CN103778159A - Video detection process based on video abstraction and video retrieval - Google Patents
Video detection process based on video abstraction and video retrieval Download PDFInfo
- Publication number
- CN103778159A CN103778159A CN201210414091.4A CN201210414091A CN103778159A CN 103778159 A CN103778159 A CN 103778159A CN 201210414091 A CN201210414091 A CN 201210414091A CN 103778159 A CN103778159 A CN 103778159A
- Authority
- CN
- China
- Prior art keywords
- video
- target
- concentrated
- suspicion
- snapshot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- G06F16/738—Presentation of query results
- G06F16/739—Presentation of query results in form of a video summary, e.g. the video summary being a video sequence, a composite still image or having synthesized frames
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a video detection process based on video abstraction and video retrieval. The process comprises the steps an original video related to a case is obtained from a video monitoring platform or obtained locally by a system, case basic information is added, list processing is conducted on the video, then the video is stored to a storage server, the system analyzes the video, the video is concentrated at first, frames with no movable object are removed, frames with movable objects are reserved, the concentrated video and full snapshots of all the movable targets are obtained, a suspicion target is determined according to the concentrated video and the target snapshots in cooperation with manual screening in a video comparison mode, and video clips of the suspicion target and the suspicion target snapshots are obtained. According to the video detection process based on video abstraction and video retrieval, the video clips and snapshots of the suspicion target can be obtained from the mass original videos, and the video surveillance efficiency of public security organs is improved.
Description
Technical field
The present invention relates to a kind of computer vision field, be specifically related to a kind of investigation of the video based on video frequency abstract and video frequency searching flow process.
Background technology
along with " safe city " and the propelling of " day net engineering ", utilize monitor video to become the important means of police criminal detection investigation as the video investigation of clue to solve the case, hit dramatically the criminal offence of illegal one's share of expenses for a joint undertaking.But before by manually watching magnanimity video to carry out the mode inefficiency of video criminal investigation, and easily omit target.
When video investigation, generally only pay close attention to moving target, can also obtain some features of suspicion target by eye witness or investigation in early stage.Concentrate summary and video retrieval technology by video, can omit the picture without moving target, and retrieve suspicion target moving target Rigen according to target signature, greatly improve the efficiency of video investigation.
Summary of the invention
The object of the invention is to overcome the above problem that prior art exists, a kind of investigation of the video based on video frequency abstract and video frequency searching flow process is provided, the present invention can remove to obtain the video segment of suspicion target and snapshot as clue from the original video of magnanimity, improves the efficiency of public security video investigation.
For realizing above-mentioned technical purpose, reach above-mentioned technique effect, the present invention is achieved through the following technical solutions:
A video investigation flow process based on video frequency abstract and video frequency searching, comprises the following steps:
Step 1), from monitor supervision platform or local copy video, stores storage server into after video need to be catalogued by case management;
Step 2) in client according to Allocation Analysis parameter, select video from storage server, determine as required and need concentrated or retrieval;
The automatic cloud computing of step 3) system, carries out load sharing, selects the concentrated and retrieval server that load is little to analyze;
It is concentrated that the concentrated server of step 4) carries out video, obtains comprising concentrated video and the full snapshot of all moving targets of all moving targets;
As required, retrieval server carries out video frequency searching according to target signature to step 5), obtains the target snapshot of arranging according to similarity;
Step 6) is watched concentrated video or browsing objective snapshot, determines the target snapshot of suspicion target, deposits case management server after mark;
Step 7), according to the target snapshot of suspicion target, obtains the original video fragment of suspicion target, deposits case management server after mark;
Step 8) in conjunction with electronic chart, is spliced into suspicion target trajectory by each suspicion target original video fragment;
The snapshot of suspicion target and movement locus are filed into case clue by step 9), generates Reportage on Case, for further investigating and showing.
Further, described step 2) in do not select retrieval, skips steps 5).
The invention has the beneficial effects as follows:
1, reduce manually to check the pressure of magnanimity video, the convenient suspicion target of searching from magnanimity video;
2, perfect control of authority function ensures information safety, but the functions such as client program request and mark allow again the personnel in charge of the case of authority can realize information sharing, improves the efficiency of solving a case;
3, system realizes in conjunction with criminal investigation is actual, and case management is simply orderly; The suspicion target trajectory that video-splicing generates, in conjunction with the Reportage on Case of output, allows result show convenient and swift.
Above-mentioned explanation is only the general introduction of technical solution of the present invention, in order to better understand technological means of the present invention, and can be implemented according to the content of instructions, below with preferred embodiment of the present invention and coordinate accompanying drawing to be described in detail as follows.The specific embodiment of the present invention is provided in detail by following examples and accompanying drawing thereof.
Accompanying drawing explanation
Accompanying drawing described herein is used to provide a further understanding of the present invention, forms the application's a part, and schematic description and description of the present invention is used for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is schematic flow sheet of the present invention;
Fig. 2 is topological diagram of the present invention.
Embodiment
Below with reference to the accompanying drawings and in conjunction with the embodiments, describe the present invention in detail.
Shown in Fig. 1, a kind of investigation of the video based on video frequency abstract and video frequency searching flow process, comprises the following steps:
Step 1) is obtained or from local copy original video from monitor supervision platform, and video is needed according to case management, stores storage server into after cataloguing, add case and video essential information;
Step 2) as required, Allocation Analysis parameter in concentrated and retrieval client; If do not know suspicion clarification of objective before video investigation, only carry out concentration operation; If before investigation or along with the carrying out of investigating, known some feature of suspicion target, just can also carry out video frequency searching according to feature; Selecting needed video to submit to from storage server analyzes.When submission, can submit in batches multiple videos to, configurable parameter comprises the sensitivity that represents the different scenes such as day and night, the area-of-interest of paying close attention to and lose interest in region and the color of destination object, if destination object is people, can also distinguish lower part of the body color;
Step 3) system adopts cloud computing technology automatically, carries out load sharing, and in selection server group, load little concentrated server or retrieval server are analyzed; If Servers-all is running at full capacity all, the task of these submissions enters in queue and waits in line; In the time that task is distributed, also relate to priority scheduling, the task that priority is high will be inserted into the foremost of queue;
In the concentrated server of step 4), carry out the concentrated summary of video, obtain comprising concentrated video and the full snapshot of all moving targets of all moving targets; What adopt is dynamic texture modeling algorithm, first extracts video background, then each moving target is extracted, and analyzes its feature and information is deposited to database; Finally by Image Mosaics technology, each moving target is inlayed back in background, the moving target of different time points can appear at the same picture of concentrated video, the cocnentration factor that obtains is like this high and comprise all moving targets, target in the concentrated video of click or the snapshot of moving target, the snapshot of setting up when analyzing before and the mapping relations of original video, redirect original video fast, checks the state of target in original video;
Step 5) retrieval server is according to step 2) the middle parameter configuring, in database, carry out video frequency searching according to feature, obtain the target snapshot of arranging according to target signature similarity; Click this target snapshot, redirect original video fast, checks the state of target in original video; If preceding step 2) in do not select retrieval, skip this step;
Step 6), by watching the target snapshot of concentrated video or retrieval, finds the target snapshot of suspicion target, adds mark, for example, after " suspect A ", deposit on case management server;
Step 7), on the basis of suspicion target snapshot, finds the each original video fragment of suspicion target.In the time of definite suspicion fragment, can carry out video contrast and play; Determine after suspicion video segment, deposit on case management server after adding necessary mark;
Step 8), on the basis of previous step, in conjunction with electronic chart, adopts video-splicing technology by each original video fragment of suspicion target, is spliced into suspicion target trajectory, and is saved in case management server;
The filing of the target snapshot of suspicion target and target trajectory is formed case clue by step 9), and the generating video report that investigates the case, for further investigation or displaying; There is the personnel in charge of the case of associated rights, can, at client program request associated video, check snapshot; The Reportage on Case generating according to predetermined format is that case is shown mode the most intuitively.
The principle of work of the present embodiment is as follows:
There is robbery case in certain valuables shop for example, in order to obtain suspect's photo and video segment to determine one's identity and to run away circuit, need to check 100 cameras of each bayonet socket, sets foot-point and the video of totally 5 days afterwards before the case happened.If rely on manpower to check, the total duration of video is 10,000 2 thousand hours.50 people also need to watch 10 days round the clock endlessly, when affecting case handling efficiency, are also easy to omit target because the physiology for people limits.Use after the video Reconnaissance system of video frequency abstract, video frequency searching, its instantiation is as follows:
1: after crime, from monitor supervision platform or local copy video.After video need to be catalogued by case management, store storage server into, the information of interpolation comprises case essential information, and the video obtaining is first-class from which shooting;
2: because only need to pay close attention to moving target, in the feature that starts also not know suspect.When first analysis, in client, select the concentrated video of output and full snapshot.If along with the carrying out of investigation, follow-uply can again carry out retrieval analysis to these videos.Select video to submit to from storage server and analyze, and set the priority of these videos, be made as height with near for example priority of on-the-spot one kilometer of case strong correlation;
3: the automatic cloud computing of system, carry out load sharing, select load little a certain or a few concentrated retrieval servers to analyze;
4: it is concentrated that concentrated server carries out video, obtain comprising the concentrated video of all moving targets.By watching this concentrated video, compare and watch original video, greatly save the time.If find some interested video segments, and some feature photos of suspicion target, can retrieve according to feature.
5: retrieval server is retrieved according to feature, in the target snapshot obtaining, meet the foremost that comes of feature, for fear of causing that because of illumination condition difference etc. target omits, after the target that other similarities are lower is also listed in;
6: the target snapshot being retrieved is manually investigated, found suspect's target snapshot, after mark as " suspect A ", after interpolation case information, deposit case management server
7: according to each target snapshot of suspect, obtain each original video fragment of suspicion target, after mark, deposit case management server
8: each original video fragment of suspect, in conjunction with electronic chart, is spliced into movement locus.According to this movement locus, just can determine motion state or even the identity of suspicion target;
9: the snapshot of suspicion target and movement locus are filed into case clue, generate Reportage on Case, for further investigating and showing.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (2)
1. the investigation of the video based on a video frequency abstract and video frequency searching flow process, is characterized in that: comprise the following steps:
Step 1), from monitor supervision platform or local copy video, stores storage server into after video need to be catalogued by case management;
Step 2) in client according to Allocation Analysis parameter, select video from storage server, determine as required and need concentrated or retrieval;
The automatic cloud computing of step 3) system, carries out load sharing, selects the concentrated and retrieval server that load is little to analyze;
It is concentrated that the concentrated server of step 4) carries out video, obtains comprising concentrated video and the full snapshot of all moving targets of all moving targets;
As required, retrieval server carries out video frequency searching according to target signature to step 5), obtains the target snapshot of arranging according to similarity;
Step 6) is watched concentrated video or browsing objective snapshot, determines the target snapshot of suspicion target, deposits case management server after mark;
Step 7), according to the target snapshot of suspicion target, obtains the original video fragment of suspicion target, deposits case management server after mark;
Step 8) in conjunction with electronic chart, is spliced into suspicion target trajectory by each suspicion target original video fragment;
The snapshot of suspicion target and movement locus are filed into case clue by step 9), generates Reportage on Case, for further investigating and showing.
2. a kind of video based on video frequency abstract and video frequency searching investigation flow process according to claim 1, is characterized in that: described step 2) in do not select retrieval, skips steps 5).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210414091.4A CN103778159A (en) | 2012-10-26 | 2012-10-26 | Video detection process based on video abstraction and video retrieval |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210414091.4A CN103778159A (en) | 2012-10-26 | 2012-10-26 | Video detection process based on video abstraction and video retrieval |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103778159A true CN103778159A (en) | 2014-05-07 |
Family
ID=50570401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210414091.4A Pending CN103778159A (en) | 2012-10-26 | 2012-10-26 | Video detection process based on video abstraction and video retrieval |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103778159A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104702917A (en) * | 2015-03-25 | 2015-06-10 | 成都市灵奇空间软件有限公司 | Video concentrating method based on micro map |
| CN106126680A (en) * | 2016-06-29 | 2016-11-16 | 北京互信互通信息技术有限公司 | A kind of video image reconnaissance method and system |
| CN107483880A (en) * | 2017-07-05 | 2017-12-15 | 武汉烽火众智数字技术有限责任公司 | The mobile video investigation device and its methods of investigation of a kind of on-line off-line cooperation interaction |
| CN107967348A (en) * | 2017-12-13 | 2018-04-27 | 武汉烽火众智数字技术有限责任公司 | The system and method for video investigation efficiency are improved based on more network data fusion applications |
| CN110188238A (en) * | 2019-05-15 | 2019-08-30 | 上海良相智能化工程有限公司 | A kind of wisdom public security video frequency search system |
| CN110545383A (en) * | 2019-09-16 | 2019-12-06 | 湖北公众信息产业有限责任公司 | Video integrated management platform system |
| CN112364682A (en) * | 2020-09-22 | 2021-02-12 | 苏州千视通视觉科技股份有限公司 | Case searching method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101299812A (en) * | 2008-06-25 | 2008-11-05 | 北京中星微电子有限公司 | Method, system for analyzing, storing video as well as method, system for searching video |
| US20100185608A1 (en) * | 2009-01-21 | 2010-07-22 | Seiko Epson Corporation | Information retrieval device, information retrieval system, information retrieval program and information retrieval method |
| CN101840422A (en) * | 2010-04-09 | 2010-09-22 | 江苏东大金智建筑智能化***工程有限公司 | Intelligent video retrieval system and method based on target characteristic and alarm behavior |
| CN102156707A (en) * | 2011-02-01 | 2011-08-17 | 刘中华 | Video abstract forming and searching method and system |
-
2012
- 2012-10-26 CN CN201210414091.4A patent/CN103778159A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101299812A (en) * | 2008-06-25 | 2008-11-05 | 北京中星微电子有限公司 | Method, system for analyzing, storing video as well as method, system for searching video |
| US20100185608A1 (en) * | 2009-01-21 | 2010-07-22 | Seiko Epson Corporation | Information retrieval device, information retrieval system, information retrieval program and information retrieval method |
| CN101840422A (en) * | 2010-04-09 | 2010-09-22 | 江苏东大金智建筑智能化***工程有限公司 | Intelligent video retrieval system and method based on target characteristic and alarm behavior |
| CN102156707A (en) * | 2011-02-01 | 2011-08-17 | 刘中华 | Video abstract forming and searching method and system |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104702917A (en) * | 2015-03-25 | 2015-06-10 | 成都市灵奇空间软件有限公司 | Video concentrating method based on micro map |
| CN106126680A (en) * | 2016-06-29 | 2016-11-16 | 北京互信互通信息技术有限公司 | A kind of video image reconnaissance method and system |
| CN107483880A (en) * | 2017-07-05 | 2017-12-15 | 武汉烽火众智数字技术有限责任公司 | The mobile video investigation device and its methods of investigation of a kind of on-line off-line cooperation interaction |
| CN107967348A (en) * | 2017-12-13 | 2018-04-27 | 武汉烽火众智数字技术有限责任公司 | The system and method for video investigation efficiency are improved based on more network data fusion applications |
| CN110188238A (en) * | 2019-05-15 | 2019-08-30 | 上海良相智能化工程有限公司 | A kind of wisdom public security video frequency search system |
| CN110545383A (en) * | 2019-09-16 | 2019-12-06 | 湖北公众信息产业有限责任公司 | Video integrated management platform system |
| CN112364682A (en) * | 2020-09-22 | 2021-02-12 | 苏州千视通视觉科技股份有限公司 | Case searching method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103778159A (en) | Video detection process based on video abstraction and video retrieval | |
| US11210504B2 (en) | Emotion detection enabled video redaction | |
| US20200265085A1 (en) | Searching recorded video | |
| Xiao et al. | Video-based evidence analysis and extraction in digital forensic investigation | |
| US20210397848A1 (en) | Scene marking | |
| CA2568049C (en) | Pipeline architecture for analyzing multiple video streams | |
| US9171075B2 (en) | Searching recorded video | |
| US20150264296A1 (en) | System and method for selection and viewing of processed video | |
| Chen et al. | Intelligent urban video surveillance system for automatic vehicle detection and tracking in clouds | |
| US10104345B2 (en) | Data-enhanced video viewing system and methods for computer vision processing | |
| US20100287161A1 (en) | System and related techniques for detecting and classifying features within data | |
| KR20080075091A (en) | Storage of video analysis data for real-time alerting and forensic analysis | |
| CN109740003B (en) | Filing method and device | |
| CN109800664B (en) | Method and device for determining passersby track | |
| JP2022518459A (en) | Information processing methods and devices, storage media | |
| CN109784220B (en) | Method and device for determining passerby track | |
| CN109800318B (en) | Filing method and device | |
| Xu et al. | Video analytics with zero-streaming cameras | |
| CN107358622A (en) | A kind of video information processing method and system based on visualization movement locus | |
| US20060062430A1 (en) | Feed-customized processing of multiple video streams in a pipeline architecture | |
| CN104182959A (en) | Target searching method and target searching device | |
| US7672370B1 (en) | Deep frame analysis of multiple video streams in a pipeline architecture | |
| Sharma et al. | Architectural framework for implementing visual surveillance as a service | |
| Fischer et al. | Privacy-aware smart video surveillance revisited | |
| García et al. | Features accumulation on a multiple view oriented model for people re-identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140507 |