CN103226571A - Method and device for detecting repeatability of advertisement library - Google Patents
Method and device for detecting repeatability of advertisement library Download PDFInfo
- Publication number
- CN103226571A CN103226571A CN201310100320XA CN201310100320A CN103226571A CN 103226571 A CN103226571 A CN 103226571A CN 201310100320X A CN201310100320X A CN 201310100320XA CN 201310100320 A CN201310100320 A CN 201310100320A CN 103226571 A CN103226571 A CN 103226571A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- image
- detected
- camera lens
- coupling
- 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
Images
Abstract
The invention discloses a method and a device for detecting repeatability of an advertisement library. The method comprises the steps of conducting shot breakdown treatment on an advertisement to be detected, extracting an image characteristic of a key frame of each shot after the shot breakdown treatment, and judging whether the advertisement library stores the advertisement to be detected according to the extracted image characteristic and a preset characteristic library. According to the method and the device, the image characteristic of an advertisement video is extracted by taking the shots as units, and motion characteristics and integral color distribution characteristics of the shots are kept, so that the advertisements with the same shot and shot sequence can be detected, and particularly the advertisements with the same shot and different shot sequences can be prevented from being judged to be the same.
Description
Technical field
The present invention relates to field of video processing, more specifically, relate to a kind of advertisement base repeatability detection method and device.
Background technology
Along with the continuous development of video playback medium, video ads is also more and more abundanter, all can broadcast video ads in TV station, website, the application.
For video ads is edited and managed, can set up advertisement base usually.When setting up advertisement base, by manually with ad storage to advertisement base.
But, because the ad data amount in the advertisement base is huge, during human-edited's advertisement base, the problem that same advertisement repeats to put in storage often appears.Therefore, need badly and a kind ofly can judge the method that whether has stored same advertisement in the advertisement base.
Summary of the invention
In view of this, the purpose of the embodiment of the invention is to propose a kind of advertisement base repeatability detection method and device, can judge whether stored the advertisement identical with advertisement to be detected in the advertisement base.
In order to achieve the above object, the embodiment of the invention proposes a kind of advertisement base repeatability detection method, may further comprise the steps:
Story board is carried out in advertisement to be detected to be handled;
The key-frame extraction characteristics of image of each camera lens after respectively story board being handled;
According to characteristics of image that extracts and default feature database, judge whether stored advertisement to be detected in the advertisement base; Wherein, store the characteristics of image of the key frame of each camera lens of each advertisement in the advertisement base in the feature database.
It in the embodiment of the invention is the characteristics of image that the unit extracts advertisement video with the camera lens, with camera lens is a unit, the kinetic characteristic and the integral color distribution characteristics that can keep camera lens, and general key frame has only the space characteristics of image, therefore can detect all identical advertisement of camera lens and camera lens order, especially can avoid camera lens is identical but the different advertisement of camera lens order is judged as identical advertisement.
Preferred as technique scheme, according to characteristics of image that extracts and default feature database, judge that the step that whether has stored advertisement to be detected in the advertisement base comprises:
The characteristics of image of the characteristics of image coupling of in default feature database, searching and extracting;
Whether judgement all finds the characteristics of image of coupling for each characteristics of image of video to be detected;
When each characteristics of image for video to be detected all found the characteristics of image of corresponding coupling, whether the order of camera lens of characteristics of image the correspondence whether characteristics of image of judging coupling belongs to same advertisement and coupling was consistent with the order of the camera lens of advertisement to be detected;
When the characteristics of image of coupling belongs to the sequence consensus of order and the camera lens of advertisement to be detected of camera lens of characteristics of image correspondence of same advertisement and coupling, confirm to have stored advertisement to be detected in the advertisement base.
Preferred as technique scheme, the characteristics of image of the characteristics of image coupling of searching and extracting in default feature database comprises: the characteristics of image coding that extracts is generated index value; In feature database, search characteristics of image with described index value; Similarity between the characteristics of image that calculating finds and the characteristics of image of extraction; With the characteristics of image of the similarity between the characteristics of image that finds and extract greater than predetermined threshold value, as with the characteristics of image of the characteristics of image coupling of extracting.This programme has improved search efficiency.
