CN102610054A - Video-based getting up detection system - Google Patents
Video-based getting up detection system Download PDFInfo
- Publication number
- CN102610054A CN102610054A CN2011100219797A CN201110021979A CN102610054A CN 102610054 A CN102610054 A CN 102610054A CN 2011100219797 A CN2011100219797 A CN 2011100219797A CN 201110021979 A CN201110021979 A CN 201110021979A CN 102610054 A CN102610054 A CN 102610054A
- Authority
- CN
- China
- Prior art keywords
- video
- module
- detection system
- standing
- moving target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a video-based getting up detection system. The system comprises a video acquiring module, a video calibrating module, an algorithm analyzing module and a management module, wherein the video acquiring module employs a camera, a collecting card and a computer, and is used for outputting an analog signal of the camera collected by the collecting card into a memory of the computer; the video calibrating module is used for calibrating video data collected by the collecting card, and calibrating an area focused by the algorithm analyzing module in a scene; the algorithm analyzing module is used for processing the video data collected by the collecting card, and detecting whether a monitored person gets in the bed or gets up or not through behaviors of the person in the video and by combination with the position of the area focused by the algorithm analyzing module and calibrated by the video calibrating module, and outputting a result to the management module; and the management module is used for alarm triggering management according to the analysis result output by the algorithm analyzing module. The video-based getting up detection system provided by the invention can be used for accurately judging the behaviors that the monitored person gets in the bed and gets up through analyzing the behaviors in the monitoring scene.
Description
Technical field
The present invention relates to a kind of detection system of standing up, particularly a kind of detection system of standing up based on video.
Background technology
At night and lunch break; For fear of the monitor staff particularly the key monitoring personnel (some the prison chamber have indivedual key monitoring personnel; The key monitoring personnel sleep in the fixed position of prison chamber) the generation accident; Need be by master-control room people's police's checking monitoring on duty video, and accident often occurs in monitor staff's period of key monitoring personnel bunk bed particularly, the T.T. that this generally speaking incident takes place the ratio in total monitoring time be lower than 10%.If all the period of time monitoring makes master-control room people's police on duty produce visual fatigue easily, add that the prison chamber is too many, cause it in time to pinpoint the problems.
Summary of the invention
Technical matters to be solved by this invention provides a kind of detection system of standing up based on video; It can judge the behavior of monitor staff's bunk bed accurately through to the particularly analysis of key monitoring human behavior of monitor staff in the monitoring scene, when the monitor staff being arranged particularly during key monitoring personnel bunk bed in the scene; It is externally reported to the police automatically; The people's police on duty of notice master-control room can in time handle it, stop abnormal conditions and take place.
The present invention solves above-mentioned technical matters through following technical proposals: a kind of detection system of standing up based on video; It is characterized in that; It comprises video acquiring module, video demarcating module, Algorithm Analysis module and administration module; Video acquiring module adopts video camera, capture card and computing machine, and video acquiring module outputs to calculator memory with the simulating signal of capture card acquisition camera, and the video demarcating module is demarcated the video data that capture card collects; Calibrate the zone that the Algorithm Analysis module is paid close attention in the scene; The Algorithm Analysis module is handled the video data that capture card collects, the position of the Algorithm Analysis module region-of-interest that calibrates in conjunction with the video demarcating module, and the judgement through human behavior in the video detects whether monitor staff's bunk bed is arranged; Output results to administration module, the management that administration module is reported to the police and triggered according to the analysis result of Algorithm Analysis module output.
Preferably, said video demarcating module need be demarcated scene with quadrilateral, and following correspondence position physically should be parallel on the quadrilateral.
Preferably, said monitor staff is the key monitoring personnel.
Preferably, said administration module comprises the classifying alarm function, reports to the police as one-level during key monitoring personnel bunk bed, reports to the police as secondary during non-key monitoring personnel bunk bed.
Preferably; Said video demarcating module need be demarcated overall region and key monitoring personnel region; Overall region need be demarcated with quadrilateral, and following correspondence position physically should be parallel on the quadrilateral, and the key monitoring personnel need demarcate with polygon the region.
Preferably, said Algorithm Analysis module comprise obtain video data step, background modeling step, obtain the moving target step, moving target single frames characteristic extraction step, motion target tracking step, movement objective orbit characteristic determining step.
Preferably, said background modeling step realizes according to the frame difference movement statistics of pixel.
Preferably, said obtain the moving target step comprise before and after the extraction of frame difference, frame difference image binaryzation, the connected domain analysis of frame.
Preferably, said moving target single frames characteristic extraction step judges according to humanoid characteristic whether definite moving target is the people who stands up.
Preferably, said movement objective orbit characteristic determining step comprises: through short target of filtration duration moving target duration, judge the motion less than normal of filtration amplitude, stand up wrong report through humanoid characteristic statistics judgement filtration through the moving target amplitude.
Preferably; The treatment scheme of said administration module is: if monitor staff's bunk bed is arranged, then administration module carries out the warning of sound, light and power mode to master-control room, and people's police on duty in time handle; Deposit warning picture and warning video in server database simultaneously; The user is through socket query history record after being convenient to, and generates various statistical report forms according to historical record data, is convenient to analyze and carries out relevant improvement.
Positive progressive effect of the present invention is: the present invention can accurately extract has the monitor staff particularly behavior and the warning in time of key monitoring personnel bunk bed, and whole system maintains a long-term stability and operation efficiently.Active zone componental movement target of the present invention and non-moving target, through the moving target duration judge, the moving target amplitude is judged and humanoid characteristic judges that effectively removing the monitor staff stands up the wrong report that causes, and effectively improves the accuracy of the detection system of standing up.
Description of drawings
Fig. 1 is the fundamental diagram that the present invention is based on the detection system of standing up of video.
Fig. 2 is the fundamental diagram of video demarcating module among the present invention to the monitor staff.
Fig. 3 is the fundamental diagram of video demarcating module among the present invention to the emphasis monitor staff.
Fig. 4 is the fundamental diagram of Algorithm Analysis module among the present invention.
Embodiment
Provide preferred embodiment of the present invention below in conjunction with accompanying drawing, to specify technical scheme of the present invention.
As shown in Figure 1, the detection system of standing up that the present invention is based on video comprises video acquiring module, video demarcating module, Algorithm Analysis module and administration module.Video acquiring module adopts video camera, capture card and computing machine, and video acquiring module outputs to calculator memory with the simulating signal of capture card acquisition camera.The video demarcating module is demarcated the video data that capture card collects, and calibrates the zone that the Algorithm Analysis module is paid close attention in the scene (scene is the scene or the interior scene of video of monitoring).The Algorithm Analysis module is handled the video data that capture card collects; The position of the Algorithm Analysis module region-of-interest that calibrates in conjunction with the video demarcating module; Judgement through human behavior in the video detects whether particularly key monitoring personnel bunk bed of monitor staff is arranged; Output results to administration module, this module is the core of total system, and algorithm accuracy has determined the efficient of entire system operation.The management that administration module is reported to the police and triggered according to the analysis result of Algorithm Analysis module output; Its treatment scheme is following: if particularly key monitoring personnel bunk bed of monitor staff is arranged; Then administration module carries out the warning of sound, light and power mode to master-control room; People's police on duty in time handle, and deposit warning picture and warning video in server database simultaneously, and the user is through socket query history record after being convenient to; And generate various statistical report forms according to historical record data, be convenient to analyze and carry out relevant improvement.Administration module comprises the classifying alarm function, reports to the police as one-level during key monitoring personnel bunk bed, reports to the police as secondary during non-key monitoring personnel bunk bed.
The video demarcating module is as shown in Figure 2 to monitor staff's calibration principle, the zone of dotted line for demarcating, and the zone of demarcation is mainly near big bed.The video demarcating module need be demarcated scene with quadrilateral, and following correspondence position physically should be parallel on the quadrilateral.
The video demarcating module is as shown in Figure 3 to emphasis monitor staff calibration principle, needs to demarcate overall region and key monitoring personnel region.The overall region of dotted line for demarcating, overall region need be demarcated with quadrilateral, and following correspondence position physically should be parallel on the quadrilateral.The key monitoring personnel region of thick line for demarcating, the key monitoring personnel need demarcate with polygon the region.
As shown in Figure 4, the concrete steps that the Algorithm Analysis module is implemented are following:
Diff
n(i, j)=abs (I
n(i, j)-I
N-k(i, j)) ... Formula (1)
Wherein, n is a frame number, i for the row number, j for row number, Diff
nBe the original frame difference result of n frame, I
nBe the two field picture of n frame, I
N-kIt is the two field picture of n-k frame.
Wherein, FD
nBe the frame difference result after the binaryzation, DiffTh is a frame difference limen value.
The formula of context update is following:
Wherein, BG
n(i is that (TmTh is a time threshold for i, background j), if (i j) does not have the frame difference to change for a long time, then gets the new background of current frame data as this position in the position j).
The said indoor moving target of prison that obtains judges to the size of target earlier that far-end uses different size threshold value with near-end, the position of target is judged again, filters the moving target outside the area-of-interest.
If the key monitoring personnel then confirm according to the moving target position whether moving target belongs to key monitoring personnel region, judge according to humanoid characteristic whether moving target is the people who stands up.The humanoid characteristic judged result of supposing moving target Obj n frame is Obj.Valid [n], and the key monitoring personnel region judged result of moving target Obj n frame is Obj.ER [n], and formula is following so:
If the key monitoring personnel, then said Moving Target state comprises time Obj.During, the motion amplitude Obj.MoveExtent that target exists, and humanoid characteristic statistics is Obj.Valid as a result, key monitoring personnel region judged result Ob.jER.
The said movement objective orbit characteristic of ObjValid [n] is judged available following formulate:
Wherein, Obj.WrnStatus is the alarm condition of moving target Obj; DuringTh is the duration threshold value, and MoveExtentTh is the motion amplitude threshold value, and ValidRatioTh meets the proportion threshold value of totalframes in Obj.During of humanoid characteristic for moving target Obj.
If key monitoring personnel; Then it comprises: through short target of filtration duration moving target duration, judge the motion less than normal of filtration amplitude, stand up wrong report, confirm through the statistics of key monitoring personnel region whether moving target is the emphasis personnel through humanoid characteristic statistics judgement filtration through the moving target amplitude.Said movement objective orbit characteristic is judged available following formulate:
Wherein, Obj.WrnStatus is the alarm condition of moving target Obj; DuringTh is the duration threshold value; MoveExtentTh is the motion amplitude threshold value, and ValidRatioTh meets the proportion threshold value of totalframes in Obj.During of humanoid characteristic for moving target Obj, and ERRatioTh is totalframes the proportion threshold value among Obj.Durings of moving target Obj in key monitoring personnel region.
Though more than described embodiment of the present invention, it will be understood by those of skill in the art that these only illustrate, under the prerequisite that does not deviate from principle of the present invention and essence, can make numerous variations or modification to these embodiments.Therefore, protection scope of the present invention is limited appended claims.
Claims (11)
1. detection system of standing up based on video; It is characterized in that it comprises video acquiring module, video demarcating module, Algorithm Analysis module and administration module, video acquiring module adopts video camera, capture card and computing machine; Video acquiring module outputs to calculator memory with the simulating signal of capture card acquisition camera; The video demarcating module is demarcated the video data that capture card collects, and calibrates the zone that the Algorithm Analysis module is paid close attention in the scene, and the Algorithm Analysis module is handled the video data that capture card collects; The position of the Algorithm Analysis module region-of-interest that calibrates in conjunction with the video demarcating module; Judgement through human behavior in the video detects whether monitor staff's bunk bed is arranged, and outputs results to administration module, the management that administration module is reported to the police and triggered according to the analysis result of Algorithm Analysis module output.
2. the detection system of standing up based on video as claimed in claim 1 is characterized in that said video demarcating module need be demarcated scene with quadrilateral, and following correspondence position physically should be parallel on the quadrilateral.
3. the detection system of standing up based on video as claimed in claim 1 is characterized in that said monitor staff is the key monitoring personnel.
4. the detection system of standing up based on video as claimed in claim 3 is characterized in that said administration module comprises the classifying alarm function, reports to the police as one-level during key monitoring personnel bunk bed, reports to the police as secondary during non-key monitoring personnel bunk bed.
5. the detection system of standing up based on video as claimed in claim 3; It is characterized in that; Said video demarcating module need be demarcated overall region and key monitoring personnel region; Overall region need be demarcated with quadrilateral, and following correspondence position physically should be parallel on the quadrilateral, and the key monitoring personnel need demarcate with polygon the region.
6. the detection system of standing up based on video as claimed in claim 3; It is characterized in that, said Algorithm Analysis module comprise obtain video data step, background modeling step, obtain the moving target step, moving target single frames characteristic extraction step, motion target tracking step, movement objective orbit characteristic determining step.
7. the detection system of standing up based on video as claimed in claim 3 is characterized in that, said background modeling step realizes according to the frame difference movement statistics of pixel.
8. the detection system of standing up based on video as claimed in claim 3 is characterized in that, said obtain the moving target step comprise before and after the extraction of frame difference, frame difference image binaryzation, the connected domain analysis of frame.
9. the detection system of standing up based on video as claimed in claim 3 is characterized in that, the single frames characteristic extraction step of said moving target judges according to humanoid characteristic whether definite moving target is the people who stands up.
10. the detection system of standing up based on video as claimed in claim 3; It is characterized in that; Said movement objective orbit characteristic determining step comprises: through short target of filtration duration moving target duration, judge the motion less than normal of filtration amplitude, stand up wrong report through humanoid characteristic statistics judgement filtration through the moving target amplitude.
11. the detection system of standing up based on video as claimed in claim 3; It is characterized in that; The treatment scheme of said administration module is: if monitor staff's bunk bed is arranged, then administration module carries out the warning of sound, light and power mode to master-control room, and people's police on duty in time handle; Deposit warning picture and warning video in server database simultaneously; The user is through socket query history record after being convenient to, and generates various statistical report forms according to historical record data, is convenient to analyze and carries out relevant improvement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100219797A CN102610054A (en) | 2011-01-19 | 2011-01-19 | Video-based getting up detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100219797A CN102610054A (en) | 2011-01-19 | 2011-01-19 | Video-based getting up detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102610054A true CN102610054A (en) | 2012-07-25 |
Family
ID=46527389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100219797A Pending CN102610054A (en) | 2011-01-19 | 2011-01-19 | Video-based getting up detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102610054A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103337122A (en) * | 2013-06-03 | 2013-10-02 | 国家电网公司 | Virtual isolation barrier system for power transmission and distribution line |
| CN103686092A (en) * | 2013-12-30 | 2014-03-26 | 深圳锐取信息技术股份有限公司 | Dual system detection method and system for rising of students |
| CN105940434A (en) * | 2014-03-06 | 2016-09-14 | 诺日士精密株式会社 | Information processing device, information processing method, and program |
| CN105960663A (en) * | 2014-02-18 | 2016-09-21 | 诺日士精密株式会社 | Information processing device, information processing method, and program |
| CN105960664A (en) * | 2014-02-07 | 2016-09-21 | 诺日士精密株式会社 | Information processing device, information processing method, and program |
| CN107911653A (en) * | 2017-11-16 | 2018-04-13 | 王磊 | The module of intelligent video monitoring in institute, system, method and storage medium |
| CN110633681A (en) * | 2019-09-19 | 2019-12-31 | 天津天地伟业机器人技术有限公司 | Bed-leaving detection method based on video |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005034226A (en) * | 2003-07-16 | 2005-02-10 | Keakomu:Kk | Rising detector |
| CN101154310A (en) * | 2006-09-26 | 2008-04-02 | 黄奎 | Security anti-theft alarm device |
| JP2008092538A (en) * | 2006-10-04 | 2008-04-17 | Ishihara Sangyo:Kk | Patient detection system |
| CN101281593A (en) * | 2008-04-16 | 2008-10-08 | 安防科技（中国）有限公司 | Method and system for researching intelligent video monitoring case |
| CN101464952A (en) * | 2007-12-19 | 2009-06-24 | 中国科学院自动化研究所 | Abnormal behavior identification method based on contour |
| CN201315654Y (en) * | 2008-08-25 | 2009-09-23 | 云南正卓信息技术有限公司 | Special SkyEyes** intelligent monitoring system for prison |
-
2011
- 2011-01-19 CN CN2011100219797A patent/CN102610054A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005034226A (en) * | 2003-07-16 | 2005-02-10 | Keakomu:Kk | Rising detector |
| CN101154310A (en) * | 2006-09-26 | 2008-04-02 | 黄奎 | Security anti-theft alarm device |
| JP2008092538A (en) * | 2006-10-04 | 2008-04-17 | Ishihara Sangyo:Kk | Patient detection system |
| CN101464952A (en) * | 2007-12-19 | 2009-06-24 | 中国科学院自动化研究所 | Abnormal behavior identification method based on contour |
| CN101281593A (en) * | 2008-04-16 | 2008-10-08 | 安防科技（中国）有限公司 | Method and system for researching intelligent video monitoring case |
| CN201315654Y (en) * | 2008-08-25 | 2009-09-23 | 云南正卓信息技术有限公司 | Special SkyEyes** intelligent monitoring system for prison |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103337122A (en) * | 2013-06-03 | 2013-10-02 | 国家电网公司 | Virtual isolation barrier system for power transmission and distribution line |
| CN103686092A (en) * | 2013-12-30 | 2014-03-26 | 深圳锐取信息技术股份有限公司 | Dual system detection method and system for rising of students |
| CN103686092B (en) * | 2013-12-30 | 2016-09-14 | 深圳锐取信息技术股份有限公司 | Student stands up dual system detection method and system |
| CN105960664A (en) * | 2014-02-07 | 2016-09-21 | 诺日士精密株式会社 | Information processing device, information processing method, and program |
| CN105960663A (en) * | 2014-02-18 | 2016-09-21 | 诺日士精密株式会社 | Information processing device, information processing method, and program |
| CN105940434A (en) * | 2014-03-06 | 2016-09-14 | 诺日士精密株式会社 | Information processing device, information processing method, and program |
| CN107911653A (en) * | 2017-11-16 | 2018-04-13 | 王磊 | The module of intelligent video monitoring in institute, system, method and storage medium |
| CN110633681A (en) * | 2019-09-19 | 2019-12-31 | 天津天地伟业机器人技术有限公司 | Bed-leaving detection method based on video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102610054A (en) | Video-based getting up detection system | |
| Tzeng et al. | Design of fall detection system with floor pressure and infrared image | |
| US7876351B2 (en) | Methods and systems for alerting by weighing data based on the source, time received, and frequency received | |
| CN103514694A (en) | Intrusion detection monitoring system | |
| CN106919892B (en) | Behavior monitoring method and device | |
| US8365871B2 (en) | Electronic device and method for monitoring an elevator | |
| CN112489368A (en) | Intelligent falling identification and detection alarm method and system | |
| CN100573375C (en) | Electrostatic real-time monitoring system and data acquisition thereof and analytical approach | |
| CN109657626A (en) | A kind of analysis method by procedure identification human body behavior | |
| CN112650608B (en) | Abnormal root cause positioning method, related device and equipment | |
| CN109637066A (en) | A kind of building intelligent the monitoring system of fire protection and method | |
| CN109867186A (en) | A kind of elevator malfunction detection method and system based on intelligent video analysis technology | |
| CN106448055B (en) | Monitoring alarm method and device | |
| CN110321582B (en) | Method and device for analyzing marketing activity | |
| CN112102574B (en) | Intelligent alarm system for security room | |
| Zambanini et al. | Detecting falls at homes using a network of low-resolution cameras | |
| CN107465652B (en) | Operation behavior detection method, server and system | |
| CN205847453U (en) | A kind of wisdom gold eyeball people based on intelligent video technology and the Activity recognition system of thing | |
| CN117081917A (en) | Intelligent gateway based on AI (advanced technology attachment) internet of things sewage treatment operation and maintenance management | |
| CN205211111U (en) | Security protection monitored control system of computer room | |
| CN106067963B (en) | Distributed automatic report method for remote large monitor abnormity | |
| CN111191499A (en) | Fall detection method and device based on minimum center line | |
| CN106250808A (en) | Double guard detection method based on three-dimensional camera and system | |
| Chua et al. | Intelligent visual based fall detection technique for home surveillance | |
| CN116246401A (en) | Monitoring system for community public area management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120725 |