CN103794234B - Event trace quick-searching platform based on massive video - Google Patents
Event trace quick-searching platform based on massive video Download PDFInfo
- Publication number
- CN103794234B CN103794234B CN201210420760.9A CN201210420760A CN103794234B CN 103794234 B CN103794234 B CN 103794234B CN 201210420760 A CN201210420760 A CN 201210420760A CN 103794234 B CN103794234 B CN 103794234B
- Authority
- CN
- China
- Prior art keywords
- video
- service module
- module
- analysis
- target trajectory
- 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.)
- Active
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a kind of event trace quick-searching platform based on massive video, including target trajectory space-time analysis module, integrated dispatch service module, intelligent video analysis service module, resource request service module, and monitor video network and platform database, wherein target trajectory space-time analysis module sends an instruction to described integrated dispatch service module and resource request service module, integrated dispatch service module forwards instructions to intelligent video analysis service module, intelligent video analysis service module connects described monitor video network, multiple video files are carried out Intelligent treatment according to instructing and returns result, resource request service module is connected with described platform database, provide the user inquiry and the read-write operation of resource requirement data.
Description
Technical field
The present invention relates to a kind of event trace quick-searching platform based on massive video, it is adaptable to area public security and local police station, machine
The places such as field, subway, monitoring community, it is achieved multiparty collaboration trans-regional, trans-departmental, cross-platform is disposed.
Background technology
Currently, the demand retrieved for intelligent monitoring and video image is more and more universal.Relation technological researching achieves certain one-tenth
Fruit the most also defines Related product, such as the IBM I3 intelligent monitor system of the U.S., American I BM QBIC system, Israel ioimage
Intelligent visual surveillance system.These systems or the detection for a certain specific image type, or different for a certain specific region
The detection of Chang Hangwei, or the intelligent video analysis of a certain video source, the sea of the different video form in different monitoring region
Amount video data, not one completely system can realize sea based on metropolitan area in scope trans-regional, interdepartmental
This function of quick-searching of amount video.The main weak point existed includes:
(1) massive video data retrieval spends substantial amounts of man power and material;
In actual applications, after burst security incident, the strength searched targets from massive video being also dependent on people may go out
Existing monitor video, spends substantial amounts of human and material resources.
(2) monitor video form is chaotic, it is impossible to be uniformly accessed into;
It is different that the monitoring device used on present society goes out manufacturer, video format the most difference, being uniformly accessed into for video
Difficulty is brought with video frequency searching.
(3) manually watch inefficiency, delay the time of solving a case.
During investigation crime target, still use the means of traditional artificial viewing to process monitor video, inefficiency, delay brokenly
The case time.
(4) Related Cases video and other information derive complexity.
Monitor video derives means the most easily, and existing case associated video information preserving type is different, data retrieval
Work is difficult to efficiently carry out.
Summary of the invention
It is desirable to provide a kind of event trace quick-searching platform based on massive video, this platform reads video from network and deposits
Massive video data in storage equipment, the video of decoding different coding form, by the intellectual analysis to video content, extracts and uses
Family is paid close attention to target and carries out target following and target association, and by across ken target active tracking technology, matching is formed pays close attention to target
Space historical track.Solve the problem that massive video data form is chaotic, cannot be uniformly accessed into, alleviate case detecting simultaneously
During the query and search working strength of clue target, shorten and pay close attention to target investigation required time, improve efficiency of solving a case.
Technical scheme is as follows:
A kind of event trace quick-searching platform based on massive video, it is characterised in that: include target trajectory space-time analysis module,
Integrated dispatch service module, intelligent video analysis service module, resource request service module, and monitor video network and platform
Data base, wherein:
Described target trajectory space-time analysis module comprises multiple client, accept the real-time video that user sends show, space time correlation
Analyze display and control operational order, and send an instruction to described integrated dispatch service module;Receive the history video that user sends
Retrieval, case editor control operational order, and send an instruction to described resource request service module;
Described integrated dispatch service module receives from the Video processing of target trajectory space-time analysis module or retrieves for examination instruction, and according to
The current operating conditions of each intellectual analysis processing unit, forwards instructions to suitable intellectual analysis processing unit, and intelligence is divided
The result of analysis processing unit feeds back to user;And timing receipt is reported from the running status of each intellectual analysis processing unit
And it is broadcast to all online target trajectory space-time analysis modules;
Described intelligent video analysis service module is made up of multiple intellectual analysis processing units, and it connects described monitor video network,
And receive the instruction from target trajectory space-time analysis module forwarded through integrated dispatch service module, according to the difference of different user
Request is the most parallel carries out Intelligent treatment to multiple video files, and returns result to integrated dispatch service module, then by comprehensively
Corresponding result is fed back to different users by dispatch service module;
Described resource request service module is connected with described platform database, stores the money needed for platform in described platform database
Source data, including monitoring IP Camera distribution and network topology data, the relevant information of history case, resource request takes
Business module receives the data retrieval request from all target trajectory space-time analysis modules, provides the user looking into of resource requirement data
Inquire about read-write operation.
When the present invention is directed to the metropolitan area massive video clue analysis lookup that burst occurred events of public safety faces in processing procedure of solving a case
Between long, manpower expend big, effective information and extract the various problems such as difficulty, use Distributed Calculation, intelligent video analysis and many
The advanced technologies such as dimension space-time analysis, it is adaptable to the event trace retrieval of metropolitan area massive video, can serve society's public security work under battle conditions
In, alleviate burst public safety case investigation during clue target query and search work, shorten target retrieval required time,
Improve disposal efficiency, and example use can be carried out in Internet of Things engineering, smart city, the safe city construction of the whole nation.
Accompanying drawing explanation
Fig. 1 is the logical structure schematic diagram of the present invention
Detailed description of the invention
As it is shown in figure 1, a kind of event trace quick-searching platform based on massive video of the present invention, including space division during target trajectory
Analysis module 1, integrated dispatch service module 2, intelligent video analysis service module 3, resource request service module 4, and monitoring
Video network 5 and platform database 6.
Searching platform supports multi-client, many intellectual analysis service unit, the parallel processing function of many monitor videos network insertion,
Integrate magnanimity monitor video data, improve video frequency searching efficiency.
Described target trajectory space-time analysis module comprises multiple client, accept the real-time video that user sends show, space time correlation
Analyze display and control operational order, and send an instruction to described integrated dispatch service module;Receive the history video that user sends
Retrieval, case editor control operational order, and send an instruction to described resource request service module.
Target trajectory space-time analysis submodule is platform man-machine interaction unit, uses double screen design, supports that multi-client works simultaneously.
The technology mainly solved includes: the mapping in real space of (1) target trajectory.By target movement locus in monitor video
Rationally mapping back in real space, the control point in monitoring network is demarcated by platform with real space, sets up in monitor video
Target trajectory and actual geographic space in the mapping relations of object space movement locus, real-playback target is geographical empty
Movement locus between.(2) target movement locus prediction in the non-ken.Owing to the wide of monitoring area and video camera regard
Territory limited between contradiction, and the reason in terms of economic dispatch, it is impossible to realizing the monitoring to all regions and cover, video is supervised
Control storage certainly exists a large amount of blind area.For the most overlapping and discontinuous situation of the observation ken, traditional video object detection and
Tracking technique is the most applicable, and platform uses the means that target detection tracking technique combines with GIS information analysis treatment technology, melts
Close the topological relation of video camera, it is achieved motion prediction rational to target in metropolitan area geospatial area.
Target trajectory space-time analysis module achieves the interdepartmental collaboration process of platform, and each client is unified double screen
Display operation software, provides video frequency searching, case editor, space time correlation analysis, real-time video and history video for different user
Display control operation.The photographic head network distribution situation of zones of different is shown for user search on electronic chart by platform, uses
Video file is retrieved by setting regular hour, place and photographic head data in family, includes video file taking out frame section
Browse, video topological correlation return look into, video intelligent summary processes, the mode that combines in interior multiple means of content quick-searching
Be analyzed processing, help user quickly find and position target, follow the tracks of and predict target travel direction, thus on map from
Dynamic label target and movement locus, the video segment of associated objects appearance, user can understand mesh by simple map operation
Target space motion information, by network real-time monitoring video, the different clean culture of history video segment, chain broadcast, download and spell
Connect operation and represent the time and space motion conditions of target for user.
Described integrated dispatch service module receives from the Video processing of target trajectory space-time analysis module or retrieves for examination instruction, and according to
The current operating conditions of each intellectual analysis processing unit, forwards instructions to suitable intellectual analysis processing unit, and intelligence is divided
The result of analysis processing unit feeds back to user;And timing receipt is reported from the running status of each intellectual analysis processing unit
And it is broadcast to all online target trajectory space-time analysis modules.
Due to multi-client, the composition of multiplied unit of platform, need a set of stable, high performance instruction dispatch service journey
Sequence, instruction scheduling and result that integrated dispatch service subsystem is responsible for safeguarding between each client and each processing unit return, therefore,
Integrated dispatch service is equivalent to the organ of whole searching platform, and it is by " media control service ", " retrieval dispatch service ", " shape
State monitoring management services " three module compositions, mainly achieve the merits such as video instructions control, search instruction scheduling, status monitoring
Energy.When platform startup optimization, integrated dispatch service subsystem and each intellectual analysis in video intelligent Analysis Service subsystem
Unit is set up and is connected, and receives each analytic unit running state parameter of sending of timing, then running state parameter is broadcast to all
The client of line, allows users to understand the running status that whole searching platform is current in real time;Meanwhile, integrated dispatch service subsystem
System can analyze, according to the running state parameter of each the intellectual analysis unit received, the state that each unit is current, " empty
Not busy " or " busy ", for the analytic unit of " busy ", illustrate that a certain section of video is analyzed processing by this unit,
Integrated dispatch service subsystem obtains the process progress of this unit further, thus substantially estimation has processed the required time.Combine
Closing dispatch service subsystem can be according to the current operating conditions of each intellectual analysis unit, the intellectual analysis to whole access platforms
Unit carries out the sequence of priority, the principle that sequence follows that free cells is preferential and busy unit short remaining time is preferential.When comprehensively
When dispatch service subsystem receives the retrieval dispatch command from some client in target trajectory space-time analysis subsystem, solve
Analyse the search condition that comprises in this instruction, as video file stores address, the data such as connectivity port, beginning and ending time and retrieval character,
Then determine to be sent to search instruction corresponding intellectual analysis unit according to the priority ordering of different intelligent analytic unit.For not
The retrieval dispatch command sent out with client, integrated dispatch service subsystem can be according to different user rights and retrieval scheduling
The process time length of operation that instruction is asked safeguards a job sequence to be retrieved, it then follows high authority user job preferential and
The principle of SJF.
Described intelligent video analysis service module is made up of multiple intellectual analysis processing units, and it connects described monitor video network,
And receive the instruction from target trajectory space-time analysis module forwarded through integrated dispatch service module, according to the difference of different user
Request is the most parallel carries out Intelligent treatment to multiple video files, and returns result to integrated dispatch service module, then by comprehensively
Corresponding result is fed back to different users by dispatch service module;
Intelligent video analysis service module by provide for platform the different-format video data such as DVR, IPSAN heterogeneous access,
Video intelligent processes and upload operation, it is ensured that the integration of trans-regional, trans-departmental, the cross-platform massive video data of system and
Access.User by target trajectory space-time analysis module send specific vision operation instruct, as video frequency abstract process request, interior
Hold retrieval request etc., through instruction scheduling and the forwarding of integrated dispatch service module, instruction is passed to some intellectual analysis service
Unit processes, and platform comprises multiple intellectual analysis service unit, can be the most right according to the different requests of different user
Multiple video files carry out Intelligent treatment, and return result to integrated dispatch service, then by integrated dispatch service by correspondence result
Feed back to different users.
Multiple intellectual analysis processing unit for parallel operation of intelligent video analysis service module, can carry out the decoding of multistage video simultaneously
And analyzing and processing, different processing units is separate, sets up clarification of objective model, clarification of objective mould inside processing unit
Type plays a decisive role in retrieval is followed the tracks of, and it is retrieval below and prediction offer condition.By Video segmentation target out
Unceasing study, obtains characteristic model accurately, and then rate pattern and topological relation model with target set up target at this video
In characteristic model.Moving object detection algorithm obtains background model by training and study video sequence, thus uses background phase
Subtraction detection moving target, extracts Target key frames, forms video frequency abstract, provide retrieval result.Intellectual analysis service subsystem
By using intelligent analysis process obtain result and result reports integrated dispatch service original video, integrated dispatch take
Be engaged according to the source of dispatch command result being transmitted to corresponding client, simultaneously intellectual analysis service subsystem can timing to
Integrated dispatch service reports the running status that each processing unit is current, it is achieved the function of platform monitoring running state.
Described resource request service module is connected with described platform database, stores the money needed for platform in described platform database
Source data, including monitoring IP Camera distribution and network topology data, the relevant information of history case, resource request takes
Business module receives the data retrieval request from all target trajectory space-time analysis modules, provides the user looking into of resource requirement data
Inquire about read-write operation.
The main task of resource request service module is responsible for the data query between each comprising modules of platform and platform database please
Ask and read-write operation.Platform data library storage uses the mode that classification storage and each layer map, it is achieved the magnanimity information of platform data
Storage and data sharing service, platform data is divided into basic database and user's auxiliary data base two class.Basic database is mainly deposited
The basic information data that storage platform is relevant, such as photographic head related data, the monitoring topology information of network of access, device parameter letter
Breath, device network information etc., user assistance data library storage user edits and needs the related data preserved, such as the video of association
Parameter information, user's plotted data, case editor's information etc..Resource request service subsystem receives the number from different clients
Instruct according to operation requests, complete corresponding data query, read and write, revise and deletion action return result to corresponding client.
Therefore, the platform storage data in data base will not directly be grasped by each user in target trajectory space-time analysis subsystem
Deal with, but carried out database manipulation by resource request service subsystem is unified.
Present invention event trace based on massive video quick-searching platform achieves one and can regard magnanimity in metropolitan area
Frequency carries out the system of event trace quick-searching, it is achieved that being uniformly accessed into of the massive video in different monitoring region, helps user's energy
Enough carry out trans-regional, trans-departmental, cross-platform cooperation, improve relevant staff and dispose the efficiency of case.
Claims (1)
1. an event trace quick-searching platform based on massive video, it is characterised in that: include target trajectory space-time analysis
Module, integrated dispatch service module, intelligent video analysis service module, resource request service module, and monitor video network
And platform database, wherein:
Described target trajectory space-time analysis module comprises multiple client, accept the real-time video that user sends show, space time correlation
Analyze display and control operational order, and send an instruction to described integrated dispatch service module;Receive the history video that user sends
Retrieval, case editor control operational order, and send an instruction to described resource request service module;
Described integrated dispatch service module receives from the Video processing of target trajectory space-time analysis module or retrieves for examination instruction, and according to
The current operating conditions of each intellectual analysis processing unit, forwards instructions to suitable intellectual analysis processing unit, and intelligence is divided
The result of analysis processing unit feeds back to user;And timing receipt is reported from the running status of each intellectual analysis processing unit
And it is broadcast to all online target trajectory space-time analysis modules;
Described intelligent video analysis service module is made up of multiple intellectual analysis processing units, and it connects described monitor video network,
And receive the instruction from target trajectory space-time analysis module forwarded through integrated dispatch service module, according to the difference of different user
Request is the most parallel carries out Intelligent treatment to multiple video files, and returns result to integrated dispatch service module, then by comprehensively
Corresponding result is fed back to different users by dispatch service module;
Described resource request service module is connected with described platform database, stores the money needed for platform in described platform database
Source data, including monitoring IP Camera distribution and network topology data, the relevant information of history case, resource request takes
Business module receives the data retrieval request from all target trajectory space-time analysis modules, provides the user looking into of resource requirement data
Inquire about read-write operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210420760.9A CN103794234B (en) | 2012-10-30 | 2012-10-30 | Event trace quick-searching platform based on massive video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210420760.9A CN103794234B (en) | 2012-10-30 | 2012-10-30 | Event trace quick-searching platform based on massive video |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103794234A CN103794234A (en) | 2014-05-14 |
CN103794234B true CN103794234B (en) | 2016-09-21 |
Family
ID=50669817
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210420760.9A Active CN103794234B (en) | 2012-10-30 | 2012-10-30 | Event trace quick-searching platform based on massive video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103794234B (en) |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105224535A (en) * | 2014-05-29 | 2016-01-06 | 浙江航天长峰科技发展有限公司 | Based on the concern target quick reference system of massive video |
CN104320677A (en) * | 2014-10-17 | 2015-01-28 | 深圳市同洲电子股份有限公司 | Audit server, a master control server and a video detection system |
CN107194490B (en) * | 2016-03-14 | 2022-08-12 | 商业对象软件有限公司 | Predictive modeling optimization |
CN108205528A (en) * | 2016-12-16 | 2018-06-26 | 上海仪电(集团)有限公司中央研究院 | A kind of retrieval analysis system towards magnanimity monitoring data |
CN109803067A (en) * | 2017-11-16 | 2019-05-24 | 富士通株式会社 | Video concentration method, video enrichment facility and electronic equipment |
CN109639790A (en) * | 2018-12-06 | 2019-04-16 | 上海美亦健健康管理有限公司 | A kind of distributed Internet of Things software architecture |
CN110213651A (en) * | 2019-05-28 | 2019-09-06 | 暨南大学 | A kind of intelligent merit Computer Aided Analysis System and method based on security protection video |
CN111405382B (en) * | 2019-06-24 | 2022-12-02 | 杭州海康威视系统技术有限公司 | Video abstract generation method and device, computer equipment and storage medium |
CN110795596B (en) * | 2019-11-07 | 2023-05-09 | 北京首钢自动化信息技术有限公司 | Information feedback method and device for client |
CN110933455B (en) * | 2019-12-16 | 2023-03-14 | 云粒智慧科技有限公司 | Video screening method and device, electronic equipment and storage medium |
CN111093092A (en) * | 2019-12-17 | 2020-05-01 | 成都通甲优博科技有限责任公司 | Video processing method, device, system, server and readable storage medium |
CN111147778B (en) * | 2019-12-23 | 2022-06-07 | 浙江大华技术股份有限公司 | Track recording method and device based on digital video recorder and storage medium |
CN111405246B (en) * | 2020-03-12 | 2021-04-06 | 厦门宇昊软件有限公司 | Smart city monitoring method and device and management terminal |
CN111506769B (en) * | 2020-04-21 | 2023-08-29 | 浙江大华技术股份有限公司 | Video file processing method and device, storage medium and electronic device |
CN112383800B (en) * | 2020-10-12 | 2023-03-17 | 特斯联科技集团有限公司 | Method and device for distributing and scheduling monitoring video data and electronic equipment |
CN113255477A (en) * | 2021-05-08 | 2021-08-13 | 深圳市安软科技股份有限公司 | Comprehensive management system and method for pedestrian video images |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101339553A (en) * | 2008-01-14 | 2009-01-07 | 浙江大学 | Approximate quick clustering and index method for mass data |
CN201388274Y (en) * | 2009-02-24 | 2010-01-20 | 东莞市星锋电脑办公设备有限公司 | Intelligent video quick-search system |
CN201699880U (en) * | 2010-05-14 | 2011-01-05 | 蔡晓东 | Distributed intelligent video searching system |
JP4709791B2 (en) * | 2007-03-13 | 2011-06-22 | 株式会社東芝 | Video processing apparatus and video processing method |
-
2012
- 2012-10-30 CN CN201210420760.9A patent/CN103794234B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4709791B2 (en) * | 2007-03-13 | 2011-06-22 | 株式会社東芝 | Video processing apparatus and video processing method |
CN101339553A (en) * | 2008-01-14 | 2009-01-07 | 浙江大学 | Approximate quick clustering and index method for mass data |
CN201388274Y (en) * | 2009-02-24 | 2010-01-20 | 东莞市星锋电脑办公设备有限公司 | Intelligent video quick-search system |
CN201699880U (en) * | 2010-05-14 | 2011-01-05 | 蔡晓东 | Distributed intelligent video searching system |
Non-Patent Citations (1)
Title |
---|
海量网络视频快速检索;刘守群;《中国知网》;20100401;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN103794234A (en) | 2014-05-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103794234B (en) | Event trace quick-searching platform based on massive video | |
CN105554059B (en) | Logistics transportation Intellisense and position service system based on Beidou navigation technology | |
EP2596630B1 (en) | Tracking apparatus, system and method | |
CN105407159B (en) | Logistics transportation position service system | |
EP3373549A1 (en) | A subsumption architecture for processing fragments of a video stream | |
CN105187771A (en) | Plant-level comprehensive supervision platform | |
CN102819578A (en) | Suspected target analyzing system and method by video investigation | |
US20160357762A1 (en) | Smart View Selection In A Cloud Video Service | |
US20170034483A1 (en) | Smart shift selection in a cloud video service | |
CN112087523B (en) | Intelligent building management system and device based on cloud service and computer readable storage medium | |
CN103079061A (en) | Video tracking processing device and video link processing device | |
CN113255477A (en) | Comprehensive management system and method for pedestrian video images | |
Shahabi et al. | Janus-multi source event detection and collection system for effective surveillance of criminal activity | |
US20180253491A1 (en) | Focalized Summarizations of a Video Stream | |
Chen et al. | Visualization in law enforcement | |
CN105224535A (en) | Based on the concern target quick reference system of massive video | |
CN102594897A (en) | Intelligent analysis system and method | |
CN106257447A (en) | The video storage of cloud storage server and search method, video cloud storage system | |
Yu et al. | A police big data analytics platform: Framework and implications | |
Xu | Issues in video analytics and surveillance systems: Research/prototyping vs. applications/user requirements | |
Zhu et al. | Application of Video Surveillance Intelligent Analysis System Based on KNN Algorithm | |
Zhang et al. | A Big Data based Decision Framework for Public Management and Service in Tourism | |
Humagain et al. | Determining Typology of Signalized Intersections Based on Pedestrian Actuation Through Use of Traffic Signal Controller Data | |
US11954151B1 (en) | Natural language processing for searching security video data | |
CN108416551A (en) | A kind of consignment logistic information management platform based on big data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |