CN106210450A - Video display artificial intelligence based on SLAM - Google Patents
Video display artificial intelligence based on SLAM Download PDFInfo
- Publication number
- CN106210450A CN106210450A CN201610571146.0A CN201610571146A CN106210450A CN 106210450 A CN106210450 A CN 106210450A CN 201610571146 A CN201610571146 A CN 201610571146A CN 106210450 A CN106210450 A CN 106210450A
- Authority
- CN
- China
- Prior art keywords
- video
- networking
- slam
- video source
- wireless self
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a kind of video display artificial intelligence based on SLAM.The video information relevant to self can be captured from the big data video information of socialization alternately, and generated the movie and video programs with user as leading role by inference machine and knowledge base by computer automation.
Description
Technical field
The present invention relates to a kind of video editing method, especially a kind of based on SLAM and wireless self-networking to multichannel, many
The big data video at visual angle merges editing, and the image being generated movie and video programs by computer automation by inference machine and knowledge base is special
Family's system.
Background technology
Neuroscience finds, it is similar that the imagination of human brain emotion is experienced with actual experience.
Research about Learning and Memory mechanism finds, by the effect of composite information in the lump coded memory memory when
More preferably.The memory effect that especially recall info produces when being associated with oneself is better than other information conditions, here it is self-
Anchoring effect.This advantage is mainly reflected in recall in the reaction that experience is characterized.When contacting new thing, if it and I
Self have substantial connection if, be just not easy to forget.In simple terms: people can more pay close attention to the thing relevant with oneself.
Autologous psychology thinks that autophilia is the general essence of the mankind.Everybody hankers after autodyning, but easy, auto heterodyne of certainly taking a picture
Video is difficult.
We are accustomed to every trade and take the photograph.But, in the face of let us produces the excellent of shooting impulsion, we go shooting of diverting one's attention, but
Have ignored real excellent own.
We divert one's attention to image.But, the multitude of video taking a lot of trouble shooting is often sunk into sleep hard disk, is not organized, looks back.
Go with activity time, everybody mutually shoots.But we are difficult to obtain regarding of oneself from other people camera-shooting and recording device in real time
Frequently.Also it is difficult in real time from the same activity of other people view.
Monitoring camera is universal produces massive video information, also promotes to search for the video inspection of useful information from big data video
Rope technology is gradually ripe and starts to move towards market.
The basis of tradition video display creation is literature play writing, and text image is converted into film according to literature drama by director
Video and audio language, from write out shooting script to the departments such as leader's photography, art designing, recording, performer worked in concert early stage production
Artistic creation, be the inventing again during film creation.Editing is then three degree of creation in whole film production process, by
The vision material of prophase shoot and sound material are decomposed, combine, edit and constitute a complete movie by editor again.
When different camera lenses are stitched together, do not have when can produce the most again each camera lens individualism specific contains
Justice.This mode is also montage.Montage (Montage) was architectonics term originally, meant composition, assembling, soluble
For there being the space-time of meaning to piece editing maneuver artificially together.For tradition films and television programs, montage is born in the design of literature drama
Time, it is embodied in shooting script, finalizes a text on cutting table.But, this set flow process is difficult to apply by existing mass data
It is compiled as films and television programs.
In mobile augmented reality, the technology of core the most is the tracking registration technique of destination object, and this technology can be segmented
It is 2 types: the tracking registration technique of view-based access control model, the tracking registration technique of non-vision.Wherein, the tracking registration of view-based access control model
Technology can be divided into again has the tracking registration technique of marker and without the tracking registration technique of marker (based on physical feature).Mesh
Before, mainly there is SLAM(Simultaneous Localization based on the augmented reality method following the tracks of registration technique without marker
And Mapping), PTAM (Parallel Tracking and Mapping) etc..
SLAM (simultaneous localization and mapping) is a kind of instant location and map structuring
Algorithm.The Project Tango of Google is a kind of SLAM equipment, and it comprises motion tracking (Motion Tracking), depth perception
Know (Depth Perception) and three core technologies of regional learning (Area Learning), bring one for mobile platform
Plant brand-new spatial perception to experience.But, Project Tango builds based on cell phone platform, grips blocking of mobile phone generation and makes
Project Tango is only capable of using single camera vision system, it is difficult to arrange more infrared sensor and photographic head obtains bigger
Visual angle.
Summary of the invention
For solving the problems referred to above, from the big data video information of socialization, appropriately capture information needed, join based on oneself
According to effect realize CAL, recall, conduct a sightseeing tour, play, scene walkthrough, and the application such as augmented reality, mixed reality, it is thus achieved that
Plant, based on SLAM and wireless self-networking, the big data video of multichannel, various visual angles is merged editing, by inference machine and knowledge base
Image specialist system by computer automation generation movie and video programs relevant to individuality.The invention discloses a kind of based on SLAM
Video display artificial intelligence.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of based on without marker tracking registration technique, it is based especially on the video display artificial intelligence of SLAM, including video source, network
Layer, server and movie editing specialist system.It is characterized in that:
1, arranging video source is one or more.
When video source is more than one, use at a bearing mark code defined in video source encoding and decoding rule based on SLAM
In instant location, Video stream information is mutual and editing.
1.1, described bearing mark code based on SLAM carry out towards and Attitude Calculation, definition shooting video source camera and position thereof
Putting and direction, mark world coordinates is tied to the conversion of camera coordinate system, camera coordinates is tied to turning of imaging plane coordinate system
Change and imaging plane coordinate is tied to the conversion of image coordinate system.When shooting video source camera and being static, bearing mark code includes:
Camera identification code, camera coordinates, camera orientation angle, inclination angle, left and right, pitch angles and technique for taking parameter.When shooting video source
During camera motion, bearing mark code includes: camera identification code and the camera based on timestamp produced with camera displacement run
Route, camera orientation angle, inclination angle, left and right, pitch angles and the delta data of technique for taking parameter.
1.2, arranging vision sensor based on SLAM definition bearing mark code is single camera vision system, binocular vision system
System, multi-vision visual system or overall view visual system.
1.3, when vision sensor based on SLAM definition bearing mark code is overall view visual system, at bearing mark code
Middle camera coordinates identifies with spherical coordinate system.
2, described Internet is a protocol layer, its foundation being responsible for wireless self-networking and maintenance, and Internet passes through interface
Thering is provided management service and data, services for movie editing specialist system, movie editing specialist system is positioned at wireless self-networking protocol stack
The top of framework.Network layer data Connection Service device data base also undertakes management and the maintenance work of network information database.
