% server can an ad hoc fashion dispose, and 50% server disposes by different way, and 25% server disposes in another mode), or each server 402 can be different.

In one embodiment, server 402 no disks, also be, be not that (it is optics or storage magnetic to the local high capacity reservoir with himself, the perhaps reservoir of based semiconductor, other high capacity storage devices such as flash memory or service similar functions), each server connects and the shared high capacity reservoir of access via quick base plate or network.In one embodiment, this is connected to the storage area network (SAN) 403 that is connected to raid-array (RAID) 405 series fast, has connection between the equipment that uses the hypervelocity Ethernet to implement.As known to persons skilled in the art, SAN403 can be used for many RAID arrays 405 are combined, thereby causes high bandwidth-near maybe surpassing the bandwidth that the RAM can be used for current game console and PC certainly obtains.In addition, although often have significant search time access time-delay based on the RAID array such as the rotation medium of magnetic medium, the RAID array of based semiconductor reservoir can be embodied as has much lower access time-delay.In another configuration, some or all of servers 402 provide some or all of himself high capacity reservoirs in this locality.For example, server 402 can with the information of frequent access (such as, the duplicate of its operating system and video-game or application program) is stored on the reservoir based on the low delay local flash memory, but it can utilize SAN to come the RAID array 405 with higher search time-delay of access based on the rotation medium, with the bigger database of access geometric configuration continually or game state information.

In addition, in one embodiment, host services 210 is used the low delay video compress logic of hereinafter describing in detail 404.Video compress logic 404 can software, (hereinafter describing its specific embodiment) implemented in hardware or its any combination.Video compress logic 404 comprises the logic that is used for compressed audio and visual material.

In operation, when the playing video game or when using the application program at customer site 211 places via keyboard, mouse, game console or other input equipments 421, the control signal logic 413 on the client 415 will represent that the control signal 406a-b (being generally the form that UDP divides into groups) of the button press (and the user of other types input) impelled by the user is transferred to host services 210.To be routed to suitable server (or if a plurality of servers in response to user's input equipment, then route to a plurality of servers) 402 from given user's control signal.As illustrated among Fig. 4 a, can control signal 406a be routed to server 402 via SAN.Replacedly or in addition, can be via the host services network Local Area Network of Ethernet (for example, based on) and control signal 406b is routed directly to server 402.No matter how control signal 406a-b is transmitted, this or described server are all carried out recreation or application software in response to control signal 406a-b.Although it is undeclared among Fig. 4 a, but the diverse network coupling assembling (such as, fire wall and/or gateway) but the edge of edge of processing host service 210 (for example, host services 210 with internet 410 between) and/or customer site 211 (internet 410 with family or office's client 415 between) import into and spread out of communicate by letter.The performed recreation or the figure of application software and audio frequency output (also are, new sequence of video images) provides to low delay video compress logic 404, low delay video compress logic 404 according to the low delay video compression technology (such as, described technology described herein) and the compressed video image sequence and via internet 410 (or, such as hereinafter description, via the optimum high speed network service of walking around common interconnection network) and compressed video flowing (audio frequency that has compressed or uncompressed usually) transmission is back to client 415.Then, low delay video decompression logic 412 decompressed video on the client 415 and audio stream and the video flowing of reproduction, and the common audio stream of on display device 422, playing through decompressing through decompressing.Perhaps, can be on the loudspeaker that separates with display device 422 audio plays or audio plays not.Notice that although input equipment 421 and display device 422 are shown as self contained facility in Fig. 2 a and Fig. 2 b, it can be integrated in the client device such as portable computer or action equipment.

Family or office's client 415 (before being described as family or office's client 205 in Fig. 2 a and Fig. 2 b) can be the equipment of very cheap and low ability, and it has very limited calculating or graphics performance and may have very limited local high capacity reservoir or not have local high capacity reservoir.By contrast, each server 402 that is coupled to SAN403 and a plurality of RAID405 can be especially high performance computing system, and in fact,, then exist hardly the calculated amount that can bear and the restriction of graphics capability if a plurality of servers use with parallel processing configuration cooperation ground.In addition, because low delay video compress 404 and low delay video decompression 412 (by user's perception ground), so the computing power of server 402 is offered the user.When the user pushed button on the input equipment 421, the image on the display 422 was upgraded (no significant delay in perception) in response to button press, as playing or application software is carried out in this locality.Therefore, for being the computing machine of very low performance or just implementing the low delay video decompression and the family of the cheap chip of control signal logic 413 or office's client 415, it seems that certainly available remote location provides any computing power for the user effectively in this locality.This is used to play the ability of the application program of intensive (being generally new) video-game of the superlative degree, processor and peak performance for the user provides.

Fig. 4 c shows very basis and cheap family or office's client device 465.This equipment is an embodiment according to the family of Fig. 4 a and Fig. 4 b or office's client 415.Its about 2 inches long.It has and Ethernet jack 462 with Ethernet cable interfaces of POE (PoE), and this equipment obtains its electric power and to the connectivity of internet from Ethernet jack 462.This equipment can be carried out NAT in the network of network enabled address translation (NAT).In office environment, many new ethernet switch hubs have PoE and directly take PoE in the office Ethernet jack.Under this kind situation, required is from the wall type jack to client 465 Ethernet cable.If connecting, available Ethernet (for example do not transport electric power, have DSL or cable modem but do not having in the family of PoE), then have available cheap wall type " fragment of brick (brick) " (also promptly, power supply), it will accept the Ethernet cable of unregulated power and the Ethernet that output has PoE.

Client 465 contains the control signal logic 413 that is coupled to bluetooth wireless interface (Fig. 4 a), this bluetooth wireless interface and Bluetooth input equipment 479 interfaces such as keyboard, mouse, game console and/or microphone and/or earphone.And, an embodiment of client 465 with the situation of display device 468 coupling under can be with the 120fps output video, display device 468 can support the 120fps video and to a pair of shading eyeglasses 466 signal (usually via infrared) then cover the another eye alternately to cover an eye for each successive frames.The effect that the user felt is the three-dimensional 3D rendering of " jumping out " display screen.Support a kind of this display device 468 of this operation to be Samsung HL-T5076S.Because it is independent being used for the video flowing of each eye, so in the embodiment of two independent video streams by host services 210 compressions, frame is staggered in time, and frame decompresses with two independent decompression process in client 465.

Client 465 also contains low delay video decompression logic 412, video that its decompression is imported into and audio frequency and via HDMI (HDMI (High Definition Multimedia Interface)), connector 463 outputs, HDMI (HDMI (High Definition Multimedia Interface)), connector 463 are inserted among SDTV (standard definition television) or the HDTV (high-definition television) 468, thereby provide video and audio frequency to TV, or be inserted in the monitor 468 of supporting HDMI.If user's monitor 468 is not supported HDMI, then can use HDMI to DVI (Digital Visual Interface), but audio frequency will be lost.Under the HDMI standard, display capabilities (for example, the resolution of being supported, frame rate) 464 from display device 468 expression, and then this information is transferred back to host services 210, so host services 210 can make compressed video flow with the form that is suitable for this display device via Internet connection 462.

Fig. 4 d shows family or office's client device 475, and except client device 475 had more external interfaces, it was identical with shown family or office's client device 465 among Fig. 4 c.And client 475 can be accepted PoE and power, and perhaps it can take the external power adapter of inserting in the wall (not shown).Video camera 477 uses client 475USB input that compressed video is provided to client 475, and compressed video uploads to host services 210 to be used for hereinafter described purposes by client 475.To utilize hereinafter described compress technique that the low delay compressor reducer is created in the camera 477.

Except that having the ethernet connector that is used for its Internet connection, client 475 also has the 802.11g wave point to the internet.Two kinds of interfaces all can use NAT in the network of supporting NAT.

And except that having the HDMI connector that is used for output video and audio frequency, client 475 also has two strands and connects the DVI-I connector, and two strands connects the DVI-I connector and comprises analog output (and have and will provide the VGA standard adapter cable of output).It also has the analog output that is used for composite video and S video.

For audio frequency, client 475 has a left side/three-dimensional RCA jack of right side simulation, and for DAB output, it has TOSLINK (optical fiber) output terminal.

Except to the bluetooth wireless interface of input equipment 479, it also has and is used for the USB jack of interface to input equipment.

An embodiment of the inside structure of Fig. 4 e display client 465.All devices or some equipment shown among this figure may be implemented among a programmable logic array, the customization ASIC or in several discrete device (Custom Design or ready-made).

Ethernet 497 with PoE is attached to Ethernet interface 481.The Ethernet 497 that electric power 499 just has a PoE obtains and is connected to all the other equipment in the client 465.Bus 480 is for being used for the public same bus of the communication between the equipment.

(almost any little CPU is suitable from the control CPU483 of the little client controlling application program of flash memory 476 in execution, such as the MIPS R4000 under the 100MHz with embedded RAM series CPU) implement to be used for network (also be, Ethernet interface) protocol stack and also communicating by letter, and all devices in the configuration client 465 with host services 210.It is also handled with the interface of input equipment 469 and will divide into groups (in case of necessity, together with the customer controller data that are subjected to the forward error correction protection) and sends back to host services 210.And, control CPU483 monitor packets communication (for example, grouping is lost or postponed, with and the timestamp of arrival).This information is sent back to host services 210 so that its consistently monitoring network connect and correspondingly adjust the content of its transmission.At first for being written into, flash memory 476 is used to control the control program of CPU483 and unique sequence number for particular clients Unit 465 during fabrication.This sequence number allows host services 210 identify customer end Unit 465 uniquely.

Blue tooth interface 484 wirelessly is communicated to input equipment 469 via its antenna (in client 465 inside).

Video decompressor 486 is for being configured to implement the low delay video decompressor of video decompression described herein.The multitude of video decompression apparatus exists, and perhaps is off-the-shelf, perhaps as having the intellecture property (IP) that can be incorporated into the design among FPGA or the customization ASIC.H.264 one be provided for that the company of the IP of demoder is the Ocean Logicof Manly of New South Wales,Australia (NSW Australia).Use the advantage of IP to be: compress technique used herein does not conform to compression standard.Some canonical solution compressor reducers are enough flexibly being configured to adapt to compress technique herein, but some canonical solution compressor reducers may be really not so.But, under the situation of IP, optionally have full flexibility in the redesign decompressor.

The output terminal of video decompressor is coupled to video output subsystem 487, and video output subsystem 487 is coupled to video the video output terminals of HDMI interface 490.

Audio decompression subsystem 488 or use available standard audio decompressor to implement, perhaps it can be embodied as IP, perhaps can be in the processor controls 483 of can (for example) implementing the Vorbis audio decompressor enforcement audio decompression.

The device coupled of implementing audio decompression is to audio frequency output subsystem 489, and audio frequency output subsystem 489 is coupled to audio frequency the audio output of HDMI interface 490.

An embodiment of the inside structure of Fig. 4 f display client 475.As seen, remove additional interface and from outside the optional outside DC electric power that inserts the power supply adaptor in the wall (and use if so, then optional outside DC electric power is replaced will be from the electric power of Ethernet PoE497), this framework is identical with the framework of client 465.Hereinafter will not repeat and common functional of client 465, but additional functionality will be described below.

CPU483 communicates by letter with extras and disposes extras.

WiFi subsystem 482 provides the wireless Internet access via its antenna, as substituting Ethernet 497.The WiFi subsystem can comprise the AtherosCommunications (Aunar He Lu stone letter company) of the Santa Clara of California, USA available from how tame manufacturer.

USB subsystem 485 provides substituting the Bluetooth communication that is used for wired USB input equipment 479.The suitable standard of USB subsystem and can easily be used for FPGA and ASIC, and often be created in the off-the-shelf equipment of carrying out as other functions of video decompression.

Compare with the video output in the client 465, video output subsystem 487 produces the video output of relative broad range.Except that the output of HDMI490 video was provided, it provided DVI-I491, S-video 492 and synthetic video 493.And, when the DVI-I491 interface is used for digital video, display capabilities 464 is transmitted back to control CPU483 from display device, so that it can be to the ability of host services 210 notice display devices 478.The total interface that is provided by video output subsystem 487 is the interface of suitable standard and can uses with many forms easily.

Audio frequency output subsystem 489 is via digital interface 494 (S/PDIF and/or Toslink) output audio and via the audio frequency of three-dimensional modelling interface 495 output analog forms digitally.

The round trip delay Analysis

Certainly, in order to realize the interests of the last period, the user uses the action of input equipment 421 and the time-delay of the round trip between the consequence of seeing this action on the display device 420 should be not more than 70 milliseconds-80 milliseconds.This time-delay must be considered to reach to host services 210 at the input equipment in user place 211 421 and turns back to customer site 211 all factors to the path of display device 422 once more.Fig. 4 b illustrates various assemblies and network (signal must be advanced via this assembly or network), and this assembly and network top is timeline, and this timeline is listed expected exemplary time-delay in the actual enforcement.Notice that Fig. 4 b is through simplifying so that only show the important path route.Other routes of the data of other features that are used for system are hereinafter described.Double-headed arrow (for example, arrow 453) indication round trip time-delay and single head arrow (for example, arrow 457) indication one-way delay, and "～" represents approximate the measurement.Should point out that with the real world scenarios that exists listed time-delay to reach, but under a large amount of situations, in the U.S., use DSL and cable modem connection to customer site 211, this time-delay can be reached in the situation described in next section.And, note, although will in shown system, work really to the cellular radio connectivity of internet, most of current American honeycomb fashion data systems (such as, EVDO) cause very high time-delay and can not reach time-delay shown among Fig. 4 b.Yet these ultimate principles can be implemented on the following cellular technologies of the time-delay that may be able to implement this level.

Input equipment 421 beginnings from 211 places, user place, in case the user activates input equipment 421, (it can be the autonomous device such as set-top box just user control signal to be sent to client 415, or it can be software or the hardware of carrying out in another equipment such as PC or action equipment), and with its packetizing (in one embodiment with the UDP form) and serve as the grouping provide destination-address with arrival host services 210.Grouping will also contain and be used to indicate the information of control signal from which user.Then control signal is forwarded a packet to wan interface 442 via firewall/router/NAT (network address translation) equipment 443.Wan interface 442 is for being provided to the interfacing equipment of customer site 211 by user's ISP (ISP).Wan interface 442 can be cable or dsl data machine, WiMax transceiver, fiber optical transceiver, honeycomb fashion data-interface, line of electric force Internet protocol interface (InternetProtocol-over-powerline interface), or any other interface in many interfaces of internet.In addition, firewall/router/NAT device 443 (and (possibly) wan interface 442) can be incorporated in the client 415.This example will be mobile phone, and it comprises the functional software that is used to implement family or office's client 415, and be used for via certain standard (for example, route and be connected to the device of internet 802.11g) and wirelessly.

Wan interface 442 then routes to control signal " existing a little " 441 of the alleged ISP who is used for the user (ISP) herein, and wan interface 442 is for providing the WAN conveyer that is connected to customer site 211 and the facility of the interface between common interconnection network or the private network.The characteristic of existence point the character of the Internet service that is provided will be provided and be changed.For DSL, it is telephone operator's central office of being positioned at of DSLAM normally.For cable modem, it is cable multisystem operator (MSO) front end normally.For cellular system, the pulpit that it is normally relevant with the honeycomb fashion tower.But no matter exist a little character how, it all will then route to common interconnection network 410 with the control signal grouping.Then the control signal grouping is routed to wan interface 444 to host services 210 via the interface that with most probable is the fiber optical transceiver interface.WAN 444 will then route to logical routing 409 with the control signal grouping, and (it can be implemented by many different modes, comprise ethernet switch hub and routing server), the address of logical routing 409 estimating user and control signal routed to the correct server 402 that is used for given user.

Server 402 then is considered as described control signal the input of the recreation carried out or application software and uses described control signal to handle the next frame of recreation or application program on server 402.In case produce next frame, just export video and audio frequency to video compressor 404 from server 402.Can export video and audio frequency to compressor reducer 404 from server 402 via various devices.At first, compressor reducer 404 can be created in the server 402, therefore can in server 402, implement to compress in this locality.Perhaps, can be via to the network (private network between itself or server 402 and the video compressor 404, or via network such as the community network of SAN 403) network connect (such as, Ethernet connects) with the form output video and/or the audio frequency of packetizing.Perhaps, can via video output connector (such as, DVI or VGA connector) with video from server 402 output, and then catch by video compressor 404.And, audio frequency can be output as DAB (for example, via TOSLINK or S/PDIF connector) or analogue audio frequency from server 402, analogue audio frequency comes digitizing and coding by the audio compression logic in the video compressor 404.

In case video compressor 404 has been caught from the frame of video of server 402 and the audio frequency that is produced during this frame time, then video compressor will use hereinafter described technique compresses video and audio frequency.In case video and audio frequency are compressed, just by an address with its packetizing it is sent back to user client 415, and it is routed to wan interface 444, wan interface 444 is then via common interconnection network 410 route video and audio packet, common interconnection network 410 then routes to video and audio packet the existence point 441 of user's ISP, exist point 441 video and audio packet to be routed to the wan interface 442 at customer site place, wan interface 442 routes to firewall/router/NAT device 443 with video and audio packet, and firewall/router/NAT device 443 then routes to client 415 with video and audio packet.

Client 415 decompressed video and audio frequency, and then go up display video and audio frequency sent to display device 422 or to independent amplifier/loudspeaker or to the amplifier/loudspeaker that is created in the client at display device 422 (or built-in display device of client).

For making the user feel that described just now whole process does not lag behind in perception, round trip postpones need be less than 70 milliseconds or 80 milliseconds.Some time-delays in the described round trip path postpone to be subjected to host services 210 and/or user's control, and other time-delay postpones not to be subjected to host services 210 and/or user's control.However, based on the analysis and the test of a large amount of real world conditions, below measure for approximate.

The one-way transmission time 451 that is used to transmit control signal is usually less than 1 millisecond, uses the consumer's level firewall/router/NAT interchanger that is easy to get on the Ethernets usually and finishes in about 1 millisecond via the round trip route 452 of customer site.User ISP changes its round trip widely and postpones 453, but under DSL and cable modem supplier's situation, sees that usually they are between 10 milliseconds and 25 milliseconds.Round trip on the common interconnection network 410 time-delay video capable is engaged in by how, and whether route and road are online exists any fault (and this problem is discussed hereinafter) and greatly changes, but common interconnection network provides quite best route and time-delay to be determined by the speed (given distance to destination) that light passes optical fiber to a great extent usually.As further discussed below, 1000 miles roughly maximum distances of host services 210 being put away from customer site 211 as expectation have been determined.Locate (2000 miles of round trips) at 1000 miles, being used for signal is about 22 milliseconds via actual transmissions time of internet.Wan interface 444 to host services 210 is generally the business level optical fiber high-speed interface with insignificant time-delay.Therefore, common interconnection network time-delay 454 is usually between 1 millisecond and 10 milliseconds.Unidirectional route 455 time-delays via host services 210 can be reached in less than 1 millisecond.Server 402 will calculate in less than the time of a frame time (it is 16.7 milliseconds under 60fps) usually and be used to play or the new frame of application program, and therefore 16 milliseconds is the rational maximum one-way delay 456 that will use.During the best hardware of described in this article video compress and audio compression algorithm was implemented, compression 457 can be finished in 1 millisecond.In inferior good version, compression can spend and reach 6 milliseconds (certainly, not good enough version can spend the longer time, but described enforcement will influence total time-delay of round trip and will need other time-delays to lack (for example, can reduce the admissible distance via common interconnection network) to keep 70 milliseconds-80 millisecond time-delay targets).Considered the round trip time-delay of internet 454, user ISP453 and customer site route 452, therefore remaining is video decompression 458 time-delays, video decompression 458 time-delay depend on video decompression 458 be performed on also be performed in the specialized hardware client device 415 (such as, PC or action equipment) on software in, the performance of the size of visual display unit and decompression CPU and changing.Usually, the time between decompression 458 spends 1 millisecond and 8 milliseconds.

Therefore, can by will be in practice being seen all worst the time-delay of situation be added in the user who comes together to determine system shown among Fig. 4 a and can expect that the round trip of the situation worst that will experience delays time.They are: the 1+1+25+22+1+16+6+8=80 millisecond.In addition, in fact, (explanation that preventing of having hereinafter to be discussed misread) in practice, this is roughly the being seen round trip time-delay of the prototype version that uses system shown among Fig. 4 a (using ready-made Windows PC to connect as client device and the DSL of family and cable modem in the U.S.).Certainly, the situation of situation worst of being better than can cause the time-delay of much shorter, but not responsible its developed widely used commerce services.

In order to reach time-delay listed among Fig. 4 b via common interconnection network, need video compressor 404 in the client 415 and video decompressor 412 (a) to produce stream of packets with very specific characteristic from Fig. 4, so that via from main frame service 210 packet sequence that entire path produced to display device 422 without undergoing postponing or too much packet loss, and in detail, dropping on Internet connection via the user consistently (can be used for via wan interface 442 and firewall/router/NAT433) in user's the constraint of bandwidth.In addition, video compressor must produce enough strong stream of packets, so that inevitable packet loss and packet reordering that its tolerable occurs in normal the Internet and Network Transmission.

The low delay video compress

In order to finish above-mentioned target, an embodiment adopts new video-frequency compression method, and this method reduces time-delay and the peak bandwidth requirement that is used for transmission of video.Before describing this embodiment, will provide analysis about Fig. 5 and Fig. 6 a to Fig. 6 b to the current video compress technique.Certainly, if the user possesses the bandwidth that is enough to handle the required data rate of described technology, then this technology can be used according to ultimate principle.Note, do not solve audio compression herein, but the statement audio compression is with the video compress while and synchronously implement.The prior art audio compression techniques that satisfies the requirement that is used for this system exists.

Fig. 5 explanation is used for a specific prior art of compressed video, wherein uses the specific compression algorithm to compress each individual video frame 501-503 to produce a series of compressed frame 511-513 by compressed logic 520.An embodiment of this technology is " motion JPEG ", wherein compresses each frame according to joint image expert group (JPEG) compression algorithm based on discrete cosine transform (DCT).Can use various dissimilar compression algorithms, yet, this ultimate principle (for example, based on the compression algorithm of small echo, such as JPEG-2000) still observed.

A problem of this type compression is: it has reduced the data rate of each frame, but it does not utilize the similarity between the successive frame to reduce the data rate that total video flows.For example, as illustrated in fig. 5, suppose the frame rate of 640 * 480 * 24 bits/pixel=640*480*24/8/1024=900 kilobyte/frame (KB/ frame), then for the image of given quality, motion JPEG may only will should compress 1/10 by stream, thereby produced the data stream of 90KB/ frame.Under 60 frame/seconds, this will need the channel width of 90KB*8 bit * 60 frame/second=42.2Mbps, it will be high bandwidth for the nearly all now home interconnect net of the U.S. connects, and will be too high bandwidth for the Internet connection of many offices.In fact, suppose that it requires constant traffic under the situation of this kind high bandwidth, and it will only serve a user, even then in office's lan environment, its big percentage that also will consume the bandwidth of 100Mbps ethernet lan is when supported the heavy-laden ethernet switch hub of LAN.Therefore, when when comparing, being used for the compression inefficiency of sport video with other compress techniques (such as described those technology hereinafter).In addition, use the single frame compression algorithm (as JPEG and JPEG-2000) of lossy compression method algorithm be created in the rest image may the false shadow of unnoticed compression (for example, false shadow in the intensive leaf in the scene may not be rendered as false shadow, because eye does not know definitely how intensive leaf presents).But in case scene at the volley, false shadow just may be given prominence to, because eye detects the false shadow that changes to frame from frame, although false shadow is in the zone of scene (in this zone, false shadow may be not noticeable in rest image).This causes the perception of " background noise " in the frame sequence, and the outward appearance and edge analog TV reception period visible " snowflake " noise that are somebody's turn to do " background noise " are similar.Certainly, the compression of the type still can be used in the specific embodiment described herein, but generally speaking, and the background noise in the scene for given perceived quality, needs high data rate (low compression ratio rate also promptly).

The compression of other types (such as, H.264, or windows media VC9, MPEG2 and MPEG4) all more effective in compressing video frequency flow, because it utilizes the similarity between the successive frame.These technology all depend on the identical general technology that is used for compressed video.Therefore, although will describe H.264 standard, identical General Principle is applicable to various other compression algorithms.H.264 compressor reducer and decompressor can be used in a large number, comprise the x264 open-source software library that is used to compress H.264 and H.264 FFmpeg (a kind of video and audio stream scheme) the open-source software library of being used to decompress.

Fig. 6 a and Fig. 6 b illustrative examples expressivity prior art compress technique wherein are compressed into a series of " I frames " 611,671 by compressed logic 620 with frame of video 501-503, the 559-561 of a series of uncompressed; " P frame " 612-613; And " B frame " 670.Z-axis among Fig. 6 a is represented each the gained size (although described frame is drawn not in scale) in the encoded frame substantially.As mentioned above, those skilled in the art understands well and uses the video of I frame, B frame and P frame to write sign indicating number.In brief, I frame 611 is the compression based on DCT of complete unpressed frame 501 (being similar to aforesaid compressed jpeg image).The remarkable usually size less than I frame 611 of the size of P frame 612-613 is because it utilizes the data in previous I frame or the P frame; Also promptly, it contains the data of the change between previous I frame of indication or the P frame.Except that the B frame uses frame in the reference frame subsequently and (possibly) before the frame in the reference frame, B frame 670 is similar to the P frame.

For following argumentation, will suppose that desired frame rate was 60 frame/seconds, each I frame is about 160Kb, mean P frame and B frame are 16Kb and produced a new I frame every one second.Under this group parameter, mean data rate will be 160Kb+16Kb*59=1.1Mbps.This data rate suitably drops in the maximum data rate of the many current broadband internet connection that is used for family and office.This technology is also tended to avoid from the background noise problem of intraframe coding only, because P frame and B frame are followed the trail of the difference between the frame, therefore compresses false shadow and tends to not to present to frame and disappear from frame, thereby reduce background noise problem as described above.

A problem of the compression of the above-mentioned type is: (for example, 1.1Mbps), single I frame may spend several frame times and transmit although mean data rate is low relatively.For example, use prior art, the 2.2Mbps network connects (for example, DSL or cable modem, it has the 2.2Mbps peak value from the maximum usable data rates 302 of Fig. 3 a) will enough make video flow the I frame of a 160Kbps of per 60 frames with 1.1Mbps usually.This will finish by making decompressor before decompressed video 1 second video be entered formation.In 1 second, data that will transmission 1.1Mb, it will easily adapt to by the 2.2Mbps maximum usable data rates, and will be 50% also like this even the supposition available data rate may periodically descend nearly.Unfortunately, this prior art approach will cause time-delay in 1 second of video owing to 1 second video buffer at receiver place.This kind delay is enough for many prior art application programs (for example, the playback of linear video), but for not tolerable extremely long time-delay of Yan Qiwei greater than the snap action video-game of 70 milliseconds-80 milliseconds time-delay.

If attempt eliminating 1 second video buffer, its enough time-delay that will not can cause being used for the snap action video-game reduces.For example, as discussed previously, the use of B frame will need to receive preceding all the B frames and the I frame of I frame.If 59 non-I frames are roughly divided in supposition between P frame and B frame, then will there be at least 29 B frames and can show the I frame that is received before any B frame.Therefore, no matter the available bandwidth of channel how, all needs the delay of 29+1=30 each 1/60 second duration of frame, or 500 milliseconds time-delay.Obviously, this time compole long.

Therefore, other method will be to eliminate the B frame and only use the I frame and the P frame.(one of them consequence is: for given quality level, data rate will increase, but for for the purpose of the consistance in this example, the size that continues each I frame of supposition is that the size of 160Kb and mean P frame is 16Kb, and therefore data rate still is 1.1Mbps).This method has been eliminated the inevitable time-delay of being introduced by the B frame, because the decoding of each P frame only depends on the frame that is before received.The problem that this method still exists is: the I frame is more much bigger than mean P frame, so that on low bandwidth channel (typical as reaching in most of families in many offices), the essence time-delay is added in the transmission of I frame.This is illustrated in Fig. 6 b.Video stream data speed 624 is lower than available maximum data speed 621 (except that for the I frame), wherein the required peak data rate 623 available maximum data speed 622 (and even above specified maximum data rate 621) that surpass far away of I frame.The required data rate of P frame is less than available maximum data speed.Even the available maximum data speed peak value at 2.2Mbps stably remains on its 2.2Mbps peak rate, also will spend the 160Kb/2.2Mb=71 millisecond and transmit the I frame, and 50% (1.1Mbps) if available maximum data speed 622 descends then will spend 142 milliseconds and transmit the I frame.Therefore, the time-delay in the transmission I frame will drop on the somewhere between 71 milliseconds and 142 milliseconds.The time-delay of being discerned among Fig. 4 b (described time-delay is adding up 70 milliseconds under the situation worst) is added in this time-delay to, therefore, this will cause being presented in the total round trip time-delay for the 141-222 millisecond on the display device 422 from moment that the user activates input equipment 421 up to image, and it is high.And if available maximum data speed drops to and is lower than 2.2Mbps, then time-delay will further increase.

Being also noted that with the peak data rate 623 that surpasses available data rate 622 far away makes ISP " obstruction " have serious consequence usually.Equipment among the different I SP will differently show, but when receiving grouping with the data rates more much higher than available data rate 622, following behavior is quite general in the middle of DSL and cable modem ISP: (a) make packetization delay (introducing time-delay) by grouping being entered formation, (b) abandon some or all of groupings, (c) will connect cycle time of stopping using (most probable is malicious attack because ISP worries it, attacks such as " denying service ").Therefore, be not to be feasible option with full data rate transport packet stream (having characteristic) such as described characteristic shown among Fig. 6 b.Can peak value 623 be entered formation at host services 210 places and send, thereby introduce unacceptable time-delay described in the last period with the data rate that is lower than available maximum data speed.

In addition, shown video stream data speed sequence 624 is unusual " tame (tame) " video stream data speed sequence among Fig. 6 b, and will be this kind data rate sequence of expecting generation from the video of video sequence owing to compression, this video sequence does not change very big and (for example has considerably less motion, as will being general in video conference call, in video conference call, camera is in a fixed position and has a considerably less motion, and the object in the scene (people who for example, takes one's seat talks) shows less physical activities).

Among Fig. 6 c shown video stream data speed sequence 634 for from video with much more action (such as, may in film or video-game or in certain application software, produce) expect visible type sequence.Note, except that I frame peak 633, also exist quite big and on many occasions above the P frame peak of available maximum data speed (such as, 635 and 636).Although described P frame peak is also generally quite big not as the I frame peak, it still greatly consequently can not be transported with full data rate by channel, and as the I frame peak, the P frame peak must transmit (increase whereby and delay time) lentamente.

On high-bandwidth channels (for example, 100Mbps LAN, or the connection of high bandwidth 100Mbps private), network can be tolerated the big peak value such as I frame peak 633 or P frame peak 636, but in principle, can keep low delay.But, described network shared in the middle of many users that are everlasting (for example, in office environment), and be somebody's turn to do the performance that " peak is arranged " data will influence LAN, especially under the situation of network service through routing to the shared connection of private (for example, from the remote data center to the office).At first, remember that this example is the example of the video flowing of the relative low resolution of 640 * 480 pixels under the 60fps.The HDTV fluid capacitance of under the 60fps 1920 * 1080 is easily handled by modern computer and display, and 2560 * 1440 resolution displays under the 60fps available day by day (for example, 30 of Apple company " display).Use H.264 compression, the high action video sequence of 1920 * 1080 under the 60fps may need 4.5Mbps to obtain the reasonable quality level.If supposition I frame peak is 10 times of nominal data speed, then it will produce the 45Mbps peak value, and less but still sizable P frame peak.If several users just at same 100Mbps network (for example, office is connected with private network between the data center) go up receiver, video stream, then see from the peak value of some users' video flowing how to aim at by chance easily, thereby flood the bandwidth of network, and may flood the bandwidth of the base plate of the interchanger of supporting the user on the network.Even under the situation of hypervelocity Ethernet, if enough users have enough peak values of aiming at simultaneously, then it can flood network or network switch.In addition, in case 2560 * 1440 resolution videos become more common, the average video stream data rate just may be 9.5Mbps, thereby perhaps produces the 95Mbps peak data rate.Much less, data center is connected (it is especially fast connection now) and will be routed by the peak value communication from the sole user fully with 100Mbps between the office.Therefore, even LAN and private network connect there being the mobile video in peak can have higher tolerance, the mobile video with peak value also is unwanted and may needs the special project and the adaptation of the IT department of office.

Certainly, for the normal linearity video application, this problem is not a problem, because data rate is lower than maximum usable data rates 622 at transmission point " through smoothing " and the data that are used for each frame, and before decompression I frame, P frame and B frame sequence, the impact damper in the client stores I frame, P frame and B frame sequence.Therefore, the data rate on the network keeps approaching the mean data rate of video flowing.Regret, this introduces time-delay, even do not use the B frame, for for the low delay application program of video-game that needs the fast-response time and application program, this also is unacceptable.

A prior art solution that is used to alleviate the video flowing with peak value usually is to use the technology that " constant bit-rate " (CBR) encodes that is known as.Although term CBR appears to hint to have same bits speed (also be with all frames compressions, the size), but its often mention for the compression example, the compression example in, allow the maximum bit rate of the frame (under our situation, 1 frame) of leap given number.For example, under the situation of Fig. 6 c, if coding is applied CBR constraint (its bit rate is limited to (for example) specified maximum data rate 621 70%), then compression algorithm will limit each the compression in the described frame so that will use usually specified maximum data rate 621 70% with on any frame of compressing will compress with less bit.This result is: will make the picture quality that will need more bits to keep the frame of given quality level " extremely lack " bit and described frame usually will be than not needing the picture quality than other frames of more than 70% bit of specified maximum data rate 621 to be pickled with grains or in wine.The method for the compressed video of particular type (wherein (a) expection less physical activities or scene change and (b) user can accept periodic degrading quality) can produce acceptable result.The good example that is fit to the application of CBR is a video conference call, because there is less peak value, and under the situation of the temporary transient degradation of quality (for example, if make the camera pan, thereby cause remarkable scene motion and big peak value, then may not exist enough bits to be used for high quality graphic compression during sweeping, it will cause the picture quality of demoting), most of users can accept.Regret, CBR is fit to have the scene of high complexity well or moves in a large number and/or many other application of the quality level that needs are rationally constant.

Employed in one embodiment low delay compressed logic 404 uses some different technologies to solve the mobile compressed video of low delay and keeps high-quality many problems simultaneously.At first, low delay compressed logic 404 only produces I frame and P frame, the needs of each B frame thereby several frame times of alleviation wait are decoded.In addition, as illustrated among Fig. 7 a, in one embodiment, low delay compressed logic 404 is divided into the frame 701-760 of each uncompressed more a series of " image block (tile) " and each image block individually is encoded to I frame or P frame.In this article compressed I frame and the P frame of this group is called " R frame " 711-770.In Fig. 7 a, in the shown particular instance, the frame of each uncompressed is divided into again 16 image blocks of 4 * 4 matrixes.Yet described ultimate principle is not limited to any specific mechanism of dividing again.

In one embodiment, low delay compressed logic 404 is divided into many image blocks with frame of video, and will (also be from an image block coding of each frame, compression) for the I frame (also is, with this image block compression, as it be 1/16 independent frame of video of the size of full images, and is used for the boil down to I frame compression of this " mini " frame) and be P frame (also promptly, the boil down to P frame that is used for each " mini " 1/16 frame compresses) with the residual image block encoding.Compressed for the image block of I frame and compressedly reach " P image block " with being known as " I image block " respectively for the image block of P frame.Change the image block of I image block that is to be encoded along with each subsequent video frame.Therefore, in given frame time, in the described image block in the frame of video only an image block be the I image block, and the surplus P image block that the rest is in the described image block.For example, in Fig. 7 a, the image block of the frame 701 of uncompressed 0 is encoded be I image block I0 and remaining 1-15 image block encoded for P image block (P1 to P15) to produce R frame 711.In the frame of video 702 of next uncompressed, the image block of the frame 701 of uncompressed 1 is encoded be I image block I1 and remaining image block 0 and 2 to 15 encoded for P image block (P0, and P2 to P15) to produce R frame 712.Therefore, it is little by little staggered in time on successive frames to be used for the I image block of image block and P image block.This process continues, until produce R image block 770 (the most last image block is encoded in the matrix be I image block (also promptly, I15)) till.This process is then restarted, thereby produces another R frame such as frame 711 (also promptly, for image block 0, coding I image block) etc.Although undeclared among Fig. 7 a, in one embodiment, a R frame of the video sequence of R frame only contains I image block (also promptly, so that P frame subsequently has reference image data (beginning to calculate motion from it)).Perhaps, in one embodiment, initiating sequence use with normal phase with I image block type sample, but do not comprise the P image block that is used for as yet not the described image block of encoding together with the I image block.In other words, before an I image block arrives not together with any data specific image block of encoding, thereby avoid startup peak value in the video stream data speed 934 among Fig. 9 a, it further describes hereinafter.In addition, as described below, various different sizes and shape can be used for described image block and still observe described ultimate principle simultaneously.

Video decompression logic 412 each image block of decompression of carrying out on client 415 are the independent video sequence of little I frame and P frame as it, and then each image block are reproduced to the frame buffer that drives display device 422.For example, use to come decompress(ion) to contract from the I0 of R frame 711 to 770 and P0 to reproduce the image block 0 of video image.Similarly, use I1 and P1 to come reconstructed image piece 1 from R frame 711 to 770, or the like.As mentioned above, the decompression of I frame and P frame is many known in this technology, and the decompression of I image block and P image block can be finished by individual the execution on client 415 of a plurality of execution that make video decompressor.Although multiplicative process appears to increase the computation burden on the client 415, but in fact it can not increase the computation burden on the client 415, because image block less pro rata (for the number of extra process) itself, therefore the number of shown pixel is identical, as the I frame and the P frame that exist one to handle and use traditional full size.

This R frame technique significantly alleviates the bandwidth peak (illustrated among Fig. 6 b and Fig. 6 c) that is associated with the I frame usually, because any given frame mainly is to be made of the common P frame littler than I frame.For example, suppose that once more typical I frame is 160Kb, then the I image block of each in the illustrated frame will be roughly 1/16 or 10Kb of this amount among Fig. 7 a.Similarly, suppose that typical P frame is 16Kb, each the P frame that then is used in the illustrated image block of Fig. 7 a can be roughly 1Kb.Net result is the R frame of about 10Kb+15*1Kb=25Kb.Therefore, each 60 frame sequence will be 25Kb*60=1.5Mbps.Therefore, under 60 frame/seconds, this will need to keep the channel of the bandwidth of 1.5Mbps, but owing to the I image block is to run through 60 frame periods to disperse to make to have much lower peak value.

