CN105631428A - Comparison and identification method and apparatus for videos - Google Patents
Comparison and identification method and apparatus for videos Download PDFInfo
- Publication number
- CN105631428A CN105631428A CN201511020455.0A CN201511020455A CN105631428A CN 105631428 A CN105631428 A CN 105631428A CN 201511020455 A CN201511020455 A CN 201511020455A CN 105631428 A CN105631428 A CN 105631428A
- Authority
- CN
- China
- Prior art keywords
- camera lens
- redaction
- video
- master
- classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/48—Matching video sequences
Abstract
The invention provides a comparison and identification method and apparatus for videos. The method and apparatus are used for identifying a part, modified relative to an original-version video, of a new-version video. The method comprises: an original-version video is divided into a plurality of original-version lens units and a new-version video is divided into a plurality of new-version lens units; each new-version lens unit is compared with each original-version lens unit to obtain a plurality of comparison results; each new-version lens unit is classified based on the comparison results of the new-version lens unit; and on the basis of the classification results, the parts, modified relative to the original-version video, of the new-version video are identified.
Description
Technical field
The present invention relates to multimedia technology field, particularly relate to a kind of video comparison discrimination method and device, for redaction video is compared discriminating relative to the amendment of this video of master.
Background technology
Flourish along with China's media business, video frequency program (such as film, TV play) is created quantity and is presented the situation increased year by year. For ensureing the correct guidance of video frequency program, prosperity video frequency program is created, and promotes the sound development of video frequency program industry, examines video program content quickly and accurately, become an important process function of relevant department of SARFT(The State Administration of Radio and Television).
Tradition manually cannot meet the needs of video program content examination by the mode of examining of DVD laser disc machine replay browsing. This kind examines mode not only inefficiency, and existence manually causes, because eye strain or spirit are concentrated, the generation leaking careful phenomenon, especially when last revision again submits examination to after film-maker revises, traditional review mode be amendment after video frequency program again browse from the beginning to the end and examine one time, so circulation, efficiency is extremely low, wastes time and energy.
In order to adapt to the needs of video program content examination under the new situation, intelligentized video frequency program must be adopted to examine method, build a set of video frequency program and examine system fast, thus conscientiously improve video program content examination ability, promote video program content examination level further, for the examination supervision of video program content provides stronger technical support and guarantee.
Summary of the invention
(1) technical problem solved
It is an object of the present invention to provide a kind of video comparison discrimination method and device, redaction video can be compared discriminating relative to the amendment of this video of master, it is to increase video examine efficiency.
(2) technical scheme
The present invention provides a kind of video comparison discrimination method, and for being compared discriminating relative to the amendment of this video of master by redaction video, method comprises:
S1, is divided at least one this camera lens of master by this video of master, and redaction video is divided at least one redaction camera lens;
S2, for each redaction camera lens, compares it with each this camera lens of master respectively, obtains at least one comparison result;
S3, for each redaction camera lens, classifies to this redaction camera lens according to the comparison result of this redaction camera lens, is differentiated relative to the amendment of this video of master by redaction video according to this classification results.
The present invention also provides a kind of video identification device, and for being differentiated relative to the amendment of this video of master by redaction video, device comprises:
Camera lens divides module, this video of master is divided at least one this camera lens of master, redaction video is divided at least one redaction camera lens;
Camera lens comparing module, for each redaction camera lens, compares it with each this camera lens of master respectively, obtains at least one comparison result;
Shot classification module, for each redaction camera lens, classifies to this redaction camera lens according to the comparison result of this redaction camera lens, is differentiated relative to the amendment of this video of master by redaction video according to this classification results.
(3) useful effect
The present invention by redaction video relative to the amendment of this video of master compare differentiate after, when examining redaction video, just can complete to examine work without the need to browsing all videos content, only need to carry out examining for emphasis camera lenses such as some " newly-increased camera lens ", " amendment camera lenses " and " not deleting camera lens ", thus significantly downscaled video examines labour intensity and the workload of personnel, it is provided that video examine efficiency.
Accompanying drawing explanation
Fig. 1 is the schema of the video discrimination method that the embodiment of the present invention provides.