2.1, when video source is more than one, described wireless self-networking is determined in video source encoding and decoding rule based on SLAM
The bearing mark code of justice, is made by procotol between the big data video of the multichannel from multiple video source nodes, various visual angles
Directly or multi-hop communication, make between node automatically, quickly, the dynamic special short distance mobile radio network set up,
In this network, each node can arrange it and have terminal system and transistroute function simultaneously concurrently, both can also may be used with data transmit-receive
Forward with multi-hop.
2.2, the plurality of video source node dynamic group net active swap bearing mark code information, and according to bearing mark code
Information judges to be suitable for third party's video source node of this node orientation, angle and distance, according to the interaction protocol set to it
Play video data call request.Third party's video source node is according to the bearing mark code information of request initiator, several from this locality
Go out relative video data according to editing real-time in video to be sent by wireless self-networking.By that analogy, multiple video source joint
Point automatically, quickly, interim, dynamic group net, and based on the Internet alternating transmission video data relevant to this node.
2.3, a kind of based on SLAM, the side that judges this node and third party's video source node according to bearing mark code information
Position, angle with the method for distance be: by the bearing mark code of known each node, calculate the three-dimensional of third party's video source node
Relation between space coordinates and this node coordinate, show that acquisition third party's video source nodal coordinate system is put down with this nodal coordinate system
Move rotational transformation matrix, thus obtain space coordinate transformation matrix.
2.4, a kind of wireless self-networking is point-to-point Ad Hoc wireless self-networking, and a kind of wireless self-networking is wireless
Mesh network.A kind of wireless self-networking is wireless self-networking based on Zigbee protocol.A kind of wireless self-networking is based on WiFi
Wireless self-networking, a kind of wireless self-networking based on WiFi is direct connection networking based on Wi-Fi hotspot, a kind of based on WiFi
Wireless self-networking is HaLow wireless self-networking.A kind of wireless self-networking is wireless self-networking based on bluetooth, a kind of based on bluetooth
Wireless self-networking be wireless self-networking based on low-power consumption bluetooth BLE, a kind of wireless self-networking based on bluetooth be based on
The point-to-point wireless self-networking of bluetooth of Multipeer Connectivity framework, a kind of wireless self-networking based on bluetooth is base
Wireless self-networking in iBeacon.A kind of wireless self-networking is Ad Hoc wireless self-networking based on ultra broadband UWB.A kind of nothing
Line MANET is based on ultra broadband UWB and the wireless self-networking of bluetooth mixed communication.A kind of wireless self-networking be based on WIFI and
The wireless self-networking of bluetooth mixed communication.A kind of wireless self-networking is based on WIFI and ZigBee mixed communication wireless from group
Net.
When wireless self-networking be based on or during the wireless self-networking of mixing WiFi technology, a kind of global function node still couples
Wireless self-networking and the across a network node of the Internet.
3, movie editing specialist system is set and includes human-computer interaction interface, video frequency searching engine, inference machine, knowledge base, work
Make memorizer and interpreter.
3.1, described movie editing specialist system is to have drama, director and editing expertise and the Computing Intelligence of experience
Energy programming system, by the modeling of the problem solving ability to human expert, uses the representation of knowledge in artificial intelligence and knowledge
Inference technology simulates the challenge generally solved by expert.Described movie editing specialist system regards with heuristic interaction process
Frequency symbol, separates knowledge and control, to process uncertain problem, reaches acceptable solution.
3.2, the big data from local and Internet are regarded by described video frequency searching engine by intelligent video retrieval technique
Frequently real time filtering, detect, identify, classify and multiple target tracking, according to time, scape not, image, intonation, emotion, emotion shape
State and the judgement to inter personal contact, automatically video source is cut into a series of comprise index identify label, semantics identity label,
Scape does not identify label or the story board of editing identification label.
The algorithm that described story board processes is target detection, target following, target recognition, behavior analysis or based on content
Video frequency searching and data fusion.
Based on intelligent video retrieval technique, video frequency searching includes characteristic extracting module, Video segmentation module, filtration and video
Steady as module, intelligent retrieval matching module.
3.3, described inference machine is to realize based on drama plot, director and the parts of editing knowledge reasoning, mainly includes pushing away
Reason and two parts of control, it is the program explaining knowledge, according to the semanteme of knowledge, to knowing of strategically finding
Know and explain execution, and result be recorded in the suitable space of working storage.
The inference logic of a kind of inference machine is classical logic.A kind of classical logic is deductive logic, and a kind of classical logic is
Inductive logic.The inference logic of a kind of inference machine is non-classicol logic, and a kind of non-classicol logic is dialectical logic.
A kind of working method of inference machine be deduct, arrange by video frequency searching engine provide some comprise editing know
The camera lens of distinguishing label, as the known fact, derives video display structure, plot understanding or scene planning according to axiomatics；
Or, the working method of a kind of inference machine is non-monotonic reasoning, and described non-monotonic reasoning includes based on default information silent
Recognize reasoning and constraint reasoning.Described default reasoning logic is: and if only if not fact proved that camera lens S editing identification label does not becomes
Immediately, S always sets up.The logic of described constraint reasoning is: and if only if not fact proved that camera lens S editing identification label exists
When setting up in larger scope, S only sets up in the range of specifying.
Or, the working method of a kind of inference machine is qualitative reasoning, described qualitative reasoning from physical system, the mankind directly perceived
Thinking is set out, and derives behavior description, in order to the behavior of prognoses system.In movie editing specialist system, qualitative reasoning uses a point mirror
The partial structurtes rule of head predicts that the plot of film understands or scene planning.
3.4, described knowledge base is play writing, director and the set of editing domain knowledge, including basic fact, rule and
Other are for information about.Knowledge base and System program are separate, and user can be by changing, improving in knowledge base
Knowledge content improves the performance of specialist system.A kind of knowledge base is by scenarist, director and editing expert and right
Existing films and television programs, musical works, literary works, 3D model, the degree of depth study of picture works, unsupervised learning, transfer learning
Or multi-task learning structure.
3.5, described working storage is the set of reflection current problem solving state, in storage system running
Produced all information, and required initial data, the information inputted including user, the intermediate object program of reasoning, reasoning
The record of process.The state being made up of basic fact, proposition and relation in working storage, is that inference machine selects depending on of knowledge
According to, also it is the source of explanation facility acquisition Induction matrix.
