CN109996107A - Video generation method, device and system - Google Patents
Video generation method, device and system Download PDFInfo
- Publication number
- CN109996107A CN109996107A CN201711487230.5A CN201711487230A CN109996107A CN 109996107 A CN109996107 A CN 109996107A CN 201711487230 A CN201711487230 A CN 201711487230A CN 109996107 A CN109996107 A CN 109996107A
- Authority
- CN
- China
- Prior art keywords
- image
- original image
- video
- presented
- pushed information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000011218 segmentation Effects 0.000 claims abstract description 21
- 238000006243 chemical reaction Methods 0.000 claims description 24
- 230000000007 visual effect Effects 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 17
- 238000003709 image segmentation Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000003384 imaging method Methods 0.000 claims description 9
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 238000003786 synthesis reaction Methods 0.000 claims description 4
- 238000003780 insertion Methods 0.000 abstract description 11
- 230000037431 insertion Effects 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 17
- 230000006870 function Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 10
- 238000002513 implantation Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000009738 saturating Methods 0.000 description 1
- 230000036555 skin type Effects 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
Abstract
The present invention proposes a kind of video generation method, device and system, wherein method includes: each frame original image for obtaining original video;For each frame original image, using trained image instance parted pattern, identification is obtained in original image according to the target area that pushed information to be presented in the image block and image block that Object Segmentation obtains is presented;Pushed information is presented in the target area of image block according to the image block of original image for each frame original image, to obtain the corresponding target image of original image;It is synthesized according to the corresponding target image of each frame original image, obtains required target video.Due to containing the video of pushed information in target video, to which intelligence insertion advertisement in video when pushed information is advertisement, may be implemented, the dispensing form of advertisement is enriched, it solves in the prior art by being implanted into bumper advertisements in video, the more single problem of form is launched in advertisement.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of video generation methods, device and system.
Background technique
With the continuous development of Internet technology, video is watched in more and more users' selection in video website, and wide
Announcement is the major source of revenues of video website.In the prior art, by being implanted into bumper advertisements in video, advertisement launch form compared with
It is single.
Summary of the invention
The present invention is directed to solve at least some of the technical problems in related technologies.
For this purpose, the first purpose of this invention is to propose a kind of video generation method, contain push letter in target video
The video of breath, so that intelligence insertion advertisement in video may be implemented, can effectively enrich advertisement when pushed information is advertisement
Dispensing form, solve in the prior art by being implanted into bumper advertisements in video, the more single problem of form is launched in advertisement.
Second object of the present invention is to propose a kind of video-generating device.
Third object of the present invention is to propose a kind of video generating system.
Fourth object of the present invention is to propose a kind of calculating skill equipment.
5th purpose of the invention is to propose a kind of non-transitorycomputer readable storage medium.
6th purpose of the invention is to propose a kind of computer program product.
In order to achieve the above object, first aspect present invention embodiment proposes a kind of video generation method, comprising:
Obtain each frame original image of original video;
For each frame original image, using trained Image Segmentation Model, identification obtain in the original image according to
According to the target area that pushed information to be presented in Object Segmentation obtained image block and described image block is presented;
For each frame original image, according to the image block of the original image, in the target area of described image block
The pushed information is presented, to obtain the corresponding target image of the original image;
It is synthesized according to the corresponding target image of each frame original image, obtains required target video.
The video generation method of the embodiment of the present invention, by obtaining each frame original image of original video, then for each
Frame original image, using trained Image Segmentation Model, identification obtains obtaining in original image according to presentation Object Segmentation
Image block and image block in pushed information to be presented target area, then for each frame original image, according to described
The pushed information is presented in the image block of original image in the target area of described image block, to obtain the original image
Corresponding target image is finally synthesized according to the corresponding target image of each frame original image, obtains required target video.This
In embodiment, containing the video of pushed information in target video, to may be implemented in video when pushed information is advertisement
Intelligence insertion advertisement, can effectively enrich the dispensing form of advertisement, solve wide by implantation patch in video in the prior art
It accuses, the more single problem of form is launched in advertisement.
In order to achieve the above object, second aspect of the present invention embodiment proposes a kind of video-generating device, comprising:
Module is obtained, for obtaining each frame original image of original video;
Region identification module, for being directed to each frame original image, using trained Image Segmentation Model, identification is obtained
According to the mesh that pushed information to be presented in Object Segmentation obtained image block and described image block is presented in the original image
Mark region;
Synthesis module, for being directed to each frame original image, according to the image block of the original image, in described image block
Target area in the pushed information is presented, to obtain the corresponding target image of the original image;According to each frame original graph
As corresponding target image is synthesized, required target video is obtained.
The video-generating device of the embodiment of the present invention, by obtaining each frame original image of original video, then for each
Frame original image, using trained Image Segmentation Model, identification obtains obtaining in original image according to presentation Object Segmentation
Image block and image block in pushed information to be presented target area, then for each frame original image, according to described
The pushed information is presented in the image block of original image in the target area of described image block, to obtain the original image
Corresponding target image is finally synthesized according to the corresponding target image of each frame original image, obtains required target video.This
In embodiment, containing the video of pushed information in target video, to may be implemented in video when pushed information is advertisement
Intelligence insertion advertisement, can effectively enrich the dispensing form of advertisement, solve wide by implantation patch in video in the prior art
It accuses, the more single problem of form is launched in advertisement.
In order to achieve the above object, third aspect present invention embodiment proposes a kind of video generating system, comprising:
Off-line training node, for obtaining trained Image Segmentation Model;
Base video analysis node, for obtaining each frame original image of original video;
Service node, for being directed to each frame original image, using trained image instance parted pattern, identification is obtained
According to the mesh that pushed information to be presented in Object Segmentation obtained image block and described image block is presented in the original image
Mark region;It is in the target area of described image block according to the image block of the original image for each frame original image
The existing pushed information, to obtain the corresponding target image of the original image;
The base video analysis node is also used to be synthesized according to the corresponding target image of each frame original image, obtain
To required target video.
The video generating system of the embodiment of the present invention, by obtaining each frame original image of original video, then for each
Frame original image, using trained Image Segmentation Model, identification obtains obtaining in original image according to presentation Object Segmentation
Image block and image block in pushed information to be presented target area, then for each frame original image, according to described
The pushed information is presented in the image block of original image in the target area of described image block, to obtain the original image
Corresponding target image is finally synthesized according to the corresponding target image of each frame original image, obtains required target video.This
In embodiment, containing the video of pushed information in target video, to may be implemented in video when pushed information is advertisement
Intelligence insertion advertisement, can effectively enrich the dispensing form of advertisement, solve wide by implantation patch in video in the prior art
It accuses, the more single problem of form is launched in advertisement.
To achieve the goals above, fourth aspect present invention embodiment proposes a kind of computer equipment, comprising: storage
Device, processor and storage on a memory and the computer program that can run on a processor, the processor execution journey
When sequence, the video generation method as described in first aspect present invention embodiment is realized.
To achieve the goals above, fifth aspect present invention embodiment proposes a kind of computer-readable storage of non-transitory
Medium is stored thereon with computer program, which is characterized in that such as first aspect present invention is realized when the program is executed by processor
Video generation method described in embodiment.
To achieve the goals above, sixth aspect present invention embodiment proposes a kind of computer program product, when described
When instruction in computer program product is executed by processor, executes the video as described in first aspect present invention embodiment and generate
Method.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is the flow diagram of the first video generation method provided by the embodiment of the present invention;
Fig. 2 is the original image schematic diagram of the embodiment of the present invention;
Fig. 3 is the flow diagram of second of video generation method provided by the embodiment of the present invention;
Fig. 4 is the flow diagram of the third video generation method provided by the embodiment of the present invention;
Fig. 5 is a kind of structural schematic diagram of video-generating device provided in an embodiment of the present invention;
Fig. 6 is the structural schematic diagram of another video-generating device provided in an embodiment of the present invention;
Fig. 7 is a kind of structural schematic diagram of video-generating device provided in an embodiment of the present invention;
Fig. 8 is the generating process schematic diagram of target video in the embodiment of the present invention;
Fig. 9 shows the block diagram for being suitable for the exemplary computer device for being used to realize the application embodiment.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to is used to explain the present invention, and is not considered as limiting the invention.
For existing by being implanted into bumper advertisements in video, the more single technical problem of form, this hair are launched in advertisement
In bright embodiment, by obtaining each frame original image of original video, it is then directed to each frame original image, use is trained
Image Segmentation Model, identification obtain in the image block and image block that obtain in original image according to presentation Object Segmentation wait be in
The target area of existing pushed information, then for each frame original image, according to the image block of original image, in the mesh of image block
It marks and pushed information is presented in region, it is finally corresponding according to each frame original image to obtain the corresponding target image of original image
Target image is synthesized, and required target video is obtained.In the present embodiment, containing the video of pushed information in target video, from
And when pushed information is advertisement, intelligence insertion advertisement in video may be implemented, can effectively enrich the dispensing form of advertisement.
Below with reference to the accompanying drawings video generation method, the device and system of the embodiment of the present invention are described.
Fig. 1 is the flow diagram of the first video generation method provided by the embodiment of the present invention.The embodiment of the present invention
The video generation method of offer is configured in video-generating device, which can carry out data with video website
Interaction.Wherein, video website refers in the case where perfect technology platform is supported, allow the online smooth publication of Internet user, browsing and
The network media of sharing video frequency works, such as can be the websites such as iqiyi.com, Baidu be audio-visual.
As shown in Figure 1, the video generation method the following steps are included:
Step 101, each frame original image of original video is obtained.
In the embodiment of the present invention, original video can be any video in video website.Specifically, user can upload
Video is to video website, and then, the video-generating device of the embodiment of the present invention can obtain on any user from video website
The video of biography, as original video.
Optionally, original video be by camera sequentially in time, what the picture frame that successively acquires was constituted, alternatively, former
Beginning video be by video production person sequentially in time, successively each frame original image is synthesized, therefore, is being obtained
After original video, each frame original image of available original video.
Step 102, for each frame original image, using trained image instance parted pattern, identification obtains original
According to the target area that pushed information to be presented in Object Segmentation obtained image block and image block is presented in image.
In the embodiment of the present invention, pushed information to be presented is the pushed information for needing to present in the target area, for example, to
It can be advertisement that pushed information, which is presented, or be other pushed informations, with no restriction to this.
In the embodiment of the present invention, image instance parted pattern can be trained in advance, it is real by the image of the training
Example parted pattern can identify push to be presented in the image block and image block obtained in image according to presentation Object Segmentation
The target area of information.
As a kind of possible implementation, the sample image of multiple subjects, the sample image can be obtained in advance
In be labeled with target area, image instance parted pattern can be then trained using sample image.To obtain respectively
After frame original image, trained image instance parted pattern can be used, identification obtains in original image according to presentation pair
Target area as dividing pushed information to be presented in obtained image block and image block, it is easy to operate and be easily achieved.
Wherein, in sample image, target area can be adjacent with the imaging region of object, alternatively, target area can be with
Inside imaging region in object, the embodiment of the present invention to this with no restriction.
As an example, referring to fig. 2, Fig. 2 is the original image schematic diagram of the embodiment of the present invention.In Fig. 2, original image
Middle presentation object includes: red sun 21, green hill 22, flying bird 23, trees 24, lorry 25.For original image, use is trained
Image instance parted pattern, the target area that identification obtains pushed information to be presented in original image is region 1, the target area
In the imaging region of object lorry 25.
Step 103, for each frame original image, according to the image block of original image, in the target area of image block
Pushed information is presented, to obtain the corresponding target image of original image.
It is former for each frame after the image block and target area for identifying each frame original image in the embodiment of the present invention
Pushed information can be presented in the target area of image block, to obtain original graph according to the image block of original image in beginning image
As corresponding target image.
Still with above-mentioned example, when the target area for identifying pushed information to be presented in original image is region 1,
Pushed information can be presented in region 1, such as when pushed information is advertisement, advertisement can be presented in zone 1.
Step 104, it is synthesized according to the corresponding target image of each frame original image, obtains required target video.
In the embodiment of the present invention, after obtaining the corresponding target image of each frame original image, existing video can use
Synthetic technology synthesizes the corresponding target image of each frame original image, obtains required target video.Due in target video
Video containing pushed information, so that intelligence insertion advertisement in video, Neng Gouyou may be implemented when pushed information is advertisement
Imitate the dispensing form of abundant advertisement.
The video generation method of the present embodiment, it is then former for each frame by obtaining each frame original image of original video
Beginning image, using trained Image Segmentation Model, identification obtains the figure obtained in original image according to presentation Object Segmentation
As the target area of pushed information to be presented in block and image block, then for each frame original image, according to original image
Image block, pushed information is presented in the target area of image block, to obtain the corresponding target image of original image, last root
It is synthesized according to the corresponding target image of each frame original image, obtains required target video.In the present embodiment, contain in target video
There is the video of pushed information, so that intelligence insertion advertisement in video may be implemented when pushed information is advertisement, it can be effective
The dispensing form of abundant advertisement solves in the prior art by being implanted into bumper advertisements in video, and it is more single that form is launched in advertisement
One the problem of.
In addition, in the prior art, by being implanted directly into bumper advertisements in video, it may occur however that advertisement and view after implantation
Take place frequently raw incompatible with situation, seriously reduces the display effect of video.
It therefore,, can be to target area in order to solve the problems, such as the poor display effect of above-mentioned video in the embodiment of the present invention
The object presented in the affiliated image block in domain identifies shooting visual angle, later according to shooting visual angle, to the view for presenting pushed information
Carry out perspective conversion.Since the object presented in the view and the affiliated image block in target area after perspective conversion is flat in same view
Face, thus behind the target area of view covering original image after using perspective conversion, the view after perspective can be made to convert
Scheme merged with original image more naturally, greatly promoting the treatment effect of image in turn.Below with reference to Fig. 3, to above-mentioned mistake
Journey is described in detail.
Fig. 3 is the flow diagram of second of video generation method provided in the embodiment of the present invention.
As shown in figure 3, step 103 specifically includes following sub-step on the basis of embodiment shown in Fig. 1:
Step 201, to the object presented in the affiliated image block in target area, shooting visual angle is identified.
In the embodiment of the present invention, shooting visual angle includes shooting height, shooting direction and shooting distance;Shooting height includes flat
Clap, take a crane shot and face upward bat;Shooting direction includes positive angle, flank angle, oblique side angle degree, back angle etc.;Shooting distance, which refers to, to be taken the photograph
As the distance between head and subject.
There is the view of pushed information may be with pair that presents in the affiliated image block in target area in original image due to showing
As not in same view plane, therefore, if directly using the target area for the view covering original image for presenting pushed information,
It then will lead to the ineffective of picture processing.It therefore, can be according to in the affiliated image block in target area in the embodiment of the present invention
The step of object of presentation identifies shooting visual angle, synthesizes target image with triggering following.
Step 202, according to shooting visual angle, perspective conversion is carried out to the view for presenting pushed information.
It optionally, can be to presenting after the shooting visual angle of the object presented in determining the affiliated image block in target area
The view of pushed information carries out perspective conversion, so that presenting in the view and the affiliated image block in target area after perspective conversion
Object be in same view plane, and then promote the treatment effect of subsequent image.
Step 203, using the target area of the view covering original image after perspective conversion, it is corresponding to obtain original image
Target image.
View covering in the embodiment of the present invention, after obtaining the view after perspective conversion, after can use perspective conversion
The target area of original image obtains the corresponding target image of original image.View and target area after being converted due to perspective
The object presented in affiliated image block is in same view plane, thus view covering original image after using perspective conversion
Behind target area, can make perspective convert after view merged with original image more naturally, greatly promoting figure in turn
The treatment effect of picture.
The video generation method of the present embodiment, by the object presented in the affiliated image block in target area, identification shooting
Visual angle carries out perspective conversion to the view for presenting pushed information later according to shooting visual angle, the view after recycling perspective conversion
The target area of map combining original image obtains the corresponding target image of original image.In the present embodiment, after perspective conversion
View covering original image target area after, can make perspective convert after view merged with original image more oneself
So, to greatly promote the treatment effect of image, and then the display effect of target video is promoted, solution is regarding in the prior art
Bumper advertisements are implanted directly into frequency, it may occur however that advertisement and video after implantation are seriously reduced there is a situation where incompatible with
The problem of display effect of video.
For an embodiment in clear explanation, another video generation method is present embodiments provided, Fig. 4 is that the present invention is real
Apply the flow diagram of the third video generation method provided by example.
As shown in figure 4, the video generation method may comprise steps of:
Step 301, each frame original image of original video is obtained.
The implementation procedure of step 301 can participate in the implementation procedure of step 101 in above-described embodiment, and this will not be repeated here.
Step 302, the sample image of multiple subjects is obtained;Sample image is labeled with target area;Wherein, in sample
In this image, target area is adjacent with the imaging region of object, alternatively, target area is in inside the imaging region of object.
In the embodiment of the present invention, subject can be scenery, personage, scene etc..
In the embodiment of the present invention, the sample image of available a subject, such as can be obtained from the network platform
The image comprising multiple subjects that user uploads, as sample image.
