CN109462730A - Method and apparatus based on video acquisition panorama sketch - Google Patents
Method and apparatus based on video acquisition panorama sketch Download PDFInfo
- Publication number
- CN109462730A CN109462730A CN201811249707.0A CN201811249707A CN109462730A CN 109462730 A CN109462730 A CN 109462730A CN 201811249707 A CN201811249707 A CN 201811249707A CN 109462730 A CN109462730 A CN 109462730A
- Authority
- CN
- China
- Prior art keywords
- mark
- panorama
- video
- text
- server
- 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.)
- Pending
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
- 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
- H04N5/265—Mixing
Abstract
The embodiment of the present application provides a kind of method and apparatus based on video acquisition panorama sketch, this method comprises: obtaining text relevant to the video when playing video；Obtain the mark in the text；Multiple images for the object that the mark is identified are obtained, which is the image of the object different direction；Splice multiple images, obtain the panorama sketch of the object, and shows the panorama sketch of the object.The application is realized when user watches video, and the purpose of the panorama sketch of the object in video is shown to user.
Description
Technical field
The invention relates to field of computer technology more particularly to a kind of method based on video acquisition panorama sketch and
Device.
Background technique
First learn about that tourist famous-city is very important before tourism, for example user can be by watching related tourism mesh
The video on ground tourist famous-city is understood.
But the video of tourist famous-city can only generally meet the effect at photographer visual angle, when user is using browser
When watching the video of tourist famous-city, it may be unable to satisfy the demand of user, for example user wants in viewing tourism purpose
The panorama sketch of tourist famous-city is obtained when the video on ground.So, when user watches video, how to be shown in video to user
The panorama sketch of object is a problem to be solved.
Summary of the invention
The embodiment of the present application provides a kind of method and apparatus based on video acquisition panorama sketch, realizes and watches view in user
When frequency, the purpose of the panorama sketch of the object in video is shown to user.
In a first aspect, the embodiment of the present application provides a kind of method based on video acquisition panorama sketch, it is applied to terminal, packet
It includes:
When playing video, text relevant to the video is obtained；
Obtain the mark in the text；
Multiple images of the identified object of the mark are obtained, multiple described images are the figure of the object different direction
Picture；
Splice multiple described images, obtains the panorama sketch of the object, and show the panorama sketch of the object.
In a kind of possible design, text relevant to video is obtained, comprising:
The first text relevant to video and/or the second text are obtained, first text is can be with the video point
The text cut, second text is can not be with the text of the Video segmentation.
In a kind of possible design, described multiple images for obtaining the identified object of the mark, comprising:
The mark is sent to server；
Multiple images of the identified object of the mark are obtained from server.
In a kind of possible design, described multiple images that the identified object of the mark is obtained from server, packet
It includes:
Entry data is received from server, the entry data includes the mark of multiple images；
According to the entry data, panorama entrance icon is drawn；
It receives user and instruction is checked by the panorama that the panorama entrance icon inputs；
It checks that instruction generates panorama and checks request according to the panorama, and the panorama is checked that request is sent to server,
The panorama checks that request includes the mark of multiple images；
Multiple described images are obtained from the server.
In a kind of possible design, the vocabulary of the video is cached in the terminal, it is described to send the mark
To server, comprising:
If in presently described vocabulary not including the mark, the mark is sent to server.
In a kind of possible design, further includes:
If in presently described vocabulary not including the mark, the mark is added to the vocabulary.
In a kind of possible design, the second text of the acquisition, comprising:
According to the video and machine learning model, area information is obtained, the area information is used to indicate the video
In character area；
According to the area information, the character area in the video is obtained；
Text identification is carried out to the character area, obtains second text.
Second aspect, the embodiment of the present application provide a kind of device based on video acquisition panorama sketch, comprising:
Module is obtained, for obtaining text relevant to the video when playing video；
The acquisition module, is also used to obtain the mark in the text；
The acquisition module, is also used to obtain multiple images of the identified object of the mark, multiple described images are
The image of the object different direction；
Splicing module obtains the panorama sketch of the object for splicing multiple described images；
Display module, for showing the panorama sketch of the object.
In a kind of possible design, the acquisition module is specifically used for:
The mark is sent to server；
Multiple images of the identified object of the mark are obtained from server.
In a kind of possible design, the acquisition module is specifically used for:
Entry data is received from server, the entry data includes the mark of multiple images；
According to the entry data, panorama entrance icon is drawn；
It receives user and instruction is checked by the panorama that the panorama entrance icon inputs；
It checks that instruction generates panorama and checks request according to the panorama, and the panorama is checked that request is sent to server,
The panorama checks that request includes the mark of multiple images；
Multiple described images are obtained from the server.
