CN106507041A - Video data analysis method - Google Patents
Video data analysis method Download PDFInfo
- Publication number
- CN106507041A CN106507041A CN201610952083.3A CN201610952083A CN106507041A CN 106507041 A CN106507041 A CN 106507041A CN 201610952083 A CN201610952083 A CN 201610952083A CN 106507041 A CN106507041 A CN 106507041A
- Authority
- CN
- China
- Prior art keywords
- data
- video
- video data
- collecting
- crowd
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
- G06F16/71—Indexing; Data structures therefor; Storage structures
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/80—Information retrieval; Database structures therefor; File system structures therefor of semi-structured data, e.g. markup language structured data such as SGML, XML or HTML
- G06F16/81—Indexing, e.g. XML tags; Data structures therefor; Storage structures
Abstract
The present invention proposes a kind of video data analysis method, comprises the following steps：Video data is gathered by video acquisition terminal；And the video data for collecting is stored respectively in database and storage server with xml data；Obtained by Resource Server and be detected item correction data；The video data for collecting is analyzed with detected item correction data by video analytics server and is mated；Matching result will be analyzed with xml data is activations to data acquisition program；Data acquisition program extracts the picture and video segment data being matched from the video data for collecting by the xml data for analyzing matching result.The present invention is by video analytics server can video data be detected whether as doubtful dangerous goods, whether detection article is stolen, detect whether article leaves, detects whether flame, detecting whether that crowd massing, the crowd of detecting whether run, detect whether the application for invading the aspect such as circumference to collecting.
Description
Technical field
The present invention relates to video detection technology field, more particularly to a kind of video data analysis method.
Background technology
Video analysis or video content analysis are covered (to be included from Video Motion Detection and audio detection to more advanced system
Camera modify unilaterally (tampering) detection, personnel count, detection object through line interested or region, License Plate Identification,
Video is divided into foreground part and background parts, tracking target, traffic analysis, meta-data extraction, biometric applications, Yi Jiren
Face is recognized). video analysis also cause monitoring system more intelligent, and substantial amounts of view data is reduced to manageable level.
Intelligent video surveillance system for example can automatically analyze monitoring video in real time and to monitoring that video tags, and detect suspicious work
Dynamic, start videograph, activate alarm or other actions to alert operator or other staff.
However, the search efficiency of traditional video analysis is low and inquiry velocity is slow, its range of application is narrow.
Content of the invention
The purpose of the present invention is intended at least solve one of described technological deficiency.
For this purpose, it is an object of the invention to propose a kind of video data analysis method, using the data storage and query of XML
Feature, is effectively accessed to video data and is managed, and improves search efficiency and speed, analysis video data is carried out excellent
Change.
To achieve these goals, the present invention provides a kind of video data analysis method, comprises the following steps：
Step S1, gathers video data by video acquisition terminal；And the video data for collecting is distinguished with xml data
It is stored in database and storage server；
Step S2, is obtained by Resource Server and is detected item correction data；
The video data for collecting is analyzed with detected item correction data by step S3 by video analytics server
Coupling；
Step S4, will analyze matching result with xml data is activations to data acquisition program；
Step S4, data acquisition program are extracted from the video data for collecting by the xml data for analyzing matching result
The picture being matched and video segment data；
Step S5, data acquisition program by process after data be stored respectively in database and storage server.
Further, the video acquisition terminal can also gather the public place that the crowd is dense, and what the crowd is dense is public
Place at least includes airport, railway station, bus station, building, school.
Further, in step s 2, being detected item correction data at least includes:The data of flame, the data of dangerous material,
The gathered video data of video acquisition terminal.
Further, video analytics server is analyzed coupling to the video data for collecting, for detecting whether being
Doubtful dangerous goods, detection article whether stolen, detected whether that article is left, detected whether flame, detected whether crowd
Aggregation, the crowd of detecting whether run, detect whether to invade circumference.