3.6, described interpreter is for explaining to solution procedure, and answers the enquirement of user.Allow user's prehension program
Doing what and why do so.
3.7, movie editing specialist system by inference machine combine knowledge base to through video frequency searching engine filter index divide mirror
Head is created again, generates movie and video programs by server cognition calculation automation.Its method of work is:
Story board is transferred very elegant intelligence and claps specialist system.The inference machine being clapped specialist system by very elegant intelligence combines the story of a play or opera, director
And editing knowledge base rule, select, call knowledge base comprises plot, video display, scene, sound, picture, word, 3D model
In material, story board choice, decomposition are connect with group, thus automatically generated user's original video work of acceptable solution by computer
Product.
A, Internet call all local video sources relevant to this node and the 3rd based on timestamp by setting the time period
Side's video source；
B, based on the best video source of image recognition technology filter quality；
Bearing mark code in c, comprehensive video search engine and video source and coordinates matrix identification code, for video source story board and
Index, the scape of definition story board is other；
D, optimize story board further based on Video Stabilization algorithm；
E, based on video frequency searching engine, story board and natural semanteme are contacted.
F, inference machine story board based on some natural semantizations, calculates in conjunction with knowledge base rule, and calls knowledge
The materials such as the video display that comprise in storehouse, sound, picture, word, 3D model by the logical AND story board assemble editing calculated, thus by
Computer automatically generates the films and television programs of acceptable solution.
G, according to human-computer interaction interface set, the films and television programs automatically generated by computer are stored in working storage, hands
Machine, Dropbox, or it is sent to video website, social media, mailbox, or as Streaming Media real-time play.
4, for comprise more information in short-sighted frequency, the thirst for knowledge of people is met.Video display artificial intelligence based on SLAM sets
Being equipped with video hyperlink function, its method is:
4.1, based on SLAM at a hyperlink label defined in video source encoding and decoding rule.
4.2, the encoding and decoding rule of video display pattern, picture, word and the 3D model material comprised for knowledge base defines one
Hyperlink label；
4.3, described hyperlink label is the connection pass that the certain content from a short-sighted frequency points to the short-sighted frequency of another target
System, it is shown as a recognizable hot zone that can trigger when video source is play, and described hot zone runs through this component camera lens
Or the broadcasting of material is all the time.A kind of hot zone is to realize at a single layer defined in the encoding and decoding rule of video source；
4.4, when controlling with mouse, touch, gesture or eye is dynamic controls to trigger hot zone, then player redirects and presents this hot zone and surpass
Short-sighted frequency, captions, sound or the 3D material of link label definition.
4.5, when video playback apparatus is screen, the information that the hyperlink label in video calls be same picture in
Show the internal links of picture-in-picture or redirect broadcasting external linkage at same picture；When video playback apparatus is VR playback equipment,
The information that hyperlink label in video calls be the picture-in-picture internal links presented at present viewing field or switch another visual angle in
Existing visual angle link.
5, current panorama system uses the video source of single point of observation.When same place comprises multiple panorama system video source
Time, a kind of artificial intelligent set of video display based on SLAM has the scene walkthrough function that other people visual angle of switching browses in real time, its method
It is:
5.1, when some video source dynamic group nets, based on SLAM be at that time each video source in network distribute one unique
Bearing mark code.
5.2, be shown as on described bearing mark code VR browser in a network or video-frequency monitor one recognizable can
The hot zone that triggers or be shown as a recognizable focus that can trigger on Internet map.Described Internet map is wireless
The Real-time and Dynamic state diagram of all members distribution in MANET；
5.3, when controlling with mouse, touch, gesture or eye is dynamic controls to trigger hot zone or focus, then local node is to being triggered
Third party's video source node of hot zone or hotspot's definition initiates video data call request, allows through third party's video source node
Or after obtaining permission according to procotol, switch broadcasting third party's video source node at VR browser or video-frequency monitor and clap in real time
The video taken the photograph or the video playing third party's video source node definition, it is achieved the real-time scene roaming merit browsed with other people visual angle
Energy.
6, video display artificial intelligence based on SLAM can realize basic function by Mobile Shape ' with single camera vision system.So
And, overall view visual system can bring preferably shares experience.For adaptive overall view visual system working method, by the attention of people
Free from shooting work.The invention discloses the vehicle-mounted pattern of a kind of support, wearing pattern and hand-held mode, foolproof bat
Take the photograph, panoramic camera based on SLAM, it technology is characterized in that
Described panoramic camera based on SLAM is a kind of modular SLAM equipment, it by the data-interface of more than a group and
The interface module of more than one group is connected with smart mobile phone.Described interface module is Quick demounting buckle, in order to quick and smart mobile phone
Destructing, and it is connected with the foot rest of interface module of adaptation, unmanned plane, vehicle head, folding handle, the helmet, medicated cap, head
Decorations, braces, belt or bracelet.
Panoramic camera based on SLAM include shell, more than 2 groups pick-up lenss, vision coprocessor, infrared transmitter,
Depth of field induction apparatus, thermal camera, gyroscope/acceleration sensor, working storage, wireless self-networking module, data-interface, connect
Mouth die block and battery.When pick-up lens is 2 groups, arranging pick-up lens is fish eye lens.When pick-up lens is 6 groups, arrange
Pick-up lens is towards before and after up and down.
Preferably, the panoramic camera based on SLAM of a kind of wearable pattern, it is connected to medicated cap by interface module
Top, medicated cap is with flexible battery manufacture.A kind of flexible battery is thin-film solar cells.
The described artificial structure of intelligence of video display based on SLAM at least sets one or more.
The invention has the beneficial effects as follows:
The invention discloses a kind of video display artificial intelligence based on SLAM.Take the photograph including video display specialist system and panorama based on SLAM
Camera.
Video display artificial intelligence based on SLAM can capture relevant to self from the big data video information of socialization alternately
Video information, and generated the movie and video programs with user as leading role by inference machine and knowledge base by computer automation.
Video display artificial intelligence based on SLAM makes us need not divert one's attention to shoot, and can obtain more multi-faceted, the essence of multi-angle
Color frequency, and realizes scene walkthrough, CAL, recall, conduct a sightseeing tour, play, scene walkthrough, competing in film, concert, physical culture
Match, educate, travel, extreme sport, the news record, game, multiple content zone such as on-the-spot collaborative work realize augmented reality, mixed
Close the application such as reality.