In a kind of possible design, the word of the video is cached in the device based on video acquisition panorama sketch
Table, the acquisition module, is specifically used for:
If in presently described vocabulary not including the mark, the mark is sent to server.
It further include adding module in a kind of possible design；
The adding module, for adding the mark to the vocabulary.
The third aspect, the embodiment of the present application also provide a kind of terminal, comprising: processor, the processor and memory coupling
It closes；
The memory is used for, and stores computer program；
The processor is used for, and calls the computer program stored in the memory, to realize any institute of first aspect
The method stated.
Fourth aspect, the embodiment of the present application also provide a kind of readable storage medium storing program for executing, including program or instruction, work as described program
Or instruction, when running on computers, any method of first aspect is performed.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this Shen
Some embodiments please for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Figure 1A is application scenarios schematic diagram one provided by the embodiments of the present application；
Figure 1B is application scenario diagram two provided by the embodiments of the present application；
Fig. 2 is the flow chart of the method provided by the embodiments of the present application based on video acquisition panorama sketch；
Fig. 3 is the interaction figure of the method provided by the embodiments of the present application based on video acquisition panorama sketch；
Fig. 4 A is user interface map one provided by the embodiments of the present application；
Fig. 4 B is user interface map two provided by the embodiments of the present application；
Fig. 4 C is user interface map three provided by the embodiments of the present application；
Fig. 5 is the structural schematic diagram one of the device provided by the embodiments of the present application based on video acquisition panorama sketch；
Fig. 6 is the structural schematic diagram two of the device provided by the embodiments of the present application based on video acquisition panorama sketch；
Fig. 7 is the structural schematic diagram of terminal provided by the embodiments of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
In the application, "at least one" refers to one or more, and " multiple " refer to two or more."and/or",
The incidence relation of affiliated partner is described, indicates may exist three kinds of relationships, for example, A and/or B, can indicate: individualism A,
Exist simultaneously A and B, the case where individualism B, wherein A, B can be odd number or plural number.Character "/" typicallys represent front and back and closes
Connection object is a kind of relationship of "or".At least one of " following (a) " or its similar expression, refer to these in any group
It closes, any combination including individual event (a) or complex item (a).For example, at least one (a) in a, b or c, can indicate:
A, b, c, a-b, a-c, b-c or a-b-c, wherein a, b, c can be individually, be also possible to multiple.Term " in the application
One ", " second " etc. is to be used to distinguish similar objects, without being used to describe a particular order or precedence order.
Panorama sketch passes through the forms such as expression means and drawing, photograph, video, the threedimensional model of wide-angle, as more as possible
The environment of surrounding, such as 360 panorama sketch are shown, are by the image information that captures entire scene to mm professional camera special or to make
Picture after being rendered with modeling software carries out picture split using software, and is played out with special player, i.e., will put down
Face photo or computer modeling picture become 360 degree and see entirely, browse for virtual reality, and the simulation of two-dimensional plan view is come true
Real three-dimensional space.
Figure 1A is application scenario diagram one provided by the embodiments of the present application, and Figure 1B is application scenarios provided by the embodiments of the present application
Figure two；Referring to Fig. 1, user uses terminal plays video 11, when terminal is the text 12 and video title occurred from video
13, after the text identification to the mark that can be identified for that object in the description information of video, it can show what the mark indicated to user
The panorama sketch 14 of object.It is understood that the image in Figure 1B is a part of panorama sketch, when user drags the boundary in Figure 1B
When face, the image in other orientation of the object in Figure 1B can be shown.
In the following, technical solution shown in the application is described in detail by specific embodiment.Under it should be noted that
The several specific embodiments in face can be combined with each other, and for the same or similar content, no longer carry out weight in various embodiments
Multiple explanation.
Fig. 2 is the flow chart of the method provided by the embodiments of the present application based on video acquisition panorama sketch, and the present embodiment is held
Row main body may be based on the device of video acquisition panorama sketch, which can be located in terminal；Referring to fig. 2, the method for this implementation, packet
It includes:
Step S101, when playing video, text relevant to the video is obtained；
Specifically, the video in the present embodiment can be one section of video in a complete video, one section of video
Duration can be a preset duration, for example preset duration can be 2s~10SIn any duration.It is every in one complete video
Section video is executed according to the step in step S101~step S104.
Wherein, text relevant to the video is obtained, comprising: obtain the first text relevant to the video and/or second
Text, which is can be with the text of the Video segmentation, which is can not be with the text of the Video segmentation.
Specifically, the first text may include the description text of subtitle in the video, barrage, the title of video, video
At least one of in.Subtitle, barrage, the title of video, video description text be can with the text of the Video segmentation, or
It is independent that it is with the video that person, which says,.
It is made of due to video multi-frame video frame image, the second text can be the text in video frame images, can not
With Video segmentation.For example, the gate of a colleges and universities, is carved with " XX university " above, when to the gate recorded video, " XX university "
As with the indivisible text of video.
Further, it in order to guarantee that the accuracy of the second text obtained obtains the second text in a kind of mode, wraps
It includes:
A1, according to the video and machine learning model, obtain area information, which is used to indicate in the video
Character area；
Specifically, the video frame images that the video includes can be extracted at interval of a period of time, according to the video frame
Image and machine learning model obtain area information, i.e., by the feature input machine learning model of the video frame images, export
One area information, the area information are used to indicate the character area in the video frame images.
It is understood that the area information can be instruction video frame if not having text in the video frame images extracted
There is no the information of text, if having text in the video frame images extracted, which can be the text of the video frame images
The coordinate on four vertex in region.
Wherein, the 1/N that the duration that video frame images are spaced can be the video length is extracted, N can be any in 5~20
Integer value can also be other values, be not intended to limit in the present embodiment.
Above-mentioned machine learning model is obtained based on the training of multiple training samples, and training sample needs to include that basis does not have
The training sample for having the image of text to obtain also will include the training sample that basis has the image of text to obtain, training sample
Label can be the coordinate on four vertex of character area or the information for indicating not text, and the form of label can be character string
Form.According to the label of training sample and training sample, acquires machine learning algorithm and training sample is trained, can obtain
Machine learning model.Wherein, machine learning model can be neural network model.
A2, according to the area information, obtain the character area in the video；
For every video frame images of the video of extraction, according to the method in a1, an area information can be obtained.
For the video frame images with text, according to the area information, it may be determined that the character area in video frame images；For not having
The video frame images of text, according to the area information, it may be determined that do not have text in video frame images.
A3, text identification is carried out to the character area, obtains second text.
Text identification is carried out to the character area in every video frame images with text, the second text can be obtained.
Step S102, the mark in the text is obtained；
Specifically, it obtains in the text for identifying the mark of object, can be the device based on video acquisition panorama sketch
What itself was obtained, it is also possible to obtain from server.
Obtaining the mark in the text includes: the mark obtained in first text and/or second text.That is the text
Including first text and/or second text.
Mark can be the title, the title in city, the title of building etc. at sight spot.Correspondingly, if being identified as sight spot
Title, then identifying identified object is sight spot, if being identified as the title in city, identifying identified object is city
City, if being identified as the title of building, identifying identified object is building；Building such as can be library,
Teaching building, famous landmark etc..
If the mark obtained in text is obtained from server, the mark obtained in the text includes:
The text is sent to server；
The mark in the text is received from server.
Wherein, server extracts the noun in the text after receiving the text, and the noun in the text is located at
Noun in default identification list is determined as the mark in the text, and then, server sends out the mark in the determining text
It send to terminal.
In this way, a default identification list is stored in server, if the noun in the text is located at pre- bidding
Know in list, then the noun is the mark in the text.
It is that the device based on video acquisition panorama sketch itself obtains if obtaining for identifying the mark of object in the text
, then HanLP kit is installed in the device based on video acquisition panorama sketch, place name, mechanism are identified using HanLP kit
Name etc. realizes the purpose for identifying the mark in the text.
It is understood that the number for the mark that then text includes is extremely if can recognize that mark according to the text
It is one few.
In a kind of improved mode, the device based on video acquisition panorama sketch is cached with the corresponding complete video of the video
Vocabulary, the vocabulary the complete video start play when foundation, the complete video stop play when delete.
After getting the mark in the text, for each mark in the text, judge in the vocabulary whether include
The mark is added to the vocabulary if not including by the mark.
Step S103, multiple images for the object that the mark is identified are obtained, which is the position different direction
Image；
Specifically, for identifying the mark duplicate removal in the text, M mark in the text is obtained；In a kind of side
In formula, for each mark in M mark, multiple images for identifying identified object are obtained, it may include:
B1, mark is sent to server；
Specifically, each mark in this M mark is sent the mark if in vocabulary not including the mark
To server.
If in vocabulary not including the mark, illustrate that the mark is identified for the first time, user did not check the mark institute
The panorama sketch to picture of mark, needs to identify and is sent to server.If in vocabulary including the mark, illustrate the mark not and be the
It is once identified, what which was identified user may not check the panorama sketch of picture, then did not sent the mark
To server.