Notice that formerly in the example, be used under the identical tentation data rate behavior of I frame and P frame, mean data rate is 1.1Mbps.This is because formerly in the example, only introduces new I frame every 60 frame times, and in this example, 16 image blocks that constitute the I frame circulate in 16 frame times, and therefore, introduce the equipollent of I frame every 16 frame times, thereby cause high slightly mean data rate.But in practice, introducing more frequent I frame can't increase data rate linearly however.This is due to the fact that the main difference to next frame from previous frame of encoding of P frame (or P image block).Therefore, if previous frame and next frame are quite similar, then the P frame will be very little, if previous frame is quite different with next frame, then the P frame will be very big.But because the P frame is to derive from previous frame to a great extent, but not derive, so the encoded frame of gained may contain the mistake (for example, visual artifacts) of Duoing than the I frame of the bit with enough numbers from actual frame.In addition, when a P frame is followed another P frame, mistake add up (when having long P frame sequence, becoming even worse) can appear.Now, most advanced and sophisticated video compressor will detect the fact of the quality of image at the back degradation of a sequence P frame, and in case of necessity, and it will more Bit Allocation in Discrete gives subsequently P frame improving the quality, or if it be the most effective course of action, then uses I frame replacement P frame.Therefore, when using long P frame sequence (for example, 59 P frames are in the previous as mentioned example), particular words when scene has large amount of complex degree and/or motion, common, need more bits (becoming farther) for the P frame apart from the I frame because of it.

Perhaps, a little see the P frame from watching relatively, the P frame of closely following the I frame tends to the bit that need the P frame more farther than distance I frame lacks.Therefore, in Fig. 7 a, in the shown example, do not have the P frame to separate 15 frames farther (before the I frame), and formerly in the example, the P frame may separate 59 frames from the I frame than apart from the I frame.Therefore, under more frequent I frame condition, the P frame is less.Certainly, definite relative size will change based on the character of video flowing, but in the example of Fig. 7 a, if the I image block is 10Kb, then the size of P image block on average can be only 0.75kb, thereby causes 10Kb+15*0.75Kb=21.25Kb, or under 60 frame/seconds, data rate will be 21.25Kb*60=1.3Mbps, or than the data rate high about 16% that the I frame is followed the stream of 59 P frames subsequently that has under the 1.1Mbps.Again, be used for relative result between described two kinds of methods of video compress and will look video sequence and change, but usually, we find by rule of thumb, for given quality level, use the R frame than the bit that uses I/P frame sequence needs and Duo about 20%.But certainly, the R frame reduces peak value sharp, and this makes video sequence available under the time-delay of I/P frame sequence.

The character of visual video sequence, the reliability of channel and available data rate and dispose the R frame with multitude of different ways.In alternate embodiment, in 4 * 4 configurations, use the image block be different from 16 number.For example, can in 2 * 1 or 1 * 2 configuration, use 2 image blocks, can in 2 * 2,4 * 1 or 1 * 4 configuration, use 4 image blocks, can in 3 * 2,2 * 3,6 * 1 or 1 * 6 configuration, use 6 image blocks or can in 4 * 2 (as shown in as Fig. 7 b), 2 * 4,8 * 1 or 1 * 8 configuration, use 8 image blocks.Notice that image block does not need for square, frame of video also needn't be for square, or even rectangle.Image block can be resolved into the shape whatsoever that is fit to employed video flowing and application program best.

In another embodiment, the circulation of I image block and P image block is not locked to the number of image block.For example, in the configuration of 8 image blocks 4 * 2, still can be as illustrated among Fig. 7 b and use 16 cyclic sequences.The frame 721,722,723 of the uncompressed of order is respectively hung oneself and is divided into 8 image block 0-7, and each image block is compressed individually.From R frame 731, only image block 0 is compressed to the I image block, and the residual image piece is compressed to the P image block.For R frame 732 subsequently, all 8 image blocks are compressed to the P image block, and then for subsequently R frame 733, image block 1 is compressed to the I image block and other image blocks all are compressed to the P image block.In addition, so proceed ordering for 16 frames, only produce an I image block every a frame, therefore (not shown among Fig. 7 b) reaches and produce the most last I image block (using all P image block compression R frames 780) that is used for image block 7 during the 16th frame time during the 15th frame time.Then, sequence is compressed to I image block and other image blocks with image block 0 once more and is compressed to the P image block and begins.As among the embodiment formerly, first frame of whole video sequence will be the I image block usually, to be provided for from the reference of this some P image block forward.The circulation of I image block and P image block does not even need the even multiple for the number of image block.For example, under the situation of 8 image blocks, before using another I image block, each frame with an I image block can be 2 frames that all are the P image block afterwards.In another embodiment, if the specific region of (for example) known screen has more do more physical exercises (needing more frequent I image block), and other zones are more static (for example, the mark that shows recreation) (needs more not frequent I image block), then compare, can more frequently specific image block be sorted together with the I image block with other image blocks.In addition, although each frame of explanation has single I image block, a plurality of I image blocks (bandwidth that depends on transmission channel) of can encoding in single frame in Fig. 7 a-Fig. 7 b.On the contrary, particular frame or frame sequence can transmit under the situation that does not have I image block (also promptly, only P image block).

The reason that the method for the last period suitably works is: do not appear to cause big peak value although do not have the I image block of crossing over each single frame and disperseing, the behavior of system is so not simple.Because each image block is to separate with other image blocks to compress, so when image block diminishes, it is more ineffective that the coding of each image block can become, because the compressor reducer of given image block can not be used to similar characteristics of image and similar motion from other image blocks.Therefore, compare, become 16 image blocks will cause more not efficient coding usually screen divider with screen divider being become 8 image blocks.But if become 8 image blocks and its to cause the data of introducing a complete I frame every 8 frames (but not every 16 frames) screen divider, then it causes much higher generally data rate.Therefore, by introducing a complete I frame, reduced total data rate every 16 frames (but not every 8 frames).And, by using 8 big image blocks (but not 16 less image blocks), having reduced total data rate, it also will be alleviated by the data peaks that big image block causes to a certain degree.

In another embodiment, the low delay video compress logic 404 among Fig. 7 a and Fig. 7 b is by based on the known features of video sequence to be compressed and by setting pre-configured or based on the ongoing analysis of the picture quality in each image block and automatically be controlled to the distribution of the bit of each image block in the R frame.For example, in some contest video-games, the place ahead of player's automobile (it is for nonmotile relatively in the scene) occupies the major part of the Lower Half of screen, and the first half of screen is filled just approaching road, buildings and landscape fully, and it almost always at the volley.If compressed logic 404 is given each image block with the Bit Allocation in Discrete of equal number, then the image block (image block 4-7) on the Lower Half of the screen in the frame 721 of the uncompressed among Fig. 7 b usually will be to compress than (image block 0-3) the high quality of the image block in the first half of the screen in the frame 721 of the uncompressed among Fig. 7 b.If this special scenes of known this particular game or recreation has described characteristic, then the configurable compressed logic 404 of the operator of host services 210 is with the image block of will more Bit Allocation in Discrete giving the top of screen (bit of the image block of locating with the bottom of distributing to screen is compared).Perhaps, compressed logic 404 can be after the condensed frame compression quality of estimated image piece (use in many compression qualities tolerance one or more, such as the peak signal noise than (PSNR)), and if determine on the special time window, specific image block produces the better quality result consistently, then it little by little gives the image block that produces than the inferior quality result with more Bit Allocation in Discrete, reaches until various image blocks till the quality of similar level.In alternate embodiment, compressor logic 404 allocation bit are to reach better quality in specific image block or image block group.For example, it can provide preferable general perceives outward appearance, has the quality higher than edge with the center at screen.

In one embodiment, for the resolution of the specific region of improveing video flowing, what video compress logic 404 used that less image block comes encoded video streams has the many relatively scene complexities and/or a zone (the relative few scene complexity with having of video flowing and/or the zone of motion are compared) of motion.For example, as illustrated in fig. 8, use less image block around the mobile personage 805 in a zone of a R frame 811 (a series of R frames (not shown) that may and then have the identical image block size subsequently).Then, when personage 805 moves to the new region of image, use less image block around this new region in another R frame 812, as described.As mentioned above, various different sizes and shape can be used as " image block " simultaneously still in accordance with described ultimate principle.

Although circulation I/P image block as described above reduces the peak value in the data rate of video flowing in fact, but it also not exclusively eliminates peak value, especially change fast or the situation of the video image (such as occurring under film, video-game and a certain application software) of high complexity under.For example, during unexpected scene transitions, complex frames may be followed diverse another complex frames subsequently.Even several I image blocks can be led over the only several frame times of scene transitions, it does not have help in this case yet, because the material of new frame is irrelevant with previous I image block.(even reach not is being that all change in this case, under other situations that great amount of images also changes), video compressor 404 will determine that many (if be all) P image block is more effectively write sign indicating number is the I image block, and what caused is very large peak value in the data rate of described frame.

As discussed previously, it only is the situation for most consumers level Internet connection (and many offices connect), and it only can not " stop up " to surpass and be shown as 622 the available maximum data speed and the data of specified maximum data rate 621 among Fig. 6 c.Notice that specified maximum data rate 621 (for example, " 6Mbps DSL ") is essentially the sales figure for the user who considers to buy Internet connection, but its guaranteed performance level not usually.For this application aims, it is incoherent, because we only pay close attention to the available maximum data speed 622 when via connection video being flowed.Therefore, in Fig. 9 a and Fig. 9 c, when the solution described spike problem, omit specified maximum data rate from curve map, and only show available maximum data speed 922.Video stream data speed must not surpass available maximum data speed 922.

For head it off, first thing that video compressor 404 carries out is to determine peak data rate 941, the data rate that it can stably be handled for channel.This speed can be determined by many technology.A kind of this technology be will all the more uprise data rate test stream be sent to client 415 (among Fig. 4 a and Fig. 4 b) gradually from main frame service 210, and client will be provided to host services about the feedback of the level of packet loss and time-delay.When packet loss and/or time-delay began to show sharp-pointed increase, it was the indication that reaches available maximum data speed 922.Afterwards, host services 210 can little by little reduce to test the data rate of stream, until client 415 be reported in received test stream (acceptable level of packet loss and time-delay is near minimum) in the rational time cycle till.This determines peak value maximum data rate 941, and it then will be with the peak data rate that acts on the video that flows.As time goes on, peak data rate 941 (for example will fluctuate, internet usage connects if another user in the family begins seriously), and client 415 will need to monitor consistently whether peak data rate 941 increases (indication available maximum data speed 922 drops to and is lower than previous determined peak data rate 941) to watch packet loss or time-delay, and peak data rate 941 then if so.Similarly, if As time goes on, client 415 finds that packet loss and time-delay remain on optimum level, whether then it can ask video compressor to increase data rate lentamente (for example increases to watch available maximum data speed, if another user in the family has stopped the serious use to Internet connection), and wait for once more until packet loss and/or higher time-delay and indicating above till the available maximum data speed 922, and can find to be used for the reduced levels of peak data rate 941 once more, but this reduced levels may be higher than the data rate level before that test increases.Therefore, can find peak data rate 941 by using this technology (and similar its other technologies), and optionally and periodically adjust.Peak data rate 941 is determined and can be used so that video flows to user's maximum data rate by video compressor 404.Be used for determining that the logic of peak data rate can and/or be implemented at customer site 211 places on host services 210.At customer site 211 places, client device 415 is carried out and is calculated to determine peak data rate and this information transmission is back to host services 210; At host services 210 places, the server at host services place 402 is carried out and is calculated to determine peak data rate based on the statistics that is received from client 415 (for example, peak value is lost, time-delay, maximum data rate etc.).

Fig. 9 a shows to have the instance video stream data rate 934 of essence scene complexity and/or motion, and it is to use the previous circulation I/P image block compress technique of describing and being illustrated and produces in Fig. 7 a, Fig. 7 b and Fig. 8.Video compressor 404 is configured and exports compressed video with the mean data rate that is lower than peak data rate 941, and notices that the most of the time, video stream data speed keeps below peak data rate 941.The circulation I/P image block compression that relatively shows of shown video stream data speed 634 among data rate 934 and Fig. 6 c (its be to use I/P/B or I/P frame and produce) produces much level and smooth data rate.But under 2 times of peak values 952 of frame (it is near 2 times of peak data rate 942) and 4 times of peak values 954 of frame (it is near 4 times of peak data rate 944), data rate still surpasses peak data rate 941, and this is unacceptable.In practice, even for high action video from the video-game of quick change, the peak value that surpasses peak data rate 941 also occurs in less than 2% frame, and the peak value that surpasses 2 times of peak data rate 942 seldom occurs, and seldom occurs above the peak value of 3 times of peak data rate 943.But when it occurs really (for example, in scene between tour), its required data rate must produce the video image of good quality.

A mode of head it off is to dispose video compressor 404 simply so that its maximum data rate is output as peak data rate 941.Unfortunately, the gained video output quality of peak value image duration is bad, because compression algorithm " extremely lacks " bit.What caused is to occur compressing false shadow when having transformation suddenly or rapid movement, and in time, the user begins to recognize: the vacation shadow always occurs suddenly when having flip-flop or rapid movement, and it can become quite disagreeable.

Although people's vision system is quite responsive to the visual artifacts that occurs during flip-flop or rapid movement, under described situation, detect frame rate to reduce not be very responsive.In fact, when described flip-flop occurs, appear people's vision system and be absorbed in and follow the trail of described change, and if frame rate temporarily drops to 30fps and then turns back to 60fps immediately from 60fps, then people's vision system can not noticed.In addition, under the situation of very rapid transformation (as unexpected scene change), if frame rate drop to 20fps or even 15fps and then turn back to 60fps immediately, then people's vision system can not noticed.As long as frame rate reduces only to occur once in a while, for the people observer, appear video constantly to carry out with 60fps.

Utilize this characteristic of people's vision system by technology illustrated among Fig. 9 b.Server 402 (from Fig. 4 a and Fig. 4 b) produces the video output streams of uncompressed with stabilizer frame speed (in one embodiment, under 60fps).Each frame 961-970 output that timeline shows each 1/60 second.From frame 961 beginning, export the frame of video of each uncompressed to low delay video compressor 404, low delay video compressor 404 compress described frame in less than the time of a frame time, and generation is used for the compressed frame 1981 of first frame.Be used for data visualization many factors as described earlier of compressed frame 1981 and bigger or less through generation.If data are enough little so that can transmit it to client 415 at a frame time (1/60 second) or in less than a frame time by peak data rate 941, then during the transmission time (xmit time) 991 (indicating the length of arrow of the duration in transmission time) with its transmission.In next frame time, server 402 produces the frame 2962 of uncompressed, it is compressed into compressed frame 2982, and transmits it to client 415 with peak data rate 941 during the transmission time 992 less than a frame time.

Then, in next frame time, server 402 produces the frame 3963 of uncompressed.When compressing the frame 3963 of uncompressed by video compressor 404, the data of the compressed frame of gained 3983 for Duoing than the data of can peak data rate 941 in a frame time, transmitting.Therefore, with its transmission, it occupies the part of all frame times and next frame time during the transmission time (2 times of peak values) 993.Now, during next frame time, server 402 produces the frame 4964 of another uncompressed and exports it to video compressor 404, but data are left in the basket and illustrate by 974.This is because video compressor 404 is configured to ignore the frame of video of other uncompressed that arrive when it still transmits before compressed frame.Certainly, the video decompressor of client 415 will fail to receive frame 4, and display frame 3 lasts 2 frame times (also promptly, temporarily frame rate being decreased to 30fps from 60fps) on display device 422 but it continues simply.

For next frame 5, the frame 5965 of server 402 output uncompressed, with its be compressed into compressed frame 5985 and during the transmission time 995 in 1 frame with its transmission.The video decompressor decompressed frame 5 of client 415 also is shown in it on display device 422.Then, the frame 6966 of server 402 output uncompressed, video compressor 404 is compressed into compressed frame 6986 with it, but the data of gained are very big at this moment.With the compressed frame of peak data rate 941 transmission, 4 frame times come transmission frame but spend almost during the transmission time (4 times of peak values) 996.During ensuing 3 frame times, video compressor 404 is ignored 3 frames from server 402, and the decompressor of client 415 stably remains on frame 6 and lasts 4 frame times (also promptly, temporarily frame rate being decreased to 15fps from 60fps) on the display device 422.Then last, server 402 output frames 10970, video compressor 404 is compressed into compressed frame 10987 with it, and during the transmission time 997 with its transmission, and the decompressor decompressed frame 10 of client 415 and be shown in it on display device 422 and again video restart with 60fps.

Note, although video compressor 404 has abandoned the frame of video of the video flowing that comes free server 402 generations, but it can not abandon voice data (no matter audio frequency is with what form to come), and video compressor 404 continues audio compressed data and transmits it to client 415 when abandoning frame of video, and client 415 continues the decompression voice data and audio frequency is provided to the equipment whatsoever that is used by the user with plays back audio.Therefore during abandoning the cycle of frame, audio frequency continues and does not weaken.Compare with compressed video, the bandwidth of the compressed relatively little number percent of audio frequency consumption, and therefore can considerable influence not arranged to total data rate.Although all undeclared in any one in data rate figure, always exist in the peak data rate 941 through being preserved for the data rate capacity of compressed audio stream.

Select just the example described in Fig. 9 b illustrate data rate between the peak period frame rate how to descend, but unaccounted is when using previous described circulation I/P image block technology, described data rate peak value and with generation the frame that abandons seldom, even high scene complexity/high action sequence (such as in video-game, film and certain application software, occur those) during also like this.Therefore, the frame rate that reduces is rare and temporary transient, and people's vision system can not detect them.

If will be just described frame rate reduce mechanism and be applied to video stream data speed illustrated among Fig. 9 a, the video stream data speed of explanation gained in Fig. 9 c then.In this example, 2 times of peak values 952 have been decreased to 2 times of peak values 953 of planarization, and 4 times of peak values 955 have been decreased to 4 times of peak values 955 of planarization, and whole video stream data rate 934 remains in or is lower than peak data rate 941.

Therefore, use technology as described above, can transmit high action video stream with low delay via common interconnection network and the Internet connection of consumer's level.In addition, at LAN (for example, 100Mbs Ethernet or 802.11g wireless network) go up or private network (for example, data center is connected with 100Mbps between the office) on office environment in, can under no peak condition, transmit high action video stream, so that a plurality of users (for example, with 1920 * 1080 under the 4.5Mbps transmission 60fps) can use LAN or shared private data to connect, and do not make the overlapping peak value flood (overwhelm) network or network switch base plate.

Data rate is adjusted

In one embodiment, the available maximum data speed 622 of host services 210 initial evaluation channels and time-delay are with the proper data speed that is identified for video flowing and then dynamically adjust data rate in response to this.In order to adjust data rate, host services 210 can (for example) be revised the image resolution ratio and/or the number of pictures per second of the video flowing to client 415 to be sent.And, the quality level of host services is adjustable warping compressed video.When changing the resolution of video flowing (for example, from 1280 * 720 resolution to 640 * 360), the video decompression logic 412 on the client 415 can increase image to keep the identical image size on display screen in proportion.

In one embodiment, under the situation that channel withdraws from fully, host services 210 is with suspension of game play.Under the situation of multiplayer, host services to this user of other user report withdrawed from the recreation and/or with suspension of game play to be used for other users.

The grouping that abandons or postpone

In one embodiment, if data are lost owing to the video compressor 404 among Fig. 4 a or Fig. 4 b and the packet loss between the client 415, or received out of orderly and lose owing to arriving evening so that can not decompressing and satisfy grouping through the delay requirement of decompressed frame, then video decompression logic 412 can alleviate visual artifacts.In mobile I/P frame was implemented, if there is the grouping of losing/postponing, then whole screen was influenced, thereby may cause that screen freezes cycle a period of time fully or shows the wide visual artifacts of other screens.For example, if the grouping of losing/postponing causes losing of I frame, then before the new I frame of reception, the reference of all P frames that decompressor is used to shortage to follow.If lose P frame, then its P frame that is used for whole screen that influence is followed.Look the I frame and occur how long having before, this will have long or short visual impact.Use as among Fig. 7 a and Fig. 7 b as shown in staggered I/P image block, the grouping of losing/postponing is unlikely to influence whole screen, because it only influences the image block that is contained in the affected grouping.If the data of each image block are to send in individual packets, then as if packet loss, then it only influences an image block.Certainly, the duration of visual artifacts will be depended on whether the grouping of I image block loses and will spend what frames under the situation that the P image block is lost before the appearance of I image block.But, suppose different images piece on the screen be by the I frame very continually (possible each frame) upgrade, even the image block then on the screen is influenced, other image blocks also may be unaffected.In addition, if a certain incident causes some groupings and (for example loses simultaneously, the spiking of the temporary transient interruption data stream in the electric power of DSL line), then some image blocks will be subjected to bigger influence than other image blocks, but because some image blocks will promptly upgrade by new I image block, so it is only temporarily influenced.And, under the situation that the I/P frame that flows is implemented, not only the I frame is the most critical frame, and the I frame is very big, therefore if there is the incident that causes the grouping that abandons/postpone, then compare with much smaller I image block, the I frame is influenced to exist higher probability (also to be, if any part of I frame is lost, the I frame then may be able to not decompress).Owing to all described reasons, compare with the situation of I/P frame, when grouping be dropped/when postponing, use the I/P image block to cause much smaller visual artifacts.

The effect that embodiment attempts to reduce lost packets in TCP (transmission control protocol) grouping or UDP (User Datagram Protoco (UDP)) grouping by compressed image block is packaged in intelligently.For example, in one embodiment, as possible, be about to image block and aim at boundaries of packets.How Figure 10 a explanation can be packaged in image block in a series of grouping 1001-1005 under the situation of not implementing this feature.In specific words, in Figure 10 a, image block crosses boundaries of packets and losing of single packet causes losing of a plurality of frames through encapsulating consequently inefficiently.For example,, then lose three image blocks, cause visual artifacts if grouping 1003 or 1004 is lost.

By contrast, Figure 10 b explanation is used for image block is packaged in the grouping image block encapsulation logical one 010 with the effect that reduces packet loss intelligently.At first, image block encapsulation logical one 010 is aimed at image block with boundaries of packets.Therefore, image block T1, T3, T4, T7 and T2 respectively with the grouping 1001-1005 boundary alignment.Image block encapsulation logic also attempts in possible more effective mode image block to be combined in the grouping, and does not cross boundaries of packets.Based on each the size in the image block, image block T1 and T6 are combined in the grouping 1001; T3 and T5 are combined in the grouping 1002; Image block T4 and T8 are combined in the grouping 1003; Image block T8 is added into grouping 1004; And image block T2 is added into grouping 1005.Therefore, under this scheme, single packet loss will cause losing of no more than 2 image blocks (but not as 3 illustrated among Figure 10 a image blocks).

The additional benefit of shown embodiment is among Figure 10 b: image block is to transmit with its different order that are shown in image.If contiguous grouping is owing to the same incident (it will influence the zone of keeping off each other on the screen) of disturbing transmission is lost, then this mode produces more unnoticed false shadow on display.

An embodiment uses forward error correction (FEC) technology to protect the specific part of video flowing so that it avoids the influence of channel error.As known in the art, the FEC technology such as Read-Solomon and Viterbi (Viterbi) produces error correction data information and it is attached to the data of transmitting via communication channel.If wrong appearance in master data (for example, the I frame), then FEC can be used for proofreading and correct this mistake.

The FEC sign indicating number increases the data rate of transmission, and therefore ideally, it only uses when needing most.If data just are sent out, and it will not cause very attractive visual artifacts, then can preferablely not use the FEC sign indicating number to come protected data.For example, be next to the I image block P image block of losing before and will only on screen, produce 1/60 second visual artifacts (promptly, the image block on the screen will not be updated yet).This kind visual artifacts almost can not be detected by human eye.Along with the P image block from the I image block further backward, lose the P image block and all the more become more noticeable.For example, if image block circular form sample is that the I image block is followed 15 P image blocks subsequently before the I image block is available once more, then lose if be next to I image block P image block afterwards, then it causes this image block to show that incorrect image lasts 15 frame times (under 60fps, this will be 250 milliseconds).Human eye will detect the interruption of 250 milliseconds stream easily.Therefore, the P image block is got over (also promptly, it is approaching more that the P image block is followed the I image block) backward apart from new I image block, and then false shadow is noticeable more.As discussed previously, however, but generally speaking, it is approaching more that the P image block is followed the I image block, and the data that are used for this P image block are more little.Therefore, the P image block of following the I image block not only for protection in order to avoid more crucial for losing, and its size is less.In addition, generally speaking, the data that need protection are more little, protect its required FEC sign indicating number more little.

Therefore, as illustrated among Figure 11 a, in one embodiment, because the importance of I image block in video flowing, only the I image block possesses the FEC sign indicating number.Therefore, FEC1101 contains the error correcting code and the FEC1104 that are useful on I image block 1100 and contains the error correcting code that is useful on I image block 1103.In this embodiment, do not produce FEC for the P image block.

In Figure 11 b, among the illustrated embodiment, cause that for most probable when losing the P image block of visual artifacts also produces the FEC sign indicating number.In this embodiment, FEC1105 is provided for preceding 3 P image blocks but is not used in the error correcting code of the P image block of following.In another embodiment, for the P image block of size of data minimum produce the FEC sign indicating number (its will tend to from be selected in the I image block after the P image block that occurs the earliest, it is the most key for protection).

In another embodiment, be not that the FEC sign indicating number is sent together with image block, but, in different grouping, transmit at every turn image block transmission twice.If another grouping is then used in a packet loss/delay.

In Figure 11 c among the shown embodiment, produce be respectively applied for video simultaneously from the audio packet 1110 of main frame service transmission and 1112 FEC sign indicating number 1111 and 1113.Keep the integrality particular importance of the audio frequency in the video flowing, (for example, ticktack or fizz) will cause undesirable especially user experience because the audio frequency of distortion.The FEC sign indicating number assists in ensuring that audio content reproduces at client computer 415 places undistortedly.

In another embodiment, be not that the FEC sign indicating number is sent together with voice data, but, in different grouping, transmit at every turn audio data transmission twice.If another grouping is then used in a packet loss/delay.

In addition, among the illustrated embodiment, FEC sign indicating number 1121 and 1123 is respectively applied for the user input commands (for example, button press) 1120 and 1122 that transmits upstream to host services 210 from client 415 in Figure 11 d.This is important, because miss button press or mouse movement may cause undesirable user experience in video-game or application program.

In another embodiment, be not that the FEC sign indicating number is sent together with the user input commands data, but, in different grouping, transmit at every turn user input commands data transmission twice.If another grouping is then used in a packet loss/delay.

In one embodiment, the quality of host services 210 assessment and the communication channel of client 415 determining whether to use FEC, and if use, is then determined what certain applications FEC of reply video, audio frequency and user command." quality " of assessment channel can comprise aforesaid such as the function of estimating packet loss, time-delay etc.If channel is unreliable especially, then host services 210 can be used FEC to all I image blocks, P image block, audio frequency and user command.By contrast, if channel is reliable, then host services 210 can only be used FEC to audio frequency and user command, or can audio or video not used FEC, or can not use FEC.Can use various other arrangements of the application of FEC, still observe described ultimate principle simultaneously.In one embodiment, host services 210 constantly monitoring channel situation and correspondingly change the FEC strategy.

In another embodiment, referring to Fig. 4 a and Fig. 4 b, when packet loss/delay, thereby when causing the losing of image block data, or if may be because poor especially packet loss make FEC can not proofread and correct the image block data of losing, client 415 be evaluated at receive remain before the new I image block what frames and with its with from client 415 round trip to host services 210 delay time and compare.The number of the frame before if the round trip time-delay should arrive less than new I image block, then client 415 sends message, the I image block that please look for novelty to host services 210.This message is routed to video compressor 404, and it is not to produce the P image block be used for the image block that data have lost, but produces the I image block.Suppose that system shown among Fig. 4 a and Fig. 4 b delays time less than 80 milliseconds round trip to provide usually through design, then this causes image block to be corrected in 80 milliseconds (under 60fps, frame has 16.67 milliseconds duration, therefore at full frame in the time, 80 millisecond time-delay will cause the calibrated image block in 83.33 milliseconds, 83.33 millisecond is 5 frame times, it is attractive interruption, but noticeable for 250 milliseconds of interruptions of 15 frames far away from (for example)).When producing this kind I image block when compressor reducer 404 its common cyclic orders of disengaging, if the I image block will cause the bandwidth of described frame and surpass available bandwidth, then compressor reducer 404 will postpone the circulation of other image blocks, so that other image blocks receive P image block (even described image duration an image block will should be the I image block usually) during described frame time, and following common circulation will begin to continue from next frame, and the image block that will receive the I image block in the previous frame usually will receive the I image block.Although this moves the temporary delay R frame round-robin stage, it will be visually not noticeable usually.

Video and audio compressor/decompressor is implemented

Figure 12 illustrates a specific embodiment, wherein uses multinuclear and/or multiprocessor 1200 to compress 8 image blocks concurrently.In one embodiment, use dual core processor, four nuclear Xeon (to strong) CPU computer systems in 2.66GHz or more relative superiority or inferiority execution, each core implements to increase income the x264H.264 compressor reducer as self-contained process.Yet, can use various other hardware/software configuration, still observe described ultimate principle simultaneously.For example, each in the core cpu can be replaced by the H.264 compressor reducer of implementing with FPGA.In the shown example, core 1201-1208 is used for handling I image block and P image block simultaneously as eight independent lines threads in Figure 12.As well-known in this technology, current multinuclear and multiprocessor computer system and when handling operating system and integrate such as the multi-thread thread of Microsoft Windows XP professional version (64 than the special edition of a book or 32 than the special edition of a book) and Linux, it can carry out multi-thread thread inherently and handle.

In embodiment illustrated in fig. 12, because each in these 8 cores only is responsible for an image block, so it is independent of other cores to a great extent and operates, each carries out the independent instantiation of x264.Use based on the DVI capured keystroke of PCI Express x1 (such as, Sendero video imaging IP development board from the Microtronix of Oosterhout of Netherlands) catch the video of the uncompressed under 640 * 480,800 * 600 or 1280 * 720 resolution, and the FPGA on the card uses direct memory access (DMA) (DMA) that institute's video captured is sent among the RAM of system via the DVI bus.Described image block is configured to 4 * 2 configurations, 1205 (although it is illustrated as square image block, in this embodiment, they have 160 * 240 resolution).Each instantiation of x264 is configured to compress one in these 8 160 * 240 image blocks, and its through synchronization so that each core enters a circulation after initial I image block compression, each frame and another frame be homophase not, with compress that an I image block continues with seven P image blocks, as illustrated in fig. 12.

At each frame time, use previous described technology that the compressed image block of gained is combined into grouping stream, and then compressed image block is transferred to destination client 415.

Although undeclared among Figure 12, if surpassing, the data rate of 8 image blocks of combination specifies peak data rate 941, then all 8 x264 processes will be supspended to last and reach necessary frame time, till the data of transmitting 8 image blocks that are used to make up.

In one embodiment, client 415 is embodied as software on the PC of 8 instantiations carrying out FFmpeg.Receiving course receives 8 image blocks, and each image block is routed to the FFmpeg instantiation, and FFmpeg instantiation decompressing image piece also reproduces suitable image block position to the display device 422 with it.

Client 415 receptions are transferred to server 402 from keyboard, mouse or the game console input of the input equipment driver of PC and with it.Recreation or application program that server 402 is then used the input equipment data that received and is applied to carry out on server 402, server 402 is carried out the PC of Windows for using Intel 2.16GHz double-core CPU.Server 402 then produces new frame and via its DVI output terminal new frame is exported based on the graphics system of motherboard or via the DVI output terminal of NVIDIA8800GTX PCI Express card certainly.

Simultaneously, server 402 via its DAB output terminal (for example, the S/PDIF) audio frequency that produces by recreation or application program of output, this DAB output terminal be coupled to implement video compress based on the DAB input end on the PC of two four nuclear Xeon.The Vorbis audio compressor of increasing income is used to use the core whatsoever that can be used for handling the line thread to come and video compressed audio side by side.In one embodiment, the core of finishing its image block of compression is at first carried out audio compression.Then compressed audio frequency is transmitted together with compressed video, and on client 415, use the Vorbis audio decompressor compressed audio frequency that decompresses.

The host services server-centric distributes

Light via glass (such as, optical fiber) is advanced with certain part of light speed in a vacuum, and therefore can determine the definite velocity of propagation of light in optical fiber.But, in practice, considering to be used for that route postpones, the time of transmission inefficiency and other consumptions, we observe optimum delay reflection on the internet near 50% transmission speed of the light velocity.Therefore, best 1000 miles round trips time-delay is about 22 milliseconds, and best 3000 miles round trips time-delay is for about 64 milliseconds.Therefore, the individual server on U.S.'s seashore consequently can not be with the client on servo another seashore of desired time-delay (it may reach 3000 miles far away) with hypertelorism.Yet, as illustrated among Figure 13 a, if the center that host services 210 server-centrics 1300 are positioned the U.S. (for example, the Kansas State, the Nebraska State etc.), so that the distance of any point to the ConUS is about below 1500 miles or 1500 miles, and the time-delay of round trip internet can be low to moderate 32 milliseconds.Referring to Fig. 4 b, note: although the situation worst that user ISP 453 is allowed time-delay is 25 milliseconds, usually, we observe than the time-delay near the 10-15 millisecond under the situation of DSL and cable modem system.And the ultimate range to Co-location center 210 is 1000 miles from user place 211 in Fig. 4 b supposition.Therefore, reach under the situation of 1500 miles the maximum internet distance of delaying time for 32 milliseconds round trip in employed typical 15 milliseconds user ISP round trip time-delay, the moment to the total round trip time-delay of seeing response on display device 422 that activates input equipment 421 from the user is the 1+1+15+32+1+16+6+8=80 millisecond.Therefore, can on 1500 miles internet distance, reach 80 milliseconds of response times usually.This Any user place that will allow to have in the ConUS user ISP time-delay 453 of enough weak points is accessed in the individual server center of centralized positioning.

In Figure 13 b among illustrated another embodiment, be positioned on the host services 210 server-centric HS1-HS6 strategies U.S. (or other geographic areas) around, specific bigger host services server-centric is located (for example, HS2 and HS5) near high population center.In one embodiment, server-centric HS1-HS6 is via network 1301 exchange messages, and network 1301 can be internet or private network or both combinations.Under the situation of a plurality of server-centrics, can provide service to user than low delay with high user ISP time-delay 453.

Although the distance on the internet for to the influential factor of delaying time via the round trip of internet, also works with other the irrelevant factors of delaying time really sometimes to a great extent.Sometimes via the internet stream of packets is routed to the position of distance and return once more, thereby cause from macrocyclic time-delay.Sometimes on the path, there is the routing device of inappropriate operation, thereby causes the delay transmitted.Sometimes have the communication that makes the path overload, it introduces delay.In addition, sometimes, be to exist to prevent that user's ISP from routing to the fault of given destination at all.Therefore, although common interconnection network provides connection from any to another point with quite reliable and best route and time-delay usually, route that this is quite reliable and best and time-delay are to determine (especially under the situation that the long distance of the outside of the local zone that causes routing to the user connects) by distance to a great extent, but this reliability and time-delay can not get any assurance and usually can not from user's locality to the common interconnection network given destination and reach.

In one embodiment, when subscription client 415 is connected to host services 210 at first with playing video game or use application program, client when starting with available host services server-centric HS1-HS6 in each communicate by letter (for example, using technology as described above).If time-delay is enough low for specific connection, then use this connection.In one embodiment, client is communicated by letter with a subclass of All hosts service server center or host services server-centric, selects to have the host services server-centric that minimum time-delay connects.Client can select to have the service centre that minimum time-delay connects, or server-centric can be discerned and has server-centric that minimum time-delay connects and this information form of internet address (for example, with) is offered client.

If particular host service server center overload and/or user's recreation or application program tolerable to another, the time-delay of the less host services server-centric that is written into, then client 415 can be redirected to another host services server-centric.Under this kind situation, recreation or application program that the user is just being carried out are suspended on the server 402 at user's overload server-centric place, and will be played or application state data is sent to the server 402 at another host services server-centric place.Then will restart this recreation or application program.In one embodiment, host services 210 will wait for that reaching nature breakpoint (for example, between the rank in the recreation, perhaps after user's initial in application program " preservations " operates) until recreation or application program just transmits.In another embodiment, host services 210 will be waited for until User Activity and stop to last cycle fixed time till (for example, 1 minute) and then with initial transmission at this moment.

As mentioned above, in one embodiment, host services 210 is subscribed to the internet bypass service 440 of Figure 14 to attempt that guaranteed time-delay is offered its client.The internet bypass service provides some service to the private network route of the guaranteed characteristic of having of another point (for example, time-delay, data rate etc.) on the internet as used herein.For example, if the AT﹠amp that provides in the San Francisco just is being provided host services 210; The mass communication that the DSL service of T receives from the user (but not routes to AT﹠amp; The San Francisco of T is the central office in base), then host services 210 will be rented from the ISP between one or the many persons that with the San Francisco are the central office in base and the server-centric that is used for host services 210 and (may be AT﹠amp; T itself or another supplier) the high power capacity private data connect.Then, if to the San Francisco, use AT﹠amp via common interconnection network from All hosts service server center HS1-HS6; The user's of T DSL route causes too high time-delay, then can change into using private data to connect.Although private data connects more expensive than the route via common interconnection network usually, as long as it keeps a little number percent of host services 210 to be connected to the user, the total cost influence is just low, and the user will experience more consistent service experience.

Under the situation of power failure, server-centric usually has two standby power layers.Ground floor is generally the standby power from battery (or from the available immediately energy source that substitutes, such as keeping running and being attached to the flywheel of generator), and it provides electric power immediately and keeps the server-centric running when feeder cable is out of order.If power failure is temporary transient, and feeder cable returns (for example, in one minute) rapidly, and what then battery was required is to keep the server-centric running.But if power failure is lasted the long time cycle, then usually starter-generator (for example, diesel engine power supply) as long as replace battery and generator has fuel and can turn round.Described power generator electrode costliness reaches server-centric usually from the resulting electric power of feeder cable because it must produce.