Step 303, image instance parted pattern is trained using sample image.
After obtaining sample image, image instance parted pattern can be trained using sample image, thus obtaining
After taking each frame original image, trained image instance parted pattern can be used, identification object region is easy to operate and easy
In realization.
Step 304, for each frame original image, using trained image instance parted pattern, identification obtains original
According to the target area that pushed information to be presented in Object Segmentation obtained image block and image block is presented in image.
Step 304 implementation procedure can participate in the implementation procedure of step 102 in above-described embodiment, and this will not be repeated here.
Step 305, to the object presented in the affiliated image block in target area, shooting visual angle is identified.
The implementation procedure of step 305 can participate in the implementation procedure of step 201 in above-described embodiment, and this will not be repeated here.
Step 306, scene type belonging to original image is identified.
In the embodiment of the present invention, scene type belonging to different images may be same or different.For example, 1 institute of image
The scene of category is bustling shopping center, scene is the beautiful mountain forest of scenery belonging to image 2, and scene belonging to image 3 is
Bedroom.Therefore, after obtaining original image, the scene type of the original image can be identified.
As a kind of possible implementation, the corresponding relationship between each scene type and object can be pre-established, from
And after determining the object that original image is presented, above-mentioned corresponding relationship can be inquired, scene class corresponding with the object is obtained
Not, as the scene type of original image.
As alternatively possible implementation, can training image scene Recognition model in advance, be then directed to original graph
Picture, can use trained image scene identification model, and identification obtains scene type belonging to original image;Wherein, scheme
Image field scape identification model is that multiple images are shot under each scene type as training sample and using corresponding scene type pair
Training sample is labeled, and is trained according to the training sample by mark.
Step 307, according to scene type, the label of each pushed information is inquired, it is matched with scene type to obtain label
Pushed information.
As a kind of possible implementation, can pre-establish between each scene type and the label of pushed information
Corresponding relationship obtains and scene class to can inquire above-mentioned corresponding relationship after determining scene type belonging to original image
The label of not corresponding pushed information, and then can be obtained and the matched pushed information of scene type according to label.
Specifically, clustering processing can be carried out to each pushed information in advance, according to the pushed information after clustering processing, really
The label of fixed each pushed information.For example, clustering processing can be carried out according to different advertisements when pushed information is advertisement,
It then determines the label of the advertisement after clustering processing, for example the advertisement of tourism is clustered, the mark of the advertisement of the tourism
Label be tourism or skin type advertisement label be skin care, the advertisement of health class label be health etc., it is different herein
One enumerates.
After the label for determining each pushed information, it can establish between each scene type and the label of pushed information
Corresponding relationship obtains and scene class to can inquire above-mentioned corresponding relationship after determining scene type belonging to original image
The label of not corresponding pushed information, and then can be obtained and the matched pushed information of scene type according to label.
For example, when crossing a bus in original video, which travels the winding public affairs in beautiful scenery
On the road, at this point, can be the advertisement of tourism with the matched pushed information of scene type.
It should be noted that Same Scene classification can correspond to a label, or multiple labels can also be corresponded to.Citing
For, when in original video being a bedroom, at this point, can be the wide of Household appliances with the matched pushed information of scene type
Announcement, furniture series advertisements, decoration series advertisements etc., therefore, label corresponding with bedroom scene type can for household electrical appliance, furniture,
Decoration etc..
Step 308, according to shooting visual angle, perspective conversion is carried out to the view for presenting pushed information.
Step 309, using the target area of the view covering original image after perspective conversion, it is corresponding to obtain original image
Target image.
Step 308~309 implementation procedures may refer to the implementation procedure of step 202~203 in above-described embodiment, herein not
It repeats.
Step 310, it is synthesized according to the corresponding target image of each frame original image, obtains required target video.
The implementation procedure of step 310 may refer to the implementation procedure of step 104 in above-described embodiment, and this will not be repeated here.
As an example, referring to fig. 2, it is assumed that pushed information to be presented is advertisement.For original image, using by instructing
Experienced image instance parted pattern, the target area that identification obtains pushed information to be presented in original image is region 1, at this point,
The object that can be presented according to original image inquires the corresponding object of each scene type, identifies the scene class of the original image
It Wei not travel, then the advertisement of tourism can be presented in zone 1, so that advertisement and the original image of target area presentation
Scene matching so that generate target video more naturally, do not influence user viewing in the case where, promoted ad stream
The consumption rate of amount reduces advertiser or agential dispensing cost.
The video generation method of the present embodiment, it is then former for each frame by obtaining each frame original image of original video
Beginning image, using trained Image Segmentation Model, identification obtains the figure obtained in original image according to presentation Object Segmentation
As the target area of pushed information to be presented in block and image block, then to pair presented in the affiliated image block in target area
As identifying shooting visual angle, later according to shooting visual angle, carrying out perspective conversion to the view for presenting pushed information, recycle saturating
Depending on the target area of the view covering original image after conversion, the corresponding target image of original image is obtained, finally according to each frame
The corresponding target image of original image is synthesized, and required target video is obtained.In the present embodiment, the view after perspective conversion is utilized
Behind the target area of map combining original image, can make perspective convert after view merged with original image more naturally,
To greatly promote the treatment effect of image, and then promote the display effect of target video.It is pushed away in addition, containing in target video
It delivers letters the video of breath, so that intelligence insertion advertisement in video may be implemented, enrich the throwing of advertisement when pushed information is advertisement
Put form.Further, in this embodiment the scene matching of advertisement and original image that target area is presented, so that raw
At target video more naturally, in the case where not influencing user's viewing, promote the consumption rate of ad traffic, reduce advertisement
Main or agential dispensing cost.
In order to realize above-described embodiment, the present invention also proposes a kind of video-generating device.
Fig. 5 is a kind of structural schematic diagram of video-generating device provided in an embodiment of the present invention.
As shown in figure 5, the video-generating device 400 includes: to obtain module 401, region identification module 402, and synthesize
Module 403.Wherein,
Module 401 is obtained, for obtaining each frame original image of original video.
Region identification module 402, for being directed to each frame original image, using trained Image Segmentation Model, identification
It obtains in original image according to the target area that pushed information to be presented in Object Segmentation obtained image block and image block is presented
Domain.
Synthesis module 403, for being directed to each frame original image, according to the image block of original image, in the mesh of image block
It marks and pushed information is presented in region, to obtain the corresponding target image of original image;According to the corresponding target of each frame original image
Image is synthesized, and required target video is obtained.
As a kind of possible implementation, synthesis module 403, specifically for being presented in the affiliated image block in target area
Object, identify shooting visual angle;According to shooting visual angle, perspective conversion is carried out to the view for presenting pushed information;Utilize perspective
The target area of view covering original image after conversion, obtains the corresponding target image of original image.
Further, in a kind of possible implementation of the embodiment of the present invention, referring to Fig. 6, embodiment shown in Fig. 5
On the basis of, which can also include: to obtain training module 404 and identification enquiry module 405.
Training module 404 is obtained, for obtaining the sample image of multiple subjects;Sample image is labeled with target area
Domain;Wherein, in sample image, target area is adjacent with the imaging region of object, alternatively, target area is in the imaging of object
Inside region;Image instance parted pattern is trained using sample image.
Enquiry module 405 is identified, for carrying out perspective conversion to the view for presenting pushed information according to shooting visual angle
Before, scene type belonging to original image is identified;According to scene type, the label of each pushed information is inquired, label is obtained
With the matched pushed information of scene type.
As a kind of possible implementation, enquiry module 405 is identified, specifically for pair presented according to original image
As inquiring the corresponding object of each scene type, identifying the scene type of original image.
As alternatively possible implementation, enquiry module 405 is identified, be specifically used for original image, using process
Trained image scene identification model, identification obtain scene type belonging to original image;Wherein, image scene identification model,
It is to shoot multiple images under each scene type to mark training sample as training sample and using corresponding scene type
Note is trained according to the training sample by mark.
It should be noted that the aforementioned video for being also applied for the embodiment to the explanation of video generation method embodiment
Generating means 400, details are not described herein again.
The video-generating device of the present embodiment, it is then former for each frame by obtaining each frame original image of original video
Beginning image, using trained Image Segmentation Model, identification obtains the figure obtained in original image according to presentation Object Segmentation
As the target area of pushed information to be presented in block and image block, then for each frame original image, according to original image
Image block, pushed information is presented in the target area of image block, to obtain the corresponding target image of original image, last root
It is synthesized according to the corresponding target image of each frame original image, obtains required target video.In the present embodiment, contain in target video
There is the video of pushed information, so that intelligence insertion advertisement in video may be implemented when pushed information is advertisement, it can be effective
The dispensing form of abundant advertisement solves in the prior art by being implanted into bumper advertisements in video, and it is more single that form is launched in advertisement
One the problem of.
In order to realize above-described embodiment, the present invention also proposes a kind of video generating system.
Fig. 7 is a kind of structural schematic diagram of video-generating device provided in an embodiment of the present invention.
As shown in fig. 7, the video generating system includes: off-line training node 601, base video analysis node 602, service
Node 603 and base video analysis node 604.Wherein,
Off-line training node 601, for obtaining trained Image Segmentation Model.
Base video analysis node 602, for obtaining each frame original image of original video.
Service node 603, for being directed to each frame original image, using trained image instance parted pattern, identification
It obtains in original image according to the target area that pushed information to be presented in Object Segmentation obtained image block and image block is presented
Domain;Pushed information is presented in the target area of image block according to the image block of original image for each frame original image,
To obtain the corresponding target image of original image.
Base video analysis node 602 is also used to be synthesized according to the corresponding target image of each frame original image, obtain
Required target video.
It should be noted that the aforementioned video for being also applied for the embodiment to the explanation of video generation method embodiment
Generation system, details are not described herein again.
It as an example, is the generating process schematic diagram of target video in the embodiment of the present invention referring to Fig. 8, Fig. 8.Fig. 8
Using pushed information to be presented as advertisement example.Base video analysis node obtains the original video that video production person uploads, and obtains
Each frame original image of original video is taken, then, identifies to obtain the target of advertisement to be presented in original image by service node
Region, and through service node in the target area of original image, generate the mesh of the advertisement material sent comprising advertiser
Logo image.Finally, being synthesized target image by base video analysis node, obtains the target comprising advertisement material and regard
Frequently.
The video generating system of the present embodiment, it is then former for each frame by obtaining each frame original image of original video
Beginning image, using trained Image Segmentation Model, identification obtains the figure obtained in original image according to presentation Object Segmentation
As the target area of pushed information to be presented in block and image block, then for each frame original image, according to original image
Image block, pushed information is presented in the target area of image block, to obtain the corresponding target image of original image, last root
It is synthesized according to the corresponding target image of each frame original image, obtains required target video.In the present embodiment, contain in target video
There is the video of pushed information, so that intelligence insertion advertisement in video may be implemented when pushed information is advertisement, it can be effective
The dispensing form of abundant advertisement solves in the prior art by being implanted into bumper advertisements in video, and it is more single that form is launched in advertisement
One the problem of.
In order to realize above-described embodiment, the present invention also proposes a kind of computer equipment, comprising: memory, processor and deposits
The computer program that can be run on a memory and on a processor is stored up, when the processor executes described program, is realized such as this
The video generation method that invention previous embodiment proposes.
In order to realize above-described embodiment, the present invention also proposes a kind of non-transitorycomputer readable storage medium, deposits thereon
Contain computer program, which is characterized in that the view proposed such as present invention is realized when the program is executed by processor
Frequency generation method.
In order to realize above-described embodiment, the present invention also proposes a kind of computer program product, when the computer program produces
When instruction in product is executed by processor, the video generation method proposed such as present invention is executed.
Fig. 9 shows the block diagram for being suitable for the exemplary computer device for being used to realize the application embodiment.What Fig. 9 was shown
Computer equipment 12 is only an example, should not function to the embodiment of the present application and use scope bring any restrictions.
As shown in figure 9, computer equipment 12 is showed in the form of universal computing device.The component of computer equipment 12 can be with
Including but not limited to: one or more processor or processing unit 16, system storage 28 connect different system components
The bus 18 of (including system storage 28 and processing unit 16).
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (Industry Standard
Architecture;Hereinafter referred to as: ISA) bus, microchannel architecture (Micro Channel Architecture;Below
Referred to as: MAC) bus, enhanced isa bus, Video Electronics Standards Association (Video Electronics Standards
Association;Hereinafter referred to as: VESA) local bus and peripheral component interconnection (Peripheral Component
Interconnection;Hereinafter referred to as: PCI) bus.
Computer equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that computer equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
Memory 28 may include the computer system readable media of form of volatile memory, such as random access memory
Device (Random Access Memory;Hereinafter referred to as: RAM) 30 and/or cache memory 32.Computer equipment 12 can be with
It further comprise other removable/nonremovable, volatile/non-volatile computer system storage mediums.Only as an example,
Storage system 34 can be used for reading and writing immovable, non-volatile magnetic media, and (Fig. 9 do not show, commonly referred to as " hard drive
Device ").Although being not shown in Fig. 9, the disk for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided and driven
Dynamic device, and to removable anonvolatile optical disk (such as: compact disc read-only memory (Compact Disc Read Only
Memory;Hereinafter referred to as: CD-ROM), digital multi CD-ROM (Digital Video Disc Read Only
Memory;Hereinafter referred to as: DVD-ROM) or other optical mediums) read-write CD drive.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 18.Memory 28 may include that at least one program produces
Product, the program product have one group of (for example, at least one) program module, and it is each that these program modules are configured to perform the application
The function of embodiment.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 include but is not limited to operating system, one or more application program, other program modules and
It may include the realization of network environment in program data, each of these examples or certain combination.Program module 42 is usual
Execute the function and/or method in embodiments described herein.
Computer equipment 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display 24
Deng) communication, the equipment interacted with the computer system/server 12 can be also enabled a user to one or more to be communicated, and/
Or with enable the computer system/server 12 and one or more of the other any equipment (example for being communicated of calculating equipment
Such as network interface card, modem etc.) communication.This communication can be carried out by input/output (I/O) interface 22.Also, it calculates
Machine equipment 12 can also pass through network adapter 20 and one or more network (such as local area network (Local Area
Network;Hereinafter referred to as: LAN), wide area network (Wide Area Network;Hereinafter referred to as: WAN) and/or public network, example
Such as internet) communication.As shown, network adapter 20 is communicated by bus 18 with other modules of computer equipment 12.It answers
When understanding, although not shown in the drawings, other hardware and/or software module can be used in conjunction with computer equipment 12, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize the video generation method referred in previous embodiment.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present invention, the meaning of " plurality " is at least two, such as two, three
It is a etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing custom logic function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can then be edited, be interpreted or when necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.Such as, if realized with hardware in another embodiment, following skill well known in the art can be used
Any one of art or their combination are realized: have for data-signal is realized the logic gates of logic function from
Logic circuit is dissipated, the specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene can compile
Journey gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although having been shown and retouching above
The embodiment of the present invention is stated, it is to be understood that above-described embodiment is exemplary, and should not be understood as to limit of the invention
System, those skilled in the art can be changed above-described embodiment, modify, replace and become within the scope of the invention
Type.
Claims (11)
1. a kind of video generation method, which comprises the following steps:
Obtain each frame original image of original video;
For each frame original image, using trained image instance parted pattern, identification obtain in the original image according to
According to the target area that pushed information to be presented in Object Segmentation obtained image block and described image block is presented;
It is presented in the target area of described image block for each frame original image according to the image block of the original image
The pushed information, to obtain the corresponding target image of the original image;
It is synthesized according to the corresponding target image of each frame original image, obtains required target video.
2. video generation method according to claim 1, which is characterized in that the image according to the original image
The pushed information is presented in block in the target area of described image block, to obtain the corresponding target image of the original image,
Include:
To the object presented in the affiliated image block in the target area, shooting visual angle is identified;
According to the shooting visual angle, perspective conversion is carried out to the view for presenting the pushed information;
The target area that the original image is covered using the view after perspective conversion, obtains the corresponding target of the original image
Image.
3. video generation method according to claim 1, which is characterized in that it is described to be directed to each frame original image, using warp
Trained image instance parted pattern is crossed, identification obtains the image block obtained in the original image according to presentation Object Segmentation,
And in described image block before the target area of pushed information to be presented, further includes:
Obtain the sample image of multiple subjects;The sample image is labeled with the target area;Wherein, in the sample
In this image, the target area is adjacent with the imaging region of the object, alternatively, the target area is in the object
Inside imaging region;
Described image example parted pattern is trained using the sample image.
4. video generation method according to claim 2, which is characterized in that it is described according to the shooting visual angle, to presentation
Before thering is the view of the pushed information to carry out perspective conversion, further includes:
Identify scene type belonging to the original image;
According to the scene type, the label of each pushed information is inquired, obtains label and the matched push of the scene type
Information.
5. video generation method according to claim 4, which is characterized in that field belonging to the identification original image
Scape classification, comprising:
According to the object that the original image is presented, the corresponding object of each scene type is inquired, identifies the original image institute
The scene type stated.
6. video generation method according to claim 4, which is characterized in that field belonging to the identification original image
Scape classification, comprising:
To the original image, using trained image scene identification model, identification is obtained belonging to the original image
Scene type;Wherein, described image scene Recognition model is that multiple images are shot under each scene type as training sample
And the training sample is labeled using corresponding scene type, it is trained to obtain according to the training sample by mark
's.
7. a kind of video generating system characterized by comprising
Off-line training node, for obtaining trained Image Segmentation Model;
Base video analysis node, for obtaining each frame original image of original video;
Service node, for being directed to each frame original image, using trained image instance parted pattern, identification obtains described
According to the target area that pushed information to be presented in Object Segmentation obtained image block and described image block is presented in original image
Domain;Institute is presented in the target area of described image block according to the image block of the original image for each frame original image
Pushed information is stated, to obtain the corresponding target image of the original image;
The base video analysis node is also used to be synthesized according to the corresponding target image of each frame original image, obtains institute
Need target video.
8. a kind of video-generating device, which is characterized in that including
Module is obtained, for obtaining each frame original image of original video;
Region identification module, for being directed to each frame original image, using trained Image Segmentation Model, identification obtains described
According to the target area that pushed information to be presented in Object Segmentation obtained image block and described image block is presented in original image
Domain;
Synthesis module, for being directed to each frame original image, according to the image block of the original image, in the mesh of described image block
It marks and the pushed information is presented in region, to obtain the corresponding target image of the original image;According to each frame original image pair
The target image answered is synthesized, and required target video is obtained.
9. a kind of computer equipment, which is characterized in that on a memory and can be in processor including memory, processor and storage
The computer program of upper operation when the processor executes described program, realizes such as video as claimed in any one of claims 1 to 6
Generation method.
10. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the program
Such as video generation method as claimed in any one of claims 1 to 6 is realized when being executed by processor.
11. a kind of computer program product, which is characterized in that when the instruction in the computer program product is executed by processor
When, execute such as video generation method as claimed in any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711487230.5A CN109996107A (en) | 2017-12-29 | 2017-12-29 | Video generation method, device and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711487230.5A CN109996107A (en) | 2017-12-29 | 2017-12-29 | Video generation method, device and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109996107A true CN109996107A (en) | 2019-07-09 |
Family
ID=67110389
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711487230.5A Pending CN109996107A (en) | 2017-12-29 | 2017-12-29 | Video generation method, device and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109996107A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110443310A (en) * | 2019-08-07 | 2019-11-12 | 浙江大华技术股份有限公司 | Compare update method, server and the computer storage medium of analysis system |
CN110517187A (en) * | 2019-08-30 | 2019-11-29 | 王�琦 | Advertisement generation method, apparatus and system |
CN110708593A (en) * | 2019-09-06 | 2020-01-17 | 深圳平安通信科技有限公司 | Method, device and storage medium for embedding advertisement in video content |
CN111292280A (en) * | 2020-01-20 | 2020-06-16 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
CN111556362A (en) * | 2020-03-19 | 2020-08-18 | 上海万面智能科技有限公司 | Vehicle body advertisement implanting method and device, electronic equipment and storage medium |
CN111738107A (en) * | 2020-06-08 | 2020-10-02 | Oppo(重庆)智能科技有限公司 | Video generation method, video generation device, storage medium, and electronic apparatus |
CN112037121A (en) * | 2020-08-19 | 2020-12-04 | 北京字节跳动网络技术有限公司 | Picture processing method, device, equipment and storage medium |
CN112214643A (en) * | 2020-10-15 | 2021-01-12 | 百度(中国)有限公司 | Video patch generation method and device, electronic equipment and storage medium |
WO2021057704A1 (en) * | 2019-09-23 | 2021-04-01 | Maycas System Limited | Methods and systems for incorporating advertising materials into video images |
WO2021169396A1 (en) * | 2020-02-27 | 2021-09-02 | 腾讯科技(深圳)有限公司 | Media content placement method and related device |
CN113490028A (en) * | 2021-06-01 | 2021-10-08 | 深圳喜悦机器人有限公司 | Video processing method, device, storage medium and terminal |
CN114760517A (en) * | 2022-04-15 | 2022-07-15 | 广州华多网络科技有限公司 | Image activity embedding method and device, equipment, medium and product thereof |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101571875A (en) * | 2009-05-05 | 2009-11-04 | 程治永 | Realization method of image searching system based on image recognition |
CN103297811A (en) * | 2012-02-24 | 2013-09-11 | 北京明日时尚信息技术有限公司 | Method for realizing video advertisement in intelligently embedding mode |
CN103366190A (en) * | 2013-07-26 | 2013-10-23 | 中国科学院自动化研究所 | Method for identifying traffic sign |
CN104486680A (en) * | 2014-12-19 | 2015-04-01 | 珠海全志科技股份有限公司 | Video-based advertisement pushing method and system |
CN104581430A (en) * | 2013-10-21 | 2015-04-29 | 华为技术有限公司 | Advertisement insertion method and equipment in video display |
CN105872588A (en) * | 2015-12-09 | 2016-08-17 | 乐视网信息技术(北京)股份有限公司 | Method and device for loading advertisement in video |
JP2016162029A (en) * | 2015-02-27 | 2016-09-05 | トッパン・フォームズ株式会社 | Information providing system and information providing device |
CN106156732A (en) * | 2016-07-01 | 2016-11-23 | 合网络技术(北京)有限公司 | Object identifying method and object recognition equipment |
CN107493488A (en) * | 2017-08-07 | 2017-12-19 | 上海交通大学 | The method that video content thing based on Faster R CNN models is intelligently implanted into |
-
2017
- 2017-12-29 CN CN201711487230.5A patent/CN109996107A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101571875A (en) * | 2009-05-05 | 2009-11-04 | 程治永 | Realization method of image searching system based on image recognition |
CN103297811A (en) * | 2012-02-24 | 2013-09-11 | 北京明日时尚信息技术有限公司 | Method for realizing video advertisement in intelligently embedding mode |
CN103366190A (en) * | 2013-07-26 | 2013-10-23 | 中国科学院自动化研究所 | Method for identifying traffic sign |
CN104581430A (en) * | 2013-10-21 | 2015-04-29 | 华为技术有限公司 | Advertisement insertion method and equipment in video display |
CN104486680A (en) * | 2014-12-19 | 2015-04-01 | 珠海全志科技股份有限公司 | Video-based advertisement pushing method and system |
JP2016162029A (en) * | 2015-02-27 | 2016-09-05 | トッパン・フォームズ株式会社 | Information providing system and information providing device |
CN105872588A (en) * | 2015-12-09 | 2016-08-17 | 乐视网信息技术(北京)股份有限公司 | Method and device for loading advertisement in video |
CN106156732A (en) * | 2016-07-01 | 2016-11-23 | 合网络技术(北京)有限公司 | Object identifying method and object recognition equipment |
CN107493488A (en) * | 2017-08-07 | 2017-12-19 | 上海交通大学 | The method that video content thing based on Faster R CNN models is intelligently implanted into |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110443310A (en) * | 2019-08-07 | 2019-11-12 | 浙江大华技术股份有限公司 | Compare update method, server and the computer storage medium of analysis system |
CN110443310B (en) * | 2019-08-07 | 2022-08-09 | 浙江大华技术股份有限公司 | Updating method of comparison analysis system, server and computer storage medium |
CN110517187A (en) * | 2019-08-30 | 2019-11-29 | 王�琦 | Advertisement generation method, apparatus and system |
CN110708593A (en) * | 2019-09-06 | 2020-01-17 | 深圳平安通信科技有限公司 | Method, device and storage medium for embedding advertisement in video content |
WO2021057704A1 (en) * | 2019-09-23 | 2021-04-01 | Maycas System Limited | Methods and systems for incorporating advertising materials into video images |
CN111292280A (en) * | 2020-01-20 | 2020-06-16 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
CN111292280B (en) * | 2020-01-20 | 2023-08-29 | 北京百度网讯科技有限公司 | Method and device for outputting information |
WO2021169396A1 (en) * | 2020-02-27 | 2021-09-02 | 腾讯科技(深圳)有限公司 | Media content placement method and related device |
CN111556362A (en) * | 2020-03-19 | 2020-08-18 | 上海万面智能科技有限公司 | Vehicle body advertisement implanting method and device, electronic equipment and storage medium |
CN111738107A (en) * | 2020-06-08 | 2020-10-02 | Oppo(重庆)智能科技有限公司 | Video generation method, video generation device, storage medium, and electronic apparatus |
CN112037121A (en) * | 2020-08-19 | 2020-12-04 | 北京字节跳动网络技术有限公司 | Picture processing method, device, equipment and storage medium |
CN112214643A (en) * | 2020-10-15 | 2021-01-12 | 百度(中国)有限公司 | Video patch generation method and device, electronic equipment and storage medium |
CN112214643B (en) * | 2020-10-15 | 2024-01-12 | 百度(中国)有限公司 | Video patch generation method and device, electronic equipment and storage medium |
CN113490028A (en) * | 2021-06-01 | 2021-10-08 | 深圳喜悦机器人有限公司 | Video processing method, device, storage medium and terminal |
CN114760517A (en) * | 2022-04-15 | 2022-07-15 | 广州华多网络科技有限公司 | Image activity embedding method and device, equipment, medium and product thereof |
CN114760517B (en) * | 2022-04-15 | 2024-02-02 | 广州华多网络科技有限公司 | Image moving embedding method and device, equipment, medium and product thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109996107A (en) | Video generation method, device and system | |
US11217006B2 (en) | Methods and systems for performing 3D simulation based on a 2D video image | |
Chen et al. | What comprises a good talking-head video generation?: A survey and benchmark | |
CN108833973A (en) | Extracting method, device and the computer equipment of video features | |
CN105975581B (en) | Methods of exhibiting, client and the server of media information | |
Butler | Television style | |
CN101563698A (en) | Personalizing a video | |
CN107633441A (en) | Commodity in track identification video image and the method and apparatus for showing merchandise news | |
US20110026609A1 (en) | Image tracking and substitution system and methodology | |
CN109348275A (en) | Method for processing video frequency and device | |
CN102930454A (en) | Intelligent 3D (Three Dimensional) advertisement recommendation method based on multiple perception technologies | |
CN107943291A (en) | Recognition methods, device and the electronic equipment of human action | |
CN109978618A (en) | Advertisement interacts jettison system under line based on cloud artificial intelligence | |
Zhou et al. | Now you shake me: Towards automatic 4D cinema | |
CN110214343A (en) | Information processing unit, information processing method and its program | |
Cerankowski | Spectacular asexuals: Media visibility and cultural fetish | |
CN109191585A (en) | Information processing method, device, equipment and computer readable storage medium | |
CN108076355A (en) | Video playing control method and device | |
CN109816444A (en) | A kind of advertisement placement method and device | |
Qian | Three narrative patterns of the city image visually presented on Instagram under the influence of self-presentation | |
CN108833964A (en) | A kind of real-time successive frame Information Embedding identifying system | |
CN109711335A (en) | The method and device that Target Photo is driven by characteristics of human body | |
CN208013969U (en) | A kind of content reproduction terminal and system | |
Jones | Quantification and substitution: the abstract space of virtual cinematography | |
Srivastava et al. | Recognizing emotion in the wild using multimodal data |
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: 20190709 |