Panoramic camera based on SLAM is based on instant location and the panoramic video monitor of map structuring (SLAM), can pass through
Interface module quickly connects mobile phone, automobile, unmanned plane, folding handle, support, the helmet, medicated cap, headwear, braces, belt or hands
Ring, records your life comprehensively.
Accompanying drawing explanation；
The present invention is further described with embodiment below in conjunction with the accompanying drawings.
Fig. 1 is workflow schematic diagram of the present invention,
Fig. 2 is present invention video interactive based on wireless self-networking schematic diagram,
Detailed description of the invention:
As shown in Figure 1 and 2: in an embodiment, panoramic camera based on SLAM is based on instant location and map structuring
(SLAM) panoramic video monitor, can by interface module quickly connect mobile phone, automobile, unmanned plane, folding handle, support,
The helmet, medicated cap, headwear, braces, belt or bracelet, record your life comprehensively.Between some panoramic cameras based on SLAM
Can automatically, quickly, dynamic group net, and according in the bearing mark code interactive video information defined in video source encoding and decoding rule.
In an embodiment, video display artificial intelligence based on SLAM by intelligent video retrieval technique to from this locality based on
The panoramic camera of SLAM and the big data video real time filtering of Internet panoramic camera based on SLAM, detect, identify, point
Class and multiple target tracking, according to time, scape not, image, intonation, emotion, emotional state and the judgement to inter personal contact, from
Dynamic video source being cut into indexes the story board identifying label a series of comprising.
Story board is transferred video display artificial taste intelligent system based on SLAM.Special by video display artificial intelligence based on SLAM
Family system inference machine combine the story of a play or opera, director and editing knowledge base rule, select, call knowledge base comprises plot, video display,
The materials such as scene, sound, picture, word, 3D model, connect with group story board choice, decomposition, thus are automatically generated by computer
The acceptable user's original video works solved.
In an embodiment, video display artificial intelligence application scene based on SLAM includes:
Mixed reality travel notes:
Neuroscience finds, it is similar that the imagination of human brain emotion is experienced with actual experience.In tourism, we simply see moment
One jiao.Go on a tour circuit and the sight spot that lives through of the artificial Intelligent Recognition user of video display based on SLAM, user based on
In the panoramic camera source video of SLAM the relevant sight spot of mixing more comprehensively, more polynary, the camera lens of more high-quality or material, being trimmed into can
With the small video shared in social media.Experience by the imagination and psychology substitutes the width expanding Tourist Experience.
Accepting study:
Research to Learning and Memory finds, is not easy to forget with the information of our self substantial connection.Video display based on SLAM
Artificial intelligence passes through target detection, target following, target recognition, behavior analysis or based on content in the video that you are leading role
Video frequency searching sets image, and one hyperlink label layer of definition for it.When controlling or the dynamic control of eye with mouse, touch, gesture
Triggering hyperlink label then redirects and presents background context knowledge, and linear video playback is become netted Accepting study.
Panoramic video is mutual and plot is implanted:
From taking a picture easily, the difficulty that certainly shoots the video, the high threshold of video later stage flim editing and making Ye Shi domestic consumer.Shadow based on SLAM
Companion is allowed to pass through the video at the mutual to one's name visual angle of wireless self-networking depending on artificial intelligence.And by video display artificial intelligence from
Multichannel, the video clipping of various visual angles become mixed reality short-movie.Tradition films and television programs are from drama to story board, to being clipped to work
Product, and video display artificial intelligence based on SLAM is from big data story board, inference machine combine video display knowledge base, by non-prison
Educational inspector practises implantation plot, conflict and drama, automatically generates the interesting works of acceptable solution.
Displaying marketing and LBS play:
When monitoring system and the artificial intelligent subscriber networking of video display based on SLAM of enterprise, complete appointed task, give to set prize
Encourage, so that it may allow the monitoring data being sunk into sleep with the video display artificial intelligence based on SLAM of client from broadcasting media.Put into
Fixed assets are vitalized as marketing tool and LBS game item.
Mobile monitor:
The conversion of this security protection instrument and game item is reversible.Panoramic camera based on SLAM is also a kind of random mobile
Watch-dog.
Scene walkthrough:
Panoramic camera based on SLAM in wireless self-networking can call other panoramas based on SLAM according to procotol and take the photograph
The visual field of camera, switches other people visual angle in real time and browses, it is achieved scene walkthrough, see my finding.Thus performance in terms of the visual angle of singer
Meeting, from judge visual angle watch a ball game, see working site from multiple visual angles ... virtual experience others' experience thing.
Above example is only in order to illustrate the present invention without limiting the present invention described technical scheme；Therefore, although this
The present invention has been elaborated by description with reference to above-described embodiment, but one of ordinary skill in the art is appreciated that
Still the present invention can be modified, equivalent or permutation and combination；And all are without departing from the skill of spirit and scope of the invention
Art scheme and improvement thereof, it all should be contained among scope of the presently claimed invention.
Claims (6)
1. follow the tracks of a registration technique based on without marker, be based especially on the video display artificial intelligence of SLAM, including video source, net
Network layers, server and movie editing specialist system；It is characterized in that:
1.1, arranging video source is one or more；
When video source is more than one, based on SLAM at a bearing mark code defined in video source encoding and decoding rule for i.e.
Shi Dingwei, Video stream information be mutual and editing；
1.2, described Internet is a protocol layer, its foundation being responsible for wireless self-networking and maintenance, and Internet by interface is
Movie editing specialist system provides management service and data, services, and movie editing specialist system is positioned at wireless self-networking protocol stack frame
The top of frame；Network layer data Connection Service device data base also undertakes management and the maintenance work of network information database；
1.3, movie editing specialist system is set and includes human-computer interaction interface, video frequency searching engine, inference machine, knowledge base, work
Memorizer and interpreter；
Automatic, quick, dynamic group net between some video source, and according at the bearing mark defined in video source encoding and decoding rule
Code interactive video information；Described video frequency searching engine passes through intelligent video retrieval technique to from local and the big data of Internet
Video real time filtering, detect, identify, classify and multiple target tracking, according to time, scape not, image, intonation, emotion, emotion shape
State and the judgement to inter personal contact, automatically video source is cut into a series of comprise index identify label, semantics identity label,
Scape does not identify label or the story board of editing identification label；Movie editing specialist system is combined knowledge base to through video by inference machine
Search engine filters the story board of index and creates, and generates movie and video programs by server cognition calculation automation.