In one embodiment, the shared each other user data of among the host services HS1-HS5 each, so that when a server-centric has power failure, it can suspend afoot recreation and application program, and then will play or application state data is sent to the server 402 at other server-centric places from each server 402, and then will notify each user client 415 to be conveyed to new server 402 to instruct it.Suppose that described situation occurs once in a while, then the user being transferred to provide the host services of optimum delay server-centric (also to be, the user will only must tolerate that higher time-delay lasts the duration of power failure) can be acceptablely, it will allow to be used for the option of much wide scope of transferring user.For example, the time zone of the given leap U.S. is poor, and then the user on the east coast may will sleep at 11:30PM, and the user on the West Coast is just beginning to reach peak value in the video-game use at 8:30PM.If have power failure in the host services server-centric on the West Coast at that time, then may there be the enough West Coast servers 402 that are used to handle all users in other host services server-centric places.Under this kind situation, some users can be transferred to the host services server-centric that has available server 402 on the east coast, and the unique consequence for the user will be higher time-delay.In case the user is shifted from the server-centric that loses electric power, and server-centric can begin the orderly cut-out of its server and equipment with that, so that before battery (or other CAPACITY IN ELECTRICITY) immediately exhausts, cut off all devices.In this way, can avoid being used for the cost of the generator of server-centric.

In one embodiment, the time durations that seriously is written in host services 210 (perhaps is written into owing to peak user, perhaps because one or more server-centrics are out of order), the recreation of just using based on the user or the delay requirement of application program are transferred to other server-centrics with the user.Therefore, will for use need the user of the recreation of low delay or application program provide to the available low delay server that has limited supply connect preferred.

The host services feature

The embodiment of the assembly of the server-centric that is used for host services 210 that Figure 15 explanation utilizes in following feature description.As host services illustrated among Fig. 2 a 210, unless have ready conditions in addition, the assembly of this server-centric is controlled by host services 210 control system 401 and is coordinated.

To be directed to into port route 1502 from the port internet communication 1501 of going into of user's client 415.Usually, going into port internet communication 1501 will be via connecting to the high speed fibre of internet and enters server-centric, but any network connection device with enough bandwidth, reliability and low delay will be enough.Going into port route 1502 is that (this network can be embodied as Ethernet, fibre channel networks to network, or via any other conveying device) interchanger and support the system of the routing server of described interchanger, it is obtained the grouping of arrival and each grouping is routed to appropriate application/game server 1521-1525.In one embodiment, the grouping that is sent to application-specific/game server is represented a subclass of the data that receive from client and/or can be translated/change by other assemblies in the data center (for example, the network coupling assembling is such as gateway and router).Under some situations, (for example) then routes to grouping an above server 1521-1525 if recreation or application program are carried out simultaneously concurrently at every turn on a plurality of servers.RAID array 1511-1512 is connected to into port route network 1502, so that application program/game server 1521-1525 can read RAID array 1511-1512 and writes RAID array 1511-1512.In addition, RAID array 1515 (it can be embodied as a plurality of RAID arrays) also is connected to into port route 1502, but and reads from the data self-application program/game server 1521-1525 of RAID array 1515.Going into port route 1502 can implement in the multiple prior art network architecture (interchanger that comprises tree construction is gone into port internet communication 1501 at its root); In the reticulate texture of all various devices of interconnection, implement; Or the sub-network sequence of conduct interconnection (the concentrated communication in the middle of the interwork unit and the concentrated isolation of communicating by letter in the middle of other equipment) is implemented.The network configuration of one type is SAN (storage area network), although it is generally used for storage facilities, its universal high speed data that also can be used between the equipment transmit.Again, application program/game server 1521-1525 can have separately to a plurality of networks connections of going into port route 1502.For example, server 1521-1525 can have to the network of the sub-network that is attached to RAID array 1511-1512 and connects and connect to another network of the sub-network that is attached to other equipment.

Application program/game server 1521-1525 can through in the same manner, some differently or all differently disposes, as previous described about the server among the embodiment illustrated among Fig. 4 a 402.In one embodiment, each user is generally at least one application program/game server 1521-1525 when using host services.For explanation for simplicity, will suppose that given user is just using application program/game server 1521, but a plurality of server can be by user use, and a plurality of user can shared single application program/game server 1521-1525.The user's who is sent from client 415 (as described previously) control input is through being received as into port internet communication 1501, and routes to application program/game server 1521 via going into port route 1502.Application program/game server 1521 uses user's control to import as the control input to recreation of carrying out on server or application program, and calculates the next frame that video reaches the audio frequency that is associated with it.Application program/game server 1521 then exports the video/audio 1529 of uncompressed to shared video compress 1530.Application program/game server can be exported the video of uncompressed via any device (comprising that one or more hypervelocity Ethernet connects), but in one embodiment, video is to connect and export via DVI (Digital Video Interactive), and audio frequency and other compressions and communication channel state information system connect via universal serial convergence bus (USB) and export.

Shared video compress 1530 compressions are from the video and the audio frequency of the uncompressed of application program/game server 1521-1525.This compression can be implemented with hardware or with the hardware of executive software fully.Can there be the special-purpose compressor reducer that is used for each application program/game server 1521-1525, or, then can uses given compressor reducer to compress video/audio from an above application program/game server 1521-1525 if compressor reducer is enough fast.For example, under 60fps, video frame time is 16.67 milliseconds.If compressor reducer can compress 1 frame in 1 millisecond, then this compressor reducer can be used for compressing from the video/audio of 16 application program/game server 1521-1525 nearly by obtaining from the input of one by one server, and this compressor reducer is preserved the state of each video/audio compression process and switched background when its circulation time in the middle of from the video/audio stream of server.This causes the essence cost savings of compression hardware.Because different server will be finished frame at different time, so in one embodiment, the compressor reducer resource be in have the state that is used to store each compression process shared storage device (for example, RAM, flash memory) in the shared collection district 1530, and complete and when preparing to be compressed, control device determines which compressed resource can be used at that time when server 1521-1525 frame, the frame of the video/audio of the state of compression process of server and uncompressed to be compressed is provided for this compressed resource.

Notice that the part of state that is used for the compression process of each server comprises about compressing the information of itself, such as the frame buffered data (it can be used as the reference that is used for the P image block) through decompressing of previous frame, the resolution of video output; The quality of compression; The image block structure; The distribution of the bit of every image block; Compression quality, audio format (for example, stereo, around audio, Dolby AC-3 (Doby

) AC-3).But the compression process state also comprises about following communication channel state information: peak data rate 941, and current whether just being output of previous frame (as illustrated among Fig. 9 b) (and therefore should ignore present frame), and whether exist potentially should in compression, consider (such as, too much packet loss) influence compression decision-making (for example, aspect the frequency of I image block, etc.) the characteristic of channel.Because peak data rate 941 or other characteristics of channel changed along with the time, as by supporting that each user's supervision is determined from the application program/game server 1521-1525 of the data of client 415 transmissions,, application program/game server 1521-1525 compresses 1530 so being sent to common hardware with relevant information.

Common hardware compression 1530 also uses device such as previous described described device with compressed video/audio packetizing, and in due course, use the FEC sign indicating number, duplicate particular data, or take other steps, so that the ability of guaranteeing fully that video/audio data stream is received by client 415 and decompressing with feasible high-quality and reliability.

Some application programs (such as, hereinafter described application program) need the video/audio output while under a plurality of resolution (or with other a plurality of forms) of given application program/game server 1521-1525 available.If application program/game server 1521-1525 so notifies common hardware to compress 1530 resources, then the video/audio 1529 of the uncompressed of this application program/game server 1521-1525 will be by with different-format, different resolution and/or compression simultaneously in different grouping/error correction structure.Under some situations, some compressed resources can sharedly in the middle of a plurality of compression processes of the same video/audio of compression (for example, in many compression algorithms, exist so as to the preceding step that image is adjusted in proportion a plurality of sizes in applied compression.If need the image of the different sizes of output, then this step can be used for serving simultaneously several compression processes).Under other situations, will need independent compressed resource for each form.Under any situation, will be used for all the required various resolution of given application program/game server 1521-1525 (one or more) and the compressed video/audio 1539 of form and output to the route 1540 that goes out of the port simultaneously.In one embodiment, the output of compressed video/audio 1539 is to be in the UDP form, so it is unidirectional stream of packets.

The route network 1540 that goes out of the port comprises a series of routing servers and interchanger, this series routing server and the interchanger video/audio stream that each is compressed is directed to user or other destinations of having a mind to and/or is back to delay buffer 1515 via internet communication 1599 interfaces that go out of the port (it will be connected to the optical fiber interface to the internet usually), and/or be back to, and/or export for carrying out video distribution via private network (not shown) into port route 1502.Note (as described below): the route that goes out of the port 1540 can export given video/audio stream to a plurality of destinations simultaneously.In one embodiment, this is to use Internet protocol (IP) multicast to implement, and wherein broadcasting is intended to flow to simultaneously the given UDP stream of a plurality of destinations, and this broadcasting comes repetition by routing server and interchanger in the route 1540 that goes out of the port.This a plurality of destinations of broadcasting can arrive via the internet a plurality of user client 415, arrive a plurality of application programs/game server 1521-1525 via going into port route 1502, and/or arrive one or more delay buffers 1515.Therefore, the output of given server 1521-1522 is compressed into one or more forms, and the stream that each is compressed is directed to one or more destinations.

In addition, in another embodiment, if a plurality of application programs/game server 1521-1525 (is for example used by a user simultaneously, be used for producing the parallel processing configuration of 3D output with complex scene) and each server produce the part of gained image, then can compress 1530 video outputs and be combined into a combined frames by common hardware with a plurality of server 1521-1525, and this point is handled this combined frames forward as mentioned above certainly, seems that it is from single application program/game server 1521-1525.

Note, in one embodiment, the duplicate of all videos that will be produced by application program/game server 1521-1525 (at least with the resolution of the video watched by the user or high resolving power more) is recorded in minute (being 15 minutes in one embodiment) of lasting a certain at least number in the delay buffer 1515.This allows the video of each user " playback " from each session, so that verify previous work or achievement (under the situation of recreation).Therefore, in one embodiment, each compressed video/audio output 1539 stream that routes to subscription client 415 also are multicasted to delay buffer 1515.When video/audio being stored on the delay buffer 1515, the catalogue on the delay buffer 1515 provides the cross reference between the position that can find the video/audio that postpones on the network address of application program/game server 1521-1525 (it is the source of the video/audio that postpones) and the delay buffer 1515.

Recreation live, that can watch at once, that can play at once

Application program/game server 1521-1525 not only can be used for carrying out user's given application program or video-game, and it can be used for setting up the user interface application that is used to support via the host services 210 of the navigation of host services 210 and other features.A kind of screen shot of this user interface application is presented at (" recreation view finder (Game Finder) " screen) among Figure 16.This particular user interface screen allows user to watch on-the-spot (or the delay) of playing 15 recreation by other users.In " thumbnail " video window each (such as, 1600) be live video window at the volley, it shows a video from a user's recreation.Shown view can be the same view that the user is just seeing in the thumbnail, or its view that can be delay (for example, if the user is just playing the fight recreation, then the user may not wish that other users see where it be hidden in and it can select any view of its game play is postponed cycle time (for example, 10 minutes)).View also can be the camera view of the recreation of the view that is different from Any user.Select (not shown in this explanation) by menu, the user can select the selection of the recreation that will watch simultaneously based on multiple standards.Little sampling as exemplary selection, the user can select the selection at random (all recreation as shown in Figure 16) of playing, the recreation (playing by different players) of all classifications, the top player of only recreation, given other player of level in the recreation, or more rudimentary player (for example, if the positive learning foundation of player), be " partner " (or being the rival) the player, have maximum number beholders' recreation etc.

Note, usually, each user will determine whether can be watched by other people from the video of its recreation or application program, and if so, then determine this video other people to watch and when can watch, determine this video whether to watch having under the situation of delay only by which by other people.

Application program/game server the 1521-1525 that produces user interface screen shown among Figure 16 obtains these 15 video/audios and presents by the application program/game server 1521-1525 transmission message to each user (this application program/game server 1521-1525 is just asking the recreation from this user).This message is via going into port route 1502 or another network sends.This message will comprise the size and the form of requested video/audio, and identification be watched the user of user interface screen.Given user can select " piracy " pattern and disapprove the video/audio that any other user watches its recreation (watch a little or from another watch a little from it), or as previous section described in, the user can select to allow to watch the video/audio from its recreation, but postpones the video/audio watched.Therefore user application/game server 1521-1525 (its reception also accepts to allow the viewed request of its video/audio) will be confirmed to request server, and it also will notify common hardware compression 1530 to need generation to be requested the extra compressed video flowing of form or screen size (supposition form and screen size are different from form and the screen size that has produced), and it also will indicate the destination (request server also promptly) of compressed video.If requested video/audio only is delayed, then request applications/game server 1521-1525 will be notified like this, and the position that it will be by searching the video/audio in the catalogue on the delay buffer 1515 and obtain the video/audio of delay for the network address self-dalay impact damper 1515 of the application program/game server 1521-1525 in the source of the video/audio that postpones.In case all these requests are produced and are handled, then will be routed to into port route 1502, to the application program/game server 1521-1525 that produces user interface screen from the route 1540 that goes out of the port, and will decompress and show by this server up to the video flowing of 15 live thumbnail size.The video/audio stream that postpones may be in excessive screen size, if like this, and will decompress described stream and video flowing is reduced to thumbnail size in proportion of application program/game server 1521-1525 then.In one embodiment, to send to the request of audio/video and similarly central authorities' " management " service of the host services control system of Fig. 4 a (showing among Figure 15) (and managed by central authorities' " management " service), central " management " served and then described request is redirected to appropriate application/game server 1521-1525.In addition, in one embodiment, may not need request, because thumbnail is " pushed " to those user client that allow it.

All audio frequency that mix simultaneously from 15 recreation may produce ear-piercing sound.The user can select in this way all sound mix (may just be the sensation that obtains by " clamour " of viewed everything generation) together that perhaps the user can select only to listen to the audio frequency from a recreation at every turn.The selection of single recreation be by yellow is selected frame 1601 move to given recreation finish (yellow frame move can by use arrow key on the keyboard, by rolling mouse, finish such as the arrow button on another equipment of mobile phone by mobile operating rod or by promoting).In case selected single recreation, then only from the voice playing of this recreation.And, show game information 1602.Under the situation of this recreation, for example, publisher sign (" EA ") and recreation sign " this valley of Need For Speed card " and orange horizontal stripe indicates under relative conditon in this particular moment and are played games or watch the people's of recreation number (under this situation, many, therefore recreation is " hot topic ")." state " is provided in addition, and indication exists 145 players to play 80 different instantiations (also promptly, this recreation can be played by indivedual player or multiplayer) of Need For Speed recreation just energetically, and has 680 beholders (this user is one of them).Note, this statistics (and other statisticss) is collected and is stored on the RAID array 1511-1512 by host services control system 401, to be used to the keeping daily record of host services 210 operations and to be used for suitably chargeing and to publisher's defrayment that content is provided to the user.Some statisticss are records owing to the action of being undertaken by operation control system 401, and some statisticss are to report to operation control system 401 by individual application/game server 1521-1525.For example, when recreation is just viewed, (reaches when playing and be stopped when watching), application program/game server the 1521-1525 that carries out this recreation view finder application program sends message to host services control system 401, so that 401 renewable what recreation of host services control system are in the statistics in watching.It is used that some statisticss can be user interface application (such as, this recreation view finder application program).

If the start button on its input equipment of user click, then it will see that the thumbnail video amplification thumbnail video maintenance simultaneously on-the-spot broadcasting in the yellow frame is the full screen size.This effect is presented in the process among Figure 17.Notice that the size of video window 1700 increases.In order to implement this effect, application program/game server 1521-1525 has the duplicate of video flowing of the full screen size (with the resolution of user's display device 422) of the recreation that is routed to it from the application program/game server 1521-1525 request that moves selected recreation.Application program/game server 1521-1525 notice common hardware compressor reducer 1530 of carrying out recreation no longer needs the duplicate (unless Another Application program/this thumbnail of game server 1521-1525 needs) of the thumbnail size of playing, and then its guide common hardware compressor reducer 1530 is sent to the duplicate of the full screen size of video the application program/game server 1521-1525 of amplified video.The user who plays this recreation can or can not have the identical display device 422 of resolution of resolution and the user's that amplifies of will playing described display device.In addition, other beholders of recreation can or can not have the resolution display device 422 identical with the user that amplifies of will playing (and can have different audio playbacks, for example, stereo or around audio).Therefore, common hardware compressor reducer 1530 determines whether to produce the suitable compressed video/audio stream of the user's who satisfies the request video/audio stream requirement, and if suitable compressed video/audio stream exists really, then go out of the port duplicate that route 1540 will flow of common hardware compressor reducer 1530 notice routes to the application program/game server 1521-1525 of this video of amplification, and if suitable compressed video/audio stream do not exist, then another duplicate that is suitable for described user of compressed video and guides the route that goes out of the port to send back to this stream into port route 1502 and amplifies the application program/game server 1521-1525 of this video.To decompress this full screen version and it little by little is amplified to full size in proportion of this server that receives now the full screen version of selected video.

Figure 18 explanation will play be amplified to full screen fully and show recreation with the full resolution of user's display device 422 after screen how to seem (as indicated) by the image of arrow 1800 sensings.Application program/game server the 1521-1525 that carries out recreation view finder application program sends message to other application programs that thumbnail is provided/game server 1521-1525 no longer to be needed and sends message to host services Control Server 401 no longer to watch other recreation with indication to indicate described thumbnail.At this moment, unique superimposed layer (overlay) 1801 that is shown as the top of screen of generation, it offers the user with information and menu control.Notice that along with this game progress, spectators rise to 2,503 beholders.Under so many beholder's situation, certainly exist the many beholders with display device 422, described display device 422 has identical or approaching resolution (each application program/game server 1521-1525 have adjust video in proportion to be used to adjust the ability of fitness).

Because shown recreation is a multiplayer, so the user can determine to carve at a time this recreation of adding.Owing to multiple reason, host services 210 can or can not allow the user to add this recreation.For example, the user may must pay the expense of playing games and select nonpayment, the user may not have be enough to add described particular game enough grades (for example, for other players, it will be not competitive), perhaps user's Internet connection may not have is enough to allow enough low time-delay that the user plays (for example, there is not the time-delay constraint that is used to watch recreation, therefore can watch under the situation that time-delay pays close attention to by at a distance (in fact not having, land greatly at another) recreation played, but for recreation to be played, time-delay must be enough low so that user (a) enjoys this recreation, and (b) be in and may have the status that other players of being connected than low delay equate).If permitting the user plays, then with 401 initialization of requesting host service control server (also be for the user provides the application program/game server 1521-1525 of recreation view finder user interface, the location also starts) thus the application program/game server 1521-1525 that is configured to be used to play particular game suitably is written into this recreation from RAID array 1511-1512, and then host services Control Server 401 will instruct common hardware compression 1530 to come to switch to compression from the present video/audio that recreation is carried out the application program/game server of Co-location from the video/audio of the application program/game server of Co-location recreation view finder application program from compression with instructing port route 1502 will be sent to now application program/game server that recreation is carried out the application program/game server of Co-location and now Co-location carried out in recreation from user's control signal.The vertical synchronization of recreation view finder application program/game services and the new application program/game server that recreation is carried out Co-location is also asynchronous, and therefore may life period poor between synchronously at these two.Because shared video compress hardware 1530 will promptly begin compressed video after application program/game server 1521-1525 finishes frame of video, the full frame time of the comparable legacy server of first frame of server finishes early so make a fresh start, first frame of server of making a fresh start (for example may formerly compressed frame be finished before its transmission, consider the transmission time 992 of Fig. 9 b: if the frame of uncompressed 3963 early a frame time half finish, then it will influence (impinge) transmission time 992).In this case, first frame that shared video compress hardware 1530 will be ignored the server of making a fresh start (for example, as ignore (974) frame 4964), and client 415 will keep an extra frame time from the most last frame of legacy server, and shared video compress hardware 1530 will begin to compress the next frame time video from the new application program/game server that recreation is carried out Co-location.For the user, visually, the transformation from an application program/game server to Another Application program/game server will be seamless.Host services Control Server 401 then will notify application program/game server 1521-1525 that the recreation view finder is carried out Co-location to switch to idle state, till needing it once more.

The user then can play this recreation.In addition, what make an exception is that recreation will play (because recreation is loaded on application program/game server 1521-1525 from Raid array 1511-1512 with 1,000,000,000 bps speed) immediately in the perception, and will will play and be loaded into the server that accurately is suitable for this recreation by desirable driver, working storage configuration (under the situation of Windows), and not have other application programs of the operation competition of possibility and this recreation on this server, to carry out together with the operating system that correctly is configured to be used for this recreation.

And, along with the user makes progress in recreation, in the fragment of recreation each will (also be with 1,000,000,000 bps speed, in 8 seconds, be written into gigabyte) be written into the server from RAID array 1511-1512, and because the huge storage volume of RAID array 1511-1512 is (because it is many users' a common source, so it may be very big, but still cost-effective), make computational geometry shape setting in advance or other recreation fragment settings and it is stored in RAID array 1511-1512 goes up and extremely fast be written into.In addition, because the hardware configuration of each application program/game server 1521-1525 and computing power are known, so calculating pixel and vertex coloring in advance.

Therefore, recreation can almost start at once, and it will be carried out in ecotopia, and fragment subsequently will almost be written at once.

But except that these advantages, the user can watch other people to play games by (via previous described recreation view finder, and other devices), and both determine all whether recreation is interesting, if like this, then from watching other people to come learning skill.In addition, the user can demonstrate this recreation immediately, and needn't wait for big download and/or installation, and the user can play this recreation (may on the basis on probation of less expense, or on longer basis) at once.In addition, the user can be by the wireless connections of enough low delays on Windows PC, the Macintosh, on the televisor, at home, when advancing and even on mobile phone, play this recreation.In addition, this all can be not once entity have under the situation of the duplicate of playing and finish.

As previous narration, the user can determine not allow its game play to be watched by other people, allows its recreation to watch after postponing, and allows its recreation chosen user to watch, or allows its recreation to be watched by all users.In any case, in one embodiment, video/audio is stored in the delay buffer 1515 lasts 15 minutes, and the user can " return " and watch its previous game play, and with suspension of game play, the playback lentamente of will playing, the F.F. etc. of will playing, as its when watching the have digital video recorder TV of (DVR) can carry out.Although in this example, the user is playing games, if the user is just using application program, then identical " DVR " ability is available.This reaches in other application as detailed below useful in verifying previous work.In addition, if recreation is returned the ability of falling through being designed to have based on utilizing game state information, so that can change camera view etc., then also will support this " 3D DVR " ability, but it will need with game design for supporting " 3D DVR " ability." DVR " ability of use delay buffer 1515 will be (certain together with any recreation or application program, be limited to the video that when using recreation or application program, is produced) work together, but under the situation of recreation with 3D DVR ability, the 3D of the previous fragment of playing of user's may command " leaps (fly-through) ", and makes the game state of delay buffer 1515 record gained videos and recording game fragment.Therefore, specific " leaping " is recorded as compressed video, but because also with the recording game state, so different leaping may be on the date after a while of the same fragment of playing.

As described below, the user on the host services 210 will have a User Page separately, and in this User Page, the user can announce about the information of itself and other data.One of thing that the user can announce is the video segment from its game play of having preserved.For example, if the user has overcome the challenge of difficulty especially in the recreation, before then the user can just " return " and obtain the place of its big achievement to it in recreation, and then instructing host services 210 video segment of a certain duration (for example, 30 seconds) to be kept on user's the User Page watches for other users.In order to implement these, the thing that the application program that the user is just using/game server 1521-1525 only will do is to be stored in video playback in the delay buffer 1515 to RAID array 1511-1512 and index then for described video segment on user's User Page.

If recreation has the ability of 3D DVR, as mentioned above, then also can use by the User Page that the user writes down the required game state information of 3D DVR and is the user.

In recreation (also be through being designed to except that having the player of enlivening, also to have " onlooker ", can advance and observing the user of action in the 3D world under the situation about not participating in) situation under, the view finder application program of then playing will make the user add recreation as onlooker and player.From the enforcement point of watching, for host computer system 210, the user is the onlooker rather than enlivens the player and not there are differences.Recreation is written into application program/game server 1521-1525 goes up and the user will control this recreation (for example, controlling the virtual camera of watching the world).Unique difference is user's game experiencing.

A plurality of users cooperate

Another feature of host services 210 is the ability (even it is also like this to use far different equipment to watch) that a plurality of users cooperate when watching live video.When playing games and when using application program, this is all useful.

Many PC and mobile phone are equipped with video camera and have the ability of carrying out real-time video compression (especially when image hour).And little camera is available, can be attached to TV, and be used for software or use compressed video many hardware-compressed equipment one to implement Real Time Compression not difficult.And many PC and all mobile phones have microphone, and earphone have under the microphone situation available.

Combination has the described camera and/or the microphone of local video/audio compression ability (specifically, using low delay video compression technology described herein) will make the user video and/or audio can be transferred to host services 210 together with the input device controls data from customer site 211.When using described technology, then can realize ability illustrated in fig. 19: the user can make its video and audio frequency 1900 appear in another user's the recreation or the screen in the application program.This example is a multiplayer, and wherein the teammate cooperates in racing car.User's video/audio only can optionally be watched by its teammate/hear.In addition, because use technology as described above not have time-delay effectively, so the player can talk each other in real time or move and not have appreciable delay.

It is to arrive and finish as going into port internet communication 1501 by making from the compressed video and/or audio of camera/microphone of user that this video/audio is integrated.Then, go into port route 1502 and this video and/or audio is routed to the application program/game server 1521-1525 that is allowed to watch/hear video and/or audio.Then, select to use the user's decompressed video of application program out of the ordinary/game server 1521-1525 of video and/or audio and/or audio frequency and optionally it is integrated to come across in recreation or the application program, such as illustrated by 1900.

The example of Figure 19 shows how to use this cooperation in recreation, but this cooperation can be the extremely powerful instrument that is used for application program.Consider each situation: wherein an edifice just by the architect in Chicago for being that the real estate developer in base designs for the New York with New York, but this decision-making relates in tourism and happens to be in the financial investment person on Miami airport, and need carry out the decision-making of particular design key element (aspect near the buildings how it arranges in pairs or groups it), to satisfy investor and real estate developer about buildings.Suppose that building constructor has the high resolution monitor of the camera that is attached to PC in Chicago, the real estate developer has the notebook of band camera in New York, and the investor has the mobile phone of band camera in Miami.Building constructor can use host services 210 that the powerful architectural design application program that can carry out high fidelity 3D and reproduce is carried out Co-location, and it can utilize the big database of the buildings of New York, and the database of the buildings that is just designing.The architectural design application program will be in application program/game server 1521-1525 one on (or if it needs a large amount of computing powers, then on some persons) carry out.Each that is among 3 users of different entirely (disparate) position will be connected to host services 210, and when will having the video output of architectural design application program, each watches, but what it will be had at each user suitably (for example sets size to locking equipment and network connection performance by common hardware compression 1530, building constructor can see that 2560 * 1440 60fps show via the commercial Internet connection of 20Mbps, the real estate developer in New York can connect via the 6Mbps DSL on its notebook sees 1280 * 720 60fps images, and the investor can see 320 * 180 60fps images via the connection of the 250Kbps honeycomb fashion data on its mobile phone).Each side will hear the voice (will handle Conference Calling by in the many widely available Conference Calling package software among application program/game server 1521-1525 any one) of its other party, and via the actuating of the button on the user input device, the user can use its this ground camera that video is occurred.Along with meeting is carried out, the architect can reproduce show what buildings look like when it rotates buildings and makes its another buildings in this zone leap (fly-by) by the 3D that has the photo realistic sense, and all Fang Jun will can see same video under the resolution of the display device of each side.It is not problem that in the local device that is used by any side any one all can be handled the 3D animation with this sense of reality, says nothing of to download or even store the required huge database of surrounding buildings thing that reproduces the New York.The viewpoint of each in the user is seen, although distance is far, although and be complete different local device, it will have seamless experience simply under fabulous sense of reality degree.In addition, when a side wished that its face be it seems and preferably passes on its emotional state, it can so carry out.In addition, if real estate developer or investor wish to control building construction program and use the input equipment (it is keyboard, mouse, keypad or touch screen) of himself, then it can be like this, and it can respond (supposing that its network connection does not have irrational time-delay) with the time-delay of unaware.For example, under the situation of mobile phone, if mobile phone is connected to the WiFi network on airport, then it will have low-down time-delay.But if it uses the available now cellular data network of the U.S., then it will suffer attractive hysteresis probably.But for most of purposes of meeting (wherein the investor is just watching the architect to control that buildings leaps or just talking about video conference call), even the honeycomb fashion time-delay also should be acceptable.

At last, when the cooperative Conference Calling finishes, real estate developer and investor will carry out its comment and break from host services, and video that has been recorded in the meeting on the delay buffer 1515 and comment, facial expression and/or the action of verifying the 3D model that is applied to buildings that carries out in the session can " be returned " by building constructor.If exist it to wish the specific fragment of preserving, then the described fragment self-dalay impact damper 1515 of video/audio can be moved to RAID array 1511-1512 and store and playback after a while to be used for archives.

And, from the cost viewpoint, if the architect only needs to use the computing power of New York and the Conference Calling that big database lasts 15 minutes, then it only needs to pay the expense of the time that described resource is used, and needn't have the worktable of high ability and needn't buy the expensive duplicate of big database.

The community service that video is abundant

Host services 210 makes has unprecedented chance to set up the abundant community service of video on the internet.Figure 20 shows the exemplary User Page that is used for the game player on the host services 210.As recreation view finder application program, User Page in application program/game server 1521-1525 one on the application program carried out.All thumbnails on this page and video window show the video (if fragment is short, then its circulation) that moves consistently.

Use video camera or pass through uploaded videos, user's (its user is called " KILLHAZARD ") can announce the video 2000 (other users can watch this video) of itself.This video storage is on RAID array 1511-1512.And, when other users come the User Page of KILLHAZARD, if KILLHAZARD is just using host services 210 this moment, then will show its live video 2001 whatsoever that is just carrying out (supposition KILLHAZARD permits watching the user of its User Page to watch this video).Whether this will be that (and if so, then the asking its application program of just using/game server 1521-1525) of enlivening finished from operation control system 401 request KILLHAZARD by the application program/game server 1521-1525 that the User Page application program is carried out Co-location.Then, use the same procedure of using by recreation view finder application program, the compressed video flowing of adequate resolution and form is sent to application program/game server 1521-1525 of carrying out the User Page application program and its demonstration.If the user select to have KILLHAZARD live game play window and then suitably click its input equipment, then this window will amplify (reusing and the identical method of view finder application program of playing), and live video will be filled screen with the resolution of the display device 422 of watching the user (being suitable for watching the characteristic of user's Internet connection).

This key advantage that is better than prior art approach is: watch the user of User Page can see the recreation of the on-the-spot broadcasting ground broadcast that the user does not have, and can not have local computer or the game console that can play this recreation.It provides the fabulous chance of seeing in the User Page that the user that is shown as " in the activity " plays games for the user, and this is a chance of understanding the recreation of watching the user may wish to attempt or being good at.

Video clipping cameras record or that upload from the partner 2002 of KILLHAZARD also is shown on the User Page, and the below of each video clipping is this partner of indication online literal of playing games (for example, six_shot just play games " Dragon Knight (Eragon) " and MrSnuggles99 off-line etc.) whether.By clicking menu item (not shown), partner's video clipping is from showing that video switch that write down or that upload is engraved in the live video of ongoing content in its recreation to the current partner who is just playing the recreation in the main frame service 210 when described.Therefore, it becomes the recreation view finder that hives off for the partner.If recreation and the user click selecting to work together should be played, then this recreation will be amplified to full screen, and the user can watch the recreation of full screen on-the-spot broadcasting ground broadcast.

Once more, watch the user of partner's recreation not have the duplicate of recreation, also do not have this locality calculating/game console resource that is used to play this recreation.It is significant instant that recreation is watched.

Previous as mentioned institute was described, and when the user played recreation in the main frame service 210, the user can " return " video segment of playing and finding its hope preservation, and then this video segment is saved in its User Page.This is called as " self-admiration montage (Brag Clip) ".Video segment 2003 all is the self-admiration montage 2003 of being preserved from its previous recreation of playing by KILLHAZARD.Numeral 2004 shows the viewed how many times of self-admiration montage, and when viewed the self-admiration montage is, and the user has the chance to its rating, and how high the number of the diagram 2005 of orange keyhole shape indication grade be.When the user watched User Page, self-admiration montage 2003 circulated consistently together with all the other videos on the page.If the user selects also to click one in the self-admiration montage 2003, then it amplifies presenting self-admiration montage 2003, and allow to play, suspend, return, the DVR control of these montages such as F.F., stepping.

Self-admiration montage 2003 playback are to be stored in the compressed video segment on the RAID array 1511-1512 when being written into the montage of user record self-admiration by application program/game server 1521-1525 and its decompress(ion) contractd its playback is implemented.

Self-admiration montage 2003 also can be " 3D DVR " video segment (also promptly, from being reset and allow the user to change the game state sequence that camera is watched recreation a little) of the recreation of self-supporting 3D DVR ability.Under this situation, the compressed videograph of specific " the leaping " of carrying out when the recording game fragment except that the user, also stores games status information.The equal circulation time consistently of just viewed and all thumbnails and video window when User Page, 3D DVR self-admiration montage 2003 will make the self-admiration montage 2003 that is recorded as compressed video when " leaping " of user record recreation fragment circulate consistently.But when the user selects 3D DVR self-admiration montage 2003 and clicks the montage 2003 of 3D DVR self-admiration, except that the DVR control of allow playing the montage of compressed video self-admiration, the user can click the button of the 3D DVR ability that provides its fragment that is used to play.Its camera that can control independently during the recreation fragment " leaps ", and if it wishes (and the user who has User Page allows so), then it can write down substituting self-admiration montage with the form of compressed video and " leap ", substituting self-admiration montage " leaps " other beholders that will then can be User Page used (immediately, perhaps after the owner of User Page has the chance of verifying the self-admiration montage).

These 3D DVR self-admiration montage 2003 abilities are to enable by the recreation that starts the game state information that write down will reset on Another Application program/game server 1521-1525.Because the recreation can be started (as described previously) almost instantaneously, so start its (its broadcast is limited to the game state by self-admiration compilation film segment record) and then allow the user with compressed videograph in delay buffer 1515 with camera carry out " leaping " not difficult.Carry out " leaping " in case the user finishes, then startup is cancelled in recreation.

From user's viewpoint, it is difficult unlike the DVR control of the linear self-admiration montage 2003 of control to start " leaping " with 3D DVR self-admiration montage 2003.The user can not know this recreation or does not even know how to play this recreation.The user indicates the virtual camera operator in the 3D world during the recreation fragment of staring at another operator's record.

The user (perhaps writes down or uploads from microphone) also the audio frequency of himself being added to record in the self-admiration montage.By this way, can use the self-admiration montage to use personage and action to produce custom tailored motion picture from recreation.This animation design technique is commonly called " recreation film (machinima) ".

Along with the user makes progress in recreation, it will reach different technical ability ranks.The recreation of being play is given operation control system 401 with achievement Report, and described technical ability rank also will be shown on the User Page.

Interactive animated advertising

Online advertisement is converted to still image, video from literal, and is converted to interactive fragment now, uses usually and implements as the animation thin client of Adobe Flash.Use the reason of animation thin client to be: the user does not have patience for being delayed because of the privilege of promoting the sale of products to it or serve usually.And thin client is carried out on the PC of unusual low performance, and therefore advertiser can have height confidence: interactive type advertisement will suitably be worked.Regret, upward restricted such as the animation thin client of Adobe Flash in the duration of interactive degree and experience (to reduce download time).

Figure 21 illustrates an interactive type advertisement, and wherein the user will select the outside and inner color of automobile when automobile rotates in the showroom, and how the ray tracing display automobile seems in real time simultaneously.Then the user selects the role to drive a car, and then the user can adopt this automobile to be used on the contest track or pass such as the foreign place of Monaco and drive.The user can select big engine or preferable tire, and can see then how the configuration of change influences the automobile acceleration or keep stable ability.

Certainly, advertisement effectively be most advanced and sophisticated 3D video-game.But for this advertisement that can play on PC or video game console, it will need and may download by 100MB, and under the situation of PC, it may need to install special driver, and may not carry out when PC lacks enough CPU or GPU computing power.Therefore, described advertisement is formerly unrealistic in the technical configuration.

In host services 210, described advertisement is almost thrown in immediately, and preferably carries out, regardless of user client 415 abilities.Therefore, it is more promptly thrown in than thin client interactive type advertisement, and is abundanter in the experience, and highly reliable.

The geometric configuration that flows during the real-time animation

RAID array 1511-1512 and go into port route 1502 and so fast data rate can be provided and have so low time-delay, so that might design and depend on RAID array 1511-1512 and go into port route 1502 in the video-game and the application program that in the centre of game play or application program, directly transmit geometric configuration during the real-time animation (for example, having leaping of complex database) reliably.

Formerly the system of technology (such as, shown video game system among Fig. 1) under, available a large amount of storage facilitiess (especially in the household equipment of practicality) extremely slowly so that can not be in flow geometry during the game play (except required geometric configuration the predictable a little situation).For example, in the driving recreation that has particular link, can predict suitably reasonably that the geometric configuration of the buildings in being used to come into view and a large amount of storage facilities can search the position that geometric configuration on the horizon is located in advance.

But in having the complex scene of uncertain change (for example, have around in complicated personage's the campaign scene), if the RAM on PC or the video game system is filled the geometric configuration that is used for current object at view fully, and then the user turns to its personage suddenly to watch what its personage is afterwards, if geometric configuration is not written among the RAM in advance, then may before geometric configuration can be shown, there be delay.

In host services 210, the speed that RAID array 1511-1512 can surpass the hypervelocity ethernet speed makes streams data, and under the SAN network, might reach 10,000,000,000 bps the speed that is better than 10 1,000,000,000 bit Ethernets or is better than other network technologies.10,000,000,000 bps will be written into the data of gigabyte in less than one second.In 60fps frame time (16.67 milliseconds), can be written into the data of about 170 megabits (21MB).Certainly, even in RAID configuration, the rotation medium also will cause the time-delay greater than a frame time, but general big and will can not cause this height and delay time with rotation medium RAID array the most at last based on the RAID reservoir of flash memory.In each embodiment, use the high-speed cache that writes via a large amount of RAM that the very access of low delay is provided.

Therefore, at sufficiently high network speed, and under the mass storage of enough low delays, can handle that the 3D data are general to be flow to geometric configuration among application program/game server 1521-1525 fastly with CPU and/or GPU.Therefore, in the formerly given example, wherein the user turns to its personage suddenly and sees backward, can before finishing rotation, the personage be written into its all personages' after one's death geometric configuration, and therefore, for the user, it is in the world with the general real photo realistic of live action with appearing.

As discussed previously, one in the last border in the computer animation of photo realistic is people's faces, and because human eye for the susceptibility of imperfection, can cause negative reaction from the beholder from the small fault of the face of photo realistic.Figure 22 shows use Contour ^TMAuthenticity capture technique (the theme of the application in the following common co-pending application: the 10/942nd, No. 609 " Apparatus and method for capturing the motion of a performer " of application on September 15th, 2004; The 10/942nd, No. 413 " Apparatus and method for capturing theexpression of a performer " of application on September 15th, 2004; The 11/066th, No. 954 " Apparatusand method for improving marker identification within a motion capturesystem " of application on February 25th, 2005; The 11/077th, No. 628 " Apparatus and method forperforming motion capture using shutter synchronization " of application on March 10th, 2005; The 11/255th, No. 854 " Apparatus and method for performing motion captureusing a random pattern on capture surfaces " of application on October 20th, 2005; The 11/449th, No. 131 " System and method for performing motion capture usingphosphor application techniques " of application on June 7th, 2006; The 11/449th, No. 043 " System and method for performing motion capture by strobing a fluorescentlamp " of application on June 7th, 2006; The 11/449th of application on June 7th, 2006, No. 127 " System and method for threedimensional capture of stop-motion animated characters ", in the above-mentioned application each all is transferred to the assignee of this CIP application) how the live performance of catching to cause the very level and smooth surface of catching, afterwards reach the tracking surface (also promptly, facial motion is accurately followed in the polygon motion) of high polygon counting.At last, when the video with live performance is mapped in the tracking surface upward with the generation grain surface, produce the result of photo realistic.

Although current GPU technology can be reproduced many polygons and this surface of throwing light in real time of following the trail of in surface and the texture, but if each frame time of polygon and texture changes (result that it will produce tool photo realistic sense), then it will promptly consume all available RAM of modern PC or video game console.

Use flow geometry technology as described above, thereby geometric configuration constantly is fed among application program/game server 1521-1525 so that the video-game that its face permission generation of cartoon making photo realistic constantly has the face that almost can not be different from live action face becomes actual.

The integration of linear content and interactive feature

Film, TV programme and audio material (general designation " linear content ") can be used for family and office user with many forms widely.Linear content can be obtained on the tangible media as CD, DVD, HD-DVD and blue light medium.It also can come record by the DVR from satellite and cable tv broadcasting.In addition, its payable at sight that can reach cable tv is via satellite promptly seen (PPV) content and available with the video request program on the cable tv (VOD).

The linear content of Zeng Jiaing can be used with the downloaded contents and the content that flows via the internet day by day.Now, there is not the position that to experience all features relevant really with linear media.For example, DVD and other video optical medias have usually in other positions disabled interactive feature (as director's comment, " titbit " short-movie etc.).The Online Music website has disabled Album Cover Art and song information on CD usually, but is not that all CD are online available.And the website that is associated with TV programme usually has additional features, blog and sometimes from performer or creator's comment.

In addition, under the situation of many films or motion event, usually often have and issue the video-game that (under the situation of film) or (under the situation of motion) can closely be related to real world event (for example, player's transaction) together with linear media.

Host services 210 is very suitable for transmitting linear content when the related content with complete special-shaped formula links together.Really, transmitting film not as transmitting the video-game of high interaction formula has challenge, and host services 210 can be sent to linear content the plurality of devices in family or the office, or is sent to mobile device.Figure 23 shows the exemplary user interface page that is used for host services 210, and it shows the selection of linear content.

But, be different from most of linear content distribution systems, host services 210 can also transmit relevant interactive composition (for example, the interactive superimposed layer on menu on the DVD and feature, the HD-DVD, and the Adobe Flash animation (as mentioned below) on the website).Therefore, the restriction which feature can be used is no longer introduced in client device 415 restrictions.

In addition, Co-location system 210 can dynamically and in real time link together linear content and video game content.For example, if the user is just watching Quidditch (Quidditch) match in Harry Potter's film, and determine it to be ready attempt to play Quidditch, then it can only click button and film will suspend and it will be transported to the Quidditch fragment of Harry Potter's video-game immediately.After object for appreciation Quidditch match, button is clicked in another time, and film will restart at once.

Under the situation of the figure of photo realistic and manufacturing technology, the video captured of wherein photographing can not be different from live action figure, when the user carries out Quidditch in live action movie when playing the transformation of the Quidditch recreation in the video-game to host services (as described herein), in fact these two scenes can not be distinguished.This is that linear content and both directors of interactive (for example, video-game) content provide brand-new creation option, can not distinguish because the line between this two worlds becomes.

Utilize host services framework shown among Figure 14, the control of the virtual camera in the 3D film can be offered the beholder.For example, in the scene in betiding train, might allow the beholder when story is made progress, to control virtual camera and look about train.All 3D objects (" assets ") and can in real time the reproduce enough computing power level of described scene and original film of this supposition in train is available.

And even, there is the available interactive feature that stimulates very much for the amusement that non-computer produces.For example, 2005 films " Pride and Prejudice " have the many scenes in the old Britain mansion that is gaily decorated.For specific mansion scene, the user can suspend video and then control camera with the tour mansion, or possible peripheral region.In order to implement these, portability has fish-eye camera and passes mansion, when it follows the trail of its position, is very similar to the QuickTimeVR that implements prior art Apple (apple) company.Various frames then will be converted, so image is undistorted, and then it is stored on the RAID array 1511-1512 together with film, and when the user selects to continue virtual tour by playback.

Under the situation of motion event, can live motion event (such as, Basketball Match) be flowed via host services 210 and watch (as it for common TV wanted) for the user.After the user watches specific broadcast, the video-game of recreation (final basketball player seems and the true general photo realistic of player) can be caught up with the player who begins in same position, and user's (may control a player separately) can play again whether comparable described player is De Gengjia to watch it.

Host services 210 described herein extremely is suitable for supporting this future world, because its can bear unrealistic so that can not be installed in the family or most of offices background in computing power and high capacity storage resources, and always up-to-date (under the situation of available up-to-date computing hardware) of its computational resource, but in family background, have the PC in older generation and the family of video-game with always existing.In addition, in host services 210, the user is concealed all these computation complexities, therefore, even the user may just use very most advanced and sophisticated system, sees from user's viewpoint, and is also simple as the channel on changing TV.In addition, the user can all computing powers of access and the computing power experience that will bring from any client 415.

Multiplayer

Be the degree of multiplayer for recreation, then recreation can not only be communicated to application program/game server 1521-1525 via going into port route 1502 networks, and be conveyed to by network bridge to have not the server carried out or the internet (not shown) of game machine in host services 210.When playing multiplayer by the computing machine on the common interconnection network, then application program/game server 1521-1525 will have the benefit (comparing with situation about carrying out on the recreation server in the family) of the access internet of being exceedingly fast, but it will be subjected in the capabilities limits that slowly connects other computing machines of playing games, and also be subjected to game server on the internet to be designed to adapt to the fact restriction of minimum common ground (common denominator) (described game server is the home computer in relatively slow consumer's Internet connection) potentially.

But when in host services 210 server-centrics, playing multiplayer fully, then can reach very big difference.To the recreation that is used for the user carry out Co-location each application program/game server 1521-1525 will with other application programs/game server 1521-1525 and with flank speed, utmost point low delay connectivity and huge, very fast storage array to carry out any server interconnect of Co-location at central authorities' control of multiplayer.For example, if the hypervelocity Ethernet is used to into port route 1502 networks, then application program/game server 1521-1525 will pass in the middle of each other, and be communicated to 1,000,000,000 bps speed under the potential only time-delay below 1 millisecond or 1 millisecond to carry out any server of Co-location at central authorities' control of multiplayer.In addition, RAID array 1511-1512 can respond very apace and follow with 1,000,000,000 bps data speed transmissions.As an example, if the user customizes the personage aspect appearance and clothes, so that the personage has a large amount of geometric configuratioies and behavior unique for the personage, be limited in the family under the prior art system of the game client of carrying out on PC or the game console, if described personage will enter in another user's the visual field, then the user will wait for till long slow download is finished, so that all geometric configuratioies and behavioral data are written in its computing machine.In host services 210, described identical download can be better than with the hypervelocity Ethernet of 1,000,000,000 bps speed from RAID array 1511-1512 service.Even the domestic consumer has 8Mbps Internet connection (it is exceedingly fast according to standard now), also fast 100 times of hypervelocity Ethernet.Therefore, will spend less than one second being operated on the hypervelocity Ethernet of carrying out in one minute of cost in the fast Internet connection.

Top player hives off and championship

Host services 210 extremely is suitable for championship.Do not carry out in local client because there is recreation, so the chance that does not exist the user to practise fraud.And, because the ability of output route 1540 multicast UDP stream makes that host services 210 can the thousands of people broadcasting big championship of while in spectators.

In fact, when exist so be in fashion so that thousands of users when just receiving the particular video stream of same stream (for example, the view that shows big championship), can be more effective with video flowing send to content distribution network (CDN) (such as, Akamai (A Kamai company) or Limelight (spotlight company)) to be used for being assigned to many client devices 415 in a large number.

When the recreation view finder page that uses CDN to show that top player hives off, can obtain the efficient of similar level.

For big championship, can use live famous person announcer that comment is provided during particular game.Although a large number of users will be to watch big championship, and the relatively small number order will be to play in championship.Audio frequency from famous person announcer can be routed to the user who plays in championship is carried out Co-location and any onlooker's pattern duplicate of the recreation in the championship is carried out the application program/game server 1521-1525 of Co-location, and audio frequency can be added record in the recreation audio frequency on.Can be in recreation (also may just on onlooker's view) stack famous person announcer's video.

The acceleration that webpage is written into

The main transportation protocol of world wide web, HTTP(Hypertext Transport Protocol) are only conceived and are limited at wherein commerce and have high speed internet and connect, and online consumer used in the epoch of dial data machine or ISDN.At this moment, " golden standard " that be used for connecting fast is the T1 line, and it provides 1.5Mbps data rate (also promptly, having identical data speed in the both direction) symmetrically.

Now, situation is different fully.The average family connection speed that connects via DSL or cable modem in a large amount of developed worlds has the downstream data rate more much higher than T1 line.In fact, in some places in the world, Fiber To The Curb (fiber-to-the-curb) just will bring family into up to the data rate of 50Mbps to 100Mbps.

Unfortunately, HTTP is not become to effectively utilize this rapid speed improvement by framework (yet not being implemented).The website is the set of the archives on the remote server.Very briefly, HTTP asks first archives, these archives that wait for downloads, and then ask second archives, these archives etc. wait for downloads.In fact, HTTP allows " the open connection " (also promptly, asking above archives) more than one at every turn, but only permits considerably less open the connection owing to the standard of deciding through consultation (and preventing the hope that the webserver is overloaded) makes.In addition, because the mode that webpage is configured, browser is not usually recognized a plurality of while pages (yet promptly, only just becoming apparent: need to download the new archive as image) that can be used for downloading immediately after page of analysis.Therefore, the archives on the website come down to one by one to be written into.In addition, owing to the request and the response protocol that use by HTTP, there is the time-delay of roughly (typical web servers of the visit U.S.) relevant with each loaded archives 100 milliseconds.

Under the situation that low speed connects relatively, this can not introduce a large amount of problems, because be used for the stand-by period of the download time decision webpage of archives itself.But,, begin to cause problem along with connection speed increases (under the especially complicated webpage situation).

In Figure 24, in the shown example, shown typical commercial website (this specific website is from bigger sport footwear trade mark).Have 54 archives on the website.Archives comprise HTML, CSS, JPEG, PHP, JavaScript and Flash archives, and comprise video content.Live at the scene webpage (also promptly, the user can click this webpage and bring into use this webpage) before, must be written into 1.5M byte altogether.There are many reasons for a large amount of archives.At first, this webpage is complicated and most advanced and sophisticated webpage, and secondly, this webpage for the webpage that dynamically makes up based on information about the user of this page of access (for example, the user is from which country, which kind of language whether buy before the user etc.), and look all of these factors taken together and download different archives.But it still is very typical commercial webpage.

Figure 24 shows along with connection speed increases live at the scene webpage elapsed time amount before.1.5Mbps connection speed 2401 times, use legacy network server with conventional web browser, spend 13.5 seconds before the live at the scene webpage.12Mbps connection speed 2402 times, be written into time decreased to 6.5 second, or fast again approximately.But 96Mbps connection speed 2403 times, the time that is written into only is reduced to about 5.5 seconds.This reason is because under this high speed of download, downloads the time minimum of archives itself, but each archives separately roughly 100 milliseconds time-delay still keep, thereby cause 100 milliseconds=5.4 seconds time-delay of 54 archives *.Therefore, how soon the connection of no matter arriving family will always spend at least 5.4 seconds before this website is live at the scene.Another factor is the server side queuing; Each HTTP request is to add at the rear portion of formation, and therefore this will have appreciable impact on busy server, because for each small project that will obtain from the webserver, the HTTP request needs to wait for that it returns.

A mode that addresses these problems is discarded or limits HTTP again.Perhaps, may make website owner preferably its archives are merged into single archives (for example, with Adobe Flash form).But, as a practical problems, the said firm and many other people in its web site architecture, have great amount of investment.In addition, connect although some families have 12-100Mbps, most of families still have speed more slowly, and HTTP is slowly working well under the speed really.

An alternative method is on application program/game server 1521-1525 web browser to be carried out Co-location, and at (or potentially among the RAM on the application program/game server 1521-1525 that web browser is carried out Co-location or on the local reservoir) on the RAID array 1511-1512 archives that are used for the webserver is carried out Co-location.Because via the very fast interconnection of going into port route 1502 (or to local reservoir), be not to use every archives under the HTTP to have 100 milliseconds time-delay, but will have the minimum time-delay of every archives under the HTTP using.Then, be not to make user in the family, but the user can be via client 415 accessing web pages via the HTTP accessing web page.Then, even under 1.5Mbps connects (because this webpage does not need massive band width to be used for its video), webpage also will be in on-the-spot broadcasting in less than 1 second time at each line 2400.In fact, before the web browser of carrying out on application program/game server 1521-1525 shows the live page, will there be time-delay, and before the video output of client 415 demonstrations, will do not have the time-delay that can detect from web browser.When the user uses mouse to search webpage and/or key in word on webpage, user's input information is sent to the web browser of carrying out on application program/game server 1521-1525, and web browser will respond correspondingly.

A disadvantage of the method is: if compressor reducer transmitting video data just consistently, then utilized bandwidth is also like this even webpage becomes static state.This can be by the configuration compressor reducer only just to transmit data when (and if) web-page change and then only data transmission partly to be made up to the page that changes.When existence had consistently some webpages of the flicker poster that changes etc., described webpage was often horrible, unless and exist will mobile something () reason for example, video clipping, otherwise webpage be a static state usually.For described webpage, may be following situation: use host services 210 will transmit less data (comparing) with the legacy network server, because will only transmit the image of actual displayed, there is not the thin client executable code, and big object that cannot be never viewed (such as, the rolling flip image).

Therefore, use host services 210 to come the old edition webpage is carried out Co-location, webpage can be written into time decreased to turning on the degree that webpage is the channel on the similar change TV: this webpage of broadcasting live immediately effectively.

Be convenient to play and the debug of application program

As discussed previously, have the video-game of real-time graph and application program for very complicated application program and usually when it is issued in this field, it contains defectiveness.Although the software developer will obtain feedback about defective from the user; and it may have some modes after collapse machine state passed back of being used for, but identification is what causes recreation or real-time application collapse or carries out very difficult inadequately definitely.

When recreation or application program when in host services 210, carrying out, the video/audio output of recreation or application program is recorded on the delay buffer 1515 consistently.In addition, the house dog process is carried out each application program/game server 1521-1525, this house dog process will to host services control system 401 termly reporting application/game server 1521-1525 carry out just reposefully.If the house dog process fails to report that then server control system 401 will be attempted to communicate by letter with application program/game server 1521-1525, and if success then will be collected available machine state whatsoever.Information available is whatsoever sent to the software developer together with the video/audio by delay buffer 1515 records.

Therefore, as recreation or application software developer during from notice that main frame service 210 obtains collapsing, it obtains causing the frame of the reason of collapsing to connect the record of frame.This information track defective and with defect repair in may be valuable.

Should also be noted that when application program/game server 1521-1525 collapses, restart server in the nearest moment of restarting, and message is offered the user, thereby apologize with regard to technical difficulty.

Resource sharing and cost savings

Shown system provides multiple benefit for terminal user and recreation and application developers among Fig. 4 a and Fig. 4 b.For example, usually, family and office's client (for example, PC or game console) only the little number percent in a week hour in be in use.According to by Nielsen (Nelson) amusement " Active Gamer Benchmark Study (enliven player's reference point research) " (http://www.prnewswire.com/cgi-bin/stories.pl? ACCT=104﹠amp; STORY=/www/story/10-05-2006/0004446115﹠amp; EDATE=) communication in 5 days October in 2006 original text, active average cost of one week of player came playing on the video game console and about 17 hours weeks play on handheld device in 14 hours.This report is also stated: for all game play activities (comprising control desk, handheld device and PC game play), and average 13 hours weeks of active player.Consider the control desk video-game reproduction time of higher number, have all 24*7=168 hour, this hints in enlivening player's family, video game console only the 17/168=10% in a week hour in be in use.Perhaps, 90% time, video game console leaves unused.Given video game console expensive, and manufacturer subsidizes the fact of described equipment, this is the very inefficient use of expensive resource.PC in commercial also only uses in the part in a week hour usually, especially the usually required non-portable Desktop PC of high-end applications program (such as, Autodesk Maya).Although some commerce were all operated in all hours and holiday, and some PC (for example, take home to be used for carrying out at night the portable PC of work) be to use in all hours and holiday, but most of business activities tend in given commercial time zone, concentrate on about 9AM to 5PM from Mon-Fri, less holiday and time of having a rest (such as, lunch), and occur when the user utilizes PC energetically because most of PC uses, so it is followed: the utilization of Desktop PC tends to follow these hours run numbers.If supposition five days in one week constantly use PC from 9AM to 5PM, then this will hint PC the 40/168=24% in a week hour in be used.The high-performance Desktop PC is to be used for commercial very expensive investment, and this has reflected low-down availability.The school that imparts knowledge to students on the desk-top computer can a week in addition more use a computer in the fraction, although and its look the hourage of teaching and change, the great majority teaching from Mon-Fri in the daytime hour during occur.Therefore, generally speaking, PC and video game console only are utilized in the fraction in a week hour.

Notably, because many people the Mon-Fri of eekday in the daytime hour during commercial or work in school, so these people are playing video game not during these hours usually, and therefore when its certain playing video game, its normally during other hours (such as, evening, weekend and holiday).

The configuration of shown host services among given Fig. 4 a, the use pattern described in then above-mentioned two sections causes the very effective utilization of resource.Obviously, there is limited in number, especially need be used under the situation of real-time responsiveness of complex application (as most advanced and sophisticated 3D video-game) the user for the user that can serve by host services 210 in preset time.But, the PC that is different from the video game console in the family or uses (it is usually idle placement of most of times) by commerce, server 402 can be utilized at different time again by different user.For example, the high-performance server 402 with the two CPU of high-performance and two GPU and a large amount of RAM can be utilized at the 9AM to 5PM of eekday by commerce and school, but by the player who plays most advanced and sophisticated video-game at night, weekend and holiday utilize.Similarly, the low performance application program can utilized on the low performance server 402 that have Celeron (Celeron) CPU, no GPU (or very the GPU of low side) and limited RAM during commercial hour and low performance is played and can be utilized low performance server 402 during non-commercial hour by commerce and school.

In addition, under the situation of described in this article host services configuration, resource is shared effectively in the middle of thousands of names (if not millions of name) user.Generally speaking, online service only has the little number percent of its total user base in use service preset time.If consider previous listed Nielsen video-game usage statistics, what then be appreciated that easily.If enliven the only object for appreciation control desk recreation in 17 hours of one week of player, and if peak usage time of make is (5-12AM at night, 7*5 days=35 hours/week) and weekend (8AM-12AM, 16*2=32 hour/week) typical inoperative, non-commercial hour during, then for 17 hours game play, there be 35+32=65 peak value hour a week.Because following many former thereby feasible definite peak user loads that are difficult on the estimating system: some users will play by time durations outside peak value, may exist time between particular day to have user's (clustering) peak value of gathering together, the type that time to peak can be subjected to be played games influences such as (for example, child's recreation may be to play at night time early).But, suppose when the player may play games, the player plays mean hours number much smaller than in the daytime hourage, then only the user of a part of number of host services 210 uses host services 210 in preset time.For this analysis, we suppose that peak load is 12.5%.Therefore, only 12.5% calculating, compression and bandwidth resources are to use in preset time, thereby because re-using of resource only causes 12.5% hardware cost to support given user to play the given rank that performance is played.

In addition, suppose the computing power that some recreation and application program need be Duoed than other persons, then can come dynamically Resources allocation based on the recreation of being played by the user or by application program executing.Therefore, select the user of low performance recreation or application program will be assigned with low performance (cheaper) server 402, and select the user of high-performance recreation or application program will be assigned with high-performance (expensive) server 402.In fact, given recreation or application program may have the lower-performance and the superior performance district of recreation or application program, and can between the district of recreation or application program, the user be switched to another server 402 from a server 402, on the least cost server 402 of the needs that satisfy recreation or application program, carry out to keep the user.Note, than the faster RAID array 405 of single disk can by in addition low performance server 402 used, this has the benefit of very fast disk transfer rate.Therefore, cross over that institute plays games to some extent or every server 402 average unit costs of employed application program peak performance is played or the cost of the most of expensive server 402 of application program is much smaller than playing, yet, even low performance server 402 also can obtain the disk performance benefit from RAID array 405.

In addition, the server 402 in the host services 210 may be the PC motherboard with disk or perimeter interface (being different from network interface), and just, can be integrated into the single chip that just has to the fast network interface of SAN 403 downwards.And RAID array 405 may be with shared in the middle of than the much more user of the situation that has disk, so each active user's disk cost will be much smaller than a disc driver.All these equipment may reside on the environment in the support in the in check room server environment.If server 402 is out of order, then it can be easily in host services 210 places place under repair or replacement.By contrast, PC in family or the office or game console must be firm, must be able to survive rational wearing and tearing and tear in case thumped or the independent utensil that lands needs shell, has at least one disc driver, must survive hostile environment condition (for example, being filled in reluctantly in the overheated AV cabinet with other apparatus), need service guarantees, must be packed and shipment, and sell by the retailer that may collect retail interest.In addition, PC or game console must be configured to and satisfy the expection recreation the most intensive in the calculating that will use in a certain moment in future or the peak performance of application program, even lower-performance recreation or application program (or district of recreation or application program) also may be played in most of times.In addition, if PC or control desk are out of order, then making it obtain repairing is costliness and time-consuming procedure (influencing manufacturer, user and software developer unfriendly).

Therefore, suppose that the experience that system shown among Fig. 4 a will be equivalent to the experience of local computational resource offers the user, in family, office or school, experience the computing power of given level for the user, then provide described computing power to want much cheap by framework shown among Fig. 4 a.

Elimination is to the needs of upgrading

In addition, the user needn't worry the upgrading of PC and/or control desk to play new game or to handle the new application program of superior performance again.It is used that any recreation on the host services 210 or application program (no matter described recreation or application program need the server 402 of what type) all can be the user, and all recreation and application program near carrying out immediately (also are, local reservoir on RAID array 405 or the server 402 is written into apace) and suitably have latest update and defect repair (also is, the software developer can select to be used to carry out the desired server configuration of the server 402 of given recreation or application program, and then server 402 is disposed the optimal drive device, and then As time goes on, the developer can will upgrade simultaneously, defect repair etc. offer recreation in the host services 210 or all duplicates of application program).In fact, after the user brings into use host services 210, the user may find that recreation and application program (for example continue to provide preferable experience, via upgrading and/or defect repair) and may be following situation: the user finds after 1 year that new game or application program (for example can be used for utilizing computing technique, the GPU of superior performance) in the service 210 of (it does not even exist the year before), therefore for the user, will can not purchase will after 1 year, play games or the technology the year before of executive utility.Because play games or the computational resource of executive utility is invisible for the user (also is, viewpoint from the user is seen, the user only selects to begin to change channel on the TV near the recreation of carrying out immediately or application program-more as the user), so user's hardware will even not recognized under the situation of upgrading by " upgrading " the user.

Elimination is for the needs of backup

Another big problem for the user in commerce, school and the family is backup.If disk is out of order, or if exist and be not intended to wipe, then being stored in information in local PC or the video game console (for example, under the situation of control desk, user's recreation achievement and grade) may lose.The many available application program that has the manual or automated back-up that is provided for PC, and the game console state can be uploaded to line server for backup, but usually local backup is copied to another local disk (or other non-volatile storage facilitiess) that must be stored in safe and organized somewhere, and makes for the backup of online service usually limited owing to connecting available slow speed uplink via typical low-cost Internet.The host services of Fig. 4 a 210 times, the data that are stored in the RAID array 405 can use the prior art RAID configuring technical that is well known to those skilled in the art to dispose, so that when disk is out of order, to not obliterated data, and will notify technician at the server-centric place that holds out of order disk, and then the technician will replace this disk, and this disk then will automatically be upgraded so that the RAID array is tolerated fault again.In addition, because all disc drivers are closer to each other and have quick local network via SAN 403 therebetween, so it is not difficult in server-centric all disk systems configurations to be backuped to secondary reservoir (it can be stored in the server-centric place or reorientate through changing places) termly.From the user's of host services 210 viewpoint, its data are overall safety all the time, and it is from considering backup.

Access to demonstration

The user often wishes in preceding trial game or the application program of buying recreation or application program.As discussed previously, there is prior art apparatus, demonstrates by this prior art apparatus that (verb form of " demonstration " meaning is a crippled version on probation, and crippled version is also referred to as " demonstration ", but as noun) recreation and application program, but wherein each is limited and/or is not convenient.Use host services 210, for the user, easily and be convenient to demonstration on probation.In fact, the user carried out is to select demonstration and this demonstration on probation via user interface (such as, hereinafter described user interface).Demonstration will almost be written on the server 402 that is suitable for this demonstration immediately, and it carries out any other recreation of all fours or application program.The demonstration server 402 that to need very high performance server 402 still be low performance no matter, and what type family or office's client 415 that no matter the user uses are, see from user's viewpoint, demonstrate and all will work.The software publisher of game demonstration or application demo can be controlled definitely and permit user's what demonstration on probation and how long on probation, and certainly, demonstration can be included as the user recreation of acquisition to being demonstrated or the user interface key element of the access chance of the full version of application program are provided.

Because demonstration may be to be lower than cost price or to provide free, so some users may attempt to use the demonstration (especially repeatedly play may be interesting game demonstration) of repetition.The demonstration that host services 210 can be used various technology to limit and be used for given user is used.The most direct method is to set up the user ID and the restriction that are used for each user to allow given user ID to play the number of times of demonstration.Yet the user can be provided with a plurality of user ID, and especially it is freely under the situation.A technology that is used for head it off is that restriction allows given client 415 to play the number of times of demonstration.If client is autonomous device, then this equipment will have a sequence number, and host services 210 can limit demonstration can be by the number of times of client access with described sequence number.If client 415 is just carried out with the software on PC or other equipment, then can be assigned sequence number and this sequence number is stored in PC by host services 210 goes up and uses this sequence number to limit the demonstration use, but supposition PC can come sequencing again by the user, and sequence number is wiped free of or changes, then another option is that host services 210 keeps the record of PC network adapter media interviews control (MAC) addresses (and/or other machines specific identifiers, such as hard disk drive sequence number etc.) and will demonstrate use being limited to this MAC Address.Suppose the MAC Address that can change network adapter, yet this is not open-and-shut method.Other method is the number of times that the restriction demonstration can be played to given IP address.Although can come periodically to assign again the IP address by cable modem and DSL supplier, but it can not take place in practice very continually, and if (for example can determine, by contact ISP) IP is the block that is in the IP address that is used for dwelling house DSL or cable modem access, then can set up the demonstration of the peanut that is used for given family usually and use.And, after the NAT router of shared same IP address, may there be a plurality of equipment in the family, but usually in the dwelling house background, will have the described equipment of limited number.If the IP address is to be in the commercial block of service, then can set up the demonstration that is used for commercial greater number.But last, the combination of all previous described methods is best modes of the number of the demonstration on the restriction PC.Although may there not be the open-and-shut mode that makes that determined and technical skilled user may be restricted in the number of repeat playing demonstration, but set up that a large amount of obstacles can be set up enough obstructions so that most of pc user is unworthy taking great energy and abuses demo system, and opposite, it uses demonstration when it is intended to new game on probation and application program.

Benefit to school, commerce and other mechanisms

Significantly benefit especially appears at commerce, school and other mechanisms that utilizes system shown among Fig. 4 a.Commerce and school have and install, safeguard and essence cost that upgrading PC is associated, especially when the PC of the high performance application of referring to execution such as Maya.As stated previously, PC usually only a week hour a part in be utilized, and as in the family, the cost of PC in office or school environment of performance capability with given level is far above the cost in the server-centric environment.

Than large-scale commerce or school (for example, big university under) the situation, the IT department of described entity server-centric is set and safeguard via the LAN level connect and remotely the computing machine of access can be actual.Exist and be used for connecting and many solutions of remote access computing machine via LAN or via the private high bandwidth between the office.For example, Windows Terminal server by Microsoft, perhaps by virtual network computing application program (as VNC) or by thin client device from Sun Microsystems (sun computing machine system house) from RealVNC (Long-distance Control) company limited, the user can obtain the remote access to PC or server, has the quality of certain limit in graphic response time and user experience.In addition, the described server-centric of management voluntarily is exclusively used in single commerce or school usually, and therefore can not utilize complete different application program (for example, amusement and business applications) when the different time in a week utilizes same computational resource possible use overlapping.Therefore, many commerce and school lack independent scale, resource or the expertise with the server-centric that connects to the network of each user's LAN speed that be provided with.In fact, greatly the school of number percent and commerce have the Internet connection identical with family (for example, DSL, cable modem).

Yet, the described needs that still may have (perhaps termly or periodically) of organizing for very high performance calculating.For example, Minor Construction company may only have the architect of peanut, when carrying out design effort, has the calculating needs of appropriateness relatively, but it may periodically need very high performance 3D to calculate (when for example, the 3D that is used for the new building design of client when foundation leaps).System shown among Fig. 4 a extremely is suitable for described tissue.Described organizing only needs to connect (for example, DSL, cable modem) and very cheap usually for providing to the network of the same kind of family.It can utilize cheap PC as client 415, does not perhaps have PC also passable fully, and utilizes the simple cheap specialized equipment of implementing control signal logic 413 and low delay video decompression 412.This feature is for the stealing that may have PC or attractive especially to the school of the problem of the damage of the personal module in the PC.

This configuration has solved the many problems (and many this advantages are also shared for the domestic consumer who carries out general-purpose computations) that are used for described tissue.For example, running cost (it finally must be back to the user so that have feasible commerce with certain form transmission) may be much lower, because (a) computational resource is shared with other application programs that have different peak usage times in a week, (b) described tissue can only obtain (and causing cost) access to the high-performance calculation resource when needed, and (c) described tissue needn't be provided for backing up or otherwise safeguarding the resource of high-performance calculation resource.

Pirate elimination

In addition, recreation, application program, interactive film etc. may be for another example now like this by piracies.Because recreation is to carry out at the server-centric place,, therefore there is not piracy so the user does not possess the access for the base program sign indicating number.Even the user will the replicating original sign indicating number, the user can not carry out this sign indicating number on standard game control desk or home computer.This has opened the normal video recreation market of disabled all over the world (such as, China).Again the sale of the recreation of having used also is impossible.

For the game developer,, there is less city field's discontinuity as situation now.Force user and developer's upgrading and game developer to depend on the current situation contrast of the timely transmission of hardware platform with a brand-new generation technique, can require change and little by little upgrade host services 210 along with recreation along with the time.

Streaming interactive video

More than describing provides that (it impliedly also comprises the audio frequency together with video, the multiple application of novel key concept activation as used herein) by the low-latency streaming interactive video based on common interconnection network.Provide the prior art system of the video that flows only to have the application that to pass through the interactive institute's activation implemented of high time-delay via the internet.For example, the basic playback controls (for example, suspend, return, F.F.) that is used for linear video is suitably worked under the height time-delay, and might select in the middle of linear video feed.In addition, as stated previously, the character of some video-games allows it to delay time with height to play.But, the height time-delay (or low compression ratio rate) that is used for the prior art approach of mobile video seriously limits the potential application of the video that flows or makes its deployment narrow to specialized network environment, and even in described environment, prior art is also introduced the essence burden on the network.Technology described herein has been opened the gate of multiple application possible under the low-latency streaming interactive video via the internet, especially the described application of activation via the Internet connection of consumer's level.

In fact, with the general little client device of the client 465 of Fig. 4 c under, be enough to the computing power by effective any amount, the quick storage of any amount and the user experience that network connects provides enhancing that is exceedingly fast between the powerful server, it makes the new calculating epoch become possibility.In addition, because bandwidth requirement does not increase along with the computing power growth of system, because bandwidth requirement is only about display resolution, quality and frame rate), in case so the broadband internet connectivity be ubiquitous (for example, contain via widespread low delay is wireless), reliably and have a sufficiently high bandwidth of the needs of the display device 422 that is enough to satisfy all users, then problem will be typical consumer and commercial use necessary be thick and heavy client (such as, carry out Windows, Linux, the PC of OSX etc. or mobile phone) still in addition thin client (such as, Adobe Flash or Java).

The appearance of streaming interactive video causes rethinking about the supposition of the structure of computing architecture.This example is host services 210 server-centric embodiment shown among Figure 15.The video path that is used to postpone to cushion the G device and/or hive off video 1550 is a backfeed loop, and wherein being fed after selectable delay in real time or via path 1551 via path 1552 through the output of the streaming interactive video of multicast of application program/game server 1521-1525 got back among application program/game server 1521-1525.This make by prior art server or local computing architecture will be impossible or infeasible multiple practical applications (for example, such as Figure 16, Figure 17 and application illustrated in fig. 20) become possibility.But as architectural features more generally, backfeed loop 1550 provides the recurrence under the streaming interactive video level, because can when application program needs video video ad infinitum be circulated.Never available multiple application possibility became possibility before this made.

Another crucial architectural features is: video flowing is unidirectional UDP stream.This realizes the multicast (by contrast, the bidirectional flow such as TCP/IP stream will produce increasing communication stagnation along with user's number increase on from the network of communication back and forth) of any degree of streaming interactive video effectively.Multicast is the significant capability in the server-centric because its permission system to the needs of Internet user's's (and in fact, the population in the world) growth respond with one-to-many or even the multi-to-multi basis on communicate by letter.Once more, the example of the explanation streaming interactive video recurrence of being discussed herein and the use of multicast (such as, Figure 16) only be tip with very large iceberg of possibility.

In one embodiment, illustrated herein various functional module group and the step that is associated can be by containing the specific hardware components that is useful on the hardwired logic of carrying out described step (such as, specific use integrated circuit (" ASIC ")) or being carried out by any combination of computer module that is programmed and custom hardware components.

In one embodiment, described module can be implemented on TMS320x framework such as the Texas instrument (for example, TMS320C6000, TMS320C5000 ... etc.) programmable digital signal processor (" DSP ") on.Can use various DSP, still observe described ultimate principle simultaneously.

The various steps that embodiment can comprise as mentioned being set forth.Described step can be embodied in the machine-executable instruction that causes universal or special processor execution particular step.Will with the irrelevant various elements of these ultimate principles (such as, computer memory, Hard Disk Drive, input equipment) from figure, save with the related fields of avoiding confusion.

The key element of disclosed subject matter also can be used as the machine-readable medium that is used for the store machine executable instruction and provides.Machine-readable medium can include, but is not limited to flash memory, laser disc, CD-ROM, DVDROM, RAM, EPROM, EEPROM, magnetic or optical card, communications media or be suitable for the machine-readable medium of the other types of stored electrons instruction.For example, the present invention can be used as computer program and downloads, this computer program can be via communication link (for example, modem or network connect) by means of be embodied in carrier wave or other communications medias data-signal and from remote computer (for example, server) is sent to requesting computer (for example, client).

Will also be understood that, the key element of disclosed subject matter also can be used as computer program and provides, above can being included in, this computer program stores the machine-readable medium of instruction, described instruction can be used for programmed computer (for example, processor or other electronic equipments) to carry out a series of operations.Perhaps, described operation can be carried out by the combination of hardware and software.Machine-readable medium can include, but is not limited to floppy disk, CD, CD-ROM, and magneto-optic disk, ROM, RAM, EPROM, EEPROM, magnetic or optical card, communications media or be suitable for the medium/machine-readable medium of the other types of stored electrons instruction.For example, the key element of disclosed subject matter can be used as computer program and downloads, wherein program can be sent to request process by means of being embodied in the data-signal in carrier wave or other communications medias from remote computer or electronic equipment via communication link (for example, modem or network connect).

In addition, although describe disclosed subject matter in conjunction with specific embodiment, numerous modifications and changes will suitably be in the category of the present disclosure.Therefore, instructions and graphicly should be considered as illustrative and nonrestrictive meaning.

Claims (3)

1. computer-implemented method that is used to carry out video compress, this method comprises:

In logic each image in the image sequence is divided into a plurality of image blocks again, each image block in the described image block has the qualification position in each image in described image sequence, and described qualification position keeps identical between consecutive image;

The motion that detection takes place in each position of each described image block in described image sequence;

Use first compressed format or second compressed format that each image block in each image of described image sequence is encoded, wherein the frequency that specific image block is encoded according to described first compressed format in described image sequence is based on detect in the place, position of described image block in the described image sequence momental.

2. method according to claim 1, wherein said first compressed format comprises intraframe coding.

3. method according to claim 2, wherein said second compressed format comprises interframe encode.

Images