Fig. 2 is the schema that in the embodiment of the present invention, camera lens divides.
Fig. 3 is the structural representation of the video identification device that the embodiment of the present invention provides.
Embodiment
The present invention provides a kind of video comparison discrimination method and device, for redaction video is compared discriminating relative to the amendment of this video of master, first this video of master is divided into multiple this camera lens of master by method, and redaction video is divided into multiple redaction camera lens, then for each redaction camera lens, it is compared with each this camera lens of master respectively, obtain multiple comparison result, last for each redaction camera lens, this redaction camera lens is classified by the comparison result according to this redaction camera lens, according to this classification results, redaction video is differentiated relative to the amendment of this video of master.
According to one embodiment of the present invention, video comparison discrimination method comprises:
S1, this video of master is divided at least one this camera lens of master, redaction video is divided at least one redaction camera lens, examine in process at video, normally in units of camera lens, therefore present method first respectively video for two different editions carry out camera lens cutting, to form video unit one by one.
S2, for each redaction camera lens, compares it with each this camera lens of master respectively, obtains one or more comparison result.
S3, for each redaction camera lens, classifies to this redaction camera lens according to the comparison result of this redaction camera lens, is differentiated relative to the amendment of this video of master by redaction video according to this classification results.
According to one embodiment of the present invention, camera lens refers to by the continuous pictures of same frame pick up camera shooting, according to transient mode between camera lens, camera lens can be divided into shearing lens and gradual shot. In step sl, first the color histogram figure characteristic sum UniformLBP feature of this video of master and redaction video is extracted respectively, then, described color histogram figure characteristic sum UniformLBP feature is utilized to divide out shearing lens and gradual shot in this video frequency program of master and redaction video frequency program. Specifically, utilize described UniformLBP latent structure diversity factor sequence, then utilize figure model that diversity factor sequence structure is gone out image difference xor signal, in this video frequency program of master and redaction video frequency program, divide out shearing lens and gradual shot according to image difference signal and color histogram figure feature.
According to one embodiment of the present invention, step S2 comprises:
S21, extracts the unique point of each redaction camera lens and this camera lens of master respectively; Unique point can comprise the characteristic informations such as black frame per second, advertisement title image, edge rate, frame difference degree, lens frequency, audio jump point, sound type histogram and color distortion degree, generally speaking, unique point is divided into image characteristic point and audio frequency characteristics point, after extraction, covariance descriptor is utilized to carry out unique point from motion tracking under Bayesian frame, thus the track descriptor to each feature point extraction space-time, recycle the uncommon inquiry in the local sensitivity Kazakhstan algorithm tracking mark descriptor based on sparse coding and set up index; For audio frequency characteristics point, adopt a kind of feature extracting method based on multiband energy relative ratios, the energy distribution trend of each frequency band of this characteristic use corresponding to each moment is relatively stable, and this is specific, overcomes the labile factor owing to sound signal distortion etc. causes well.
S22, for each redaction camera lens, by the unique point of this redaction camera lens, unique point with each this camera lens of master carries out Feature Points Matching respectively, obtains at least one comparison result. In this step, adopt template matches technology, the unique point of redaction camera lens with this camera lens of master is mated, concrete, it is the track descriptor utilizing redaction lens features point, the index of this camera lens of master carries out the retrieval of quick search algorithm, obtain the unique point similarity score of often pair of camera lens according to result for retrieval, as this to the comparison result of camera lens, namely this is to the similarity of camera lens.
According to one embodiment of the present invention, this redaction camera lens is classified by step S3, comprising:
If all comparison results of a redaction camera lens are all less than or equal to the first threshold value, then it is the first classification camera lens by this redaction shot classification;
If at least one comparison result of a redaction camera lens is greater than the first threshold value and is less than Second Threshold, then by this redaction shot classification be the 2nd classification camera lens;
If at least one comparison result of a redaction camera lens is more than or equal to Second Threshold, then by this redaction shot classification be the 3rd classification camera lens.
Preferably, first threshold value is 5%, Second Threshold is 95%, when two camera lenses are compared, if the similarity of these two camera lenses (i.e. comparison result) is less than or equal to 5%, then think that the content of two camera lenses is inconsistent, can think that these two camera lenses are unrelated, if the similarity of these two camera lenses (i.e. comparison result) is greater than 5% and is less than 95%, then think and have similar place in two camera lenses, namely it can be inferred that this redaction camera lens has been revised relative to this camera lens of master, if the similarity of these two camera lenses (i.e. comparison result) is more than or equal to 95%, then think that the content of two camera lenses is completely the same, namely think that redaction camera lens is revised relative to this camera lens of master.
For a redaction camera lens, after itself and all this camera lenses of master contrast, it may occur that following situation:
The comparing result of this redaction camera lens and all this camera lenses of master is all less than or equal to 5%, and namely this redaction camera lens is all unrelated with all this camera lenses of master, can think that it newly increases camera lens;
The comparing result of this redaction camera lens and one of them this camera lens of master is greater than 5% and is less than 95%, then think that this redaction camera lens has been revised on the basis of this this camera lens of master;
This redaction camera lens and one of them this camera lens of master be more than or equal to 95%, then think this redaction camera lens on the basis of this this camera lens of master and unmodified.
According to one embodiment of the present invention, step S3 also comprises: if a redaction camera lens is classified as the 3rd classification camera lens according at least one comparison result, then judge whether this camera lens of master that this comparison result is corresponding is the 4th class camera lens, if then this redaction camera lens being categorized as further the 4th classification camera lens. When the similarity (i.e. comparison result) of two camera lenses is more than or equal to 95%, namely when the content of two camera lenses is completely the same, need to judge further, because when being examined by this video of master, it is possible to think that some these camera lenses of master do not conform with regulation, need amendment or delete, therefore it has been marked, but corresponding redaction camera lens has not carried out respective handling yet, at this moment, these redaction camera lenses need to be classified specially, again examine to facilitate.
After the above-mentioned type determining each redaction camera lens, by set label mode, each redaction camera lens is classified, such as, " newly increases camera lens ", " amendment rear lens ", " not deleting camera lens ", " unmodified camera lens ". Like this, when redaction video is examined, only " newly increasing camera lens ", " amendment rear lens ", " not deleting camera lens " need to be checked and audit, save the time examining " unmodified camera lens ".
In specifically examining, for " newly increasing camera lens ", the mode of single player is adopted to carry out playback, manually it being audited mark one by one, in replayed section, operator can perform time-out, broadcasting, F.F., rewind, full frame, labeled fragment plays stop, mark examines result type, fill in camera lens appraises the operations such as content through discussion. For " not deleting camera lens ", two player is adopted synchronously to broadcast this camera lens of two versions, the camera lens being labeled as " requiring to delete in redaction " for master in this needs artificial it to carry out examination & verification mark, in replayed section operator can perform for the video of two versions synchronous to suspend, synchronous play, synchronous F.F., synchronous rewind operation, it is possible to performs, for the video of single version, time-outs, broadcasting, F.F., rewind, labeled fragment play stop, mark and examine result type, fill in camera lens and appraise content etc. through discussion and operate. For " amendment rear lens ", two player is adopted synchronously to play this camera lens of two versions, need manually it to be carried out one by one examination & verification mark, in replayed section operator can perform for the video of two versions synchronous to suspend, synchronous play, synchronous F.F., synchronous rewind operation, it is possible to performs, for the video of single version, time-outs, broadcasting, F.F., rewind, labeled fragment play stop, mark and examine result type, fill in camera lens and appraise content etc. through discussion and operate.
According to one embodiment of the present invention, video comparison identification device comprises:
Camera lens divides module, this video of master is divided at least one this camera lens of master, redaction video is divided at least one redaction camera lens;
Camera lens comparing module, for each redaction camera lens, compares it with each this camera lens of master respectively, obtains at least one comparison result;
Shot classification module, for each redaction camera lens, classifies to this redaction camera lens according to the comparison result of this redaction camera lens, is differentiated relative to the amendment of this video of master by redaction video according to this classification results.
According to one embodiment of the present invention, this camera lens of master and redaction camera lens are divided into shearing lens and gradual shot, camera lens divides the color histogram figure characteristic sum UniformLBP feature that module extracts this video of master and redaction video first respectively, then, described color histogram figure characteristic sum UniformLBP feature is utilized to divide out shearing lens and gradual shot in this video frequency program of master and redaction video frequency program.
According to one embodiment of the present invention, camera lens comparing module comprises:
Feature point extraction submodule block, extracts the unique point of each redaction camera lens and this camera lens of master respectively;
Feature Points Matching submodule block, for each redaction camera lens, by the unique point of this redaction camera lens, unique point with each this camera lens of master carries out Feature Points Matching respectively, obtains at least one comparison result.
According to one embodiment of the present invention, shot classification module performs:
If all comparison results of a redaction camera lens are all less than or equal to the first threshold value, then it is the first classification camera lens by this redaction shot classification;
If at least one comparison result of a redaction camera lens is greater than the first threshold value and is less than Second Threshold, then by this redaction shot classification be the 2nd classification camera lens;
If at least one comparison result of a redaction camera lens is more than or equal to Second Threshold, then by this redaction shot classification be the 3rd classification camera lens.
According to one embodiment of the present invention, shot classification module also performs:
If a redaction camera lens is classified as the 3rd classification camera lens according at least one comparison result, then judge whether this camera lens of master that this comparison result is corresponding is the 4th class camera lens, if then this redaction camera lens being categorized as further the 4th classification camera lens.
For making the object, technical solutions and advantages of the present invention clearly understand, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in more detail.
Fig. 1 is the schema of the video comparison discrimination method that the embodiment of the present invention provides, and as shown in Figure 1, method comprises:
S1, extract the color histogram figure characteristic sum UniformLBP feature of this video of master and redaction video respectively, then, described color histogram figure characteristic sum UniformLBP feature is utilized to divide out shearing lens and gradual shot in this video frequency program of master and redaction video frequency program. Specifically, utilize described UniformLBP latent structure diversity factor sequence, then utilize figure model that diversity factor sequence structure is gone out image difference xor signal, in this video frequency program of master and redaction video frequency program, divide out shearing lens and gradual shot according to image difference signal and color histogram figure feature; As shown in Figure 2, by divide out camera lens FOI camera lens, the alternatively camera lens such as shearing lens, and carry out aftertreatment.
S2, extracts the unique point of each redaction camera lens and this camera lens of master respectively, and for each redaction camera lens, by the unique point of this redaction camera lens, unique point with each this camera lens of master carries out Feature Points Matching respectively, obtains at least one comparison result;
S3, for a redaction camera lens, after itself and all this camera lenses of master contrast, it may occur that following situation:
The similarity of this redaction camera lens and all this camera lenses of master is all less than or equal to 5%, and namely this redaction camera lens is all unrelated with all this camera lenses of master, can think that it newly increases camera lens, and is " newly increasing camera lens " by this redaction shot classification;
The comparing result of this redaction camera lens and one of them this camera lens of master is greater than 5% and is less than 95%, then think that this redaction camera lens has been revised on the basis of this this camera lens of master, and is " amendment rear lens " by this redaction shot classification;
This redaction camera lens and one of them this camera lens of master be more than or equal to 95%, then think this redaction camera lens on the basis of this this camera lens of master and unmodified, and be " unmodified camera lens " by this redaction shot classification, then, judge further, if this this camera lens of master is the camera lens deleted, then it is " not deleting camera lens " by this redaction shot classification.
According to this classification results, redaction video is differentiated relative to the amendment of this video of master.
Fig. 3 is the structural representation of the video comparison identification device that the embodiment of the present invention provides, and as shown in Figure 3, video comparison identification device comprises camera lens and divides module, feature point extraction module, Feature Points Matching module, shot classification module and playing module.
Camera lens divides module and master this video V1 is divided at least one this camera lens of master, and redaction video is divided at least one redaction camera lens V2; Feature point extraction module, extracts the unique point of each redaction camera lens and this camera lens of master respectively; Feature Points Matching module, for each redaction camera lens, by the unique point of this redaction camera lens, unique point with each this camera lens of master carries out Feature Points Matching respectively, obtains at least one comparison result; Shot classification module, for each redaction camera lens, classifies to this redaction camera lens according to the comparison result of this redaction camera lens, for a redaction camera lens, after itself and all this camera lenses of master contrast, it may occur that following situation:
The similarity of this redaction camera lens and all this camera lenses of master is all less than or equal to 5%, and namely this redaction camera lens is all unrelated with all this camera lenses of master, can think that it newly increases camera lens, and is " newly increasing camera lens " by this redaction shot classification;
The comparing result of this redaction camera lens and one of them this camera lens of master is greater than 5% and is less than 95%, then think that this redaction camera lens has been revised on the basis of this this camera lens of master, and is " amendment rear lens " by this redaction shot classification;
This redaction camera lens and one of them this camera lens of master be more than or equal to 95%, then think this redaction camera lens on the basis of this this camera lens of master and unmodified, and be " unmodified camera lens " by this redaction shot classification, then, judge further, if this this camera lens of master is the camera lens deleted, then it is " not deleting camera lens " by this redaction shot classification.
Playing module adopts the non-linear editing technique of video, the mode that two player the indirect labor such as is synchronously play and audited fast is provided, operator can perform for the video of two versions synchronous to suspend, synchronous play, synchronous F.F., synchronous rewind, it is possible to performs, for the video of single version, time-outs, broadcasting, F.F., rewind, labeled fragment play stop, mark and examine result type, fill in camera lens and appraise content etc. through discussion and operate. Indirect labor completes to examine work fast.
Above-described specific embodiment; the object of the present invention, technical scheme and useful effect have been further described; it is it should be understood that; the foregoing is only specific embodiments of the invention; it is not limited to the present invention; within the spirit and principles in the present invention all, any amendment of making, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. a video comparison discrimination method, for differentiating relative to the amendment of this video of master redaction video, it is characterised in that, method comprises:
S1, is divided at least one this camera lens of master by this video of master, and redaction video is divided at least one redaction camera lens;
S2, for each redaction camera lens, compares it with each this camera lens of master respectively, obtains at least one comparison result;
S3, for each redaction camera lens, classifies to this redaction camera lens according to the comparison result of this redaction camera lens, is differentiated relative to the amendment of this video of master by redaction video according to this classification results.
2. method according to claim 1, it is characterized in that, described this camera lens of master and redaction camera lens are divided into shearing lens and gradual shot, when carrying out camera lens division in step sl, first the color histogram figure characteristic sum UniformLBP feature of this video of master and redaction video is extracted respectively, then, described color histogram figure characteristic sum UniformLBP feature is utilized to divide out shearing lens and gradual shot in this video frequency program of master and redaction video frequency program.
3. method according to claim 1, it is characterised in that, described step S2 comprises:
S21, extracts the unique point of each redaction camera lens and this camera lens of master respectively;
S22, for each redaction camera lens, by the unique point of this redaction camera lens, unique point with each this camera lens of master carries out Feature Points Matching respectively, obtains at least one comparison result.
4. method according to claim 3, it is characterised in that, this redaction camera lens is classified by described step S3, comprising:
If all comparison results of a redaction camera lens are all less than or equal to the first threshold value, then it is the first classification camera lens by this redaction shot classification;
If at least one comparison result of a redaction camera lens is greater than the first threshold value and is less than Second Threshold, then by this redaction shot classification be the 2nd classification camera lens;
If at least one comparison result of a redaction camera lens is more than or equal to Second Threshold, then by this redaction shot classification be the 3rd classification camera lens.
5. method according to claim 4, it is characterised in that, described step S3 also comprises:
If a redaction camera lens is classified as the 3rd classification camera lens according at least one comparison result, then judge whether this camera lens of master that this comparison result is corresponding is the 4th class camera lens, if then this redaction camera lens being categorized as further the 4th classification camera lens.
6. a video comparison identification device, for differentiating relative to the amendment of this video of master redaction video, it is characterised in that, device comprises:
Camera lens divides module, this video of master is divided at least one this camera lens of master, redaction video is divided at least one redaction camera lens;
Camera lens comparing module, for each redaction camera lens, compares it with each this camera lens of master respectively, obtains at least one comparison result;
Shot classification module, for each redaction camera lens, classifies to this redaction camera lens according to the comparison result of this redaction camera lens, is differentiated relative to the amendment of this video of master by redaction video according to this classification results.
7. device according to claim 6, it is characterized in that, described this camera lens of master and redaction camera lens are divided into shearing lens and gradual shot, described camera lens divides the color histogram figure characteristic sum UniformLBP feature that module extracts this video of master and redaction video first respectively, then, described color histogram figure characteristic sum UniformLBP feature is utilized to divide out shearing lens and gradual shot in this video frequency program of master and redaction video frequency program.
8. device according to claim 6, it is characterised in that, described camera lens comparing module comprises:
Feature point extraction submodule block, extracts the unique point of each redaction camera lens and this camera lens of master respectively;
Feature Points Matching submodule block, for each redaction camera lens, by the unique point of this redaction camera lens, unique point with each this camera lens of master carries out Feature Points Matching respectively, obtains at least one comparison result.
9. device according to claim 8, it is characterised in that, described shot classification module performs:
If all comparison results of a redaction camera lens are all less than or equal to the first threshold value, then it is the first classification camera lens by this redaction shot classification;
If at least one comparison result of a redaction camera lens is greater than the first threshold value and is less than Second Threshold, then by this redaction shot classification be the 2nd classification camera lens;
If at least one comparison result of a redaction camera lens is more than or equal to Second Threshold, then by this redaction shot classification be the 3rd classification camera lens.
10. method according to claim 9, it is characterised in that, described shot classification module also performs:
If a redaction camera lens is classified as the 3rd classification camera lens according at least one comparison result, then judge whether this camera lens of master that this comparison result is corresponding is the 4th class camera lens, if then this redaction camera lens being categorized as further the 4th classification camera lens.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511020455.0A CN105631428B (en) | 2015-12-29 | 2015-12-29 | Video comparison identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511020455.0A CN105631428B (en) | 2015-12-29 | 2015-12-29 | Video comparison identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105631428A true CN105631428A (en) | 2016-06-01 |
| CN105631428B CN105631428B (en) | 2019-12-10 |
Family
ID=56046341
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511020455.0A Active CN105631428B (en) | 2015-12-29 | 2015-12-29 | Video comparison identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105631428B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325405A (en) * | 2018-08-10 | 2019-02-12 | 北京奇艺世纪科技有限公司 | A kind of mask method of lens type, device and equipment |
| WO2022116552A1 (en) * | 2020-12-02 | 2022-06-09 | 深圳市前海手绘科技文化有限公司 | Method for finding and presenting version differences of produced short videos |
| CN116152530A (en) * | 2023-04-21 | 2023-05-23 | 青岛尘元科技信息有限公司 | Image difference determining method and device, storage medium and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1968358A (en) * | 2006-09-14 | 2007-05-23 | 浙江大学 | Time constraint-based automatic video summary generation method in frequent camera mode |
| CN101540907A (en) * | 2009-04-28 | 2009-09-23 | 无锡天脉聚源传媒科技有限公司 | Method for auditing safety of internet video |
| US20100011392A1 (en) * | 2007-07-16 | 2010-01-14 | Novafora, Inc. | Methods and Systems For Media Content Control |
| US20110035373A1 (en) * | 2009-08-10 | 2011-02-10 | Pixel Forensics, Inc. | Robust video retrieval utilizing audio and video data |
| CN102855449A (en) * | 2012-09-18 | 2013-01-02 | 上海高越文化传媒股份有限公司 | Playing control safety control system |
| CN103079105A (en) * | 2013-01-21 | 2013-05-01 | 深圳创维数字技术股份有限公司 | Method and device for protecting program source |
| CN103092988A (en) * | 2013-02-07 | 2013-05-08 | 广州市久邦数码科技有限公司 | Realizing method of directly managing mobile phone media resources on desktop |
| CN103514293A (en) * | 2013-10-09 | 2014-01-15 | 北京中科模识科技有限公司 | Method for video matching in video template library |
-
2015
- 2015-12-29 CN CN201511020455.0A patent/CN105631428B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1968358A (en) * | 2006-09-14 | 2007-05-23 | 浙江大学 | Time constraint-based automatic video summary generation method in frequent camera mode |
| US20100011392A1 (en) * | 2007-07-16 | 2010-01-14 | Novafora, Inc. | Methods and Systems For Media Content Control |
| CN101540907A (en) * | 2009-04-28 | 2009-09-23 | 无锡天脉聚源传媒科技有限公司 | Method for auditing safety of internet video |
| US20110035373A1 (en) * | 2009-08-10 | 2011-02-10 | Pixel Forensics, Inc. | Robust video retrieval utilizing audio and video data |
| CN102855449A (en) * | 2012-09-18 | 2013-01-02 | 上海高越文化传媒股份有限公司 | Playing control safety control system |
| CN103079105A (en) * | 2013-01-21 | 2013-05-01 | 深圳创维数字技术股份有限公司 | Method and device for protecting program source |
| CN103092988A (en) * | 2013-02-07 | 2013-05-08 | 广州市久邦数码科技有限公司 | Realizing method of directly managing mobile phone media resources on desktop |
| CN103514293A (en) * | 2013-10-09 | 2014-01-15 | 北京中科模识科技有限公司 | Method for video matching in video template library |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325405A (en) * | 2018-08-10 | 2019-02-12 | 北京奇艺世纪科技有限公司 | A kind of mask method of lens type, device and equipment |
| WO2022116552A1 (en) * | 2020-12-02 | 2022-06-09 | 深圳市前海手绘科技文化有限公司 | Method for finding and presenting version differences of produced short videos |
| CN116152530A (en) * | 2023-04-21 | 2023-05-23 | 青岛尘元科技信息有限公司 | Image difference determining method and device, storage medium and electronic equipment |
| CN116152530B (en) * | 2023-04-21 | 2023-10-03 | 青岛尘元科技信息有限公司 | Image difference determining method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105631428B (en) | 2019-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102760169A (en) | Method for detecting advertising slots in television direct transmission streams | |
| US9087125B2 (en) | Robust video retrieval utilizing video data | |
| CN101894125B (en) | Content-based video classification method | |
| TW200306114A (en) | Middle data editing device, middle data generation device, middle data transmission device, middle data searching device, middle data regeneration condition configuration device, and middle data transmission method | |
| CN102890950B (en) | Media automatic editing device, method, media transmissions method and its broadcasting system | |
| CN104133875A (en) | Face-based video labeling method and face-based video retrieving method | |
| CN101937506A (en) | Similar copying video detection method | |
| CN103617263A (en) | Automatic TV advertisement movie clip detection method based on multi-mode features | |
| Awad et al. | Content-based video copy detection benchmarking at TRECVID | |
| CN105631428A (en) | Comparison and identification method and apparatus for videos | |
| CN102236714A (en) | Extensible markup language (XML)-based interactive application multimedia information retrieval method | |
| CN101382998A (en) | Testing device and method of switching of video scenes | |
| CN110569390B (en) | Efficient retrieval method for massive case data based on storage medium distinguishing | |
| US20040030694A1 (en) | Search information transmitting apparatus | |
| CN103631786A (en) | Clustering method and device for video files | |
| CN112291574B (en) | Large-scale sports event content management system based on artificial intelligence technology | |
| WO2023246259A1 (en) | Video identification method and apparatus, computer device, and storage medium | |
| CN113992944A (en) | Video cataloging method, device, equipment, system and medium | |
| US20150078730A1 (en) | Signal recording apparatus, camera recorder, and signal processing system | |
| O'Connor et al. | The acetoolbox: Low-level audiovisual feature extraction for retrieval and classification | |
| CN111615008A (en) | Intelligent abstract generation and subtitle reading system based on multi-device experience | |
| Abdel-Mottaleb et al. | MPEG-7: a content description standard beyond compression | |
| Yang et al. | Multiscale video sequence matching for near-duplicate detection and retrieval | |
| Bai et al. | A semantic event detection approach for soccer video based on perception concepts and finiste state machines | |
| US20080196054A1 (en) | Method and system for facilitating analysis of audience ratings data for content |
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 |