Preferred as technique scheme, described method also comprises: when not storing advertisement to be detected in the advertisement base, with ad storage to be detected to advertisement base.This programme carries out storage operation automatically according to judged result.
Preferred as technique scheme, described method also comprises: do not store advertisement to be detected in advertisement base, and when comprising advertisement in the advertisement base in the advertisement to be detected, will be contained in the advertisement deletion of advertisement to be detected in the advertisement base.The ad storage to be detected that this programme has avoided comprising the advertisement in the advertisement base duplicates the situation of advertisement to the advertisement base.
The embodiment of the invention also proposes a kind of advertisement base repeatability pick-up unit, comprising:
The story board processing module is used for that story board is carried out in advertisement to be detected and handles;
Extract the characteristics of image module, the key-frame extraction characteristics of image of each camera lens after being used for respectively story board being handled;
Judge module is used for judging whether stored advertisement to be detected in the advertisement base according to characteristics of image that extracts and default feature database; Wherein, store the characteristics of image of the key frame of each camera lens of each advertisement in the advertisement base in the feature database.
Preferred as technique scheme, described judge module comprises:
Search the unit, the characteristics of image that the characteristics of image that is used for searching and extract at default feature database mates;
First judging unit is used to judge the characteristics of image that whether all finds coupling for each characteristics of image of video to be detected;
Second judging unit, be used for when each characteristics of image for video to be detected all finds the characteristics of image of corresponding coupling, whether the order of camera lens of characteristics of image the correspondence whether characteristics of image of judging coupling belongs to same advertisement and coupling is consistent with the order of the camera lens of advertisement to be detected;
Confirmation unit when being used for characteristics of image when coupling and belonging to the sequence consensus of order and the camera lens of advertisement to be detected of camera lens of characteristics of image correspondence of same advertisement and coupling, is confirmed to have stored advertisement to be detected in the advertisement base.
Preferred as technique scheme, the described unit of searching is used for:
The characteristics of image coding that extracts is generated index value;
In feature database, search characteristics of image with described index value;
Similarity between the characteristics of image that calculating finds and the characteristics of image of extraction;
With the characteristics of image of the similarity between the characteristics of image that finds and extract greater than predetermined threshold value, as with the characteristics of image of the characteristics of image coupling of extracting.
Preferred as technique scheme, described device also comprises:
Memory module is used for when advertisement base does not store advertisement to be detected, with ad storage to be detected to advertisement base.
Preferred as technique scheme, described device also comprises:
Removing module is used for not storing advertisement to be detected when advertisement base, and when comprising advertisement in the advertisement base in the advertisement to be detected, will be contained in the advertisement deletion of advertisement to be detected in the advertisement base.
The further feature of the embodiment of the invention and advantage will be set forth in the following description, and, partly from instructions, become apparent, perhaps understand by implementing the present invention.Purpose of the present invention and other advantages can realize and obtain by specifically noted structure in the instructions of being write, claims and accompanying drawing.
Below by drawings and Examples, the technical scheme of the embodiment of the invention is described in further detail.
Description of drawings
Accompanying drawing is used to provide the further understanding to the embodiment of the invention, and constitutes the part of instructions, is used from explanation the present invention with embodiments of the invention one, does not constitute the restriction to the embodiment of the invention.In the accompanying drawings:
Fig. 1 is the main method process flow diagram that the advertisement base repeatability in the embodiment of the invention detects;
Fig. 2 is the concrete grammar process flow diagram that the advertisement base repeatability in the embodiment of the invention detects;
Fig. 3 is the concrete grammar process flow diagram that the another kind of advertisement base repeatability in the embodiment of the invention detects;
Fig. 4 is the primary structure synoptic diagram of the advertisement base repeatability pick-up unit in the embodiment of the invention
Fig. 5 is the concrete structure synoptic diagram of the advertisement base repeatability pick-up unit in the embodiment of the invention.
Embodiment
Below in conjunction with accompanying drawing the preferred embodiments of the present invention are described, should be appreciated that preferred embodiment described herein only is used for the description and interpretation embodiment of the invention, and be not used in the qualification embodiment of the invention.
Be illustrated in figure 1 as the main method flow process that the advertisement base repeatability in the preferred embodiment of the present invention detects, comprise:
Step S101: story board is carried out in advertisement to be detected handle.
Step S102: the key-frame extraction characteristics of image of each camera lens after respectively story board being handled.
Step S103:, judge whether stored advertisement to be detected in the advertisement base according to characteristics of image that extracts and default feature database; Wherein, store the characteristics of image of the key frame of each camera lens of each advertisement in the advertisement base in the feature database.
Wherein, store advertisement to be detected in the advertisement base and be meant and have such advertisement in the advertisement base: identical with advertisement to be detected, perhaps comprise and the identical fragment of advertisement to be detected.
It in the embodiment of the invention is the characteristics of image that the unit extracts advertisement video with the camera lens, with camera lens is a unit, the kinetic characteristic and the integral color distribution characteristics that can keep camera lens, and general key frame has only the space characteristics of image, therefore can detect all identical advertisement of camera lens and camera lens order, especially can avoid camera lens is identical but the different advertisement of camera lens order is judged as identical advertisement.
Below by two exemplary embodiments the repeatability of the advertisement base in embodiment of the invention detection method is elaborated.
Be illustrated in figure 2 as the specific embodiment of advertisement base repeatability detection method in the embodiment of the invention, particularly, may further comprise the steps:
Step S201: set up feature database in advance.
Store the characteristics of image of the key frame of each camera lens of each advertisement in the advertisement base in the feature database.
At first the advertisement in the advertisement base is carried out story board and handled, extract the key frame of each camera lens then, the characteristics of image of key-frame extraction characteristics of image as this camera lens.Extraction method of key frame commonly used has pair video every frame sampling, based on frame-to-frame differences extraction key frame.The feature of extracting can be the color, edge, texture, unique point, fingerprint of image etc.
In the present embodiment, preferably, short-term information with lens unit is expressed image (Temporally Informative Representative Image, TIRI) as the key frame of each camera lens, and the fingerprint of extraction key frame, with the characteristics of image of this fingerprint, set up feature database with this as key frame.
Preferably, because ad data is bigger, therefore can also set up concordance list to feature database.Index is meant the catalogue that can directly find certain part from whole content.When setting up index, consider that characteristics of image mostly is high dimension vector, at first the characteristics of image vector is quantized, produce the data (being generally an integer) of low-dimensional, the method for quantification has the method for hash algorithm and digital finger-print etc.; Numerical value after the quantification is index value.Characteristics of image is arranged (the characteristics of image row who promptly has same index value is delegation or row) according to index value, so just formed concordance list.In addition, with itself and corresponding camera lens ID and the related preservation of advertisement ID, therefore, can know from feature database: the characteristics of image of storage is the characteristics of image of which camera lens of which advertisement during the memory image feature.For example, adopt following structure during the memory image feature:
Wherein video_id is the advertisement numbering, and shot_id is a camera lens numbering (serial number of camera lens in advertisement), and fingerprint is a characteristics of image.
Step S202: story board is carried out in advertisement to be detected handle.
Shot Detection is carried out in advertisement to be detected, make story board and handle.Camera lens is a framing sequence, and the picture frame in the same camera lens is more approaching, and feature is constant substantially.If more violent changing features takes place between the consecutive frame, just thinks the camera lens switching has taken place.At present lens detection method mainly contains based on histogram, template matches, based on the method for statistics etc.Advertisement to be detected is made up of one or more camera lenses, and it is the video segment of unit that advertisement to be detected is divided into the camera lens, and adds label according to their orders in advertisement to be detected for them, for example is followed successively by 1,2,3...n.Therefore, advertisement to be detected shot sequence [S1, S2 ... Sn] represent.With the camera lens is the unit, can keep the kinetic characteristic and the integral color distribution characteristics of camera lens, have space characteristics and temporal characteristics, and general key frame has only the space characteristics of image.
Step S203: the key frame of determining each camera lens.
In the present embodiment, respectively with the TIRI of each camera lens key frame as each camera lens.The advantage of TIRI is time and the space characteristic that has comprised video, by calculating the weighted mean value of the image in the camera lens, obtains the image that a width of cloth merges, and it can not only reflect the color distribution information of camera lens, has also reflected the kinetic characteristic of camera lens.
Make l
M, n, kBe the k two field picture (m, the n) grey scale pixel value of position, the pixel value of TIRI image can be by following equation expressions:
Wherein, N is a number of image frames that camera lens comprises, ω
kBe weighting function.Can adopt different methods of weighting to obtain the TIRI image, as constant weighting, linear weighted function and exponential weighting etc.Selection index weighting function ω in the present embodiment
k=γ
k, γ=1.1.
Step S204: respectively to the key-frame extraction characteristics of image of each camera lens.
In the present embodiment, the TIRI image to camera lens extracts the characteristics of image of finger image as camera lens.
At first, the TIRI image is divided into the M*N piece, the size of each piece is 2w*2w (window size of w for being provided with), calculates the DCT coefficient of the horizontal direction and the vertical direction of each piece.
Horizontal direction DCT coefficient is: β
I, j=l
TB
I, jV;
Vertical direction DCT coefficient is: a
I, j=v
TB
I, jL;
Wherein l is the unit vector, B
I, jBe image block, v is the cosine vector:
v＝[cos(0.5π/2w)，cos(1.5π/2w)，...cos(π-0.5π/2w)]
T
Secondly, the above M*N*2 that an obtains coefficient is formed a vector f in order, f is quantized.Quantization method has a variety of, for example can be the mean value or the intermediate value of amount of orientation.The mean value a of amount of orientation in the present embodiment, with each dimension of f and a relatively, obtain one by 0, the 1 two-value vector f of forming ', be the fingerprint characteristic of image:
Step S205: the characteristics of image that each characteristics of image mated of in default feature database, searching extraction respectively.
Can in feature database, search the characteristics of image of coupling by the method for calculating similarity.
Described in step 201, preferred, the characteristics of image in the feature database is with the form storage of concordance list.Therefore, accordingly, in this step, at first the characteristics of image with advertisement to be detected is encoded to an integer as index value (should guarantee to adopt same coding method with the concordance list of feature database), in concordance list, search the characteristics of image of this index value correspondence then, carry out similar calculating to the characteristics of image that each finds, and index entry that will be the most similar is as matching result with same index value.
Because fingerprint characteristic is formed by a series of 0 and 1, therefore can adopt Hamming distance to calculate similarity.The length of supposing the vector of fingerprint characteristic is N, the identical number M of value on two vectorial same positions, then the similarity ratio of two vectors
As s during greater than predetermined threshold value T, think two fingerprint characteristics couplings, T gets 0.9 in the present embodiment.
Step S206: judge the characteristics of image that whether all finds coupling for each characteristics of image of video to be detected, if, execution in step S207, if not, execution in step S210.
Step S207: whether the characteristics of image of judging coupling belongs to same advertisement, if, execution in step S208, if not, execution in step S210.
The characteristics of image that finds from feature database is:
Obtain advertisement numbering under this characteristics of image by reading wherein video_id, the characteristics of image of same advertisement has identical advertisement numbering.
Step S208: judge coupling the characteristics of image correspondence camera lens order whether with the camera lens sequence consensus of advertisement to be detected, if, execution in step S209, if not, execution in step S210.
According to characteristics of image
In shot_id can determine the pairing camera lens of each characteristics of image numbering.Can be with the characteristics of image of coupling according to the series arrangement of the characteristics of image of the advertisement to be detected of its coupling, if the camera lens of the characteristics of image after arranging is numbered when increasing progressively continuously, then represent continuously the pairing camera lens order of characteristics of image of coupling and the camera lens sequence consensus of advertisement to be detected.
For example, when advertisement to be detected is divided into 3 camera lenses, if the camera lens of the characteristics of image correspondence after arranging is numbered shot_3, shot_4, shot_5, then with the camera lens sequence consensus of advertisement to be detected, the fragment that shot_3, the shot_4 in advertisement promptly to be detected and this advertisement, shot_5 form is in full accord; If the camera lens of the characteristics of image correspondence after arranging is numbered shot_3, shot_4, shot_6, then and the camera lens of advertisement to be detected order inconsistent (having more a camera lens between latter two camera lens than advertisement to be detected); If the camera lens of the characteristics of image correspondence after arranging is numbered shot_3, shot_5, shot_4, then with the camera lens order inconsistent (sequencing of latter two camera lens is different) of advertisement to be detected.
Step S209: confirm to have stored advertisement to be detected in the advertisement base.
Step S210: confirm not store advertisement to be detected in the advertisement base.
By the embodiment of the invention, can detect and whether exist in the advertisement base and the identical advertisement of advertisement to be detected, perhaps whether there is the advertisement that comprises with the identical fragment of advertisement to be detected.
Preferably, can also carry out following steps according to above-mentioned affirmation result:
When in confirming advertisement base, not storing advertisement to be detected, with ad storage to be detected to advertisement base.
In another embodiment of the present invention, also consider following situation: in advertisement base, do not store advertisement to be detected, but comprise the advertisement in the advertisement base in the advertisement to be detected.As shown in Figure 3, this embodiment may further comprise the steps:
Step S301: set up feature database in advance.
Step S302: story board is carried out in advertisement to be detected handle.
Step S303: the key frame of determining each camera lens.
Step S304: respectively to the key-frame extraction characteristics of image of each camera lens.
Step S305: the characteristics of image that each characteristics of image mated of in default feature database, searching extraction respectively.
Step S306: judge the characteristics of image that whether all finds coupling for each characteristics of image of video to be detected, if, execution in step S307, if not, execution in step S309.
Step S307: whether the characteristics of image of judging coupling belongs to same advertisement, if, execution in step S308, if not, execution in step S309.
Step S308: judge coupling the characteristics of image correspondence camera lens order whether with the camera lens sequence consensus of advertisement to be detected, if, execution in step S313, if not, execution in step S314.
Putting in order of the characteristics of image of coupling is (corresponding according to matching relationship) with the camera lens sequence consensus of advertisement to be detected.Obtain the order of camera lens of the characteristics of image correspondence of coupling, judge coupling the characteristics of image correspondence camera lens order whether with the camera lens sequence consensus of advertisement to be detected.
Step S309: the characteristics of image of coupling is divided by affiliated advertisement.
Step S310: judge whether the characteristics of image after dividing is all images feature of advertisement under it, if, execution in step S311, if not, execution in step S314.
Step S311: whether the order of judging the pairing camera lens of characteristics of image after dividing increases progressively continuously, if, execution in step S312, if not, execution in step S314.
Step S312: ad storage to be detected to advertisement base, and is deleted the advertisement A in the advertisement base.
Step S313: not with ad storage to be detected to advertisement base.
Step S314: with ad storage to be detected to advertisement base.
Present embodiment can be with ad storage to be detected to advertisement base the time, will be contained in the advertisement deletion of advertisement to be detected in the advertisement base, avoids existing in the advertisement base advertisement that repeats.
Be shown advertisement base repeatability pick-up unit in the embodiment of the invention as Fig. 4, comprise:
Story board processing module 401 is used for that story board is carried out in advertisement to be detected and handles;
Extract characteristics of image module 402, the key-frame extraction characteristics of image of each camera lens after being used for respectively story board being handled;
Preferably, judge module 403 comprises:
Search the unit, the characteristics of image that the characteristics of image that is used for searching and extract at default feature database mates;
First judging unit is used to judge the characteristics of image that whether all finds coupling for each characteristics of image of video to be detected;
Second judging unit, be used for when each characteristics of image for video to be detected all finds the characteristics of image of corresponding coupling, whether the order of camera lens of characteristics of image the correspondence whether characteristics of image of judging coupling belongs to same advertisement and coupling is consistent with the order of the camera lens of advertisement to be detected;
Confirmation unit when being used for characteristics of image when coupling and belonging to the sequence consensus of order and the camera lens of advertisement to be detected of camera lens of characteristics of image correspondence of same advertisement and coupling, is confirmed to have stored advertisement to be detected in the advertisement base.
Preferably, searching the unit is used for:
The characteristics of image coding that extracts is generated index value;
In feature database, search characteristics of image with described index value;
Similarity between the characteristics of image that calculating finds and the characteristics of image of extraction;
With the characteristics of image of the similarity between the characteristics of image that finds and extract greater than predetermined threshold value, as with the characteristics of image of the characteristics of image coupling of extracting.
Preferably, as shown in Figure 5, described device also comprises:
Preferably, as shown in Figure 5, described device also comprises:
Removing module 405 is used for not storing advertisement to be detected when advertisement base, and when comprising advertisement in the advertisement base in the advertisement to be detected, will be contained in the advertisement deletion of advertisement to be detected in the advertisement base.
Those skilled in the art should understand that embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt complete hardware embodiment, complete software implementation example or in conjunction with the form of the embodiment of software and hardware aspect.And the present invention can adopt the form that goes up the computer program of implementing in one or more computer-usable storage medium (including but not limited to magnetic disk memory and optical memory etc.) that wherein include computer usable program code.
The present invention is that reference is described according to the process flow diagram and/or the block scheme of method, equipment (system) and the computer program of the embodiment of the invention.Should understand can be by the flow process in each flow process in computer program instructions realization flow figure and/or the block scheme and/or square frame and process flow diagram and/or the block scheme and/or the combination of square frame.Can provide these computer program instructions to the processor of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing device to produce a machine, make the instruction of carrying out by the processor of computing machine or other programmable data processing device produce to be used for the device of the function that is implemented in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame appointments.
These computer program instructions also can be stored in energy vectoring computer or the computer-readable memory of other programmable data processing device with ad hoc fashion work, make the instruction that is stored in this computer-readable memory produce the manufacture that comprises command device, this command device is implemented in the function of appointment in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame.
These computer program instructions also can be loaded on computing machine or other programmable data processing device, make on computing machine or other programmable devices and to carry out the sequence of operations step producing computer implemented processing, thereby the instruction of carrying out on computing machine or other programmable devices is provided for being implemented in the step of the function of appointment in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame.
Obviously, those skilled in the art can carry out various changes and modification to the present invention and not break away from the spirit and scope of the present invention.Like this, if of the present invention these are revised and modification belongs within the scope of claim of the present invention and equivalent technologies thereof, then the present invention also is intended to comprise these changes and modification interior.
Claims (10)
1. an advertisement base repeatability detection method is characterized in that, may further comprise the steps:
Story board is carried out in advertisement to be detected to be handled;
The key-frame extraction characteristics of image of each camera lens after respectively story board being handled;
According to characteristics of image that extracts and default feature database, judge whether stored advertisement to be detected in the advertisement base; Wherein, store the characteristics of image of the key frame of each camera lens of each advertisement in the advertisement base in the feature database.
2. method according to claim 1 is characterized in that, according to characteristics of image that extracts and default feature database, judges that the step that whether has stored advertisement to be detected in the advertisement base comprises:
The characteristics of image of the characteristics of image coupling of in default feature database, searching and extracting;
Whether judgement all finds the characteristics of image of coupling for each characteristics of image of video to be detected;
When each characteristics of image for video to be detected all finds the characteristics of image of corresponding coupling, whether the characteristics of image of judging coupling belongs to same advertisement, and whether the order of the camera lens of the characteristics of image correspondence of coupling is consistent with the order of the camera lens of advertisement to be detected;
When the characteristics of image of coupling belongs to the sequence consensus of order and the camera lens of advertisement to be detected of camera lens of characteristics of image correspondence of same advertisement and coupling, confirm to have stored advertisement to be detected in the advertisement base.
3. method according to claim 2 is characterized in that, the step of the characteristics of image of the characteristics of image coupling of searching and extracting in default feature database comprises:
The characteristics of image coding that extracts is generated index value;
In feature database, search characteristics of image with described index value;
Similarity between the characteristics of image that calculating finds and the characteristics of image of extraction;
With the characteristics of image of the similarity between the characteristics of image that finds and extract greater than predetermined threshold value, as with the characteristics of image of the characteristics of image coupling of extracting.
4. method according to claim 1 is characterized in that, described method also comprises:
When not storing advertisement to be detected in the advertisement base, with ad storage to be detected to advertisement base.
5. method according to claim 4 is characterized in that, described method also comprises:
In advertisement base, do not store advertisement to be detected, and when comprising advertisement in the advertisement base in the advertisement to be detected, will be contained in the advertisement deletion of advertisement to be detected in the advertisement base.
6. an advertisement base repeatability pick-up unit is characterized in that, comprising:
The story board processing module is used for that story board is carried out in advertisement to be detected and handles;
Extract the characteristics of image module, the key-frame extraction characteristics of image of each camera lens after being used for respectively story board being handled;
Judge module is used for judging whether stored advertisement to be detected in the advertisement base according to characteristics of image that extracts and default feature database; Wherein, store the characteristics of image of the key frame of each camera lens of each advertisement in the advertisement base in the feature database.
7. device according to claim 6 is characterized in that, described judge module comprises:
Search the unit, the characteristics of image that the characteristics of image that is used for searching and extract at default feature database mates;
First judging unit is used to judge the characteristics of image that whether all finds coupling for each characteristics of image of video to be detected;
Second judging unit, be used for when each characteristics of image for video to be detected all finds the characteristics of image of corresponding coupling, whether the order of camera lens of characteristics of image the correspondence whether characteristics of image of judging coupling belongs to same advertisement and coupling is consistent with the order of the camera lens of advertisement to be detected;
Confirmation unit when being used for characteristics of image when coupling and belonging to the sequence consensus of order and the camera lens of advertisement to be detected of camera lens of characteristics of image correspondence of same advertisement and coupling, is confirmed to have stored advertisement to be detected in the advertisement base.
8. device according to claim 7 is characterized in that, the described unit of searching is used for:
The characteristics of image coding that extracts is generated index value;
In feature database, search characteristics of image with described index value;
Similarity between the characteristics of image that calculating finds and the characteristics of image of extraction;
With the characteristics of image of the similarity between the characteristics of image that finds and extract greater than predetermined threshold value, as with the characteristics of image of the characteristics of image coupling of extracting.
9. device according to claim 6 is characterized in that, described device also comprises:
Memory module is used for when advertisement base does not store advertisement to be detected, with ad storage to be detected to advertisement base.
10. device according to claim 9 is characterized in that, described device also comprises:
Removing module is used for not storing advertisement to be detected when advertisement base, and when comprising advertisement in the advertisement base in the advertisement to be detected, will be contained in the advertisement deletion of advertisement to be detected in the advertisement base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310100320XA CN103226571A (en) | 2013-03-26 | 2013-03-26 | Method and device for detecting repeatability of advertisement library |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310100320XA CN103226571A (en) | 2013-03-26 | 2013-03-26 | Method and device for detecting repeatability of advertisement library |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103226571A true CN103226571A (en) | 2013-07-31 |
Family
ID=48837017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310100320XA Pending CN103226571A (en) | 2013-03-26 | 2013-03-26 | Method and device for detecting repeatability of advertisement library |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103226571A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104185060A (en) * | 2014-02-26 | 2014-12-03 | 无锡天脉聚源传媒科技有限公司 | Video de-duplication method and device |
| CN105407353A (en) * | 2014-09-11 | 2016-03-16 | 腾讯科技（深圳）有限公司 | Image compression method and apparatus |
| CN106231356A (en) * | 2016-08-17 | 2016-12-14 | 腾讯科技（深圳）有限公司 | The treating method and apparatus of video |
| CN107133264A (en) * | 2017-03-31 | 2017-09-05 | 北京奇艺世纪科技有限公司 | The detection method and device of camera lens and the update method of advertising database and device |
| CN107169004A (en) * | 2017-03-31 | 2017-09-15 | 北京奇艺世纪科技有限公司 | A kind of property data base update method and device |
| CN107194277A (en) * | 2017-05-15 | 2017-09-22 | 华中科技大学 | Towards the fine grain authority management method and system of Android advertisement base |
| CN108470290A (en) * | 2018-03-28 | 2018-08-31 | 百度在线网络技术（北京）有限公司 | Commercial detection method, device and server |
| CN110019964A (en) * | 2018-01-02 | 2019-07-16 | 北京小度互娱科技有限公司 | Video duplicate removal method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101162470A (en) * | 2007-11-16 | 2008-04-16 | 北京交通大学 | Video frequency advertisement recognition method based on layered matching |
| US20080126191A1 (en) * | 2006-11-08 | 2008-05-29 | Richard Schiavi | System and method for tagging, searching for, and presenting items contained within video media assets |
| US8079054B1 (en) * | 2008-04-14 | 2011-12-13 | Adobe Systems Incorporated | Location for secondary content based on data differential |
| CN102890778A (en) * | 2011-07-21 | 2013-01-23 | 北京新岸线网络技术有限公司 | Content-based video detection method and device |
-
2013
- 2013-03-26 CN CN201310100320XA patent/CN103226571A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080126191A1 (en) * | 2006-11-08 | 2008-05-29 | Richard Schiavi | System and method for tagging, searching for, and presenting items contained within video media assets |
| CN101162470A (en) * | 2007-11-16 | 2008-04-16 | 北京交通大学 | Video frequency advertisement recognition method based on layered matching |
| US8079054B1 (en) * | 2008-04-14 | 2011-12-13 | Adobe Systems Incorporated | Location for secondary content based on data differential |
| CN102890778A (en) * | 2011-07-21 | 2013-01-23 | 北京新岸线网络技术有限公司 | Content-based video detection method and device |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104185060A (en) * | 2014-02-26 | 2014-12-03 | 无锡天脉聚源传媒科技有限公司 | Video de-duplication method and device |
| CN104185060B (en) * | 2014-02-26 | 2017-07-07 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device of video re-scheduling |
| CN105407353A (en) * | 2014-09-11 | 2016-03-16 | 腾讯科技（深圳）有限公司 | Image compression method and apparatus |
| CN106231356A (en) * | 2016-08-17 | 2016-12-14 | 腾讯科技（深圳）有限公司 | The treating method and apparatus of video |
| CN106231356B (en) * | 2016-08-17 | 2019-01-08 | 腾讯科技（深圳）有限公司 | The treating method and apparatus of video |
| CN107133264A (en) * | 2017-03-31 | 2017-09-05 | 北京奇艺世纪科技有限公司 | The detection method and device of camera lens and the update method of advertising database and device |
| CN107169004A (en) * | 2017-03-31 | 2017-09-15 | 北京奇艺世纪科技有限公司 | A kind of property data base update method and device |
| CN107194277A (en) * | 2017-05-15 | 2017-09-22 | 华中科技大学 | Towards the fine grain authority management method and system of Android advertisement base |
| CN107194277B (en) * | 2017-05-15 | 2019-08-13 | 华中科技大学 | Fine grain authority management method and system towards Android advertisement base |
| CN110019964A (en) * | 2018-01-02 | 2019-07-16 | 北京小度互娱科技有限公司 | Video duplicate removal method and device |
| CN108470290A (en) * | 2018-03-28 | 2018-08-31 | 百度在线网络技术（北京）有限公司 | Commercial detection method, device and server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103226571A (en) | Method and device for detecting repeatability of advertisement library | |
| CN108769731B (en) | Method and device for detecting target video clip in video and electronic equipment | |
| CN108353208B (en) | Optimizing media fingerprint retention to improve system resource utilization | |
| Amel et al. | Video shot boundary detection using motion activity descriptor | |
| Zhang et al. | Efficient video frame insertion and deletion detection based on inconsistency of correlations between local binary pattern coded frames | |
| US20100284670A1 (en) | Method, system, and apparatus for extracting video abstract | |
| WO2010084739A1 (en) | Video identifier extracting device | |
| US9418297B2 (en) | Detecting video copies | |
| KR20180031024A (en) | Future audience prediction of video segments to optimize system resource utilization | |
| CN103235956A (en) | Method and device for detecting advertisements | |
| US20110249904A1 (en) | Face clustering device, face clustering method, and program | |
| CN112395457B (en) | Video to-be-retrieved positioning method applied to video copyright protection | |
| US8345742B2 (en) | Method of processing moving picture and apparatus thereof | |
| CN101872415A (en) | Video copying detection method being suitable for IPTV | |
| US20220172476A1 (en) | Video similarity detection method, apparatus, and device | |
| CN105657514A (en) | Method and apparatus for playing video key information on mobile device browser | |
| CN103984778A (en) | Video retrieval method and video retrieval system | |
| CN103020138A (en) | Method and device for video retrieval | |
| CN110717070A (en) | Video compression method and system for indoor monitoring scene | |
| CN104410867A (en) | Improved video shot detection method | |
| JP5644505B2 (en) | Collation weight information extraction device | |
| JP2010186307A (en) | Moving image content identification apparatus and moving image content identification method | |
| CN114708287A (en) | Shot boundary detection method, device and storage medium | |
| CN103093213A (en) | Video file classification method and terminal | |
| Vega et al. | A robust video identification framework using perceptual image hashing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130731 |