Video display artificial intelligence based on SLAM the most according to claim 1, is characterized in that:
2.1, described bearing mark code based on SLAM carry out towards and Attitude Calculation, definition shooting video source camera and position and
Direction, mark world coordinates is tied to the conversion of camera coordinate system, camera coordinates be tied to the conversion of imaging plane coordinate system with
And imaging plane coordinate is tied to the conversion of image coordinate system；When shooting video source camera and being static, bearing mark code includes: camera
Identification code, camera coordinates, camera orientation angle, inclination angle, left and right, pitch angles and technique for taking parameter；When shooting video source camera
During motion, bearing mark code includes: camera identification code and the camera based on timestamp produced with camera displacement run road
Line, camera orientation angle, inclination angle, left and right, pitch angles and the delta data of technique for taking parameter；
2.2, arranging vision sensor based on SLAM definition bearing mark code is single camera vision system, binocular vision system, many
Visually vision system or overall view visual system；
2.3, when vision sensor based on SLAM definition bearing mark code is overall view visual system, phase in bearing mark code
Machine coordinate identifies with spherical coordinate system；
2.4, when video source is more than one, described wireless self-networking based on SLAM defined in video source encoding and decoding rule
Bearing mark code, is made between the big data video of the multichannel from multiple video source nodes, various visual angles direct by procotol
Or multi-hop communication, make the special short distance mobile radio network set up automatically, quickly, dynamically between node, at this net
In network, each node can arrange it and have terminal system and transistroute function simultaneously concurrently, both can be with data transmit-receive, it is also possible to many
Redirect and send out；
2.5, the plurality of video source node dynamic group net active swap bearing mark code information, and according to bearing mark code information
Judge to be suitable for this node orientation, angle and third party's video source node of distance, regard to its initiation according to the interaction protocol of setting
Frequency is according to call request；Third party's video source node is according to the bearing mark code information of request initiator, and from this locality, big data regard
In Pin, real-time editing is gone out relative video data and is sent by wireless self-networking；By that analogy, multiple video source nodes are certainly
Dynamic, quickly, interim, dynamic group net, and based on the Internet alternating transmission video data relevant to this node；
2.6, a kind of based on SLAM, judge this node and the orientation of third party's video source node, angle according to bearing mark code information
Degree with the method for distance is: by the bearing mark code of known each node, calculate the three dimensions of third party's video source node
Relation between coordinate and this node coordinate, draws acquisition third party's video source nodal coordinate system and the translation rotation of this nodal coordinate system
Turn transformation matrix, thus obtain space coordinate transformation matrix；
2.7, a kind of wireless self-networking is point-to-point Ad Hoc wireless self-networking, and a kind of wireless self-networking is wireless mesh
Network；A kind of wireless self-networking is wireless self-networking based on Zigbee protocol；A kind of wireless self-networking is nothing based on WiFi
Line MANET, a kind of wireless self-networking based on WiFi is direct connection networking based on Wi-Fi hotspot, a kind of based on WiFi wireless
MANET is HaLow wireless self-networking；A kind of wireless self-networking is wireless self-networking based on bluetooth, a kind of nothing based on bluetooth
Line MANET is wireless self-networking based on low-power consumption bluetooth BLE, a kind of wireless self-networking based on bluetooth be based on
The point-to-point wireless self-networking of bluetooth of Multipeer Connectivity framework, a kind of wireless self-networking based on bluetooth is base
Wireless self-networking in iBeacon；A kind of wireless self-networking is Ad Hoc wireless self-networking based on ultra broadband UWB；A kind of nothing
Line MANET is based on ultra broadband UWB and the wireless self-networking of bluetooth mixed communication；A kind of wireless self-networking be based on WIFI and
The wireless self-networking of bluetooth mixed communication；A kind of wireless self-networking is based on WIFI and ZigBee mixed communication wireless from group
Net；
When wireless self-networking be based on or during the wireless self-networking of mixing WiFi technology, a kind of global function node still couples wireless
MANET and the across a network node of the Internet.
Video display artificial intelligence based on SLAM the most according to claim 1, is characterized in that:
3.1, described movie editing specialist system is the Computing Intelligence energy range with drama, director and editing expertise and experience
Sequence system, by the modeling of the problem solving ability to human expert, uses the representation of knowledge in artificial intelligence and knowledge reasoning
Technology simulates the challenge generally solved by expert；Described movie editing specialist system accords with heuristic interaction process video
Number, knowledge and control are separated, to process uncertain problem, reaches acceptable solution；
3.2, the algorithm that described story board processes is target detection, target following, target recognition, behavior analysis or based on content
Video frequency searching and data fusion；
Based on intelligent video retrieval technique, video frequency searching includes characteristic extracting module, Video segmentation module, filtration and Video Stabilization
Module, intelligent retrieval matching module；
3.3, described inference machine be realize based on drama plot, director and the parts of editing knowledge reasoning, mainly include reasoning and
Controlling two parts, it is the program explaining knowledge, according to the semanteme of knowledge, enters the knowledge strategically found
Row is explained and is performed, and result be recorded in the suitable space of working storage；
The inference logic of a kind of inference machine is classical logic；A kind of classical logic is deductive logic, and a kind of classical logic is to conclude
Logic；The inference logic of a kind of inference machine is non-classicol logic, and a kind of non-classicol logic is dialectical logic；
The working method of a kind of inference machine is to deduct, and arranges and some is comprised editing identification mark by what video frequency searching engine provided
The camera lens signed, as the known fact, derives video display structure, plot understanding or scene planning according to axiomatics；
Or, the working method of a kind of inference machine is non-monotonic reasoning, and described non-monotonic reasoning includes based on default information silent
Recognize reasoning and constraint reasoning；Described default reasoning logic is: and if only if not fact proved that camera lens S editing identification label does not becomes
Immediately, S always sets up；The logic of described constraint reasoning is: and if only if not fact proved that camera lens S editing identification label exists
When setting up in larger scope, S only sets up in the range of specifying；
Or, the working method of a kind of inference machine is qualitative reasoning, and described qualitative reasoning is from physical system, the intuitive thinking of the mankind
Set out, derive behavior description, in order to the behavior of prognoses system；In movie editing specialist system, qualitative reasoning uses story board
Partial structurtes rule predicts that the plot of film understands or scene planning；
3.4, described knowledge base is play writing, director and the set of editing domain knowledge, including basic fact, rule and other
For information about；Knowledge base and System program are separate, and user can be by change, the knowledge improved in knowledge base
Content improves the performance of specialist system；A kind of knowledge base is by scenarist, director and editing expert, and to existing
Films and television programs, musical works, literary works, 3D model, the degree of depth study of picture works, unsupervised learning, transfer learning or many
Tasking learning builds；
3.5, described working storage is the set of reflection current problem solving state, is produced in storage system running
Raw all information, and required initial data, the information inputted including user, the intermediate object program of reasoning, reasoning process
Record；The state being made up of basic fact, proposition and relation in working storage, is the foundation of inference machine selection knowledge,
Also it is the source of explanation facility acquisition Induction matrix；
3.6, described interpreter is for explaining to solution procedure, and answers the enquirement of user；Allow user's prehension program
Do what and why do so；
3.7, movie editing specialist system generates movie and video programs by server cognition calculation automation, and its method of work is:
A, Internet call all local video sources relevant to this node and third party regards based on timestamp by setting the time period
Frequently source；
B, based on the best video source of image recognition technology filter quality；
Bearing mark code in c, comprehensive video search engine and video source and coordinates matrix identification code, for video source story board and
Index, the scape of definition story board is other；
D, optimize story board further based on Video Stabilization algorithm；
E, based on video frequency searching engine, story board and natural semanteme are contacted；
F, inference machine story board based on some natural semantizations, calculates in conjunction with knowledge base rule, and calls in knowledge base
The materials such as the video display that comprise, sound, picture, word, 3D model are by the logical AND story board assemble editing calculated, thus by calculating
Machine automatically generates the films and television programs of acceptable solution；
G, according to human-computer interaction interface set, the films and television programs automatically generated by computer are stored in working storage, mobile phone, net
Dish, or it is sent to video website, social media, mailbox, or as Streaming Media real-time play.
Video display artificial intelligence based on SLAM the most according to claim 1, is characterized in that:
A kind of artificial intelligent set of video display based on SLAM has video hyperlink function, and its method is:
4.1, based on SLAM at a hyperlink label defined in video source encoding and decoding rule；
4.2, encoding and decoding rule one hyperlink of definition of video display pattern, picture, word and the 3D model material comprised for knowledge base
Connect label；
4.3, described hyperlink label is the connection pass that the certain content from a short-sighted frequency points to the short-sighted frequency of another target
System, it is shown as a recognizable hot zone that can trigger when video source is play, and described hot zone runs through this component camera lens
Or the broadcasting of material is all the time；A kind of hot zone is to realize at a single layer defined in the encoding and decoding rule of video source；
4.4, when controlling with mouse, touch, gesture or eye is dynamic controls to trigger hot zone, then player redirects and presents this hot zone and surpass
Short-sighted frequency, captions, sound or the 3D material of link label definition；
4.5, when video playback apparatus is screen, the information that the hyperlink label in video calls is to present picture at same picture
The internal links of middle picture or redirect broadcasting external linkage at same picture；When video playback apparatus is VR playback equipment, video
In the information called of hyperlink label be the picture-in-picture internal links presented at present viewing field or switch another visual angle and present
Visual angle links.
Video display artificial intelligence based on SLAM the most according to claim 1, is characterized in that:
When same place comprises multiple panorama system video source, a kind of artificial intelligent set of video display based on SLAM has cuts in real time
Changing the scene walkthrough function that other people visual angle browses, its method is:
5.1, when some video source dynamic group nets, based on SLAM be at that time each video source in network distribute one unique
Bearing mark code；
5.2, it is shown as one on described bearing mark code VR browser in a network or video-frequency monitor recognizable can trigger
Hot zone or on Internet map, be shown as a recognizable focus that can trigger；Described Internet map is wireless from group
The Real-time and Dynamic state diagram of all members distribution in net；
5.3, when controlling with mouse, touch, gesture or eye is dynamic controls to trigger hot zone or focus, then local node is to being triggered
Third party's video source node of hot zone or hotspot's definition initiates video data call request, allows through third party's video source node
Or after obtaining permission according to procotol, switch broadcasting third party's video source node at VR browser or video-frequency monitor and clap in real time
The video taken the photograph or the video playing third party's video source node definition, it is achieved the real-time scene roaming merit browsed with other people visual angle
Energy.
Video display artificial intelligence based on SLAM the most according to claim 1, is characterized in that:
The invention discloses and a kind of support vehicle-mounted pattern, wearing pattern and hand-held mode, panoramic camera based on SLAM, its skill
Art feature is:
Described panoramic camera based on SLAM is a kind of modular SLAM equipment, it by the data-interface of more than a group and
The interface module of more than one group is connected with smart mobile phone；Described interface module is Quick demounting buckle, in order to quick and smart mobile phone
Destructing, and it is connected with the foot rest of interface module of adaptation, unmanned plane, vehicle head, folding handle, the helmet, medicated cap, head
Decorations, braces, belt or bracelet；
Panoramic camera based on SLAM includes shell, more than 2 groups pick-up lenss, vision coprocessor, infrared transmitter, the depth of field
Induction apparatus, thermal camera, gyroscope/acceleration sensor, working storage, wireless self-networking module, data-interface, interface mould
Block and battery；When pick-up lens is 2 groups, arranging pick-up lens is fish eye lens；When pick-up lens is 6 groups, shooting is set
Camera lens is towards before and after up and down；
The panoramic camera based on SLAM of a kind of wearable pattern, it is connected to the top of medicated cap, medicated cap by interface module
With flexible battery manufacture；A kind of flexible battery is thin-film solar cells；
The described artificial structure of intelligence of video display based on SLAM at least sets one or more.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610571146.0A CN106210450B (en) | 2016-07-20 | 2016-07-20 | A kind of multichannel multi-angle of view big data video clipping method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610571146.0A CN106210450B (en) | 2016-07-20 | 2016-07-20 | A kind of multichannel multi-angle of view big data video clipping method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106210450A true CN106210450A (en) | 2016-12-07 |
| CN106210450B CN106210450B (en) | 2019-01-11 |
Family
ID=57494611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610571146.0A Active CN106210450B (en) | 2016-07-20 | 2016-07-20 | A kind of multichannel multi-angle of view big data video clipping method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106210450B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392883A (en) * | 2017-08-11 | 2017-11-24 | 陈雷 | The method and system that video display dramatic conflicts degree calculates |
| CN107600067A (en) * | 2017-09-08 | 2018-01-19 | 中山大学 | A kind of autonomous parking system and method based on more vision inertial navigation fusions |
| CN107833236A (en) * | 2017-10-31 | 2018-03-23 | 中国科学院电子学研究所 | Semantic vision positioning system and method are combined under a kind of dynamic environment |
| CN108230337A (en) * | 2017-12-31 | 2018-06-29 | 厦门大学 | A kind of method that semantic SLAM systems based on mobile terminal are realized |
| CN108257216A (en) * | 2017-12-12 | 2018-07-06 | 北京克科技有限公司 | A kind of method, apparatus and equipment in reality environment structure physical model |
| CN108322771A (en) * | 2017-12-22 | 2018-07-24 | 新华网股份有限公司 | A kind of multimedia clips method and device based on SCR signals |
| CN108537157A (en) * | 2018-03-30 | 2018-09-14 | 特斯联（北京）科技有限公司 | A kind of video scene judgment method and device based on artificial intelligence classification realization |
| CN108702464A (en) * | 2017-10-16 | 2018-10-23 | 深圳市大疆创新科技有限公司 | A kind of method for processing video frequency, control terminal and movable equipment |
| CN108933970A (en) * | 2017-05-27 | 2018-12-04 | 北京搜狗科技发展有限公司 | The generation method and device of video |
| CN109117850A (en) * | 2018-06-28 | 2019-01-01 | 上海交通大学 | The recognition methods of corresponding infrared target image is carried out using visible light target image |
| CN109996010A (en) * | 2017-12-29 | 2019-07-09 | 深圳市优必选科技有限公司 | A kind of method for processing video frequency, device, smart machine and storage medium |
| CN110009674A (en) * | 2019-04-01 | 2019-07-12 | 厦门大学 | Monocular image depth of field real-time computing technique based on unsupervised deep learning |
| CN111480348A (en) * | 2017-12-21 | 2020-07-31 | 脸谱公司 | System and method for audio-based augmented reality |
| CN112306672A (en) * | 2019-08-02 | 2021-02-02 | 通用汽车环球科技运作有限责任公司 | Architecture and method for supporting multi-vision streaming using a shared server on an embedded platform |
| CN113380088A (en) * | 2021-04-07 | 2021-09-10 | 上海中船船舶设计技术国家工程研究中心有限公司 | Interactive simulation training support system |
| WO2021242363A1 (en) * | 2020-05-27 | 2021-12-02 | Sri International | Neural network explanation using logic |
| WO2021244457A1 (en) * | 2020-05-30 | 2021-12-09 | 华为技术有限公司 | Video generation method and related apparatus |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070089151A1 (en) * | 2001-06-27 | 2007-04-19 | Mci, Llc. | Method and system for delivery of digital media experience via common instant communication clients |
| CN101093559A (en) * | 2007-06-12 | 2007-12-26 | 北京科技大学 | Method for constructing expert system based on knowledge discovery |
| US20090154791A1 (en) * | 2007-12-17 | 2009-06-18 | Samsung Electronics Co., Ltd. | Simultaneous localization and map building method and medium for moving robot |
| US20100094460A1 (en) * | 2008-10-09 | 2010-04-15 | Samsung Electronics Co., Ltd. | Method and apparatus for simultaneous localization and mapping of robot |
| KR20100070952A (en) * | 2008-12-18 | 2010-06-28 | 조선대학교산학협력단 | Multimedia content management system |
| CN101917061A (en) * | 2010-07-14 | 2010-12-15 | 山东电力集团公司泰安供电公司 | Automatic inspection method and device for substation |
| US20110165893A1 (en) * | 2010-01-04 | 2011-07-07 | Samsung Electronics Co., Ltd. | Apparatus to provide augmented reality service using location-based information and computer-readable medium and method of the same |
| CN102184200A (en) * | 2010-12-13 | 2011-09-14 | 中国人民解放军国防科学技术大学 | Computer-assisted animation image-text continuity semi-automatic generating method |
| CN102667855A (en) * | 2009-10-19 | 2012-09-12 | Metaio有限公司 | Method for determining the pose of a camera and for recognizing an object of a real environment |
| US20140118392A1 (en) * | 2009-04-22 | 2014-05-01 | Samsung Electronics Company, Ltd. | Video entertainment picture quality adjustment |
| CN104200422A (en) * | 2014-08-28 | 2014-12-10 | 邓鑫 | Expert system for remote sensing image processing |
| CN104246656A (en) * | 2012-02-23 | 2014-12-24 | 谷歌公司 | Automatic detection of suggested video edits |
| CN105224535A (en) * | 2014-05-29 | 2016-01-06 | 浙江航天长峰科技发展有限公司 | Based on the concern target quick reference system of massive video |
-
2016
- 2016-07-20 CN CN201610571146.0A patent/CN106210450B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070089151A1 (en) * | 2001-06-27 | 2007-04-19 | Mci, Llc. | Method and system for delivery of digital media experience via common instant communication clients |
| CN101093559A (en) * | 2007-06-12 | 2007-12-26 | 北京科技大学 | Method for constructing expert system based on knowledge discovery |
| US20090154791A1 (en) * | 2007-12-17 | 2009-06-18 | Samsung Electronics Co., Ltd. | Simultaneous localization and map building method and medium for moving robot |
| US20100094460A1 (en) * | 2008-10-09 | 2010-04-15 | Samsung Electronics Co., Ltd. | Method and apparatus for simultaneous localization and mapping of robot |
| KR20100070952A (en) * | 2008-12-18 | 2010-06-28 | 조선대학교산학협력단 | Multimedia content management system |
| US20140118392A1 (en) * | 2009-04-22 | 2014-05-01 | Samsung Electronics Company, Ltd. | Video entertainment picture quality adjustment |
| CN102667855A (en) * | 2009-10-19 | 2012-09-12 | Metaio有限公司 | Method for determining the pose of a camera and for recognizing an object of a real environment |
| US20110165893A1 (en) * | 2010-01-04 | 2011-07-07 | Samsung Electronics Co., Ltd. | Apparatus to provide augmented reality service using location-based information and computer-readable medium and method of the same |
| CN101917061A (en) * | 2010-07-14 | 2010-12-15 | 山东电力集团公司泰安供电公司 | Automatic inspection method and device for substation |
| CN102184200A (en) * | 2010-12-13 | 2011-09-14 | 中国人民解放军国防科学技术大学 | Computer-assisted animation image-text continuity semi-automatic generating method |
| CN104246656A (en) * | 2012-02-23 | 2014-12-24 | 谷歌公司 | Automatic detection of suggested video edits |
| CN105224535A (en) * | 2014-05-29 | 2016-01-06 | 浙江航天长峰科技发展有限公司 | Based on the concern target quick reference system of massive video |