Further, detect whether for doubtful dangerous goods when, by the video data for collecting with pass through Resource Server
The picture or video for obtaining dangerous goods is analyzed coupling；
When detecting whether that article is stolen and has detected whether that article is left, by the video data for collecting and the detection zone
Previous frame video data is analyzed coupling；
When having detected whether flame, by the video data for collecting with by Resource Server obtain flame picture or regard
Frequency is analyzed coupling；
When detecting whether crowd massing, by the number in the video data for collecting and assemble index and set aggregation number
Threshold value, assemble index threshold value are contrasted, and number that and if only if is more than set aggregation number threshold value and assemble index more than aggregation
During time threshold, it is judged as crowd massing；
When the crowd of detecting whether is run, by the behavioral data of people, time data in the video data for collecting with set
Threshold value of running, time threshold contrasted, when behavioral data and time data meet set threshold value of running, time threshold
When, judgement crowd run；
When detecting whether to invade circumference, the behavioral data of people in the video data for collecting is invaded with set circumference
Data are contrasted, and when behavioral data meets circumference invasion data, then judge there is invasion circumference situation.
Further, video analytics server can also enter line number by interface with third party's security system or rays safety detection apparatus
According to transmission.
The video data for collecting is stored respectively in database and storage server with xml data by the present invention, by regarding
After frequency analysis server is analyzed coupling, the xml data for analyzing matching result are being passed through from collection by data acquisition program
To video data in extract the picture and video segment data that are matched, using the data storage and query feature of XML, to regarding
Frequency is improved search efficiency and speed according to effectively accessing and being managed, and is optimized to analyzing video data.
The present invention by video analytics server can to collect video data detected whether for doubtful dangerous goods,
Whether detection article is stolen, detected whether that article is left, detected whether flame, detected whether crowd massing, detect whether
Crowd runs, detect whether the application of invading the aspects such as circumference.
The additional aspect of the present invention and advantage will be set forth in part in the description, and partly will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Description of the drawings
The above-mentioned and/or additional aspect and advantage of the present invention will become from the description with reference to accompanying drawings below to embodiment
Substantially and easy to understand, wherein：
Fig. 1 is the overall flow figure of the present invention；
Fig. 2 is the workflow diagram of the present invention
Specific embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from start to finish
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and be not considered as limiting the invention.
The present invention provides a kind of video data analysis method, shown in refer to the attached drawing 1-2, comprises the following steps：
Step S1, gathers video data by video acquisition terminal；And the video data for collecting is distinguished with xml data
It is stored in database and storage server；
Wherein, video acquisition terminal can also gather the public place that the crowd is dense, and the public place that the crowd is dense is at least
Including airport, railway station, bus station, building, school.
Step S2, is obtained by Resource Server and is detected item correction data；
Wherein, being detected item correction data at least includes:The data of flame, the data of dangerous material, video acquisition terminal institute
Collection video data.
The video data for collecting is analyzed with detected item correction data by step S3 by video analytics server
Coupling；
Video analytics server is analyzed coupling to the video data for collecting, for detecting whether being doubtful danger
Product, detection article whether stolen, detected whether article leave, detected whether flame, detect whether crowd massing, detection be
No crowd runs, detects whether to invade circumference.
Detect whether for doubtful dangerous goods when, by the video data for collecting with danger is obtained by Resource Server
The picture or video of product are analyzed coupling；
When detecting whether that article is stolen and has detected whether that article is left, by the video data for collecting and the detection zone
Previous frame video data is analyzed coupling；
When having detected whether flame, by the video data for collecting with by Resource Server obtain flame picture or regard
Frequency is analyzed coupling；
When detecting whether crowd massing, by the number in the video data for collecting and assemble index and set aggregation number
Threshold value, assemble index threshold value are contrasted, and number that and if only if is more than set aggregation number threshold value and assemble index more than aggregation
During time threshold, it is judged as crowd massing；
When the crowd of detecting whether is run, by the behavioral data of people, time data in the video data for collecting with set
Threshold value of running, time threshold contrasted, when behavioral data and time data meet set threshold value of running, time threshold
When, judgement crowd run；
When detecting whether to invade circumference, the behavioral data of people in the video data for collecting is invaded with set circumference
Data are contrasted, and when behavioral data meets circumference invasion data, then judge there is invasion circumference situation.
Video analytics server can also be carried out data transmission with third party's security system or rays safety detection apparatus by interface.
Step S4, will analyze matching result with xml data is activations to data acquisition program；
Step S4, data acquisition program are extracted from the video data for collecting by the xml data for analyzing matching result
The picture being matched and video segment data；
Step S5, data acquisition program by process after data be stored respectively in database and storage server.
The video data for collecting is stored respectively in database and storage server with xml data by the present invention, by regarding
After frequency analysis server is analyzed coupling, the xml data for analyzing matching result are being passed through from collection by data acquisition program
To video data in extract the picture and video segment data that are matched, using the data storage and query feature of XML, to regarding
Frequency is improved search efficiency and speed according to effectively accessing and being managed, and is optimized to analyzing video data.
The present invention by video analytics server can to collect video data detected whether for doubtful dangerous goods,
Whether detection article is stolen, detected whether that article is left, detected whether flame, detected whether crowd massing, detect whether
Crowd runs, detect whether the application of invading the aspects such as circumference.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art is in the principle and objective without departing from the present invention
In the case of above-described embodiment can be changed within the scope of the invention, change, replace and modification.The scope of the present invention
Extremely it is equal to limit by claims.
Claims (6)
1. a kind of video data analysis method, it is characterised in that comprise the following steps：
Step S1, gathers video data by video acquisition terminal；And the video data for collecting is stored respectively with xml data
In database and storage server；
Step S2, is obtained by Resource Server and is detected item correction data；
The video data for collecting and detected item correction data are analyzed by step S3 by video analytics server
Match somebody with somebody；
Step S4, will analyze matching result with xml data is activations to data acquisition program；
Step S4, data acquisition program extract quilt from the video data for collecting by the xml data for analyzing matching result
The picture that matches somebody with somebody and video segment data；
Step S5, data acquisition program by process after data be stored respectively in database and storage server.
2. video data analysis method as claimed in claim 1, it is characterised in that：The video acquisition terminal can also be gathered
The public place that the crowd is dense, the public place that the crowd is dense at least include airport, railway station, bus station, building, school.
3. video data analysis method as claimed in claim 1, it is characterised in that：In step s 2, item contrast number is detected
According at least including:The data of flame, the data of dangerous material, the gathered video data of video acquisition terminal.
4. video data analysis method as claimed in claim 1, it is characterised in that：Video analytics server is to regarding for collecting
Frequency evidence is analyzed coupling, for detecting whether for doubtful dangerous goods, whether detection article is stolen, detected whether article
Leave, detected whether flame, detect whether that crowd massing, the crowd of detecting whether run, detect whether to invade circumference.
5. video data analysis method as claimed in claim 4, it is characterised in that：Detect whether for doubtful dangerous goods when,
The video data for collecting is mated with the picture or being analyzed for video that are obtained dangerous goods by Resource Server；
When detecting whether that article is stolen and has detected whether that article is left, by one on the video data for collecting and the detection zone
Frame video data is analyzed coupling；
When having detected whether flame, by the video data for collecting and the picture or video that obtain flame by Resource Server
It is analyzed coupling；
When detecting whether crowd massing, by the number in the video data for collecting and assemble index and set aggregation number threshold
Value, assemble index threshold value are contrasted, when number that and if only if is more than aggregation more than set aggregation number threshold value and assemble index
Between threshold value when, be judged as crowd massing；
When the crowd of detecting whether is run, the behavioral data of people, time data in the video data for collecting and set are run quickly
Run threshold value, time threshold to be contrasted, when behavioral data and time data meet set threshold value of running, time threshold,
Judgement crowd run；
When detecting whether to invade circumference, by the behavioral data of people in the video data for collecting and set circumference invasion data
Contrasted, when behavioral data meets circumference invasion data, then judged there is invasion circumference situation.
6. video data analysis method as claimed in claim 1, it is characterised in that：Video analytics server can also be by connecing
Mouth is carried out data transmission with third party's security system or rays safety detection apparatus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610952083.3A CN106507041A (en) | 2016-11-02 | 2016-11-02 | Video data analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610952083.3A CN106507041A (en) | 2016-11-02 | 2016-11-02 | Video data analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106507041A true CN106507041A (en) | 2017-03-15 |
Family
ID=58321257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610952083.3A Pending CN106507041A (en) | 2016-11-02 | 2016-11-02 | Video data analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106507041A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100321183A1 (en) * | 2007-10-04 | 2010-12-23 | Donovan John J | A hierarchical storage manager (hsm) for intelligent storage of large volumes of data |
| CN203181094U (en) * | 2012-11-06 | 2013-09-04 | 湖南爱瑞杰科技发展股份有限公司 | Intelligent video monitoring system |
| CN103581626A (en) * | 2013-11-04 | 2014-02-12 | 浙江宇视科技有限公司 | Video monitoring system and video storage information recording method |
| CN103973653A (en) * | 2013-02-01 | 2014-08-06 | 上海迪爱斯通信设备有限公司 | Intelligent sensing analyzer |
| CN105450987A (en) * | 2015-11-12 | 2016-03-30 | 北京弘恒科技有限公司 | Intelligent recognition platform video monitoring early warning system |
-
2016
- 2016-11-02 CN CN201610952083.3A patent/CN106507041A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100321183A1 (en) * | 2007-10-04 | 2010-12-23 | Donovan John J | A hierarchical storage manager (hsm) for intelligent storage of large volumes of data |
| CN203181094U (en) * | 2012-11-06 | 2013-09-04 | 湖南爱瑞杰科技发展股份有限公司 | Intelligent video monitoring system |
| CN103973653A (en) * | 2013-02-01 | 2014-08-06 | 上海迪爱斯通信设备有限公司 | Intelligent sensing analyzer |
| CN103581626A (en) * | 2013-11-04 | 2014-02-12 | 浙江宇视科技有限公司 | Video monitoring system and video storage information recording method |
| CN105450987A (en) * | 2015-11-12 | 2016-03-30 | 北京弘恒科技有限公司 | Intelligent recognition platform video monitoring early warning system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109765539B (en) | Indoor user behavior monitoring method and device, electrical equipment and home monitoring system | |
| EP3654285B1 (en) | Object tracking using object attributes | |
| CN102867386B (en) | Intelligent video analysis-based forest smoke and fire detection method and special system thereof | |
| CN109766779B (en) | Loitering person identification method and related product | |
| CN102164270A (en) | Intelligent video monitoring method and system capable of exploring abnormal events | |
| US20030040925A1 (en) | Vision-based method and apparatus for detecting fraudulent events in a retail environment | |
| US20100318566A1 (en) | Behavior history retrieval apparatus and behavior history retrieval method | |
| CN111814510B (en) | Method and device for detecting legacy host | |
| CN103235942A (en) | Facial recognition method applied to entrance guard | |
| CN112132045A (en) | Community personnel abnormal behavior monitoring scheme based on computer vision | |
| KR20060031832A (en) | A smart visual security system based on real-time behavior analysis and situation cognizance | |
| Bouma et al. | Automatic detection of suspicious behavior of pickpockets with track-based features in a shopping mall | |
| CN113887445A (en) | Method and system for identifying standing and loitering behaviors in video | |
| Patil et al. | Suspicious movement detection and tracking based on color histogram | |
| CN112002094A (en) | Cell personnel management method based on triangular positioning | |
| CN113269127A (en) | Face recognition and pedestrian re-recognition monitoring method and system for real-time automatic database building | |
| CN102244769B (en) | Object and key person monitoring system and method thereof | |
| JP6893204B2 (en) | Methods, devices and systems for detecting wandering events | |
| Liao et al. | Security event recognition for visual surveillance | |
| Filonenko et al. | Detecting abandoned objects in crowded scenes of surveillance videos using adaptive dual background model | |
| KR102263512B1 (en) | IoT integrated intelligent video analysis platform system capable of smart object recognition | |
| CN117371992A (en) | Reservoir operation and maintenance control system based on GIS | |
| CN106650639A (en) | Monitoring system pedestrian re-identification method suitable for security and protection | |
| CN111597919A (en) | Human body tracking method in video monitoring scene | |
| CN111277789A (en) | Video-based community security method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170315 |
|
| RJ01 | Rejection of invention patent application after publication |