CN104504732A - Video content retrieval method based on key frame extraction - Google Patents
Video content retrieval method based on key frame extraction Download PDFInfo
- Publication number
- CN104504732A CN104504732A CN201410829677.6A CN201410829677A CN104504732A CN 104504732 A CN104504732 A CN 104504732A CN 201410829677 A CN201410829677 A CN 201410829677A CN 104504732 A CN104504732 A CN 104504732A
- Authority
- CN
- China
- Prior art keywords
- video
- time section
- key
- video content
- key frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
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
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Abstract
The invention discloses a video content retrieval method based on key frame extraction. The method includes the steps of 1, analyzing video content, to be specific, separating a background and a target from a video scene by means of the computer visual image analysis technique; 2, selecting an available-period video, to be specific, marking start and stop points-in-time of a target active-period video to obtain the available-period video between the start and stop points-in-time; and 3, retrieving the video, to be specific, retrieving video content in the available-period video. The method has the advantages that video retrieval time is shortened, video retrieval work can be decreased, and video retrieval time can be saved.
Description
Technical field
The present invention relates to technical field of video processing, be specifically related to a kind of Video content retrieval method based on key-frame extraction.
Background technology
Video content retrieval field, people often need to spend a large amount of manpowers, time, search required content by the mode of manually watching video record playback.As in criminal investigation field, for the detection of larceny case, often need a large amount of manpower to watch monitoring video, search and determine suspect.Obviously, such mode not only needs to spend a large amount of manpower, longer time, and, because of the physilogical characteristics of people, when staring at screen for a long time, easily form visual fatigue, the unconscious valuable information ignored in video.
For solving the problem, in prior art, general employing Video Image treatment technology indirect labor carries out video frequency searching.But computer checking technology more can only carry out the retrieval of people, car, thing, when judgement and the retrieval of carrying out " thing ", computing machine can't be effectively competent.
For people to the drawback of saving video frequency searching manpower and the demand of time and active computer video retrieval technology, the invention provides a kind of Video content retrieval method based on key-frame extraction, this technical scheme can while guarantee Video content retrieval accuracy rate, save a large amount of manpower and time, thus improve the work efficiency of Video content retrieval.
Summary of the invention
For above problem and demand, the present invention is by rejecting dead time section video content, key-frame extraction is carried out in useful time section video content, preliminary screening is carried out with key frame, carry out the mode of Video content retrieval with useful time section video corresponding to selected key frame for target again, a kind of Video content retrieval method based on key-frame extraction is provided.Thus while guarantee Video content retrieval accuracy rate, save a large amount of manpower and time, improve the work efficiency of Video content retrieval.
Concrete technical scheme provided by the invention is:
Based on a Video content retrieval method for key-frame extraction, the method comprises the following steps:
Video content analysis, utilizes computer picture Visual analysis techniques background in video scene to be separated with target;
Useful time section video is selected, and demarcate and have the rising of goal activities time period video, only time point, the video in described, only time point is useful time section video;
Video frequency searching, carries out Video content retrieval in useful time section video.
For improving the speed of the retrieval rate of video content, particularly manual retrieval further, described video frequency searching carries out according to following steps:
Key-frame extraction, in described useful time section video, required frame number image is chosen as key frame in interval;
Key frame is retrieved, and retrieves in described key frame, selected emphasis key frame, then with useful time section video corresponding to emphasis key frame for object carries out video frequency searching.
As further preferred version, described goal activities refers to that target occurs, disappears or motion.
Beneficial effect: a kind of Video content retrieval method based on key-frame extraction provided by the invention, by computer picture Visual analysis techniques, automatic analysis is carried out to needing retrieve video by computing machine, whether to have goal activities for foundation, automatically the differentiation of useful time section video and dead time section video is completed, and be standard according to this, reject the dead time section video in original video, retain the useful time section video in original video, and key frame is extracted in useful time section video, take key frame as preliminary search object, retrieve further with the useful time section video that key frame is corresponding again.This kind of mode greatly reduces the labour intensity of Video content retrieval, thus can save a large amount of manpower and time, improves the work efficiency of Video content retrieval.
Accompanying drawing explanation
It is workflow diagram of the present invention shown in Fig. 1;
It is embodiment of the present invention schematic diagram shown in Fig. 2;
Main mark mark: 1 is the original video time period; 2 for carrying out having goal activities video to rise, the only calibrated video time section of time point; 1-0 is original video start time point, is also first start time point having goal activities video time section simultaneously; 1-5 is original video termination time point, is also the 3rd the termination time point having goal activities video time section simultaneously; 2-1,2-3 are first and second the termination time point having goal activities video time section respectively; 2-2,2-4 are the start time point that second and the 3rd have goal activities video time section respectively; 9-1,9-2,9-3 are key frame, and wherein 9-3 also attaches most importance to key frame.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is described in more detail.Should be appreciated that specific embodiment described herein only to explain the present invention, be not intended to limit the present invention.
As shown in Figure 1 and Figure 2, the original video time period 1 i.e. duration of original video.According to the first step in Fig. 1, in the original video time period 1 shown in Fig. 2, mark first respectively has the start time point 1-0 of goal activities video time section, second to have the start time point 2-2 of goal activities video time section, the 3rd to have the start time point 2-4 of goal activities video time section, and first has the termination time of goal activities video time section point 2-1, second to have the termination time of goal activities video time section point 2-3, the 3rd to have the termination time point 1-5 of goal activities video time section.Obtain carrying out having goal activities video to rise, stop the calibrated video time section 2 of time point.Select useful time section video according to second step in Fig. 1, being respectively first has the start time point 1-0 of goal activities video time section to have the termination time of goal activities video time section point 2-1, second to have the start time point 2-2 of goal activities video time section to have the termination time of goal activities video time section point 2-3, the 3rd to have start time point 2-4 to the 1-5 the 3rd of goal activities video time section to have between the termination time of goal activities video time section point 1-5 first, second, third to have goal activities video time section to second to first.Again according to the 3rd step in Fig. 1, choose key frame 9-1,9-2,9-3 respectively.According to the 4th step in Fig. 1, key frame 9-1,9-2,9-3 are being retrieved, determining emphasis key frame 9-3.According to the 5th step in Fig. 1, what retrieval emphasis key frame 9-3 was corresponding the 3rd has start time point 2-4 to the 1-5 the 3rd of goal activities video time section to have the termination time of goal activities video time section to put the 3rd useful time section video between 1-5.In the present embodiment, namely have in goal activities video time section in each useful time section and choose a key frame respectively.Content retrieval is carried out to each key frame, when finding that there is value information, then retrieving useful time section video corresponding to key frame, finding required complete content.
For improving the practical application effect of technical solution of the present invention further, in the present embodiment, choosing of key frame can be chosen by computer automatically according to setup parameters such as moving target quantity, moving target travelling speed.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (3)
1., based on a Video content retrieval method for key-frame extraction, it is characterized in that, the method comprises the following steps:
Video content analysis, utilizes computer picture Visual analysis techniques background in video scene to be separated with target;
Useful time section video is selected, and demarcate and have the rising of goal activities time period video, only time point, the video in described, only time point is useful time section video;
Video frequency searching, carries out Video content retrieval in useful time section video.
2., as claimed in claim 1 based on the Video content retrieval method of key-frame extraction, it is characterized in that, described video frequency searching carries out according to following steps:
Key-frame extraction, in described useful time section video, required frame number image is chosen as key frame in interval;
Key frame is retrieved, and retrieves in described key frame, selected emphasis key frame, then with useful time section video corresponding to emphasis key frame for object carries out video frequency searching.
3. the Video content retrieval method based on key-frame extraction according to any one of claim 1 or 2, is characterized in that, described goal activities refers to that target occurs, disappears or motion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410829677.6A CN104504732A (en) | 2014-12-25 | 2014-12-25 | Video content retrieval method based on key frame extraction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410829677.6A CN104504732A (en) | 2014-12-25 | 2014-12-25 | Video content retrieval method based on key frame extraction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104504732A true CN104504732A (en) | 2015-04-08 |
Family
ID=52946126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410829677.6A Pending CN104504732A (en) | 2014-12-25 | 2014-12-25 | Video content retrieval method based on key frame extraction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104504732A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105407157A (en) * | 2015-11-23 | 2016-03-16 | 浙江宇视科技有限公司 | Video information push method and device |
| WO2019134587A1 (en) * | 2018-01-02 | 2019-07-11 | 阿里巴巴集团控股有限公司 | Method and device for video data processing, electronic device, and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1006459A2 (en) * | 1998-12-05 | 2000-06-07 | Lg Electronics Inc. | Content-based video story browsing system |
| CN102665064A (en) * | 2012-03-01 | 2012-09-12 | 浙江大学 | A traffic video monitoring system based on standard labeling and quick search |
| CN103871077A (en) * | 2014-03-06 | 2014-06-18 | 中国人民解放军国防科学技术大学 | Extraction method for key frame in road vehicle monitoring video |
-
2014
- 2014-12-25 CN CN201410829677.6A patent/CN104504732A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1006459A2 (en) * | 1998-12-05 | 2000-06-07 | Lg Electronics Inc. | Content-based video story browsing system |
| CN102665064A (en) * | 2012-03-01 | 2012-09-12 | 浙江大学 | A traffic video monitoring system based on standard labeling and quick search |
| CN103871077A (en) * | 2014-03-06 | 2014-06-18 | 中国人民解放军国防科学技术大学 | Extraction method for key frame in road vehicle monitoring video |
Non-Patent Citations (1)
| Title |
|---|
| 陆伟艳 等: "基于内容的视频检索的关键帧提取", 《微计算机信息》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105407157A (en) * | 2015-11-23 | 2016-03-16 | 浙江宇视科技有限公司 | Video information push method and device |
| CN105407157B (en) * | 2015-11-23 | 2019-08-02 | 浙江宇视科技有限公司 | Video information method for pushing and device |
| WO2019134587A1 (en) * | 2018-01-02 | 2019-07-11 | 阿里巴巴集团控股有限公司 | Method and device for video data processing, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101778260B (en) | Method and system for monitoring and managing videos on basis of structured description | |
| CN103778237B (en) | Video abstraction generation method based on space-time recombination of active events | |
| CN102222104B (en) | Method for intelligently extracting video abstract based on time-space fusion | |
| CN102193918B (en) | Video retrieval method and device | |
| CN103347167A (en) | Surveillance video content description method based on fragments | |
| CN104506934A (en) | Video processing method capable of saving storage space | |
| CN104063883A (en) | Surveillance video abstract generating method based on combination of object and key frames | |
| CN102610102A (en) | Suspect vehicle inspection and control method and system | |
| CN103678299A (en) | Method and device for monitoring video abstract | |
| CN110290346B (en) | Bidding video acquisition method based on intelligent video analysis | |
| CN103530638A (en) | Method for matching pedestrians under multiple cameras | |
| CN107480670A (en) | A kind of method and apparatus of caption extraction | |
| CN104298748A (en) | Device and method for face search in videos | |
| EP2426517A3 (en) | Knowledge capture and sharing for exploration and productiontool sessions | |
| CN102306153B (en) | Method for detecting goal events based on normalized semantic weighting and regular football video | |
| CN104504732A (en) | Video content retrieval method based on key frame extraction | |
| CN1662046A (en) | Apparatus and method for determining anchor shots | |
| CN103905789B (en) | The method and its device of the preservation, search and ex-post analysis of dynamic analyze data | |
| CN110457998B (en) | Image data association method and apparatus, data processing apparatus, and medium | |
| CN104182959A (en) | Target searching method and target searching device | |
| US9798932B2 (en) | Video extraction method and device | |
| CN111274435A (en) | Video backtracking method and device, electronic equipment and readable storage medium | |
| CN105516735A (en) | Representation frame acquisition method and representation frame acquisition apparatus | |
| CN104965915A (en) | User access behavior data processing method and system | |
| CN104270619A (en) | Safety warning method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150408 |
|
| WD01 | Invention patent application deemed withdrawn after publication |