| CN104200422A (en) * | 2014-08-28 | 2014-12-10 | 邓鑫 | Expert system for remote sensing image processing |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108933970B (en) * | 2017-05-27 | 2022-02-25 | 北京搜狗科技发展有限公司 | Video generation method and device |
| CN108933970A (en) * | 2017-05-27 | 2018-12-04 | 北京搜狗科技发展有限公司 | The generation method and device of video |
| CN107392883A (en) * | 2017-08-11 | 2017-11-24 | 陈雷 | The method and system that video display dramatic conflicts degree calculates |
| CN107392883B (en) * | 2017-08-11 | 2019-11-08 | 逄泽沐风 | The method and system that video display dramatic conflicts degree calculates |
| CN107600067B (en) * | 2017-09-08 | 2019-09-20 | 中山大学 | A kind of autonomous parking system and method based on more vision inertial navigation fusions |
| CN107600067A (en) * | 2017-09-08 | 2018-01-19 | 中山大学 | A kind of autonomous parking system and method based on more vision inertial navigation fusions |
| CN108702464A (en) * | 2017-10-16 | 2018-10-23 | 深圳市大疆创新科技有限公司 | A kind of method for processing video frequency, control terminal and movable equipment |
| CN107833236A (en) * | 2017-10-31 | 2018-03-23 | 中国科学院电子学研究所 | Semantic vision positioning system and method are combined under a kind of dynamic environment |
| CN107833236B (en) * | 2017-10-31 | 2020-06-26 | 中国科学院电子学研究所 | Visual positioning system and method combining semantics under dynamic environment |
| CN108257216A (en) * | 2017-12-12 | 2018-07-06 | 北京克科技有限公司 | A kind of method, apparatus and equipment in reality environment structure physical model |
| CN111480348B (en) * | 2017-12-21 | 2022-01-07 | 脸谱公司 | System and method for audio-based augmented reality |
| CN111480348A (en) * | 2017-12-21 | 2020-07-31 | 脸谱公司 | System and method for audio-based augmented reality |
| CN108322771A (en) * | 2017-12-22 | 2018-07-24 | 新华网股份有限公司 | A kind of multimedia clips method and device based on SCR signals |
| CN109996010A (en) * | 2017-12-29 | 2019-07-09 | 深圳市优必选科技有限公司 | A kind of method for processing video frequency, device, smart machine and storage medium |
| CN109996010B (en) * | 2017-12-29 | 2021-07-27 | 深圳市优必选科技有限公司 | Video processing method and device, intelligent device and storage medium |
| CN108230337A (en) * | 2017-12-31 | 2018-06-29 | 厦门大学 | A kind of method that semantic SLAM systems based on mobile terminal are realized |
| CN108230337B (en) * | 2017-12-31 | 2020-07-03 | 厦门大学 | Semantic SLAM system implementation method based on mobile terminal |
| CN108537157A (en) * | 2018-03-30 | 2018-09-14 | 特斯联（北京）科技有限公司 | A kind of video scene judgment method and device based on artificial intelligence classification realization |
| CN109117850A (en) * | 2018-06-28 | 2019-01-01 | 上海交通大学 | The recognition methods of corresponding infrared target image is carried out using visible light target image |
| CN110009674B (en) * | 2019-04-01 | 2021-04-13 | 厦门大学 | Monocular image depth of field real-time calculation method based on unsupervised depth learning |
| CN110009674A (en) * | 2019-04-01 | 2019-07-12 | 厦门大学 | Monocular image depth of field real-time computing technique based on unsupervised deep learning |
| CN112306672A (en) * | 2019-08-02 | 2021-02-02 | 通用汽车环球科技运作有限责任公司 | Architecture and method for supporting multi-vision streaming using a shared server on an embedded platform |
| WO2021242363A1 (en) * | 2020-05-27 | 2021-12-02 | Sri International | Neural network explanation using logic |
| WO2021244457A1 (en) * | 2020-05-30 | 2021-12-09 | 华为技术有限公司 | Video generation method and related apparatus |
| CN113380088A (en) * | 2021-04-07 | 2021-09-10 | 上海中船船舶设计技术国家工程研究中心有限公司 | Interactive simulation training support system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106210450B (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106210450A (en) | Video display artificial intelligence based on SLAM | |
| US11509817B2 (en) | Autonomous media capturing | |
| JP6792039B2 (en) | Systems and methods for augmented reality and virtual reality | |
| JP5866728B2 (en) | Knowledge information processing server system with image recognition system | |
| JP5898378B2 (en) | Information processing apparatus and application execution method | |
| JP2021082310A (en) | Systems and methods for augmented reality and virtual reality | |
| CN109844854A (en) | Word flow comment | |
| US20150318020A1 (en) | Interactive real-time video editor and recorder | |
| US20190156558A1 (en) | Virtual reality system | |
| Cucchiara et al. | Visions for augmented cultural heritage experience | |
| CN109176535A (en) | Exchange method and system based on intelligent robot | |
| CN108984618A (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
| Nack | AUTEUR: The application of video semantics and theme representation for automated film editing | |
| JP6910629B2 (en) | How to combine historical images and current images and express audio guides. | |
| Kimura et al. | Collectively sharing people’s visual and auditory capabilities: exploring opportunities and pitfalls | |
| WO2014179749A1 (en) | Interactive real-time video editor and recorder | |
| Plizzari et al. | An outlook into the future of egocentric vision | |
| Benjamin et al. | The entoptic field camera as metaphor-driven research-through-design with AI technologies | |
| Kimura et al. | CollectiveEars: sharing collective people’s hearing capability | |
| Gershon et al. | Actor-network theory and documentary studies | |
| Abdari et al. | Metaverse Retrieval: Finding the Best Metaverse Environment via Language | |
| Kimura et al. | Collectively sharing human eyes and ears as smart city digital platforms | |
| US20230156314A1 (en) | Gaze-based camera auto-capture | |
| Zhu | Finding the In-between Space | |
| Dahlström et al. | Battling misinformation with a graphic interface: exploring navigation through video to support digital vigilantists |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |