CN106412522A - Video analysis detection method and system of object in indoor and outdoor environment - Google Patents
Video analysis detection method and system of object in indoor and outdoor environment Download PDFInfo
- Publication number
- CN106412522A CN106412522A CN201610943656.6A CN201610943656A CN106412522A CN 106412522 A CN106412522 A CN 106412522A CN 201610943656 A CN201610943656 A CN 201610943656A CN 106412522 A CN106412522 A CN 106412522A
- Authority
- CN
- China
- Prior art keywords
- video
- video image
- indoor
- article
- time
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
The present invention provides a video analysis detection method and system of an object in the indoor and outdoor environment. The method comprises: a video front-end device installed at a monitoring area is configured to collect the video image at each position of the monitoring area; the video image is sent to a database server for storage through a switch and is subjected to intelligent video analysis; the video image is analyzed, the object features are analyzed from the video image, and it is automatically analyzed that the standing time of the object features in the video image in the preset attention area exceeds a threshold value or not; and when it is determined that the standing time of the object features exceeds the threshold value in the preset attention area, it is determined that the object features are corresponding remnants, and alarm information is emitted to prompt monitoring personnel to perform attention processing and perform real-time display of the video image of the area. The video analysis detection method and system of the object in the indoor and outdoor environment can perform detection of the remnants, the suspected dangerous goods and stolen objects in the environment so as to timely emit alarm signals in the condition mentioned above and inform monitoring personnel of measure collection and processing.
Description
Technical field
The present invention relates to intelligent video analysis technical field, divide particularly to a kind of video to object in indoor and outdoor surroundingses
Analysis detection method and system.
Background technology
With going deep into that China " safe city " builds, the demand in China's security protection market will further improve, and becomes the U.S. that continues
World's second largest security protection market after state.
Advancing by leaps and bounds of technical elements is also that the development of security protection industry provides powerful power, the sixties video image skill
Art, the application of the computer digit technology seventies, the biological identification technology eighties and the Internet technology nineties make peace
Anti- industry is rapidly developed.The Shanghai World's Fair of the Beijing Olympic Games of 2008 and 2010 is that Chinese security protection market provides
Huge business opportunity, and the stable development that Chinese continual upsurge in construction is also security protection market provides solid foundation.
In recent years, full-scale digital, networking video monitoring system advantage more obvious, the opening of its height, collection
Become second nature and motility, the development for whole security protection industry provides more wide development space, and intelligent video monitoring is then
One of application model of networked video monitoring field forefront.Intelligent video monitoring is monitored and is with digitized, networked video
Basis, but it is different from general networked video monitoring, it is a kind of more high-end video surveillance applications.
Video developmental stage：
First stage：Late nineteen seventies are to middle nineteen nineties.This stage with closed-circuit TV monitoring system (CCTV) is
Main, that is, first generation simulated television video monitoring system.At 2000 about, substantially superseded.
Second stage：Middle nineteen nineties to late nineteen nineties, based on the video monitoring system based on PC card insert type,
This stage is also referred to as the Semi-digital epoch by insider.Or second filial generation video monitoring system.
Phase III：Late nineteen nineties so far, with embedded technology for rely on, with network, communication technology as platform, with
Embed based on the network video monitor and control system that simple image analysis algorithm is characteristic in photographic head, since then, Network Video Surveillance
Development also into digital Age.Haikang at present, greatly China, what the majority security protection manufacturer such as Kodak provided is all third generation net
Network video monitoring system, is also called IP monitoring system.
Fourth stage：Earlier 2000s so far, the requirement more and more higher intelligent image analyzed with user, simple
Embed simple algorithm in photographic head the picture captured is analyzed meeting the demand of user.User couple
After the requirement of monitoring system has been engaged on, evidence obtaining turns to and prevents in advance.Monitor mode also by with people in Surveillance center's transformation on duty
On duty for Computerized intelligent.Forth generation intelligent recognition monitoring system exactly answers such demand to produce.
The main early warning of conventional third generation video monitoring system is to be realized by seeing monitoring display large-size screen monitors by personnel, needs big
The human input of amount, the responsibility to personnel simultaneously, focus requirement is very high, in most cases can only play post-mordem forensics
Effect, and post-mordem forensics is extremely inefficient.
Other manufacturers most of by algorithm integration in photographic head, simple due to by photographic head hardware limitation, can only build
Algorithm, does basic handling it is impossible to realize Intelligent Recognition truly.
Content of the invention
The purpose of the present invention is intended at least solve one of described technological deficiency.
For this reason, it is an object of the invention to proposing a kind of video analysis detection method to object in indoor and outdoor surroundingses and be
System, can detect to legacy, doubtful dangerous goods and stolen article in environment, thus when finding above-mentioned situation
Send alarm signal in time, notify monitoring personnel collection measure to process.
To achieve these goals, the embodiment of one aspect of the present invention provides a kind of video to object in indoor and outdoor surroundingses
Analyzing detecting method, comprises the steps：
Step S1, by the video figure of each position in the video front-end equipment acquisition monitoring region being arranged on monitor area
Picture；
Step S2, described video image is sent by switch and is stored to database server, and send to should
Carry out intelligent video analysis with server；
Step S3, is analyzed to video image by described application server, analyzes article from described video image
Feature, and automatically analyze whether article characteristics in the video image time of staying in default region-of-interest exceedes threshold value；
Step S4, when judging article characteristics the time of staying exceeding threshold value in default region-of-interest, then judges this thing
Product feature corresponds to legacy, from described application server to the terminal unit alert of monitoring personnel, points out monitoring
Personnel carry out concern process, and the video image in this region is shown in real time on a display screen.
Further, in described step S3, described application server monitors that the article in predeterminable area are moved further
When walking the time and exceeding threshold value, alert, point out monitoring personnel to occur to steal and move, carry out concern process.
Further, in described step S3, described application server further by the article characteristics extracting with default
Dangerous materials data base compare, when judging that this article characteristics is located in described dangerous materials data base, alert, and carry
Show that monitoring personnel carries out concern process.
Further, in described step S4, the terminal unit of described monitoring personnel obtains the video of described monitor area in real time
Image, and receive described warning message, to point out user to take treatment measures in time.
Further, in described step S4, described warning message is pointed out for sound and light alarm.
The embodiment of another aspect of the present invention provides a kind of video analysis detecting system to object in indoor and outdoor surroundingses, bag
Include：Video front-end equipment, database server, switch, application server and display device, wherein, described video front sets
Standby inclusion：Multiple video cameras, the plurality of video camera is distributed at multiple positions of monitor area, for gathering at each position
Video image；Described switch is connected with described video front-end equipment, described database server and described application server,
For described video image is sent to described database server and described application server；Described database server is used for
Store described video image and backed up；Described application server is used for video image being analyzed, from described video figure
As in analyze article characteristics, and automatically analyze article characteristics in the video image time of staying in default region-of-interest and be
No exceed threshold value, when judging article characteristics the time of staying exceeding threshold value in default region-of-interest, then judge that this article is special
Levy and correspond to legacy, from described application server to the terminal unit alert of monitoring personnel, point out monitoring personnel
Carry out concern process, described display device is connected with described application service area, for showing the video image in this region in real time
Shown in display screen.
Further, the article that described application server monitors in predeterminable area further are removed the time and exceed threshold value
When, alert, point out monitoring personnel to occur to steal shifting, carry out concern process.
Further, the article characteristics extracting are carried out by described application server further with default dangerous materials data base
Compare, when judging that this article characteristics is located in described dangerous materials data base, alert, point out monitoring personnel to be closed
Note is processed.
Further, the terminal unit of described monitoring personnel obtains the video image of described monitor area in real time, and receives institute
State warning message, to point out user to take treatment measures in time.
Further, described warning message is pointed out for sound and light alarm.
Video analysis detection method to object in indoor and outdoor surroundingses according to embodiments of the present invention and system, can basis
Analysis to video acquisition data, detects to legacy, doubtful dangerous goods and stolen article in environment, thus
Find to send in time alarm signal during above-mentioned situation, notify monitoring personnel collection measure to process.
The present invention knows serial application product based on a set of intelligence that multiple Intelligent Recognition algorithms continue to optimize design, is user
Provide Intelligent Recognition, intelligence evidence obtaining, in advance early warning, dispose afterwards, three-level linkage, manual warnings, mobile terminal application management, in advance
Alarming information classification such as pushes at multiple application services, can be by the intellectual analysis to video data before event occurs, in advance
Send early warning, and three-level linkage early warning is realized according to the degree of danger of event, the image of event can be distributed to personnel at different levels and move
In dynamic terminal, it is that event handling wins the quality time, the impact to public or private property and people's life's safety for the event is reduced
To minimum level.
The aspect that the present invention adds 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.
Brief description
The above-mentioned and/or additional aspect of the present invention and advantage will become from reference to the description to embodiment for the accompanying drawings below
Substantially and easy to understand, wherein：
Fig. 1 is the flow chart according to the embodiment of the present invention to the video analysis detection method of object in indoor and outdoor surroundingses；
Fig. 2 is the structure chart according to the embodiment of the present invention to the video analysis detecting system of object in indoor and outdoor surroundingses；
Fig. 3 is the system architecture diagram according to the embodiment of the present invention；
Fig. 4 is according to the video acquisition of the embodiment of the present invention, analysis, Stored Procedure figure.
Specific embodiment
Embodiments of the invention are described below in detail, the example of described embodiment is shown in the drawings, wherein from start to finish
The element that same or similar label represents same or similar element or has same or like function.Below with reference to attached
The embodiment of figure description is exemplary it is intended to be used for explaining the present invention, and is not considered as limiting the invention.
As shown in figure 1, the video analysis detection method to object in indoor and outdoor surroundingses of the embodiment of the present invention, including as follows
Step：
Step S1, by the video figure of each position in the video front-end equipment acquisition monitoring region being arranged on monitor area
Picture.
Specifically, by the data acquisition program gathered data (xml, picture and video segment) in video front-end equipment, lead to
After crossing process, data is stored respectively in data base and storage server.Can also realize accessing third party by interface and be safely
System or rays safety detection apparatus detection information.
Step S2, video image is sent by switch and is stored to database server, and sends to application clothes
Business device carries out intelligent video analysis.
With reference to Fig. 4, video analytics server is by analysis result with xml data is activation to data acquisition program, data acquisition
Program gathers picture and video segment by xml from video analytics server.Data after processing is divided by data acquisition program
Cun Chu not be with data base and storage server.
Step S3, is analyzed to video image by application server, analyzes article characteristics from video image, and from
Whether the time of staying in default region-of-interest of the article characteristics in dynamic analysis video image exceedes threshold value.
Wherein, when the article that application server monitors in predeterminable area further are removed the time and exceed threshold value, send
Warning message, points out monitoring personnel to occur to steal shifting, carries out concern process.
Additionally, the article characteristics extracting are compared by application server further with default dangerous materials data base,
When judging that this article characteristics is located in dangerous materials data base, alert, point out monitoring personnel to carry out concern process.
Step S4, when judging article characteristics the time of staying exceeding threshold value in default region-of-interest, then judges this thing
Product feature corresponds to legacy, from application server to the terminal unit alert of monitoring personnel, points out monitoring personnel
Carry out concern process, and the video image in this region is shown in real time on a display screen.
Separately below to leave Articles detecting, stolen Articles detecting and doubtful dangerous goods detection illustrate：
1st, leave Articles detecting：
To the article identification in monitoring range, left, identification process can be adjusted to identification parameter to adapt to not
Demand with scene.Whether the region that automatic detection is specified the object left, if legacy, system is automatic at once
Carry out (legacy event) to report to the police.
Range of application：The public place that the crowd is dense such as airport, railway station, bus station, building, school needs video monitoring
Important area.In addition department of a lot of government bodies, enterprises and institutions or even cell, museum, military security base, bank,
The unattended important security protection region such as storehouse, railway, and do not need the express highway section of parking etc..
Outdoor environment requires：Monitor area is apart from photographic head 5m～10m；Daytime, light stabilisation；At night, there is bright source
And stable, light-source brightness can not be mutated.
Indoor environment requires：Monitor area is apart from photographic head 3m～5m；Light stabilisation or have bright source and stable, light source
Brightness can not be mutated.
2nd, stolen Articles detecting
Using the detection mode anti-with legacy condition, realize the stolen behavioral value of article in monitor area.Automatic detection
Whether designated area goes out active/lost objects, if there are loss/lost objects, system carries out (losing/losing at once automatically
Goods event) report to the police.
Range of application：Museum exhibition section, exhibition of paintings, villa, department of government bodies, enterprises and institutions, military security base etc.
Unattended important security protection region etc..
Outdoor environment requires：Monitor area is apart from photographic head 5m～10m；Daytime, light stabilisation；At night, there is bright source
And stable, light-source brightness can not be mutated.
Indoor environment requires：Monitor area is apart from photographic head 3m～5m；Light stabilisation or have bright source and stable, light source
Brightness can not be mutated.
3rd, doubtful dangerous goods detection
Analyze doubtful dangerous goods such as cutter, club etc. that setting regions in video scene occurs, and extract and mutually look after
Piece, forms warning data (XML).Whether automatic detection designated area the danger that cutter, club etc. endanger personal safety
Product, if there are such dangerous goods, system automatically carries out (finding dangerous goods event) at once and reports to the police.
Range of application：The public place that the crowd is dense such as airport, railway station, bus station, building, school, is to need video
The important area of monitoring.In addition department of a lot of government bodies, enterprises and institutions or even cell, museum, military security base, storehouse
The unattended important security protection region such as room, railway.
Outdoor environment requires：Monitor area is apart from photographic head 5m～10m (5m about be preferred)；Daytime, light stabilisation；Black
At night, there is bright source and stablize, light-source brightness can not be mutated.
Indoor environment requires：Monitor area is apart from photographic head 3m～5m；Light stabilisation or have bright source and stable, light source
Brightness can not be mutated.
The terminal unit of monitoring personnel obtains the video image of monitor area in real time, and receives warning message, to point out to use
Treatment measures are taken at family in time.Wherein, warning message is pointed out for sound and light alarm.
As shown in Fig. 2 the embodiment of the present invention also proposes a kind of video analysis detecting system to object in indoor and outdoor surroundingses,
Including：Video front-end equipment 1, database server 2, switch 3, application server 4 and display device 5.
Specifically, video front-end equipment 1 includes：Multiple video cameras, multiple video cameras are distributed in multiple positions of monitor area
Put place, for gathering the video image at each position.
Switch 3 is connected with video front-end equipment 1, database server 2 and application server 4, for by video image
Send to database server 2 and application server 4.
Database server 2 is used for store video images and is backed up.
Application server 4 is used for video image is analyzed, and analyzes article characteristics, and automatically divide from video image
Whether the time of staying in default region-of-interest of the article characteristics in analysis video image exceedes threshold value, when judging that article characteristics exist
When the time of staying exceedes threshold value in default region-of-interest, then judge that this article characteristics corresponds to legacy, by application server 4
To the terminal unit alert of monitoring personnel, monitoring personnel is pointed out to carry out concern process.
Further, when the article that application server 4 monitors in predeterminable area further are removed the time and exceed threshold value, send out
Go out warning message, point out monitoring personnel to occur to steal shifting, carry out concern process.
Additionally, the article characteristics extracting are compared by application server 4 further with default dangerous materials data base,
When judging that this article characteristics is located in dangerous materials data base, alert, point out monitoring personnel to carry out concern process.
Display device 5 is connected with application service area, for being shown the video image in this region in real time on a display screen
Show.
Specifically, the terminal unit of monitoring personnel obtains the video image of monitor area in real time, and receives warning message, with
Prompting user takes treatment measures in time.
In one embodiment of the invention, the terminal unit of monitoring personnel is mobile phone or panel computer.
Wherein, warning message is pointed out for sound and light alarm.
As shown in figure 3, seven levels of system architecture, it is operating system layer, database layer, web container layer respectively, runs ring
Border layer, technology layer, Internet, access browse layer.
Below the software support platform of the present invention is illustrated：
1st, Oracle11g data base：There is provided reliable, safe data management function with tackle key business event and
Line issued transaction is applied.Oracle advanced security option provide transparent data encryption, can to lane database storage data and
The data of network transmission is encrypted.
2nd, operating system (windows/linux)：As operating system on authorization server, for running the soft of correlation
Part.
3rd, resource service (WebServer)：There is provided resource information by (resource service) operation system for other services,
It is operation system and the bridge of other service.
4th, distribution service (VideoServer)：The Video stream information that hardware device is gathered is forwarded to Analysis Service etc..
5th, website service (tomcat)：The use of the Internet end management system is provided as web container.
6th, middleware (ESB)：Interface for integrated third party software and hardware.
7th, electronic chart (GIS)：User provides integral platform electronic map function.
8th, storage service (StorageServer)：Realize the store function of history video record.
9th, receive program (FKCounter)：Realize the timely reception of early warning event information, and operation system real-time exhibition.
10th, picture publisher server (nginx)：For issuing the picture of early warning event.
11st, video playback plug-in unit (OCX)：Realizing operation system can be with displaying live view video playback.
12nd, video monitoring client terminal (VideoClient)：There is provided one to control, access the visual of headend equipment to client
Change platform.By client, user can be with the video information of displaying live view all devices, control device head, 3D positioning, viewing
History video record, browses video scheme broadcasting etc..
13rd, operation system：There is provided to client and consult in time, process the flat of the Realtime Alerts event detecting from headend equipment
Platform.
14th, defrag .rar：Make regular check on and clear up video record and the picture file of storage, prevent disk space not
Foot.
The present invention can dispose on authorization server, and supports the soft or hard system integration customizing, and compare other and be embedded in shooting
For the product of machine or soft or hard combination, extensibility is strong, can be according to some functions of the increase in demand of user；The algorithm being adopted
According to substantial amounts of contrast, test, in the case that environment reaches the requirement of products application, the accuracy rate of algorithm is higher than that other embed
Video camera or the product of soft or hard combination；Algorithm, client etc. has broken string to automatically reply function；Whole system can be compatible
The systems such as windows2003/xp/win7/win8.
Video analysis detection method to object in indoor and outdoor surroundingses according to embodiments of the present invention and system, can basis
Analysis to video acquisition data, detects to legacy, doubtful dangerous goods and stolen article in environment, thus
Find to send in time alarm signal during above-mentioned situation, notify monitoring personnel collection measure to process.
The present invention knows serial application product based on a set of intelligence that multiple Intelligent Recognition algorithms continue to optimize design, is user
Provide Intelligent Recognition, intelligence evidence obtaining, in advance early warning, dispose afterwards, three-level linkage, manual warnings, mobile terminal application management, in advance
Alarming information classification such as pushes at multiple application services, can be by the intellectual analysis to video data before event occurs, in advance
Send early warning, and three-level linkage early warning is realized according to the degree of danger of event, the image of event can be distributed to personnel at different levels and move
In dynamic terminal, it is that event handling wins the quality time, the impact to public or private property and people's life's safety for the event is reduced
To minimum level.
In order to adapt to user's request, the present invention has environment learning ability, can be carried according to the constantly improve that security protection identifies storehouse
High system recognition rate, improves the security protection work efficiency of relevant departments, preferably ensures life and the property safety of broad masses, dimension
Protect social stability.
The video analysis detection method to object in indoor and outdoor surroundingses of the embodiment of the present invention and system, have following beneficial
Effect：
1st, comprehensive
Most current Intelligent Recognition manufacturer only achieves the module of or a few Intelligent Recognition it is impossible to meet user
The demand of growing lifting safe class.Just the product of multiple commercial vendors all can only be filled one when user has multiple demand
Time, different functions is realized on different platforms.And be directed to article, colony personnel, environment, all the 11 of photographic head itself
Categorles analytic function is realized all on a platform, can meet the demand of most of clients, easy to use for user.
2nd, data evidence obtaining is quick
Most current intelligence manufacturer is will be preposition for the algorithm of Intelligent Recognition, and the evidence obtaining that this results in after an event occurs is stranded
Difficulty, and Intelligent Recognition platform, due to being in backstage deployment, it is possible to easily analyzing the video of storage, positioning rapidly needs and taking
The data of card, is that client saves substantial amounts of time cost.And support multistage linking, data distribution.
3rd, three-level linkage early warning
System can achieve patrol personnel's handheld terminal, monitoring center system platform, and the three-level of headquarter's system platform links,
Personnel for user's many levels provide decision support, and realize early warning in advance and dispose, event is compressed among cradle.
4th, sustainable development
The identification storehouse of constantly improve system, improves discrimination, newly intelligently knows also dependent on customer demand customized development meanwhile
Other algorithm, to meet different demands, keeps permanent sustainable development in following application process.
5th, bidirectional alarming
The present invention can realize video analysis early warning and the bidirectional alarming mechanism of live patrol personnel's manual alarm, in shooting
Head blind area, manually alarm image is beamed back early warning platform to live patrol personnel by form, and platform commanding is according to image feelings
Condition arranges disposing task.Thus network is disposed by the photographic head and Field Force's composition early warning commander that no dead angle covers.
6th, protect original investment
Because Intelligent Recognition platform is a set of pure software system, it is arranged in the backstage of video monitoring system, so need not be right
The video monitoring system that user has built up is transformed or is removed reconstruction, can be effectively protected the original investment of client, phase
To domestic at present most monitoring manufacturers by preposition for the algorithm pattern to photographic head, Intelligent Recognition platform can maximize protection
The original investment of client.
7th, economy
The Intelligent Recognition platform of research and development can be adjusted flexibly the region of Intelligent Recognition after client deployment, and this region
The content of identification.The region that such as some camera for supervising the square shoots, the behavior of possibly colony or the individuality of identification on daytime is known
Not, what be then possible to identification in the evening is the identification of doubtful dangerous materials or legacy.Traditional monitoring manufacturer can only rely on increase to take the photograph
Camera, increases equipment investment realizing, and Intelligent Recognition platform then only need to arrange in software it is achieved that great save
The engineering of about user puts into, equipment investment, and human input etc. has a high economy.Urban safety aspect for another example, no
It is different that the same time period needs the region of Intelligent Recognition, and traditional solution is exactly to install substantial amounts of photographic head, Lao Min additional
Lose money.Intelligent Recognition platform only needs to arrange in software and can achieve, possesses high economy.
Simultaneously as Intelligent Recognition platform is to carry out intellectual analysis by computer to video, it is possible to reduce substantial amounts of on duty
Personnel, are to save substantial amounts of human cost using unit.Possesses very high economy.
8th, practicality
Intelligent Recognition platform has extremely perfect early warning mechanism, can realize at present comprising article identification, personnel
Activity recognition, Context awareness, photographic head oneself state identification etc. 11 big functions, can according to analytical data by it may happen that thing
Part is reported to the police, and allows user carry out the disposal of correlation in event bud, with the loss avoiding event to cause after occurring.
9th, mobile interchange application
Use for the convenience of the user, in addition to the platform being arranged on Surveillance center, the present invention have also been devised cell phone customer
End (crime scene investigation device) application, sets according to the different rights of scene patrol disposal personnel, floor manager personnel, the personnel of action commander in chief
Put different inquiries, the function such as pushed, sought help, having transferred, user can have been applied by mobile phone terminal and efficiently realize and commander people
Member, the two-way interaction of command centre, greatly enhance scope and the convenience of system application.
10th, wechat pushes application
The support of mobile phone (crime scene investigation device) of the system is not installed for convenience or reinforcing personnel pick the early warning of system push
Information, system specially devises wechat pushing module, can push early warning information to specified micro-signal.And can be by paying close attention to wechat
Public number, realizes public number automatic push.It is multiple interior that push content contains early warning event property, early warning event urgency level etc.
Hold.User can arrange push content on platform, pushes the setting of the multiple personalizations such as the frequency.
11st, high efficiency
A set of platform of the intellectual analysis based on video image, the basis of the intellectual analysis to video image realized by platform
Above pass through in different scenes, the different parameters of varying environment setting realize the early warning in advance to event.Early warning information passes through platform
The three-level early warning mechanism that links be automatically distributed to the client of different persons liable, platform can also pass through correlation function simultaneously
Module realizes emergency command.Realize the quick disposal to event by the linkage of each functional module of whole platform.
Realized using pure software form, algorithm is realized by the way of OpenCV is with reference to c/c++, and OpenCV is one and is based on
The cross-platform computer vision library that (increasing income) issues, may operate in Linux, Windows and MacOS operating system.It is light
Magnitude and efficiently, be made up of a series of C function and a small amount of C++ class, provide the language such as Python, Ruby, MATLAB simultaneously
Interface it is achieved that a lot of general-purpose algorithms of image procossing and computer vision aspect.The vision processing algorithm that OpenCV provides
Very abundant, and it is partly write with C language and new outside supports that compiling link that can also be complete generates it is not necessary to add
Configuration processor.The present invention is portable high, and stability is strong, adapts to various possible environment, and technology autgmentability is strong.
Whole system after deployment, if early warning event, sends warning message, user can check and locate in time automatically
Reason.System availability is higher, is suitable for various environment, and a video camera can load several algorithms simultaneously, automatically generate warning
Information, intuitive is strong, saves substantial amounts of manpower and materials, safeguards simple, and expansible new function.
In the description of this specification, reference term " embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy describing with reference to this embodiment or example
Point is contained at least one embodiment or the example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Necessarily refer to identical embodiment or example.And, the specific features of description, structure, material or feature can be any
One or more embodiments or example in combine in an appropriate manner.
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 be interpreted as limitation of the present invention, those of ordinary skill in the art is in the principle without departing from the present invention and objective
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
By claims and its equivalent limit.
Claims (10)
1. a kind of video analysis detection method to object in indoor and outdoor surroundingses is it is characterised in that comprise the steps：
Step S1, by the video image of each position in the video front-end equipment acquisition monitoring region being arranged on monitor area；
Step S2, described video image is sent by switch and is stored to database server, and sends to application clothes
Business device carries out intelligent video analysis；
Step S3, is analyzed to video image by described application server, analyzes article characteristics from described video image,
And automatically analyze whether article characteristics in the video image time of staying in default region-of-interest exceedes threshold value；
Step S4, when judging article characteristics the time of staying exceeding threshold value in default region-of-interest, then judges that this article is special
Levy and correspond to legacy, from described application server to the terminal unit alert of monitoring personnel, point out monitoring personnel
Carry out concern process, and the video image in this region is shown in real time on a display screen.
2. the video analysis detection method to object in indoor and outdoor surroundingses as claimed in claim 1 is it is characterised in that described
In step S3, when described application server monitors that the article in predeterminable area are removed the time and exceed threshold value further, send
Warning message, points out monitoring personnel to occur to steal shifting, carries out concern process.
3. the video analysis detection method to object in indoor and outdoor surroundingses as claimed in claim 1 is it is characterised in that described
In step S3, the article characteristics extracting are compared by described application server further with default dangerous materials data base,
When judging that this article characteristics is located in described dangerous materials data base, alert, point out monitoring personnel to carry out at concern
Reason.
4. the video analysis detection method to object in indoor and outdoor surroundingses as claimed in claim 1 is it is characterised in that described step
In rapid S4, the terminal unit of described monitoring personnel obtains the video image of described monitor area in real time, and receives described alarm signal
Breath, to point out user to take treatment measures in time.
5. the video analysis detection method to object in indoor and outdoor surroundingses as claimed in claim 1 is it is characterised in that described
In step S4, described warning message is pointed out for sound and light alarm.
6. a kind of video analysis detecting system to object in indoor and outdoor surroundingses is it is characterised in that include：Video front-end equipment,
Database server, switch, application server and display device, wherein,
Described video front-end equipment includes：Multiple video cameras, the plurality of video camera is distributed at multiple positions of monitor area,
For gathering the video image at each position；
Described switch is connected with described video front-end equipment, described database server and described application server, for inciting somebody to action
Described video image sends to described database server and described application server；
Described database server is used for storing described video image and being backed up；
Described application server is used for video image is analyzed, and analyzes article characteristics from described video image, and from
Whether the time of staying in default region-of-interest of the article characteristics in dynamic analysis video image exceedes threshold value, when judging that article are special
When levying that the time of staying exceedes threshold value in default region-of-interest, then judge that this article characteristics corresponds to legacy, by described should
With server to the terminal unit alert of monitoring personnel, monitoring personnel is pointed out to carry out concern process,
Described display device is connected with described application service area, for carrying out the video image in this region in real time on a display screen
Display.
7. the video analysis detecting system to object in indoor and outdoor surroundingses as claimed in claim 6 is it is characterised in that described should
When monitoring that with server the article in predeterminable area are removed the time and exceed threshold value further, alert, point out prison
Control personnel occur to steal shifting, carry out concern process.
8. the video analysis detecting system to object in indoor and outdoor surroundingses as claimed in claim 6 is it is characterised in that described should
Further the article characteristics extracting are compared with default dangerous materials data base with server, when judging this article characteristics
When in described dangerous materials data base, alert, point out monitoring personnel to carry out concern process.
9. the video analysis detecting system to object in indoor and outdoor surroundingses as claimed in claim 6 is it is characterised in that described prison
The terminal unit of control personnel obtains the video image of described monitor area in real time, and receives described warning message, to point out user
Take treatment measures in time.
10. the video analysis detecting system to object in indoor and outdoor surroundingses as claimed in claim 6 is it is characterised in that described
Warning message is pointed out for sound and light alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610943656.6A CN106412522A (en) | 2016-11-02 | 2016-11-02 | Video analysis detection method and system of object in indoor and outdoor environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610943656.6A CN106412522A (en) | 2016-11-02 | 2016-11-02 | Video analysis detection method and system of object in indoor and outdoor environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106412522A true CN106412522A (en) | 2017-02-15 |
Family
ID=58013646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610943656.6A Pending CN106412522A (en) | 2016-11-02 | 2016-11-02 | Video analysis detection method and system of object in indoor and outdoor environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106412522A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107547869A (en) * | 2017-08-29 | 2018-01-05 | 安徽千里眼信息科技有限公司 | A kind of video monitoring system based on cloud storage |
| CN108154115A (en) * | 2017-12-22 | 2018-06-12 | 北京奇虎科技有限公司 | Object identifying method and device, computing device based on camera scene |
| CN108391092A (en) * | 2018-03-21 | 2018-08-10 | 四川弘和通讯有限公司 | Danger identifying system based on deep learning |
| CN109739155A (en) * | 2019-02-20 | 2019-05-10 | 中国人民解放军91245部队 | A kind of human-machine interaction monitoring system and monitoring method |
| CN110446009A (en) * | 2019-07-25 | 2019-11-12 | 卓集送信息科技（武汉）有限公司 | A kind of video monitoring system of storable abnormal image data |
| CN111147807A (en) * | 2018-11-06 | 2020-05-12 | 天地融科技股份有限公司 | Risk detection method, device and system based on information synchronization |
| CN111145455A (en) * | 2018-11-06 | 2020-05-12 | 天地融科技股份有限公司 | Method and system for detecting face risk in surveillance video |
| CN111159477A (en) * | 2019-12-31 | 2020-05-15 | 西安古鲸电子技术有限公司 | Intelligent image data analysis system |
| CN111522260A (en) * | 2020-04-24 | 2020-08-11 | 徐建红 | Intelligent auxiliary service method and system based on information capture identification and big data |
| CN111814509A (en) * | 2019-04-10 | 2020-10-23 | 杭州海康威视数字技术股份有限公司 | Article positioning method, device and monitoring system |
| CN111915817A (en) * | 2020-07-28 | 2020-11-10 | 中国工商银行股份有限公司 | Monitoring management method and device for bank ATM self-help bank protection cabin |
| CN113470013A (en) * | 2021-07-28 | 2021-10-01 | 浙江大华技术股份有限公司 | Method and device for detecting moved article |
Citations (6)
| 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 |
| CN103108159A (en) * | 2013-01-17 | 2013-05-15 | 新疆电力公司乌鲁木齐电业局 | Electric power intelligent video analyzing and monitoring system and method |
| CN103297751A (en) * | 2013-04-23 | 2013-09-11 | 四川天翼网络服务有限公司 | Wisdom skynet video behavior analyzing 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 |
| CN104243569A (en) * | 2014-09-09 | 2014-12-24 | 安徽四创电子股份有限公司 | City operation system |
| 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 CN201610943656.6A patent/CN106412522A/en active Pending
Patent Citations (6)
| 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 |
| CN103108159A (en) * | 2013-01-17 | 2013-05-15 | 新疆电力公司乌鲁木齐电业局 | Electric power intelligent video analyzing and monitoring system and 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 |
| CN103297751A (en) * | 2013-04-23 | 2013-09-11 | 四川天翼网络服务有限公司 | Wisdom skynet video behavior analyzing system |
| CN104243569A (en) * | 2014-09-09 | 2014-12-24 | 安徽四创电子股份有限公司 | City operation system |
| 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 |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107547869A (en) * | 2017-08-29 | 2018-01-05 | 安徽千里眼信息科技有限公司 | A kind of video monitoring system based on cloud storage |
| CN108154115B (en) * | 2017-12-22 | 2021-06-29 | 北京奇虎科技有限公司 | Object identification method and device based on camera scene and computing equipment |
| CN108154115A (en) * | 2017-12-22 | 2018-06-12 | 北京奇虎科技有限公司 | Object identifying method and device, computing device based on camera scene |
| CN108391092A (en) * | 2018-03-21 | 2018-08-10 | 四川弘和通讯有限公司 | Danger identifying system based on deep learning |
| CN111147807A (en) * | 2018-11-06 | 2020-05-12 | 天地融科技股份有限公司 | Risk detection method, device and system based on information synchronization |
| CN111145455A (en) * | 2018-11-06 | 2020-05-12 | 天地融科技股份有限公司 | Method and system for detecting face risk in surveillance video |
| CN109739155A (en) * | 2019-02-20 | 2019-05-10 | 中国人民解放军91245部队 | A kind of human-machine interaction monitoring system and monitoring method |
| CN111814509A (en) * | 2019-04-10 | 2020-10-23 | 杭州海康威视数字技术股份有限公司 | Article positioning method, device and monitoring system |
| CN111814509B (en) * | 2019-04-10 | 2023-09-29 | 杭州海康威视数字技术股份有限公司 | Article positioning method, device and monitoring system |
| CN110446009A (en) * | 2019-07-25 | 2019-11-12 | 卓集送信息科技（武汉）有限公司 | A kind of video monitoring system of storable abnormal image data |
| CN111159477A (en) * | 2019-12-31 | 2020-05-15 | 西安古鲸电子技术有限公司 | Intelligent image data analysis system |
| CN111522260A (en) * | 2020-04-24 | 2020-08-11 | 徐建红 | Intelligent auxiliary service method and system based on information capture identification and big data |
| CN111915817B (en) * | 2020-07-28 | 2022-05-27 | 中国工商银行股份有限公司 | Monitoring management method and device for bank ATM self-help bank protection cabin |
| CN111915817A (en) * | 2020-07-28 | 2020-11-10 | 中国工商银行股份有限公司 | Monitoring management method and device for bank ATM self-help bank protection cabin |
| CN113470013A (en) * | 2021-07-28 | 2021-10-01 | 浙江大华技术股份有限公司 | Method and device for detecting moved article |
| CN113470013B (en) * | 2021-07-28 | 2024-11-01 | 浙江大华技术股份有限公司 | Method and device for detecting moving object |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106412522A (en) | Video analysis detection method and system of object in indoor and outdoor environment | |
| CN106408833A (en) | Perimeter intrusion detection method and system | |
| CN106331657A (en) | Video analysis and detection method and system for crowd gathering and moving | |
| CN106454253A (en) | Method and system for detecting area wandering | |
| CN106303469A (en) | Video analysis detection method and system to indoor and outdoor surroundings Flame | |
| CN109166261B (en) | Image processing method, device and equipment based on image recognition and storage medium | |
| CN106454250A (en) | Intelligent recognition and early warning processing information platform | |
| CN103268680B (en) | A kind of family intelligent monitoring burglary-resisting system | |
| CN108197565A (en) | Target based on recognition of face seeks track method and system | |
| CN106780250B (en) | Intelligent community security event processing method and system based on Internet of things technology | |
| KR100995569B1 (en) | Intelligence cctv system for preventing crime and crime prevent system and method using the same | |
| CN106791655B (en) | A kind of method for processing video frequency and device | |
| CN108205870A (en) | A kind of campus personal safety intelligent monitoring management system | |
| CN110619277A (en) | Multi-community intelligent deployment and control method and system | |
| CN108205868A (en) | A kind of campus fire-proof and theft-proof intelligent monitoring management system | |
| CN106408894A (en) | Early-warning processing method based on mobile terminal | |
| CN108205896A (en) | A kind of Campus transport safety intelligence monitoring and controlling manages system | |
| CN210515326U (en) | Scenic spot ticket inspection system based on face AI recognition | |
| CN115002414A (en) | Monitoring method, monitoring device, server and computer readable storage medium | |
| CN115966313B (en) | Integrated management platform based on face recognition | |
| CN107123242A (en) | A kind of intelligent building Video Surveillance Alarm System | |
| CN109410497A (en) | A kind of monitoring of bridge opening space safety and alarm system based on deep learning | |
| CN107357821B (en) | System management method, device and storage medium | |
| CN111951390A (en) | Warning situation display method, system, device and storage medium | |
| WO2020037929A1 (en) | Method and device for community management and electronic apparatus |
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: 20170215 |
|
| RJ01 | Rejection of invention patent application after publication |