CN104066003B - Method and device for playing advertisement in video - Google Patents
Method and device for playing advertisement in video Download PDFInfo
- Publication number
- CN104066003B CN104066003B CN201410268322.4A CN201410268322A CN104066003B CN 104066003 B CN104066003 B CN 104066003B CN 201410268322 A CN201410268322 A CN 201410268322A CN 104066003 B CN104066003 B CN 104066003B
- Authority
- CN
- China
- Prior art keywords
- video
- advertisement
- picture
- information
- frame
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000000007 visual effect Effects 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 15
- 238000005520 cutting process Methods 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 4
- 238000001514 detection method Methods 0.000 description 14
- 238000012545 processing Methods 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 230000008901 benefit Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 239000012634 fragment Substances 0.000 description 5
- 238000007689 inspection Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 238000010191 image analysis Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000003139 buffering effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000005211 surface analysis Methods 0.000 description 1
Classifications
-
- 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
- H04N21/458—Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules ; time-related management operations
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention provides a method and device for playing an advertisement in a video. The method for playing the advertisement in the video includes the steps of obtaining the video to be played and obtaining information of the advertisement, wherein the information of the advertisement includes the content of the advertisement and information of the first position, and the first position is the position of the advertisement in the video; fusing the content of the advertisement to the first position of the video and conducting playing so that the advertisement can be located on an object, with a plane structure, of the video. By means of the method, the data size can be reduced, and data security is improved. According to the method for playing the advertisement in the video, the advertisement is made located on the object, with the plane structure, of the video, and therefore normal playing of the content of the video can not be influenced, and the watching experience of a user is improved.
Description
Technical field
The present invention relates in Internet communication technology field, more particularly to a kind of video advertisement playing method and device.
Background technology
With the development of video-on-demand live technology, Internet video is increasingly favored by people, and Internet video is net
Indispensable important component part in network application technology.As Web Video Service business, with reference to the profit mode of TV programme,
Video program content is provided for spectators, while by playing a number of network video advertisement to spectators, having become one kind
Ripe pattern.
At present the input mode of network video advertisement mainly uses film buffering loading, plays and suspend or between the dragging time
Gap completes advertisement broadcasting, but, this mode can cause the time during video-see to wait, so as to injure the sight of user
See experience.
The content of the invention
It is contemplated that at least solving one of technical problem in correlation technique to a certain extent.
For this purpose, it is an object of the present invention to proposing a kind of player method of advertisement in video, the method can not shadow
Ring the viewing experience of user.
Further object is that proposing a kind of playing device of advertisement in video.
To reach above-mentioned purpose, the player method of advertisement in the video that first aspect present invention embodiment is proposed, including：Obtain
The video to be played, and the information of acquisition advertisement are taken, the information of advertisement includes：Ad content and the information of first position,
First position is advertisement position in video；Ad content is dissolved into into the first position of video, and is played out so that
Advertisement is located on the object with planar structure of video.
First aspect present invention embodiment propose video in advertisement player method, by obtain the video to be played and
The information of advertisement, by ad content the first position of video is dissolved into, and is played out, and advertisement can be dissolved into into video
In, rather than in video playback gap showing advertisements, without being waited during user's viewing video, can be lifted
Consumer's Experience, also, the present embodiment can not affect video by making advertisement on the object with planar structure of video
The normal presentation of content, improves the viewing experience of user.
To reach above-mentioned purpose, the playing device of advertisement in the video that second aspect present invention embodiment is proposed, including：Obtain
Delivery block, for obtaining the video to be played, and the information of acquisition advertisement, the information of advertisement includes ad content and first
The information of position, first position is advertisement position in video；Module is incorporated, for ad content to be dissolved into into the of video
At one position, and play out so that advertisement is located on the object with planar structure of video.
Second aspect present invention embodiment propose video in advertisement playing device, by obtain the video to be played and
The information of advertisement, by ad content the first position of video is dissolved into, and is played out, and advertisement can be dissolved into into video
In, rather than in video playback gap showing advertisements, without being waited during user's viewing video, can be lifted
Consumer's Experience, also, the present embodiment can not affect video by making advertisement on the object with planar structure of video
The normal presentation of content, improves the viewing experience of user.
The additional aspect of the present invention and advantage will be set forth in part in the description, and partly will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Description of the drawings
The above-mentioned and/or additional aspect of the present invention and advantage will become from the following description of the accompanying drawings of embodiments
It is substantially and easy to understand, wherein：
Fig. 1 is the schematic flow sheet of the player method of advertisement in the video proposed according to one embodiment of the invention；
Fig. 2 is the schematic flow sheet of the player method of advertisement in the video proposed according to another embodiment of the present invention；
Fig. 3 is the schematic flow sheet that processed offline acquisition advertisement position is carried out to video of one embodiment of the invention；
Fig. 4 be one embodiment of the invention acquisition picture group in have planar structure object position flow process illustrate
Figure；
Fig. 5 be another embodiment of the present invention video in advertisement playing device structural representation；
Fig. 6 be another embodiment of the present invention video in advertisement playing device structural representation.
Specific embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from start to finish
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, is only used for explaining the present invention, and is not considered as limiting the invention.Conversely, this
Inventive embodiment includes all changes fallen in the range of the spirit and intension of attached claims, modification and is equal to
Thing.
Below with reference to the accompanying drawings the playing method and device of advertisement in video according to embodiments of the present invention is described.
Fig. 1 is the schematic flow sheet of the player method of advertisement in the video that one embodiment of the invention is proposed, the method includes：
S101：The video to be played, and the information of acquisition advertisement are obtained, the information of advertisement includes：Ad content and
The information of first position.
Wherein, first position is position of the advertisement on video, for example, advertisement in video per the position in two field picture,
It can be specifically position that the object with planar structure is located in each scene in every two field picture etc..
Advertisement refers to the advertisement being inserted in video, and advertisement is presented on the form in every two field picture and includes but is not limited to text
Word, pattern etc..
In the embodiment of the present invention, can be obtained by off-line analysiss and the advertisement position for throwing in advertisement is suitable in the video to be played simultaneously
In storing data base, afterwards when needing to throw in advertisement in the video every time, you can the advertisement position letter in data base
Breath selects first position to carry out advertisement putting.Particular content will be described in detail in subsequent embodiment.
S102：Ad content is dissolved into into the first position of video, and is played out so that advertisement is located at the tool of video
Have on the object of planar structure.
Specifically, method can be incorporated by existing, the mode such as renders for example with 3D and be dissolved into ad content and regard
The first position of frequency, and play with video so that advertisement is located on the object with planar structure of video.
Specifically incorporate that method is also various, here will not enumerate.
Video and the information of advertisement that the present embodiment to be played by acquisition, by ad content first of video is dissolved into
Put place, and play out, advertisement can be dissolved in video, rather than in video playback gap showing advertisements, from without
Want to be waited during user's viewing video, Consumer's Experience can be lifted, also, the present embodiment is located at video by making advertisement
The object with planar structure on, the normal presentation of video content can not be affected, improve the viewing experience of user.
Fig. 2 is the schematic flow sheet of the player method of advertisement in the video proposed according to another embodiment of the present invention, in order to
The viewing experience of user is further lifted, the complexity that advertisement is processed is reduced, the video for needing to insert advertisement can respectively be carried out
Processed offline and real-time processing, as shown in Fig. 2 the method includes：
S201：Obtain the video to be played, and the information for obtaining advertisement.
In video display process, the video to be played and wide can be obtained from service end by default program such as player
The information of announcement, can include the data base for preserving video and the data base for preserving advertisement in service end, and player can be respectively
The information of video and advertisement is obtained from corresponding data base.Wherein, the information of advertisement includes ad content, and first position
Information, first position is position of the advertisement on video, and first position can be chosen from predetermined advertisement position, concrete choosing
The principle for taking can be arranged according to practical situation.Space reflection information of the advertisement position such as advertisement in every two field picture of video,
In addition, the information of video ads can also include showing advertisement time etc..
Specifically, the video to be played is obtained, and the information of acquisition advertisement can be obtained using online mode.
Wherein, the advertisement position of video can be obtained using offline mode.
Advertisement position is the position of the object with planar structure of the video.
Specifically, the fragment containing non-key flat site (such as body of wall) in video can be found by processed offline, and it is right
The fragment carries out two dimensional analysises and plane tracking, the azimuth information of plane is drawn, to obtain suitable advertisement position.
Referring to Fig. 3, the process of processed offline acquisition advertisement position is carried out to video can be included：
S301：Video is decoded, each frame picture is obtained.
Specifically, pretreatment, such as video decoding etc., to obtain each frame picture can be carried out to video.
S302：Down-sampled process is carried out to each frame picture, obtain it is down-sampled after video.
Specifically, can carry out down-sampled process to each frame picture of video, reduce each frame picture sample frequency and
Resolution, to reduce the complexity of follow-up calculating.Wherein, down-sampled processing procedure can be prior art, and mode has various,
This is repeated no more.
S303：Scene cutting is carried out to the video after down-sampled, the corresponding with each scene respectively of least one set is obtained
Picture group.
Because the information gap between different scenes is larger, can be processed with independent parallel completely in process, therefore can be with
Scene cutting is carried out to the video after down-sampled, is drawn so as to improving video disposed of in its entirety speed, and eliminating many scene mixed processing
The error for entering and unstability.For example, can will be down-sampled after video slicing be scenario A and scenario B, then obtain scenario A
The frame of video picture of frame of video picture and scenario B this two groups of picture groups.
S304：In every group of picture group, the position of the object in picture group with planar structure is obtained, and be defined as advertisement
Position.
Specifically, can be by the way that there is plane in every group of picture groups of technical limit spacing such as planar structure object detection, graphical analyses
The position of the object of structure.
Referring to Fig. 4, obtaining the process of the position of the object in picture group with planar structure can include：
S401：Every frame picture in picture group carries out visual signature point extraction.
Wherein, visual signature point can be have on the violent point of surrounding brightness change or image boundary curve in image
The point of enough deep cambers.
S402：According to the visual signature point for extracting, extracted per the perspective square in frame picture by default detection algorithm
Shape planar structure.
Due to most rectangular configuration object in video under normal circumstances and non-frontal is towards camera lens, there are various perspectives
Distortion of projection, therefore rectangular planar structure is had an X-rayed including the rectangular configuration after the rectangular configuration and perspective projection deformation of standard,
Such as body of wall, desktop, window etc..
In the perspective rectangular planar structure in extracting every frame picture, can be with reference to multi-view geometry theory and graphical analyses skill
Art (analyzes low-level image feature and superstructure, so as to extract with one typically using mathematical model and with reference to image processing techniquess
Fixed intelligent information) realized by default detection algorithm.Wherein, default detection algorithm can be existing image inspection
Any algorithm that can realize above-mentioned detection function that method of determining and calculating, or future are likely to occur.
S403：Perspective rectangular planar structure to extracting in different frame is singly answered information to calculate, and judges whether to meet single
Answer characteristic.
Specifically, three-dimensionalreconstruction (is mainly studied, i.e., with the method for geometry, by some width based on multi-view geometry theory
Two dimensional image is recovering three-dimensional body), if meet in video face of the same plane under different visual angles singly answering characteristic (from one
Plane is to the particular kind of relationship between the projection mapping of another plane), then visual signature point need to have scale invariability and illumination
Invariance, therefore can singly be answered information to calculate the perspective rectangular planar structure extracted in different frame, then using optimization
Method according to the visual signature point for extracting and it is calculated singly answer information solve scene in advantage homography matrix, so as to sentence
Whether the disconnected perspective rectangular planar structure meets singly is answered characteristic.
S404：It is true according to the position that the perspective rectangular planar structure extracted in different frame is located if satisfaction singly answers characteristic
Determine the position of the object with planar structure in picture group.
Specifically, characteristic is singly answered if met, the plan-position and direction that rectangular planar structure is had an X-rayed in scene can be obtained
Etc. information, then the position that the perspective rectangular planar structure extracted in different frame is located is checked and corrected, such as manually
Check and correct, to avoid misrecognition, be then defined as the position that the perspective rectangular planar structure is located having in picture group
Position of the object of planar structure in respective frame.
It should be noted that the present embodiment is with according to visual signature point object of the determination with planar structure for extracting
As a example by position, it is to be understood that other modes can also be adopted to determine the position of the object with planar structure.For example, by
(textural characteristics are that description a kind of important of image regards to need the strict textural characteristics for relying on plane in the extraction of visual signature point
Feel feature), in the case where texture feature information does not enrich, it is impossible to which sufficient amount of characteristic point is extracted in guarantee, can not be protected
The stability of card visual signature point, and in view of consider the rectangular planar structure in scene emphatically, can carry with reference to image analysis technology
More information is taken, to determine the position of the object with planar structure.In one embodiment of the invention, can first to not
Rim detection is carried out with two field picture, using Hough transformation the linear structure in image is extracted, the closing that acquisition straight line is constituted is more
Side shape region, and real rectangular planar region is positioned by analyzing the color and gray feature in closed polygon region, finally
Go out position and the directioin parameter of plane with reference to multi-view geometry Theoretical Calculation.
It is determined that after advertisement position, by the information Store of the advertisement position to data base, to select from advertisement position
One position.In one embodiment of the invention, first position includes position of the advertisement on each frame picture of video.By institute
After the information Store of advertisement position is stated in data base, when server receives ad-request, all can be according to playing
Query video data base, obtains the information of the advertisement position in the video, to select first position to carry out advertisement from advertisement position
Throw in.
S202：Video to obtaining is decoded.
S203：The ad content of acquisition is dissolved into into the first position of decoded video, and is played out so that be wide
Accuse on the object with planar structure of video.
Specifically, the video to be played can be decoded, obtains each frame picture of the video, then basis is inquired
Advertisement position first position information, ad content is dissolved into into the corresponding position of each frame picture.In the tool of the present invention
In body embodiment, method can be incorporated by existing, the mode such as render for example with 3D and merged and represented；Can also lead to
That crosses that future is likely to occur any incorporates the corresponding position that method is dissolved into each frame picture by the ad content.
The present embodiment is entered by obtaining the video to be played, and the information of acquisition video ads to the video to be played
Row processed offline obtains advertisement position, and by the information Store of advertisement position to data base, to choose suitable first position to wide
Announcement is thrown in, and by detection algorithm and hand inspection, correction ad placement is determined, placement position is more accurate.Process
Process is divided into processed offline and real-time processing, reduces computation complexity, improves treatment effeciency.In taking full advantage of video
Non-key flat site, improves advertisement putting efficiency, reduces the wait during video-see, does not affect video content
It is normal to present, improve Consumer's Experience.
In order to realize above-described embodiment, the present invention also proposes a kind of playing device of advertisement in video.
Fig. 5 be another embodiment of the present invention video in advertisement playing device structural representation.
As shown in figure 5, the device includes：Acquisition module 100 and incorporate module 200.
Specifically, acquisition module 100 is used to obtain the video to be played, and the information of acquisition advertisement, the information of advertisement
Including ad content and the information of first position, first position is advertisement position in video.Wherein, first position is wide
Accuse position on video, for example, advertisement in video per two field picture in position, can be specifically each field in every two field picture
Position that the object with planar structure is located in scape etc..Advertisement refers to the advertisement being inserted in video, and advertisement is presented on every frame
Form in image includes but is not limited to word, pattern etc..
In the embodiment of the present invention, can be obtained by off-line analysiss and the advertisement position for throwing in advertisement is suitable in the video to be played simultaneously
In storing data base, afterwards when needing to throw in advertisement in the video every time, you can the advertisement position letter in data base
Breath selects first position to carry out advertisement putting.Particular content will be described in detail in subsequent embodiment.
Module 200 is incorporated for ad content to be dissolved into into the first position of video, and played out so that advertisement position
On the object with planar structure of video.More specifically, incorporating module 200 can incorporate method by existing, for example
Mode is rendered etc. using 3D ad content is dissolved into into the first position of video, and played with video so that advertisement position
On the object with planar structure of video.
Specifically incorporate that method is also various, here will not enumerate.
Video and the information of advertisement that the present embodiment to be played by acquisition, by ad content first of video is dissolved into
Put place, and play out, advertisement can be dissolved in video, rather than in video playback gap showing advertisements, from without
Want to be waited during user's viewing video, Consumer's Experience can be lifted, also, the present embodiment is located at video by making advertisement
The object with planar structure on, the normal presentation of video content can not be affected, improve the viewing experience of user.
Fig. 6 be another embodiment of the present invention video in advertisement playing device structural representation.
As shown in fig. 6, the device includes：Acquisition module 100, incorporate module 200, process submodule 210, incorporate submodule
220th, processed offline module 300, decoding sub-module 310, down-sampled submodule 320, cutting submodule 330, acquisition submodule
340th, the first extraction unit 341, the second extraction unit 342, judging unit 343, determining unit 344 and memory module 400.Its
In, incorporating module 200 includes processing submodule 210 and incorporates submodule 220；Processed offline module 300 includes decoding sub-module
310th, down-sampled submodule 320, cutting submodule 330 and acquisition submodule 340；Acquisition submodule 340 includes that first extracts single
First 341, second extraction unit 342, judging unit 343 and determining unit 344.
Specifically, processed offline module 300 is used to carry out video processed offline acquisition advertisement position, and advertisement position is video
The position of the object with planar structure.Advertisement position is the position of the object with planar structure of video.Processed offline module
300 can find the fragment containing non-key flat site (such as body of wall) in video by processed offline, and the fragment is put down
Surface analysis and plane are tracked, and the azimuth information of plane are drawn, to obtain suitable advertisement position.
Further, processed offline module 300 can include：
Decoding sub-module 310 is used to decode video, obtains each frame picture.More specifically, decoding sub-module 310
Pretreatment, such as video decoding etc., to obtain each frame picture can be carried out to video.
Down-sampled submodule 320 be used for down-sampled process is carried out to each frame picture, obtain it is down-sampled after video.More
Body ground, down-sampled submodule 320 can carry out down-sampled process to each frame picture of video, reduce the sampling frequency of each frame picture
Rate and resolution, to reduce the complexity of follow-up calculating.Wherein, down-sampled processing procedure can be prior art, and mode has many
Kind, will not be described here.
Cutting submodule 330 is used to carry out scene cutting to the video after down-sampled, obtain least one set respectively with often
The corresponding picture group of individual scene.Due to the information gap between different scenes it is larger, completely can be with independent parallel in process at
Reason, therefore scene cutting can be carried out to the video after down-sampled by cutting submodule 330, so as to improve video disposed of in its entirety
Speed, and eliminate error and unstability that many scene mixed processing are introduced.For example, can will be down-sampled after video slicing be field
Scape A and scenario B, then obtain the frame of video picture and the frame of video picture of scenario B this two groups of picture groups of scenario A.
Acquisition submodule 340 is used in every group of picture group, obtains the position of the object in picture group with planar structure,
And it is defined as advertisement position.More specifically, acquisition submodule 340 can be obtained by technologies such as planar structure object detection, graphical analyses
Take the position of the object with planar structure in every group of picture group.
Further, acquisition submodule 340 can also include：
Every frame picture during first extraction unit 341 is used for picture group carries out visual signature point extraction.Wherein, vision is special
Levying can be a little the point with enough deep cambers on the violent point of surrounding brightness change in image or image boundary curve.
Second extraction unit 342 is used to, according to the visual signature point for extracting, extract and be put down per the perspective rectangle in frame picture
Face structure.Due to most rectangular configuration object in video under normal circumstances and non-frontal is towards camera lens, there are various perspectives
Distortion of projection, therefore rectangular planar structure is had an X-rayed including the rectangular configuration after the rectangular configuration and perspective projection deformation of standard,
Such as body of wall, desktop, window etc..
Second extraction unit 342, can be with reference to multi-view geometry in the perspective rectangular planar structure in extracting every frame picture
Theoretical and image analysis technology (analyzes low-level image feature and upper strata knot typically using mathematical model and with reference to image processing techniquess
Structure, so as to extract with certain intelligent information) realized by default detection algorithm.Wherein, default detection algorithm
It can be any algorithm that can realize above-mentioned detection function that existing image detection algorithm, or future are likely to occur.
Judging unit 343 is used for the perspective rectangular planar structure to extracting in different frame and is singly answered information to calculate, and judges
Whether meet and singly answer characteristic.More specifically, based on multi-view geometry it is theoretical (mainly study three-dimensionalreconstruction, i.e., with the method for geometry,
Recover three-dimensional body by some width two dimensional images), if meeting Dan Yingte in video face of the same plane under different visual angles
Property (from a plane to the particular kind of relationship the projection mapping of another plane), then visual signature point need to have Scale invariant
Property and illumination invariant, therefore can in different frame extract perspective rectangular planar structure singly be answered information to calculate, Ran Houli
Square is answered according to the visual signature point for extracting and the calculated advantage list singly answered in information solution scene with optimization method
Battle array, so as to judge whether the perspective rectangular planar structure meets characteristic is singly answered.
Determining unit 344 is used for when single characteristic is met, according to the perspective rectangular planar structure institute extracted in different frame
Position determine the position of the object in picture group with planar structure.If more specifically, meet singly answer characteristic, it is determined that single
Unit 344 can obtain the information such as the plan-position and direction of rectangular planar structure that have an X-rayed in scene, then to extraction in different frame
Perspective rectangular planar structure be located position checked and corrected, such as hand inspection and correction, with avoid misrecognition, then
The position that the perspective rectangular planar structure is located is defined as in picture group position of the object with planar structure in respective frame
Put.
It should be noted that the present embodiment is with according to visual signature point object of the determination with planar structure for extracting
As a example by position, it is to be understood that other modes can also be adopted to determine the position of the object with planar structure.For example, by
(textural characteristics are that description a kind of important of image regards to need the strict textural characteristics for relying on plane in the extraction of visual signature point
Feel feature), in the case where texture feature information does not enrich, it is impossible to which sufficient amount of characteristic point is extracted in guarantee, can not be protected
The stability of card visual signature point, and in view of consider the rectangular planar structure in scene emphatically, can carry with reference to image analysis technology
More information is taken, to determine the position of the object with planar structure.In one embodiment of the invention, can first to not
Rim detection is carried out with two field picture, using Hough transformation the linear structure in image is extracted, the closing that acquisition straight line is constituted is more
Side shape region, and real rectangular planar region is positioned by analyzing the color and gray feature in closed polygon region, finally
Go out position and the directioin parameter of plane with reference to multi-view geometry Theoretical Calculation.
It is determined that after advertisement position, memory module 400 by the information Store of the advertisement position to data base, so as to from advertisement
First position is selected in position.
In one embodiment of the invention, first position includes position of the advertisement on each frame picture of video.Will
After the information Store of the advertisement position is in data base, when server receives ad-request, all can be according to playing
Query video data base, obtain the information of the advertisement position in the video, so as to from advertisement position select first position carry out extensively
Accuse and throw in.
Further, incorporating module 200 includes：
Processing submodule 210 is used to decode video, obtains each frame picture.
Submodule 220 is incorporated for according to the information of first position, ad content being dissolved into into the corresponding of each frame picture
At position.Incorporate submodule 220 to be dissolved into ad content each according to the information of the first position of the advertisement position for inquiring
The corresponding position of frame picture.In a particular embodiment of the present invention, method can be incorporated by existing, for example with 3D wash with watercolours
The modes such as dye are merged and are represented；The following any method that incorporates being likely to occur can also be passed through to incorporate the ad content
To the corresponding position of each frame picture.
The present embodiment is entered by obtaining the video to be played, and the information of acquisition video ads to the video to be played
Row processed offline obtains advertisement position, and by the information Store of advertisement position to data base, to choose suitable first position to wide
Announcement is thrown in, and by detection algorithm and hand inspection, correction ad placement is determined, placement position is more accurate.Process
Process is divided into processed offline and real-time processing, reduces computation complexity, improves treatment effeciency.In taking full advantage of video
Non-key flat site, improves advertisement putting efficiency, reduces the wait during video-see, does not affect video content
It is normal to present, improve Consumer's Experience.
It should be noted that in describing the invention, term " first ", " second " etc. are not only used for describing purpose, and not
It is understood that to indicate or implying relative importance.Additionally, in describing the invention, unless otherwise stated, the implication of " multiple "
It is two or more.
In flow chart or here any process described otherwise above or method description are construed as, expression includes
It is one or more for realizing specific logical function or process the step of the module of code of executable instruction, fragment or portion
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussion suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, the software that multiple steps or method can in memory and by suitable instruction execution system be performed with storage
Or firmware is realizing.For example, if realized with hardware, and in another embodiment, can be with well known in the art
Any one of row technology or their combination are realizing：With for realizing the logic gates of logic function to data signal
Discrete logic, the special IC with suitable combinational logic gate circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method is carried
Suddenly the hardware that can be by program to instruct correlation is completed, and described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
Additionally, each functional unit in each embodiment of the invention can be integrated in a processing module, it is also possible to
It is that unit is individually physically present, it is also possible to which two or more units are integrated in a module.Above-mentioned integrated mould
Block both can be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.The integrated module is such as
Fruit is realized and as independent production marketing or when using using in the form of software function module, it is also possible to be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read only memory, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means to combine specific features, structure, material or spy that the embodiment or example are described
Point is contained at least one embodiment of the present invention or example.In this manual, to the schematic representation of above-mentioned term not
Necessarily refer to identical embodiment or example.And, the specific features of description, structure, material or feature can be any
One or more embodiments or example in combine in an appropriate manner.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (10)
1. in a kind of video advertisement player method, it is characterised in that include：
The video to be played, and the information of acquisition advertisement are obtained, the information of the advertisement includes：Ad content and first
The information put, the first position is position of the advertisement in the video；
Processed offline is carried out to the video and obtains advertisement position, the advertisement position is the video with non-key flat site
Position, wherein, it is described the video is carried out processed offline obtain advertisement position, including：The video is decoded, is obtained
Each frame picture；Down-sampled process is carried out to each frame picture, obtain it is down-sampled after video；To it is described it is down-sampled after
Video carries out scene cutting, obtains the picture group corresponding with each scene respectively of least one set；In every group of picture group, obtain
Position with non-key flat site in the picture group, and it is defined as advertisement position；
By in the information Store of the advertisement position to data base, to select the first position from the advertisement position；
The ad content is dissolved into into the first position of the video, and is played out so that the advertisement is located at described
On the position with non-key flat site of video.
2. method according to claim 1, it is characterised in that there is non-key flat region in the acquisition picture group
The position in domain, including：
Every frame picture in the picture group carries out visual signature point extraction；
According to the visual signature point for extracting, extract per the perspective rectangular planar structure in frame picture；
Perspective rectangular planar structure to extracting in different frame is singly answered information to calculate, and is judged whether to meet and is singly answered characteristic；
If satisfaction singly answers characteristic, the picture is determined according to the position that the perspective rectangular planar structure extracted in different frame is located
Position with non-key flat site in group.
3. method according to claim 2, it is characterised in that described according to the perspective rectangle plane extracted in different frame knot
The position that structure is located determines the position with non-key flat site in the picture group, including：
After the position that the perspective rectangular planar structure extracted in the different frame is located is checked and corrected, it is defined as described
There is position of the non-key flat site in respective frame in picture group.
4. the method according to any one of claims 1 to 3, it is characterised in that the first position exists including the advertisement
Position on each frame picture of the video, the first position that the ad content is dissolved into the video, bag
Include：
The video is decoded, each frame picture is obtained；
According to the information of the first position, the ad content is dissolved into into the corresponding position of each frame picture.
5. method according to claim 4, it is characterised in that described that the ad content is dissolved into into each frame picture
Corresponding position, including：
By the way of 3D is rendered, the ad content is dissolved into into the corresponding position of each frame picture.
6. in a kind of video advertisement playing device, it is characterised in that include：
Acquisition module, for obtaining the video to be played, and the information of acquisition advertisement, the information of the advertisement includes：Advertisement
Content and the information of first position, the first position is position of the advertisement in the video；
Processed offline module, for carrying out processed offline to the video advertisement position is obtained, and the advertisement position is the video
Position with non-key flat site, wherein, the processed offline module, including：Decoding sub-module, for the video
Decoded, obtained each frame picture；Down-sampled submodule, for carrying out down-sampled process to each frame picture, obtains
Video after down-sampled；Cutting submodule, for it is described it is down-sampled after video carry out scene cutting, obtain least one set
Picture group corresponding with each scene respectively；Acquisition submodule, in every group of picture group, obtaining and having in the picture group
The position of non-key flat site, and it is defined as advertisement position；
Memory module, for by the information Store of the advertisement position to data base, to select described from the advertisement position
First position；
Module is incorporated, for the ad content to be dissolved into into the first position of the video, and is played out so that described
Advertisement is located on the position with non-key flat site of the video.
7. device according to claim 6, it is characterised in that the acquisition submodule, including：
First extraction unit, for the every frame picture in the picture group visual signature point extraction is carried out；
Second extraction unit, for according to the visual signature point for extracting, extracting per the perspective rectangle plane in frame picture
Structure；
Judging unit, for singly being answered information to calculate the perspective rectangular planar structure extracted in different frame, judges whether full
Foot singly answers characteristic；
Determining unit, for when satisfaction singly answers characteristic, according to the position that the perspective rectangular planar structure extracted in different frame is located
Put and determine the position in the picture group with non-key flat site.
8. device according to claim 7, it is characterised in that the determining unit is additionally operable to extracting in the different frame
Perspective rectangular planar structure be located position checked and corrected after, be defined as in the picture group have it is non-key flat
Position of the region in respective frame.
9. the device according to any one of claim 6 to 8, it is characterised in that the first position exists including the advertisement
Position on each frame picture of the video, it is described to incorporate module, including：
Submodule is processed, for decoding to the video, each frame picture is obtained；
Submodule is incorporated, for according to the information of the first position, the ad content being dissolved into into the phase of each frame picture
Answer at position.
10. device according to claim 9, it is characterised in that described to incorporate the side that submodule is additionally operable to be rendered using 3D
Formula, by the ad content corresponding position of each frame picture is dissolved into.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410268322.4A CN104066003B (en) | 2014-06-16 | 2014-06-16 | Method and device for playing advertisement in video |
| PCT/CN2014/090573 WO2015192585A1 (en) | 2014-06-16 | 2014-11-07 | Method and apparatus for playing advertisement in video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410268322.4A CN104066003B (en) | 2014-06-16 | 2014-06-16 | Method and device for playing advertisement in video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104066003A CN104066003A (en) | 2014-09-24 |
| CN104066003B true CN104066003B (en) | 2017-05-10 |
Family
ID=51553497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410268322.4A Active CN104066003B (en) | 2014-06-16 | 2014-06-16 | Method and device for playing advertisement in video |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN104066003B (en) |
| WO (1) | WO2015192585A1 (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104066003B (en) * | 2014-06-16 | 2017-05-10 | 百度在线网络技术（北京）有限公司 | Method and device for playing advertisement in video |
| CN104754412A (en) * | 2015-03-04 | 2015-07-01 | 深圳市亮新光电显示技术有限公司 | Interactive type advertising method and interactive type advertising system |
| CN104735466B (en) * | 2015-03-31 | 2018-04-10 | 北京奇艺世纪科技有限公司 | The method and device of pictorial trademark in a kind of replacing video |
| CN104766229A (en) * | 2015-04-22 | 2015-07-08 | 合一信息技术（北京）有限公司 | Implantable advertisement putting method |
| US11272228B2 (en) | 2016-06-30 | 2022-03-08 | SnifferCat, Inc. | Systems and methods for dynamic stitching of advertisements in live stream content |
| US9872049B1 (en) * | 2016-06-30 | 2018-01-16 | SnifferCat, Inc. | Systems and methods for dynamic stitching of advertisements |
| CN107347166B (en) * | 2016-08-19 | 2020-03-03 | 北京市商汤科技开发有限公司 | Video image processing method and device and terminal equipment |
| CN106331745A (en) * | 2016-08-31 | 2017-01-11 | 杭州探索文化传媒有限公司 | Dynamic video advertisement implanting method |
| CN108040267A (en) * | 2017-12-07 | 2018-05-15 | 北京奇虎科技有限公司 | A kind of method and apparatus for merging recommendation in video |
| CN108122198A (en) * | 2017-12-07 | 2018-06-05 | 北京奇虎科技有限公司 | A kind of implementation method, device and server for merging recommendation in video |
| CN108040280A (en) * | 2017-12-08 | 2018-05-15 | 北京小米移动软件有限公司 | Content item display methods and device, storage medium |
| CN109523297B (en) * | 2018-10-17 | 2022-02-22 | 成都索贝数码科技股份有限公司 | Method for realizing virtual advertisement in sports match |
| CN111586440B (en) * | 2019-02-15 | 2022-03-11 | 腾讯科技（深圳）有限公司 | Multimedia resource delivery method, device, server and storage medium |
| 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 |
| 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 |
| CN114051166B (en) * | 2020-07-24 | 2024-03-29 | 北京达佳互联信息技术有限公司 | Method, device, electronic equipment and storage medium for implanting advertisement in video |
| CN113222662A (en) * | 2021-05-10 | 2021-08-06 | 刘川民 | Advertisement replacement or addition processing method, system and device |
| CN113516696B (en) * | 2021-06-02 | 2025-02-28 | 广州虎牙科技有限公司 | Video advertising embedding method, device, electronic device and storage medium |
| CN113438540A (en) * | 2021-06-24 | 2021-09-24 | 广州欢网科技有限责任公司 | Advertisement pre-loading playing method and device based on advertisement exposure rate |
| CN114900722B (en) * | 2022-05-06 | 2024-12-20 | 浙江工商大学 | Personalized advertising implantation method and system based on AR technology |
| CN119815123B (en) * | 2025-03-12 | 2025-06-17 | 太逗科技集团有限公司 | Intelligent advertising placement system and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101621636A (en) * | 2008-06-30 | 2010-01-06 | 北京大学 | Method and system for inserting and transforming advertisement sign based on visual attention module |
| CN102318358A (en) * | 2011-05-26 | 2012-01-11 | 华为技术有限公司 | Method, device and system for advertisement insertion |
| CN102404642A (en) * | 2011-12-06 | 2012-04-04 | 鄂文轩 | Advertisement publishing method and equipment in mobile terminal |
| CN103780944A (en) * | 2012-10-17 | 2014-05-07 | 三亚中兴软件有限责任公司 | Advertisement playing method, advertisement playing device, advertisement playing system and matching information establishing device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060059514A1 (en) * | 2004-09-10 | 2006-03-16 | Eric Hsiao | Method and apparatus for utilizing blank space on a high definition television screen |
| CN104066003B (en) * | 2014-06-16 | 2017-05-10 | 百度在线网络技术（北京）有限公司 | Method and device for playing advertisement in video |
-
2014
- 2014-06-16 CN CN201410268322.4A patent/CN104066003B/en active Active
- 2014-11-07 WO PCT/CN2014/090573 patent/WO2015192585A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101621636A (en) * | 2008-06-30 | 2010-01-06 | 北京大学 | Method and system for inserting and transforming advertisement sign based on visual attention module |
| CN102318358A (en) * | 2011-05-26 | 2012-01-11 | 华为技术有限公司 | Method, device and system for advertisement insertion |
| CN102404642A (en) * | 2011-12-06 | 2012-04-04 | 鄂文轩 | Advertisement publishing method and equipment in mobile terminal |
| CN103780944A (en) * | 2012-10-17 | 2014-05-07 | 三亚中兴软件有限责任公司 | Advertisement playing method, advertisement playing device, advertisement playing system and matching information establishing device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104066003A (en) | 2014-09-24 |
| WO2015192585A1 (en) | 2015-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104066003B (en) | Method and device for playing advertisement in video | |
| CN108322788B (en) | A method and device for displaying advertisements in live video | |
| US11482192B2 (en) | Automated object selection and placement for augmented reality | |
| CN103299610B (en) | For the method and apparatus of video insertion | |
| US20160050465A1 (en) | Dynamically targeted ad augmentation in video | |
| CN110300316B (en) | Method and device for implanting push information into video, electronic equipment and storage medium | |
| US11232636B2 (en) | Methods, devices, and systems for producing augmented reality | |
| JP6672305B2 (en) | Method and apparatus for generating extrapolated images based on object detection | |
| CN106060572A (en) | Video playing method and device | |
| CN103873741A (en) | Method and device for substituting area of interest in video | |
| EP2719187A1 (en) | System and method for identifying and altering images in a digital video | |
| CN110969673B (en) | Live broadcast face-changing interaction realization method, storage medium, equipment and system | |
| CN105531740A (en) | Expanding a digital representation of a physical plane | |
| US20240323457A1 (en) | System and Method for Analyzing Videos in Real-Time | |
| KR20190101620A (en) | Moving trick art implement method using augmented reality technology | |
| US10674184B2 (en) | Dynamic content rendering in media | |
| US10225585B2 (en) | Dynamic content placement in media | |
| CN114501127B (en) | Inserting digital content in multi-picture video | |
| KR102334403B1 (en) | Contents production apparatus inserting advertisement in animation, and control method thereof | |
| US20240404143A1 (en) | Systems and methods for dynamic content placement based on pixel count confidences in pre-existing content | |
| WO2022236842A1 (en) | Advertisement replacement or addition processing method, system and apparatus | |
| CN113836981B (en) | Data processing method, device, storage medium and computer equipment | |
| US10674207B1 (en) | Dynamic media placement in video feed | |
| CN113784152A (en) | Video processing method and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |