CN103942337A - Video search system based on image recognition and matching - Google Patents
Video search system based on image recognition and matching Download PDFInfo
- Publication number
- CN103942337A CN103942337A CN201410193282.1A CN201410193282A CN103942337A CN 103942337 A CN103942337 A CN 103942337A CN 201410193282 A CN201410193282 A CN 201410193282A CN 103942337 A CN103942337 A CN 103942337A
- Authority
- CN
- China
- Prior art keywords
- video
- module
- user
- information
- feature
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/732—Query formulation
- G06F16/7328—Query by example, e.g. a complete video frame or video sequence
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A video search system based on image recognition and matching comprises a server side and a user side. The server side comprises a video collecting module, a video character feature collecting module, a video character information analysis module, a video preprocessing module, a video content analysis module, a video feature extraction module, a server database module, an image feature extraction module, a server control module and a user feedback information analysis and process module. The user side comprises a user search information uploading module, a video search result displaying module and a search result user feedback module. The invention provides a method for searching for videos through images. Good user experience is achieved; by uploading one image, a user can obtain video resource information related to the content of the image; the returned search result is accurate, the information amount is large, and mass video resources on the Internet can be fully utilized.
Description
Technical field
The present invention relates to a kind of video searching system, relate to internet hunt and Video processing.
Background technology
As far back as 2011, in Global Internet consumer total flow, the flow proportion of video playback surpassed 50%, did not also comprise the flow consuming by P2P mode downloading video files.Video information has occupied the major part of all information in internet.And, in video, having contained extremely abundant information, this is that Word message institute is irreplaceable.And for abundant information resources like this, current indexed mode is only by video distribution person, the very brief description of its interpolation to be realized, the potential resources being wasted in visible video enriches very much.We wish in this way, make full use of the potential resources in video, for user provides abundanter search result information, are some special industry fields, and for example historical video documents, news video tracking provide a kind of new solution.
Now, also there is a small amount of service platform of picture searching video that passes through, still substantially all concentrate on abroad, and mostly be concept product.A small amount of supplier is also difficult to provide accurate Search Results, makes full use of video features.
Summary of the invention
Technology of the present invention is dealt with problems and is: overcome the deficiencies in the prior art, provide a kind of by service system and the usage platform of picture searching video, user just can obtain video data that picture is relevant or the information of Image Documents, the body matter of the source of picture and picture by a pictures.For user provides a kind of more convenient mode of effectively searching video data, provide abundanter Search Results display form.
The technology of the present invention solution: a kind of based on image recognition and the video searching system mating, comprise server end and user side two parts.Server end comprises video acquisition module, video text collection apparatus module, video text information analysis module, video pre-filtering module, video content analysis module, video feature extraction module, server database module, picture feature extraction module, server control module, field feedback analysis and processing module; User side comprises transmission module in user search information, video search result display module, Search Results user feedback module.
Video acquisition module, realizes the structure of searching for information database source material; By web crawlers, obtain Internet video data or use the existing video content resource in collaborative video website, gather video data and additional text description, review information thereof, obtained video resource is sent into video pre-filtering module, obtained written historical materials is sent to video text collection apparatus module;
Video text collection apparatus module, obtains the feature of video text; The text description of the video that utilization gets, review information, by keyword extraction, obtain the key word of Word message, the direct information video text information analysis module of acquisition;
Video text information analysis module, obtains the character features of video data; Utilize the keyword of video text information, the degree of correlation of analysis of key word and video content, obtains describing the word keyword of video features, and the data that obtain are sent to server database;
Video pre-filtering module, obtains free of contamination video image; Due to original video data, may have the information such as station symbol, embedded captions, these information appear on picture can produce certain interference to video original contents, this module is carried out feature extraction and removes this type of information, and the video of acquisition is sent to video content analysis module;
Video content analysis module, the content information of acquisition video; The analysis changing by the overall dynamics to picture in video display process, the content style of acquisition video, splits video scene, analyzes the contact between scene; Obtained above-mentioned data are sent to video feature extraction module;
Video feature extraction module, the feature of acquisition video pictures; Pass through obtained video scene information and whole video content style, each scene of video is extracted to picture characteristic information, comprising the feature of object in variation characteristic, picture image feature and the picture of picture.By the scene contact feature obtaining in video content analysis module, above-mentioned information is proofreaied and correct, finally obtain video features, be sent to server database module;
Server database module, receiver, video feature also stores, in order to user search; Its information can serviced device control module be called, to carry out next step processing;
Image characteristics extraction module, obtains the feature that user uploads picture to be searched; User's uploading pictures is carried out to image characteristic analysis, and the Word message that may add user carries out signature analysis, obtain the feature of user's content to be searched, be sent to server control module;
Server control module, returns to user search result; Utilization obtains the characteristic information of user's uploading pictures from image characteristics extraction module, search coupling in server database module, and the video resource that feature is met is that Search Results returns, and data send to the video search information display module of user side;
Field feedback analysis and processing module, the characteristic information of video in correction database; The field feedback obtaining from Search Results user feedback module is analyzed, the characteristic information of video in correction database, the information after correction is still admitted to server database module and stores;
Transmission module in user search information, obtains user's content to be searched; Based on Html webpage, realize, the information to be searched that user is uploaded and inputted uploads to image characteristics extraction module, and institute's transmission information comprises user search content and user's ID;
Video search result display module, shows Search Results to user; Based on Html webpage, realize, by user, by the Search Results of the content that in user search information, transmission module is uploaded, the Search Results that server control module is returned, shows at user side;
Search Results user feedback module, obtains the feedback information of user to Search Results; When client video search result display module is shown Search Results, recording user obtains after Search Results, selected those results to browse, the information such as browsing time to search result items, submit to field feedback analysis and processing module by these information and carry out analyzing and processing.
The present invention's advantage is compared with prior art:
(1) with respect to text search, the present invention can more provide abundanter Search Results display form, and with respect to common search Word message, the video data of search contains abundanter content and information;
(2) with respect to video search, the present invention can provide more search condition to select, and Search Results makes full use of video pictures content information, and Search Results is more effective;
(3) Integrated using video pictures feature and text description feature are determined video features, and Search Results is more accurate;
(4) gather field feedback, according to the selection of user's navigate search results and browsing time, pass judgment on the satisfaction of user to search result items, video features is carried out to feedback compensation, make video features information more accurate;
(5) Html webpage is realized, and user logs in website in use, without any plug-in unit is installed.
Accompanying drawing explanation
Fig. 1 is that Search Results is shown interface (part);
Fig. 2 is module process flow diagram of the present invention;
Fig. 3 is modular structure figure of the present invention;
Fig. 4 is the definite workflow of video features weights in the present invention.
Embodiment
As shown in Figure 3, video searching system of the present invention, comprises server end and user side two parts.Server end comprises video acquisition module, video text collection apparatus module, video text information analysis module, video pre-filtering module, video content analysis module, video feature extraction module, server database module, picture feature extraction module, server control module, field feedback analysis and processing module; User side comprises transmission module in user search information, video search result display module, Search Results user feedback module.
Video acquisition module, due to video copyright restrictions, wouldn't use web crawlers to download collection analysis to the video of propagating on internet, use the existing video content resource in collaborative video website, obtain video file, then utilize web crawlers, obtain the written material of the video place page, include but not limited to video comment, classification, title, associated video link etc.;
Video text collection apparatus module, existing video website has visual classification to video, this classification may come from video distribution person oneself to be added, may be not too accurate, but provide one can be with reference to essential characteristic.Video to same essential characteristic, the text description information of its video is gathered, carry out cluster analysis, the keyword mainly comprising in these Word messages is proposed, be designated as the basic word of this type of video, so for each video, the word that its text description information occurs in basic word can be designated as the keyword of this video text information, this a part of keyword only comes from written material, may be irrelevant with video content, the word analyzing is for example: " fine ", " performer ", " American series ", " Zhang Yimou ", " household ", " upstairs ", " rob sofa ", " excellent cruel " etc.
Video text information analysis module, the word keyword getting in video text collection apparatus module may be irrelevant with video.With the example analyses in the preceding paragraph, wherein the word such as " Zhang Yimou ", " American series ", " household " is relevant with video content; " fine ", " performer " although relevant to video content, describe too wide in range, to video features substantially do not have effect; " upstairs ", " rob sofa ", the word such as " excellent cruel " is completely nonsensical to video content features.This module need to be differentiated three class words, and rear two class words are deleted, and first kind word is weighted according to occurrence number, as the word keyword of video.
Wherein second and third class word has following characteristics: it all can occur in the video text descriptor of each class, and probability is close, the probability distribution that we occur in different classes of video by statistical study word, variance to same keyword probability of occurrence in different classes of video arranges certain threshold value, and what variance was less can be judged to be this type of word.
Video pre-filtering module, original video data may have station symbol, embedded captions, for station symbol, embedded captions etc., it can occur and be positioned at same position and have close color in a video in most pictures, we carry out random sampling on time dimension to video, calculate change color amplitude and the variance on each position of picture, put, and certain threshold value is set, what be less than threshold value represents that this position change color amplitude is less, may be the information such as station symbol.If near the point these points also has such feature (because station symbol etc. can occupy certain area), so just the doubtful polluted information of this concentrated distribution can be carried out to mark.The picture that is labeled position does not exert an influence to the extraction of video keyword.
Video content analysis module, the analysis that the overall dynamics of picture changes, for example video pictures integral color is comparatively dim or comparatively lucid and lively, picture key colour and tonal variation situation etc.To carrying out SIFT and Optical-flow Feature coupling in video between close picture, can split video scene, split in other words video lens, record camera lens switching frequency change information.
Video feature extraction module, on the one hand, according to the picture tone information providing in video content analysis module and camera lens switching frequency, can substantially determine video style, and, for the same or similar video content of different video file including, for example the video file of different-format may content be all same portion film, we can identify and unify to sort out, it can share video features information, video text descriptor, can greatly enrich the descriptor of video file like this, improve the accuracy of video feature extraction.On the other hand, for each camera lens (scene), from the angle of graphics, extract the unique point of picture, such as the point of color acute variation, there is the corner angle point of corner angle object etc., build the spatial description vector of these unique points, as the picture feature of scene.
Server database module, for each video, records following information: source video sequence network address, video title, video text information keyword, associated video and degree of correlation thereof, video pictures whole style descriptor, video scene picture feature descriptor.
Image characteristics extraction module, the picture that user is uploaded carries out the feature extraction in graphics, and in extracting method and video, picture feature extraction mode is similar, repeats no more.And record.
Server control module, the characteristic information of user's uploading pictures that image characteristics extraction module is provided is searched coupling in database, larger for matching degree, is likely Search Results, according to matching degree, gives certain weights.Meanwhile, the associated video of this video also additionally increases weights because this video obtains weights.After search finishes, according to weights, sort, the higher result of weighting value, as first 100, is returned as Search Results.
Field feedback analysis and processing module, a video returns as Search Results, illustrates that the picture feature that its feature and user upload is close, if but after returning, user does not browse this Search Results, illustrate that so this characteristic matching may have problems.For this feature, we fall power to this Search Results video and process.Meanwhile, the associated video of this video also additionally reduces weights because this video reduces weights.Contrary, if user has selected certain search result items, and carried out browsing for a long time, illustrate that so this characteristic matching may be very rational, for this feature, we carry out liter power to this Search Results video and process.Meanwhile, the associated video of this video also additionally promotes weights because this video promotes weights.
Transmission module in user search information, realizes by webpage, and picture uploading function is provided.
Video search result display module, realizes by webpage, and video playback capability is provided.
Search Results user feedback module, is coordinated and is realized by webpage and Website server backstage, and recording user has been clicked those Search Results after search, how long has stopped in result of page searching.
In a word, the invention provides a kind ofly by service system and the usage platform of picture searching video, user just can obtain video data that picture is relevant or the information of Image Documents, the keyword of the source of picture and picture by a pictures.For user provides a kind of more convenient mode of effectively searching video data, provide abundanter Search Results display form.
The above; be only part embodiment of the present invention, but protection scope of the present invention is not limited to this, in the technical scope that any those skilled in the art disclose in the present invention; the variation that can expect easily or replacement, within all should being encompassed in protection scope of the present invention.
Claims (5)
1. one kind based on image recognition and the video searching system mating, it is characterized in that: comprise server end and user side two parts, described server end comprises: video acquisition module, video text collection apparatus module, video text information analysis module, video pre-filtering module, video content analysis module, video feature extraction module, server database module, picture feature extraction module, server control module, field feedback analysis and processing module; Described user side comprises: transmission module, video search result display module, Search Results user feedback module in user search information;
Video acquisition module, realizes the structure of searching for information database source material; By web crawlers, obtain Internet video resource or use the existing video resource in collaborative video website, gather video image and additional text description, review information thereof, obtained video resource is sent into video pre-filtering module, obtained text description, review information are sent to video text collection apparatus module;
Video text collection apparatus module, obtains the feature of video text; The text description of the video that utilization gets, review information, by keyword extraction, obtain the key word of Word message, the direct information video text information analysis module of acquisition;
Video text information analysis module, obtains the character features of video data; Utilize the keyword of video text information, the degree of correlation of analysis of key word and video content, obtains describing the word keyword of video features, and the data that obtain are sent to server database;
Video pre-filtering module, obtains free of contamination video image; Because original video data may have station symbol information, embedded caption information, these information appear on picture and can video original contents be produced and be disturbed, this module is carried out feature extraction and removes above-mentioned these information, and the video of acquisition is sent to video content analysis module;
Video content analysis module, the content information of acquisition video; The analysis changing by the overall dynamics to picture in video display process, the content style of acquisition video, splits video scene, analyzes the contact between scene; Obtained above-mentioned data are sent to video feature extraction module;
Video feature extraction module, the feature of acquisition video pictures; Pass through obtained video scene information and whole video content style, each scene of video is extracted to picture characteristic information, feature comprising object in variation characteristic, picture image feature and the picture of picture, by the scene contact feature obtaining in video content analysis module, the picture characteristic information of each scene is proofreaied and correct, the final video features that obtains, is sent to server database module;
Server database module, receiver, video feature also stores, in order to user search; Its information can serviced device control module be called, to carry out next step processing;
Image characteristics extraction module, obtains the feature that user uploads picture to be searched; User's uploading pictures is carried out to image characteristic analysis, and the Word message that may add user carries out signature analysis, obtain the feature of user's content to be searched, be sent to server control module;
Server control module, returns to user search result; Utilization obtains the characteristic information of user's uploading pictures from image characteristics extraction module, search coupling in server database module, and the video resource that feature is met is that Search Results returns, and data send to the video search information display module of user side;
Field feedback analysis and processing module, the characteristic information of video in correction database; The field feedback obtaining from Search Results user feedback module is analyzed, the characteristic information of video in correction database, the information after correction is still admitted to server database module and stores;
Transmission module in user search information, obtains user's content to be searched; Based on Html webpage, realize, the information to be searched that user is uploaded and inputted uploads to image characteristics extraction module, and institute's transmission information comprises user search content and user's ID;
Video search result display module, shows Search Results to user; Based on Html webpage, realize, by user, by the Search Results of the content that in user search information, transmission module is uploaded, the Search Results that server control module is returned, shows at user side;
Search Results user feedback module, obtains the feedback information of user to Search Results; When client video search result display module is shown Search Results, recording user obtains after Search Results, selected those results to browse, the information such as browsing time to search result items, submit to field feedback analysis and processing module by these information and carry out analyzing and processing.
2. according to claim 1 based on image recognition and the video searching system mating, it is characterized in that: described video pre-filtering module is used for:
(1) video is carried out on time dimension to random sampling;
(2) calculate change color amplitude and the variance of point in each sampling on each position;
(3) certain threshold value is set, for variance, is less than the point of threshold value, according to its variance and set threshold value, calculate this point and the incoherent probability of video content, the row labels of going forward side by side; For variance, be greater than the point of threshold value, think that this point is relevant with video content, without processing;
(4) for marked point in 0, carry out two-dimentional K-means cluster, the approaching dot-dash of location comparison is classified as to a set, thereby obtains a plurality of set that consist of point, the point in each set is non-intersect;
(5) for each set obtaining in 0, the distribution probability of counting in this set convex closure region in set of computations, probability is high, thinks that video pictures and the video content in this set Convex range is uncorrelated;
(6) for acquire in 0 with the incoherent picture area of video content, be confirmed to be irrelevant with video content, carry out tag delete.
3. according to claim 1 based on image recognition and the video searching system mating, it is characterized in that: described video content analysis module is as follows:
Described video content analysis module comprises two parts, and video global feature extracts and video scene is separated; The implementation procedure that wherein video global feature extracts is:
(1) analysis overall dynamics of each the frame picture in video being changed, obtains the average color feature of picture;
(2) specify the number of times of sampling p.s.;
(3) whole video obtain according to time sequence, the average color feature of each picture, be exactly the global feature of this video;
The implementation procedure that wherein video scene is separated is:
(1) specify a step-length frame number, get video the 1st frame as start frame;
(2) get start frame, using its with add that a frame of video after step-length is as end frame, start frame and end frame picture are carried out to SIFT and Optical-flow Feature coupling;
(3) if can mate, think that this section of video all comes from same scene, start frame increases a step-length and proceeds to (2) continuation processing; If do not mated, think a certain frame place between start frame and end frame, scene is switched, the position of finding scene to switch by binary chop;
(4) obtained a scene switching position being recorded, is at this moment a scene between start frame and end frame; Get the next frame of end frame as start frame, proceed to (2) and continue to process, until video finishes.
4. according to claim 1 based on image recognition and the video searching system mating, it is characterized in that: described video feature extraction module is used for:
(1) according to claim 3, obtain after the global feature of this video, the video in database is compared;
(2) contrast similarity higher than threshold value, thinks that video content is likely identical, is classified as same class;
(3) for of a sort video, further compare its scene segmentation result, and the picture in corresponding scene is carried out to sampling fraction pair, if similarity is still very high, think that video content is identical;
(4) for each camera lens in video, from the angle of graphics, extract the unique point of picture, comprise color acute variation point, have the corner angle point of corner angle object, build the spatial description vector of these unique points, as the picture feature of scene;
(5), for the identical video of content, share its video features, to reduce the impact of other factors on video feature extraction result.
5. according to claim 1 based on image recognition and the video searching system mating, it is characterized in that: described field feedback analysis and processing module is used for:
(1) after user's search content is processed and is returned results, the Search Results that counting user is clicked, and user browses the time of this Search Results;
(2) for user, there is no the Search Results of clicking, illustrate that this characteristic matching in current search may have problems, reduce this video for the weights of this feature; Meanwhile, for the video similar to this video content, also reduce it for the weights of this feature; The Search Results of clicking for user, illustrates that this characteristic matching in current search is more reasonable, the time of browsing this Search Results according to user, promotes this video for the weights of this feature; Meanwhile, for the video similar to this video content, also promote it for the weights of this feature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410193282.1A CN103942337B (en) | 2014-05-08 | 2014-05-08 | It is a kind of based on image recognition and the video searching system that matches |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410193282.1A CN103942337B (en) | 2014-05-08 | 2014-05-08 | It is a kind of based on image recognition and the video searching system that matches |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103942337A true CN103942337A (en) | 2014-07-23 |
| CN103942337B CN103942337B (en) | 2017-08-18 |
Family
ID=51190005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410193282.1A Active CN103942337B (en) | 2014-05-08 | 2014-05-08 | It is a kind of based on image recognition and the video searching system that matches |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103942337B (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105007524A (en) * | 2015-07-29 | 2015-10-28 | 无锡天脉聚源传媒科技有限公司 | Video processing method and device |
| CN105183478A (en) * | 2015-09-11 | 2015-12-23 | 中山大学 | Webpage reestablishing method and device based on color transmission |
| CN105912650A (en) * | 2016-04-07 | 2016-08-31 | 腾讯科技（深圳）有限公司 | Method and apparatus of recommending songs |
| CN106294454A (en) * | 2015-05-29 | 2017-01-04 | 中兴通讯股份有限公司 | Video retrieval method and device |
| CN106294690A (en) * | 2016-08-05 | 2017-01-04 | 广东云海云计算科技有限公司 | Image/video search platform based on content |
| CN106651421A (en) * | 2016-09-20 | 2017-05-10 | 中央电视台 | Multimedia data pricing system |
| CN106713859A (en) * | 2016-12-19 | 2017-05-24 | 贵州大学 | Image visual monitoring search system and search method thereof |
| CN107045730A (en) * | 2017-03-06 | 2017-08-15 | 青岛鹏海软件有限公司 | A kind of multidimensional exhibition system and method for digital culture scene or image |
| CN107301245A (en) * | 2017-07-14 | 2017-10-27 | 国网山东省电力公司淄博供电公司 | A kind of power information video searching system |
| CN107609149A (en) * | 2017-09-21 | 2018-01-19 | 北京奇艺世纪科技有限公司 | A kind of video locating method and device |
| CN108259974A (en) * | 2018-03-07 | 2018-07-06 | 优酷网络技术（北京）有限公司 | Video matching method and device |
| CN108628914A (en) * | 2017-03-22 | 2018-10-09 | 宏达国际电子股份有限公司 | Mobile device and its operating method, non-volatile computer-readable medium storing |
| CN108886631A (en) * | 2016-03-15 | 2018-11-23 | 日本电气株式会社 | Electronic data checks system, electronic data inspection method and the storage medium for being stored with electronic data inspection program |
| CN109063200A (en) * | 2018-09-11 | 2018-12-21 | 广州神马移动信息科技有限公司 | Resource search method and its device, electronic equipment, computer-readable medium |
| CN109151500A (en) * | 2018-09-29 | 2019-01-04 | 北京数美时代科技有限公司 | A kind of main broadcaster's recommended method, system and computer equipment for net cast |
| CN109635788A (en) * | 2019-01-23 | 2019-04-16 | 黑河学院 | A kind of intelligent data acquisition and video analytic system |
| CN110348824A (en) * | 2019-07-12 | 2019-10-18 | 陈虎 | A kind of wisdom of humanity, action edge Real-Time Sharing mutual assistance platform |
| CN110399515A (en) * | 2019-06-28 | 2019-11-01 | 中山大学 | Picture retrieval method, device and picture retrieval system |
| CN110809187A (en) * | 2019-10-31 | 2020-02-18 | Oppo广东移动通信有限公司 | Video selection method, video selection device, storage medium and electronic equipment |
| CN110913241A (en) * | 2019-11-01 | 2020-03-24 | 北京奇艺世纪科技有限公司 | Video retrieval method and device, electronic equipment and storage medium |
| CN110909209A (en) * | 2019-11-26 | 2020-03-24 | 北京达佳互联信息技术有限公司 | Live video searching method and device, equipment, server and storage medium |
| CN111816281A (en) * | 2020-06-23 | 2020-10-23 | 无锡祥生医疗科技股份有限公司 | Ultrasonic image inquiry unit |
| CN112231497A (en) * | 2020-10-19 | 2021-01-15 | 腾讯科技（深圳）有限公司 | Information classification method and device, storage medium and electronic equipment |
| CN112256913A (en) * | 2020-10-19 | 2021-01-22 | 四川长虹电器股份有限公司 | Video searching method based on graph model comparison |
| CN112425177A (en) * | 2018-07-12 | 2021-02-26 | 交互数字Vc控股公司 | Method and apparatus for volumetric video transmission |
| CN114339375A (en) * | 2021-08-17 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Video playing method, method for generating video directory and related product |
| CN114840093A (en) * | 2022-07-04 | 2022-08-02 | 江西工业贸易职业技术学院 | Smell simulation control system and method based on VR equipment |
| CN111816281B (en) * | 2020-06-23 | 2024-05-14 | 无锡祥生医疗科技股份有限公司 | Ultrasonic image inquiry device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080163087A1 (en) * | 2006-12-28 | 2008-07-03 | Nokia Corporation | Method, Apparatus and Computer Program Product for Providing Multi-Feature Based Sampling for Relevance Feedback |
| US20090192990A1 (en) * | 2008-01-30 | 2009-07-30 | The University Of Hong Kong | Method and apparatus for realtime or near realtime video image retrieval |
| CN101840422A (en) * | 2010-04-09 | 2010-09-22 | 江苏东大金智建筑智能化系统工程有限公司 | Intelligent video retrieval system and method based on target characteristic and alarm behavior |
| CN102073699A (en) * | 2010-12-20 | 2011-05-25 | 百度在线网络技术（北京）有限公司 | Method, device and equipment for improving search result based on user behaviors |
| CN103365854A (en) * | 2012-03-28 | 2013-10-23 | 鸿富锦精密工业（深圳）有限公司 | System and method for retrieving video files |
-
2014
- 2014-05-08 CN CN201410193282.1A patent/CN103942337B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080163087A1 (en) * | 2006-12-28 | 2008-07-03 | Nokia Corporation | Method, Apparatus and Computer Program Product for Providing Multi-Feature Based Sampling for Relevance Feedback |
| US20090192990A1 (en) * | 2008-01-30 | 2009-07-30 | The University Of Hong Kong | Method and apparatus for realtime or near realtime video image retrieval |
| CN101840422A (en) * | 2010-04-09 | 2010-09-22 | 江苏东大金智建筑智能化系统工程有限公司 | Intelligent video retrieval system and method based on target characteristic and alarm behavior |
| CN102073699A (en) * | 2010-12-20 | 2011-05-25 | 百度在线网络技术（北京）有限公司 | Method, device and equipment for improving search result based on user behaviors |
| CN103365854A (en) * | 2012-03-28 | 2013-10-23 | 鸿富锦精密工业（深圳）有限公司 | System and method for retrieving video files |
Non-Patent Citations (1)
| Title |
|---|
| 赵伟: ""基于内容的视频检索系统的设计与实现"", 《中国优秀硕士学位论文全文数据库，信息科技辑》 * |
Cited By (42)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294454A (en) * | 2015-05-29 | 2017-01-04 | 中兴通讯股份有限公司 | Video retrieval method and device |
| CN105007524A (en) * | 2015-07-29 | 2015-10-28 | 无锡天脉聚源传媒科技有限公司 | Video processing method and device |
| CN105183478A (en) * | 2015-09-11 | 2015-12-23 | 中山大学 | Webpage reestablishing method and device based on color transmission |
| CN105183478B (en) * | 2015-09-11 | 2018-11-23 | 中山大学 | A kind of webpage reconstructing method and its device based on color transfer |
| CN108886631A (en) * | 2016-03-15 | 2018-11-23 | 日本电气株式会社 | Electronic data checks system, electronic data inspection method and the storage medium for being stored with electronic data inspection program |
| CN105912650A (en) * | 2016-04-07 | 2016-08-31 | 腾讯科技（深圳）有限公司 | Method and apparatus of recommending songs |
| CN105912650B (en) * | 2016-04-07 | 2021-08-24 | 腾讯科技（深圳）有限公司 | Method and device for recommending songs |
| CN106294690A (en) * | 2016-08-05 | 2017-01-04 | 广东云海云计算科技有限公司 | Image/video search platform based on content |
| CN106651421A (en) * | 2016-09-20 | 2017-05-10 | 中央电视台 | Multimedia data pricing system |
| CN106713859A (en) * | 2016-12-19 | 2017-05-24 | 贵州大学 | Image visual monitoring search system and search method thereof |
| CN107045730A (en) * | 2017-03-06 | 2017-08-15 | 青岛鹏海软件有限公司 | A kind of multidimensional exhibition system and method for digital culture scene or image |
| CN107045730B (en) * | 2017-03-06 | 2023-10-24 | 青岛鹏海软件有限公司 | Multi-dimensional display system and method for digital cultural scene or image |
| CN108628914A (en) * | 2017-03-22 | 2018-10-09 | 宏达国际电子股份有限公司 | Mobile device and its operating method, non-volatile computer-readable medium storing |
| CN108628914B (en) * | 2017-03-22 | 2021-11-12 | 宏达国际电子股份有限公司 | Mobile device and operation method thereof, and non-volatile computer readable recording medium |
| CN107301245A (en) * | 2017-07-14 | 2017-10-27 | 国网山东省电力公司淄博供电公司 | A kind of power information video searching system |
| CN107301245B (en) * | 2017-07-14 | 2020-03-06 | 国网山东省电力公司淄博供电公司 | Power information video search system |
| CN107609149A (en) * | 2017-09-21 | 2018-01-19 | 北京奇艺世纪科技有限公司 | A kind of video locating method and device |
| CN107609149B (en) * | 2017-09-21 | 2020-06-19 | 北京奇艺世纪科技有限公司 | Video positioning method and device |
| CN108259974A (en) * | 2018-03-07 | 2018-07-06 | 优酷网络技术（北京）有限公司 | Video matching method and device |
| CN112425177B (en) * | 2018-07-12 | 2023-06-20 | 交互数字Vc控股公司 | Method and apparatus for volumetric video transmission |
| CN112425177A (en) * | 2018-07-12 | 2021-02-26 | 交互数字Vc控股公司 | Method and apparatus for volumetric video transmission |
| CN109063200A (en) * | 2018-09-11 | 2018-12-21 | 广州神马移动信息科技有限公司 | Resource search method and its device, electronic equipment, computer-readable medium |
| CN109063200B (en) * | 2018-09-11 | 2022-10-14 | 优视科技（中国）有限公司 | Resource searching method and device, electronic equipment and computer readable medium |
| CN109151500A (en) * | 2018-09-29 | 2019-01-04 | 北京数美时代科技有限公司 | A kind of main broadcaster's recommended method, system and computer equipment for net cast |
| CN109635788A (en) * | 2019-01-23 | 2019-04-16 | 黑河学院 | A kind of intelligent data acquisition and video analytic system |
| CN110399515A (en) * | 2019-06-28 | 2019-11-01 | 中山大学 | Picture retrieval method, device and picture retrieval system |
| CN110399515B (en) * | 2019-06-28 | 2022-05-17 | 中山大学 | Picture retrieval method, device and system |
| CN110348824A (en) * | 2019-07-12 | 2019-10-18 | 陈虎 | A kind of wisdom of humanity, action edge Real-Time Sharing mutual assistance platform |
| CN110809187B (en) * | 2019-10-31 | 2022-04-05 | Oppo广东移动通信有限公司 | Video selection method, video selection device, storage medium and electronic equipment |
| CN110809187A (en) * | 2019-10-31 | 2020-02-18 | Oppo广东移动通信有限公司 | Video selection method, video selection device, storage medium and electronic equipment |
| CN110913241B (en) * | 2019-11-01 | 2022-09-30 | 北京奇艺世纪科技有限公司 | Video retrieval method and device, electronic equipment and storage medium |
| CN110913241A (en) * | 2019-11-01 | 2020-03-24 | 北京奇艺世纪科技有限公司 | Video retrieval method and device, electronic equipment and storage medium |
| CN110909209B (en) * | 2019-11-26 | 2022-12-27 | 北京达佳互联信息技术有限公司 | Live video searching method and device, equipment, server and storage medium |
| CN110909209A (en) * | 2019-11-26 | 2020-03-24 | 北京达佳互联信息技术有限公司 | Live video searching method and device, equipment, server and storage medium |
| CN111816281A (en) * | 2020-06-23 | 2020-10-23 | 无锡祥生医疗科技股份有限公司 | Ultrasonic image inquiry unit |
| CN111816281B (en) * | 2020-06-23 | 2024-05-14 | 无锡祥生医疗科技股份有限公司 | Ultrasonic image inquiry device |
| CN112256913A (en) * | 2020-10-19 | 2021-01-22 | 四川长虹电器股份有限公司 | Video searching method based on graph model comparison |
| CN112231497A (en) * | 2020-10-19 | 2021-01-15 | 腾讯科技（深圳）有限公司 | Information classification method and device, storage medium and electronic equipment |
| CN112231497B (en) * | 2020-10-19 | 2024-04-09 | 腾讯科技（深圳）有限公司 | Information classification method and device, storage medium and electronic equipment |
| CN114339375A (en) * | 2021-08-17 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Video playing method, method for generating video directory and related product |
| CN114339375B (en) * | 2021-08-17 | 2024-04-02 | 腾讯科技（深圳）有限公司 | Video playing method, method for generating video catalogue and related products |
| CN114840093A (en) * | 2022-07-04 | 2022-08-02 | 江西工业贸易职业技术学院 | Smell simulation control system and method based on VR equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103942337B (en) | 2017-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103942337A (en) | Video search system based on image recognition and matching | |
| CN106354861B (en) | Film label automatic indexing method and automatic indexing system | |
| AU2017204338B2 (en) | Industry first method that uses users search query to show highly relevant poster frames for stock videos thereby resulting in great experience and more sales among users of stock video service | |
| CN108694223B (en) | User portrait database construction method and device | |
| US9471936B2 (en) | Web identity to social media identity correlation | |
| US20190362154A1 (en) | Object Detection From Visual Search Queries | |
| KR102068790B1 (en) | Estimating and displaying social interest in time-based media | |
| CN106202475B (en) | Method and device for pushing video recommendation list | |
| Schwenzow et al. | Understanding videos at scale: How to extract insights for business research | |
| CN102511048B (en) | A kind of method and system comprising the video area of text for pre-service | |
| CN105373938A (en) | Method for identifying commodity in video image and displaying information, device and system | |
| JP2019531548A (en) | Video capture framework for visual search platform | |
| CN113010703B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| US9137574B2 (en) | Method or system to predict media content preferences | |
| US9177341B2 (en) | Determining search relevance from user feedback | |
| US9305215B2 (en) | Apparatus, method and computer readable recording medium for analyzing video using image captured from video | |
| Jeong et al. | Ontology-based automatic video annotation technique in smart TV environment | |
| Tous et al. | Automated curation of brand-related social media images with deep learning | |
| US20170013309A1 (en) | System and method for product placement | |
| CN114372172A (en) | Method and device for generating video cover image, computer equipment and storage medium | |
| US9866894B2 (en) | Method for annotating an object in a multimedia asset | |
| Vandecasteele et al. | Spott: On-the-spot e-commerce for television using deep learning-based video analysis techniques | |
| CN110827063A (en) | Multi-strategy fused commodity recommendation method, device, terminal and storage medium | |
| CN103425685A (en) | Method and device for having access to paper media | |
| Wang et al. | Interactive web video advertising with context analysis and search |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200113 Address after: 519080 5th floor, building 8, science and Technology Innovation Park, No.1 Gangwan, Jintang Road, Tangjiawan, Xiangzhou District, Zhuhai City, Guangdong Province Patentee after: Zhuhai haotengzhisheng Technology Co., Ltd Address before: 100191 Haidian District, Xueyuan Road, No. 37, Patentee before: Beijing University of Aeronautics and Astronautics |
|
| TR01 | Transfer of patent right |