B2, multiple images for identifying identified object, pair which is identified by mark are obtained from server
As the image of different direction.
Specifically, it can be stored with a panorama the Resources list in server, include in the server in the panorama the Resources list
It is stored with the mark of panorama resource, panorama resource is the figure that multiple different directions of panorama sketch of object can be obtained after splicing
Picture.After server receives M mark of the text, each mark in M mark is corresponded to, server judgement identifies whether
It is present in panorama the Resources list, and if it exists, then illustrate to be stored with the different direction for identifying identified object in server
Multiple images, then server gets multiple images for identifying the different direction of identified object, and multiple images are sent out
It send to terminal.
It is understood that multiple images of the different direction for the object that the mark stored in server is identified, are being spelled
The panorama sketch of identified object available should be identified after connecing.
Wherein, panorama the Resources list can be the same table with default mark table, can also be different tables.If panorama resource arranges
Table and default mark table are not the same table, then the mark that panorama the Resources list includes with default mark table can be identical.
Step S104, for each mark in text, splicing identifies multiple images of identified object, obtained mark
Know the panorama sketch of identified object, and shows panorama sketch.
Specifically, for each mark in text, terminal is spelled after being identified multiple images of identified object
Multiple images are connect, the panorama sketch of identified object is identified, and show panorama sketch.Wherein, panorama sketch can be suspended in
Panorama immersion floating layer the effect more than video is shown.It is understood that the object that each mark in text is identified
Corresponding Zhang Quanjing figure.
Wherein, splice multiple images, obtain the method for panorama sketch referring to method in the prior art, in the present embodiment no longer
It repeats.
Further, when terminal shows panorama sketch, terminal can stop playing video.
By in video playing, identifying the mark of object relevant to video in the present embodiment, acquisition is marked
Multiple images of the different direction of the object of knowledge splice and obtain the panorama sketch to picture identified after multiple images, and to user
It shows the panorama sketch to picture identified, realizes the mesh for showing the panorama sketch of object relevant to video to user based on video
's.
It should be understood that magnitude of the sequence numbers of the above procedures are not meant that the order of the execution order, the execution of each process is suitable
Sequence should be determined by its function and internal logic, and the implementation process without coping with the embodiment of the present application constitutes any restriction.
In order to show that user wants the panorama sketch for the object seen according to the demand of user, rather than will identify that
Panorama sketch is shown in terminal, and the present embodiment has made further improvement on the basis of a upper embodiment.Fig. 3 is the application
The interaction figure for the method based on video acquisition panorama sketch that embodiment provides, the present embodiment is obtained to the step in a upper embodiment
The improvement for identifying the process of multiple images of identified object is taken, the method for the present embodiment includes:
Step S201, the mark in the text that terminal will acquire is sent to server, and text is to obtain when playing video
Text relevant to video.
Specifically, the method for the mark in the text in the step is obtained referring to step S101~step in a upper embodiment
Rapid S102, details are not described herein again.
Step S202, server obtains entry data, which includes the object that the mark in the text is identified
The respective mark of multiple images.
Clear in order to illustrate, the mark in the present embodiment text is known as first identifier, and the mark of image is known as second identifier.
Specifically, after server receives the first identifier in the text, for each first identifier in the text, service
Device judges whether to be stored with multiple images of the object that the first identifier is identified, and (judgment mode can refer in an embodiment
Method), if being stored with multiple images for the object that the first identifier is identified in server, obtains the first identifier and identified
Object multiple images second identifier, second identifier can be index value, the object identified then according to the first identifier
Multiple images second identifier, generate the entry data for the object that the first identifier is identified.
It is understood that if server receives M first identifier of the different objects of instruction in the text, and service
Multiple images for the object that each first identifier is identified in M first identifier are stored in device, then server can get M
Entry data.
Entry data may also include that the corresponding first identifier in the text；Further, entry data may also include sample
The data of this image, any image in multiple corresponding images which can be identified by corresponding first identifier.
Step S203, server sends entry data to terminal.
Step S204, terminal draws panorama entrance icon according to entry data；
Specifically, after terminal receives entry data, according to entry data, panorama entrance icon is drawn.If entry data
In include the text in corresponding first identifier, then in panorama entrance icon include the text in corresponding first identifier；
It further include the sample image in panorama entrance icon in entry data if further including the data of sample image.
It is understood that can draw to obtain M panorama entrance icon if terminal has received M entry data.
Step S205, terminal shows panorama entrance icon.
Specifically, terminal can around video or the top of video show panorama entrance icon.
Fig. 4 A is user interface map one provided by the embodiments of the present application, and 51,52 in the figure are panorama entrance icon.
Step S206, terminal receives user and checks instruction by touching the panorama of panorama entrance icon input.
When user expects checking the panorama of certain an object A, the panorama entrance icon of object A is clicked or touched, is inputted
Panorama checks instruction.
Step S207, terminal checks that instruction generates panorama and checks request according to panorama；Panorama checks that request includes the text
The respective mark of multiple images of object that is identified of mark.
Specifically, if user touches the corresponding panorama entrance icon of object A, panorama checks that request includes object A's
The respective mark of multiple images.
Step S208, panorama is checked that request is sent to server by terminal；
Step S209, server checks request according to panorama, obtains multiple images；
Specifically, server checks the mark of multiple images that request includes according to panorama, gets multiple images.
Step S210, multiple images are sent to terminal by server.
Fig. 4 B is user interface map two provided by the embodiments of the present application, and Fig. 4 C is user interface provided by the embodiments of the present application
Figure three, as shown in Figure 4 B, user click panorama entrance icon, and input panorama checks instruction, and terminal checks instruction life according to panorama
Request is checked at panorama；Panorama checks that request includes the mark of multiple images of object corresponding to panorama entrance icon, then
Panorama is checked that request is sent to server by terminal, and server checks request according to panorama, is obtained corresponding to panorama entrance icon
Object multiple images, and multiple images of object corresponding to panorama entrance icon are sent to terminal, terminal receives
Afterwards, multiple images of object corresponding to spliced panoramic entrance icon obtain the panorama of object corresponding to panorama entrance icon
Figure, shows the panorama sketch, as shown in Figure 4 C.Image in Fig. 4 C is a part of panorama sketch, when user drags the interface in 4C
When, it can show the image in the other orientation of object.
Panorama entrance icon is drawn by terminal in the present embodiment, panorama is inputted by panorama entrance icon in user and is checked
After instruction, Cai Huixiang user shows the panorama sketch of corresponding object, oneself wants to look into so that user can check according to their own needs
The panorama sketch for the object seen.
It is illustrated above in conjunction with method based on video acquisition panorama sketch of the FIG. 1 to FIG. 4 to the application, below to base
It is illustrated in the device of video acquisition panorama sketch.
Fig. 5 is the structural schematic diagram one of the device provided by the embodiments of the present application based on video acquisition panorama sketch, referring to figure
5, the device of the present embodiment includes:
Module 51 is obtained, for obtaining text relevant to the video when playing video；
The acquisition module 51, is also used to obtain the mark in the text；
The acquisition module 51 is also used to obtain multiple images of the identified object of the mark, multiple described images
For the image of the object different direction；
Splicing module 52 obtains the panorama sketch of the object for splicing multiple described images；
Display module 53, for showing the panorama sketch of the object.
In a kind of possible design, the acquisition module 51 is specifically used for: obtaining the first text relevant to video
And/or second text, first text is can be with the text of the Video segmentation, and second text is can not be with institute
State the text of Video segmentation.
In a kind of possible design, the acquisition module 51 is specifically used for:
The mark is sent to server；
Multiple images of the identified object of the mark are obtained from server.
In a kind of possible design, the acquisition module 51 is specifically used for:
Entry data is received from server, the entry data includes the mark of multiple images；
According to the entry data, panorama entrance icon is drawn；
It receives user and instruction is checked by the panorama that the panorama entrance icon inputs；
It checks that instruction generates panorama and checks request according to the panorama, and the panorama is checked that request is sent to server,
The panorama checks that request includes the mark of multiple images；
Multiple described images are obtained from the server.
In a kind of possible design, the word of the video is cached in the device based on video acquisition panorama sketch
Table, the acquisition module 51, is specifically used for:
If in presently described vocabulary not including the mark, the mark is sent to server.
The device of the present embodiment can be used for executing the technical solution of above method embodiment, realization principle and technology
Effect is similar, and details are not described herein again.
Fig. 6 is the structural schematic diagram two of the device provided by the embodiments of the present application based on video acquisition panorama sketch, such as Fig. 6 institute
Show, can also include: adding module 54 further on the basis of the device of the present embodiment apparatus structure shown in Fig. 5；
The adding module 54, for adding the mark to the vocabulary.
The device of the present embodiment can be used for executing the technical solution of above method embodiment, realization principle and technology
Effect is similar, and details are not described herein again.
Fig. 7 is the structural schematic diagram of terminal provided by the embodiments of the present application, and referring to Fig. 7, the terminal of the present embodiment includes: place
Manage device 71, memory 72 and communication bus 73, communication bus 73 for connecting processor 71 and memory 72, processor 71 with deposit
Reservoir 72 couples；
The memory 71 is used for, and stores computer program；
The processor 72 is used for, and calls the computer program stored in the memory, to realize that the above method is implemented
Method in example.
Wherein, computer program is also storable in the memory of exterior of terminal.
It should be understood that in the embodiment of the present application, which can be CPU, which can also be that other are logical
With processor, digital signal processor (DSP), specific integrated circuit (ASIC), field programmable gate array (FPGA) or its
His programmable logic device, discrete gate or transistor logic, discrete hardware components etc..General processor can be micro- place
Manage device either any conventional processor etc..
The memory 71 may include read-only memory and random access memory, and provide instruction sum number to processor 52
According to.Memory 71 can also include nonvolatile RAM.For example, memory 71 can be with storage device type
Information.
The memory 71 can be volatile memory or nonvolatile memory, or may each comprise volatibility and non-volatile
Both property memories.Wherein, nonvolatile memory can be read-only memory (read-only memory, ROM), may be programmed
Read-only memory (programmable ROM, PROM), Erasable Programmable Read Only Memory EPROM (erasable PROM,
EPROM), electrically erasable programmable read-only memory (electrically EPROM, EEPROM) or flash memory.Volatile memory
It can be random access memory (random access memory, RAM), be used as External Cache.By exemplary
It but is not restricted explanation, the RAM of many forms is available, such as static random access memory (static RAM, SRAM), dynamic
State random access memory (DRAM), Synchronous Dynamic Random Access Memory (synchronous DRAM, SDRAM), double number
According to rate synchronization dynamic random access memory (double data date SDRAM, DDR SDRAM), enhanced synchronous dynamic
Random access memory (enhanced SDRAM, ESDRAM), synchronized links dynamic random access memory (synchlink
DRAM, SLDRAM) and direct rambus random access memory (direct rambus RAM, DR RAM).
The bus 73 can also include power bus, control bus and status signal bus in addition in addition to including data/address bus
Deng.But for the sake of clear explanation, various buses are all designated as bus 53 in figure.
The embodiment of the present application provides a kind of readable storage medium storing program for executing, including program or instruction, when described program or instruction are being counted
When running on calculation machine, the method in above method embodiment is performed.
The embodiment of the present application also provides a kind of readable storage medium storing program for executing, including program or instruction, when described program or instruction exist
When running on computer, method described in above method embodiment is performed.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above various embodiments is only to illustrate the technical solution of the embodiment of the present application, rather than to it
Limitation；Although the embodiment of the present application is described in detail referring to foregoing embodiments, those skilled in the art
It is understood that it is still possible to modify the technical solutions described in the foregoing embodiments, either to part of or
All technical features are equivalently replaced；And these are modified or replaceed, it does not separate the essence of the corresponding technical solution this Shen
Please example scheme range.
Claims (14)
1. a kind of method based on video acquisition panorama sketch is applied to terminal characterized by comprising
When playing video, text relevant to the video is obtained；
Obtain the mark in the text；
Multiple images of the identified object of the mark are obtained, multiple described images are the image of the object different direction；
Splice multiple described images, obtains the panorama sketch of the object, and show the panorama sketch of the object.
2. the method according to claim 1, wherein obtaining text relevant to video, comprising:
The first text relevant to video and/or the second text are obtained, first text is can be with the Video segmentation
Text, second text is can not be with the text of the Video segmentation.
3. method according to claim 1 or 2, which is characterized in that described to obtain the more of the identified object of the mark
Open image, comprising:
The mark is sent to server；
Multiple images of the identified object of the mark are obtained from server.
4. according to the method described in claim 3, it is characterized in that, described obtain the identified object of the mark from server
Multiple images, comprising:
Entry data is received from server, the entry data includes the mark of multiple images；
According to the entry data, panorama entrance icon is drawn；
It receives user and instruction is checked by the panorama that the panorama entrance icon inputs；
It checks that instruction generates panorama and checks request according to the panorama, and the panorama is checked that request is sent to server, institute
It states panorama and checks that request includes the mark of multiple images；
Multiple described images are obtained from the server.
5. the method according to claim 3 or 4, which is characterized in that be cached with the vocabulary of the video, institute in the terminal
It states and the mark is sent to server, comprising:
If in presently described vocabulary not including the mark, the mark is sent to server.
6. according to the method described in claim 5, it is characterized by further comprising:
If in presently described vocabulary not including the mark, the mark is added to the vocabulary.
7. according to the method described in claim 2, it is characterized in that, the second text of the acquisition, comprising:
According to the video and machine learning model, area information is obtained, the area information is used to indicate in the video
Character area；
According to the area information, the character area in the video is obtained；
Text identification is carried out to the character area, obtains second text.
8. a kind of device based on video acquisition panorama sketch characterized by comprising
Module is obtained, for obtaining text relevant to the video when playing video；
The acquisition module, is also used to obtain the mark in the text；
The acquisition module is also used to obtain multiple images of the identified object of the mark, multiple described images are described
The image of object different direction；
Splicing module obtains the panorama sketch of the object for splicing multiple described images；
Display module, for showing the panorama sketch of the object.
9. device according to claim 8, which is characterized in that the acquisition module is specifically used for:
The mark is sent to server；
Multiple images of the identified object of the mark are obtained from server.
10. device according to claim 9, which is characterized in that the acquisition module is specifically used for:
Entry data is received from server, the entry data includes the mark of multiple images；
According to the entry data, panorama entrance icon is drawn；
It receives user and instruction is checked by the panorama that the panorama entrance icon inputs；
It checks that instruction generates panorama and checks request according to the panorama, and the panorama is checked that request is sent to server, it is described
Panorama checks that request includes the mark of multiple images；
Multiple described images are obtained from the server.
11. device according to claim 9 or 10, which is characterized in that in the device based on video acquisition panorama sketch
It is cached with the vocabulary of the video, the acquisition module is specifically used for:
If in presently described vocabulary not including the mark, the mark is sent to server.
12. device according to claim 11, which is characterized in that further include adding module；
The adding module, for adding the mark to the vocabulary.
13. a kind of terminal characterized by comprising processor, the processor are coupled with memory；
The memory is used for, and stores computer program；
The processor is used for, and calls the computer program stored in the memory, to realize any institute of claim 1~7
The method stated.
14. a kind of readable storage medium storing program for executing, which is characterized in that including program or instruction, when described program or instruct on computers
When operation, any method of claim 1~7 is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811249707.0A CN109462730A (en) | 2018-10-25 | 2018-10-25 | Method and apparatus based on video acquisition panorama sketch |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811249707.0A CN109462730A (en) | 2018-10-25 | 2018-10-25 | Method and apparatus based on video acquisition panorama sketch |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109462730A true CN109462730A (en) | 2019-03-12 |
Family
ID=65608437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811249707.0A Pending CN109462730A (en) | 2018-10-25 | 2018-10-25 | Method and apparatus based on video acquisition panorama sketch |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109462730A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110351596A (en) * | 2019-07-17 | 2019-10-18 | 刘进 | A kind of internet stream media big data barrage processing system and processing method |
| CN112559884A (en) * | 2020-12-25 | 2021-03-26 | 北京百度网讯科技有限公司 | Method and device for hooking panorama and interest point, electronic equipment and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020849A (en) * | 2012-12-19 | 2013-04-03 | 屠建江 | Method and system of moving scene display network sale |
| CN104135716A (en) * | 2014-06-17 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Push method and system of interest point information |
| CN104469437A (en) * | 2014-12-23 | 2015-03-25 | 小米科技有限责任公司 | Advertisement pushing method and device |
| CN106557768A (en) * | 2016-11-25 | 2017-04-05 | 北京小米移动软件有限公司 | The method and device is identified by word in picture |
| CN107180055A (en) * | 2016-03-11 | 2017-09-19 | 阿里巴巴集团控股有限公司 | The methods of exhibiting and device of business object |
| KR20180004643A (en) * | 2016-12-07 | 2018-01-12 | 주식회사 팝스라인 | Terminal and control method thereof |
| CN107633441A (en) * | 2016-08-22 | 2018-01-26 | 大辅科技（北京）有限公司 | Commodity in track identification video image and the method and apparatus for showing merchandise news |
| CN107656962A (en) * | 2017-08-09 | 2018-02-02 | 百度在线网络技术（北京）有限公司 | Panorama display methods, server and computer-readable medium in electronic map |
| CN107728787A (en) * | 2017-10-30 | 2018-02-23 | 太平洋未来科技（深圳）有限公司 | Method for information display and device in panoramic video |
| CN108090814A (en) * | 2017-12-29 | 2018-05-29 | 百维雅（东莞）网络技术有限公司 | A kind of new panorama shopping online platform |
| CN108334518A (en) * | 2017-01-20 | 2018-07-27 | 中国移动通信有限公司研究院 | A kind of advertisement loading method and device |
| CN108460104A (en) * | 2018-02-06 | 2018-08-28 | 北京奇虎科技有限公司 | A kind of method and apparatus for realizing content customization |
-
2018
- 2018-10-25 CN CN201811249707.0A patent/CN109462730A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020849A (en) * | 2012-12-19 | 2013-04-03 | 屠建江 | Method and system of moving scene display network sale |
| CN104135716A (en) * | 2014-06-17 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Push method and system of interest point information |
| CN104469437A (en) * | 2014-12-23 | 2015-03-25 | 小米科技有限责任公司 | Advertisement pushing method and device |
| CN107180055A (en) * | 2016-03-11 | 2017-09-19 | 阿里巴巴集团控股有限公司 | The methods of exhibiting and device of business object |
| CN107633441A (en) * | 2016-08-22 | 2018-01-26 | 大辅科技（北京）有限公司 | Commodity in track identification video image and the method and apparatus for showing merchandise news |
| CN106557768A (en) * | 2016-11-25 | 2017-04-05 | 北京小米移动软件有限公司 | The method and device is identified by word in picture |
| KR20180004643A (en) * | 2016-12-07 | 2018-01-12 | 주식회사 팝스라인 | Terminal and control method thereof |
| CN108334518A (en) * | 2017-01-20 | 2018-07-27 | 中国移动通信有限公司研究院 | A kind of advertisement loading method and device |
| CN107656962A (en) * | 2017-08-09 | 2018-02-02 | 百度在线网络技术（北京）有限公司 | Panorama display methods, server and computer-readable medium in electronic map |
| CN107728787A (en) * | 2017-10-30 | 2018-02-23 | 太平洋未来科技（深圳）有限公司 | Method for information display and device in panoramic video |
| CN108090814A (en) * | 2017-12-29 | 2018-05-29 | 百维雅（东莞）网络技术有限公司 | A kind of new panorama shopping online platform |
| CN108460104A (en) * | 2018-02-06 | 2018-08-28 | 北京奇虎科技有限公司 | A kind of method and apparatus for realizing content customization |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110351596A (en) * | 2019-07-17 | 2019-10-18 | 刘进 | A kind of internet stream media big data barrage processing system and processing method |
| CN110351596B (en) * | 2019-07-17 | 2021-07-27 | 上海播呗网络科技有限公司 | Internet streaming media big data bullet screen processing system and processing method |
| CN112559884A (en) * | 2020-12-25 | 2021-03-26 | 北京百度网讯科技有限公司 | Method and device for hooking panorama and interest point, electronic equipment and storage medium |
| CN112559884B (en) * | 2020-12-25 | 2023-09-26 | 北京百度网讯科技有限公司 | Panorama and interest point hooking method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7123122B2 (en) | Navigating Video Scenes Using Cognitive Insights | |
| US20140222809A1 (en) | Processing media items in location-based groups | |
| Kros | Rhodes Must Fall: archives and counter-archives | |
| CN107438864A (en) | Including viewpoint translation to prevent the virtual reality content of simulator disease from presenting | |
| CN104881860A (en) | Positioning method and apparatus based on photographs | |
| KR102082313B1 (en) | Historical experience education system using virtual reality | |
| CN106683201A (en) | Scene editing method and device based on three-dimensional virtual reality | |
| CN108681393A (en) | Translation display methods, device, computing device and medium based on augmented reality | |
| Roberts | Navigating the ‘archive city’ Digital spatial humanities and archival film practice | |
| US20230073750A1 (en) | Augmented reality (ar) imprinting methods and systems | |
| CN109462730A (en) | Method and apparatus based on video acquisition panorama sketch | |
| Callahan | Art+ Archive: Understanding the archival turn in contemporary art | |
| CN109241385A (en) | Searching method, equipment and storage medium | |
| CN105630791A (en) | Web album browsing method and device | |
| Westmoreland | Making sense: affective research in postwar Lebanese art | |
| TW202314535A (en) | Data display method, computer device and computer-readable storage medium | |
| Zhang et al. | Annotating and navigating tourist videos | |
| CN110543347A (en) | Method and device for generating screenshot image and electronic equipment | |
| CN111985035B (en) | BIM-based achievement display method and device for campus reduction system and storage medium | |
| Kaplan et al. | Mapping ararat: an augmented reality walking tour for an imaginary Jewish homeland | |
| CN114157877A (en) | Playback data generation method and device, and playback method and device | |
| Grønstad et al. | Invisibility in Visual and Material Culture | |
| CN115640611B (en) | Method for updating natural language processing model and related equipment | |
| CN114967914A (en) | Virtual display method, device, equipment and storage medium | |
| CN111652986B (en) | Stage effect presentation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190312 |