CN103873825A - ATM (automatic teller machine) intelligent monitoring system and method - Google Patents
ATM (automatic teller machine) intelligent monitoring system and method Download PDFInfo
- Publication number
- CN103873825A CN103873825A CN201410072225.8A CN201410072225A CN103873825A CN 103873825 A CN103873825 A CN 103873825A CN 201410072225 A CN201410072225 A CN 201410072225A CN 103873825 A CN103873825 A CN 103873825A
- Authority
- CN
- China
- Prior art keywords
- atm
- image
- detection
- video
- intelligent
- 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
Abstract
The invention provides an ATM (automatic teller machine) intelligent monitoring system and an ATM intelligent monitoring method. The ATM intelligent monitoring system is used for performing video monitoring on an ATM or a user under the ATM monitoring scene, and consists of an image acquisition and processing module, a sensor and sensing data processing module, an intelligent analyzing module and an alarming module. The ATM intelligent monitoring method comprises various anomalous event detection methods, such as face detection and recognition, peep behavior detection, false advertisement and hangover detection, personnel wandering analysis, acute behavior alarming, yellow line crossing alarming, video signal abnormity monitoring, ATM bayonet and keyboard refit and image quality analysis. The ATM intelligent monitoring device is characterized in that the camera is firstly used for shooting the face of an ATM operator, an ATM keyboard, an ATM screen and the scene of a room where the ATM is located, the sensing data acquisition and processing module is used for acquiring vibration of the ATM and the signal of a position where the human body is located, and the intelligent analyzing module is used for analyzing human behavior and alarming for suspicious behavior. The problems that the traditional monitoring and analyzing system is large in workload, low in efficiency, easy in neglecting and failing to report the suspicious behavior, non-real-time alarming and the like are solved.
Description
(1) technical field:
The present invention relates under a kind of ATM monitoring scene, ATM device, user be carried out the method for video monitoring, especially refer to a kind of pattern recognition and Based Intelligent Control, vision calculating and intelligent video analysis technology, image processing and data fusion method, by the fusion to visible ray and sensor information, realized under ATM monitoring scene to ATM device, operator carries out video analysis that safe early warning is provided, strick precaution destroys ATM, robbery is coerced ATM client, stolen the behaviors such as ATM customer information, belongs to technical field of information processing.
(2) background technology:
For bank ATM, crime takes place frequently in recent years, ATM is destroyed, ATM client by robbery coerce, customer information is stolen etc., and behavior happens occasionally.Traditional artificial video monitoring is by a large amount of real-time pictures of monitor staff's taking turn supervisory control system one by one, and the generation of these behaviors of presentiment and preventing comprehensively can only be transferred video recording for verification afterwards.
The major vendor of domestic market exploitation ATM intelligent monitoring software has Haikang, Infinova, Suo Bei and David logical etc., and other producers comprise that far opening up science and technology, ten thousand China Tech skills, Bel believes science and technology etc.Find by investigation, domestic manufacturer is roughly the same in the solution providing aspect ATM intelligent monitoring, mainly embody a concentrated reflection of in Hardware Design, deficiency aspect software function integration and completeness, calculates good technical scheme is not provided for complicated behavioural analysis, recognition of face, legacy real-time analysis prompting contour level vision.Provide the company of ATM intelligent monitoring solution to mainly contain ROTOTYPE, RADEN, GRG and BS/2 etc. abroad, due to market demand difference, aspect the hardware management and data base administration of distributed ATM network, there is not temporarily the intelligent monitoring scheme for atm device environment and handling safety specially in the solution advantage emphasis of offshore company.
(3) summary of the invention:
The object of the invention is to utilize image processing, vision to calculate and intelligent video analysis technology, realize the automatic monitoring early warning of ATM environment, equipment and handling safety, full-scope safeguards bank and user's property safety.This system solved that Traditional Man monitoring analysis system workload is large, efficiency is low, easily ignore fail to report suspicious actions, the problems such as non real-time property of reporting to the police, there is the feature such as high accuracy, high-intelligentization, in having improved warning precision and efficiency, greatly reducing the needed resource of system maintenance, is the indispensable part of following bank's intelligent monitoring solution.
The invention provides face detects identification, peeps behavior detection, sham publicity and legacy detects, personnel hover analysiss, aggressive behavior warning, cross the accident detections such as yellow line warning, vision signal abnormal monitoring, atm card mouth and keyboard modification monitoring, image quality analysis, combined with hardware sensor assembly possesses ATM shock detection, bayonet socket is left over the intellectual analysis alert capabilities such as prompting simultaneously.For different type of alarm, possesses the real-time recording of preservation fragment, voice bidirectional intercommunication, the functions such as the automatic control of alarm, warning lamp and gate inhibition.
(4) accompanying drawing explanation:
Fig. 1 is the deployment diagram of system hardware of the present invention under ATM monitoring scene
Fig. 2 is the structured flowchart of entire system of the present invention
Fig. 3 is the flow chart of video acquisition processing module of the present invention
Fig. 4 is the flow chart of transducer of the present invention and sensing data processing module
Fig. 5 is the flow chart of intelligent analysis module of the present invention
Fig. 6 is the present invention's report to the police and report to the police flow chart of picture recording module
Fig. 7 is the flow chart of intelligent analysis module remnant object detection method of the present invention
Fig. 8 is the flow chart of intelligent analysis module camera occlusion detection method of the present invention
Fig. 9 is the flow chart of intelligent analysis module aggressive behavior detection method of the present invention
Figure 10 is the flow chart that intelligent analysis module face of the present invention detects recognition methods
Figure 11 is the hover flow charts of analytical method of intelligent analysis module personnel of the present invention
Figure 12 is the flow chart that intelligent analysis module of the present invention is crossed yellow line alarm method
Figure 13 is the flow chart of intelligent analysis module atm card mouth of the present invention and keyboard modification detection method
Figure 14 is the flow chart of intelligent analysis module ATM shock detection method of the present invention
Figure 15 is the flow chart of intelligent analysis module video quality analytical method of the present invention
(5) specific embodiments:
ATM intelligent early-warning system is multi-functional, multimode, intelligentized software and hardware integration integrated system, the deployment scenario of the hardware device that the illustrated expression of Fig. 1 the present invention relates to, the diagrammatically shown the present invention of Fig. 2 comprises: IMAQ and processing module 202, transducer and sensing data processing module 201, intelligent analysis module 203, alarm module 204.Transducer and sensing data processing module 201, IMAQ and processing module 202 are responsible for respectively pick-up transducers signal, vision signal, send to intelligent analysis module 203 to carry out intellectual analysis, what in the result that analysis obtains, need warning sends to alarm module 204 by intelligent analysis module 203 by alarm signal, alarm module 204 drives hardware device 205 to report to the police, and reports to the police to Surveillance center 206.
1) IMAQ and processing module:
IMAQ part in this IMAQ and processing module comprise embed the fisheye camera 105 that gathers face signal in ATM, be positioned over ATM towards have people's skew back top capture ATM keyboard screen and operator infrared/the changeable camera 110 of visible ray, be positioned over indoor corner, ATM place wide-angle camera 111, record a video and the DVR 104(that carries out front-end camera control can be configured to digital hard disc video recorder DVR and network hard disc video camera NVR);
The flow process of the image processing section in the illustrated presentation video acquisition and processing of Fig. 3 module, first headend equipment obtains video flowing 303, and decoding video stream 304, single-frame images format conversion 305, frame of video buffer memory 306 operate; The decoding video stream that decoding video stream sends headend equipment becomes image one by one; Frame of video format conversion is responsible for the image unification of different coding form to be converted to the image of rgb format; Frame of video caching gets off the frame of video buffer memory of consolidation form, for intelligent analysis module processing.
2) transducer and sensing data processing module:
This transducer and sensing data processing module are made up of shock sensor 108, distance measuring sensor 109, sensing data processing module 102.Wherein shock sensor 108 is placed in ATM outer casing inner wall, for measuring the shock conditions of ATM; Distance measuring sensor 109 is placed in ATM towards there being people's side, for measuring the distance of human body distance A TM machine; Sensing data processing module 102(one chip microcomputer) be positioned over ATM inside; With the data of comprehensive each transducer and get rid of noise, offer intelligent analysis module and process;
The flow chart of the diagrammatically shown transducer of Fig. 4 and sensing data processing module, first shock sensor, distance measuring sensor signal input (403,404), remove after filtration respectively signal noise (405,406), signal lag processing (407,408), for vibration signal, in the time that vibration signal value is greater than certain threshold value within the scope of certain hour (409), send vibrations alarm signals (411) by parallel port to computer; Otherwise, send shockproof signal (411) by parallel port to meter computer; For distance signal, in the time that distance signal value is less than certain threshold value within the scope of certain hour (409), send human body close signal (411) by parallel port to meter computer; Otherwise, send without human body close signal (411) to computer by parallel port; All data all deposit computer data buffering area (415) in above.
3) intelligent analysis module:
This intelligent analysis module is made up of digital computing system 103 and intellectual analysis software, and this intellectual analysis analysis software is deployed in digital computing system 103;
The flow process of the diagrammatically shown intelligent analysis module of Fig. 5: first respectively to video frame buffers requested image (503), to the request vibrations of sensing data buffering area and human body close signal (504), then analyze (505) by intelligent analysis module, if current information enough judges, Output rusults, otherwise continuation requested image and sensor signal are until can judge; Secondly judge whether current intellectual analysis result needs to report to the police, if desired send alarm signal (508) to alarm module, otherwise intellectual analysis flow process finishes.
4) alarm module:
This alarm module, comprises hardware driving circuit 114 and gate control system 113, intercom 106, alarm lamp, loudspeaker etc.;
The diagrammatically shown alarm module flow chart of Fig. 6, first alarm module receives alarm signal 603, judges whether to send alarm signal 604 to control centre, if desired, sends alarm signal (605) to control centre, otherwise, do not send alarm signal; Then judge whether demand motive hardware circuit warning 606, if desired send hardware control instructions 607 and drive hardware to carry out controlling alarm, comprise and drive access control 113, intercom 106 etc.; Send a signal to video acquisition module the content of this time period is recorded a video to 608.
5) intelligent analysis method:
This intelligent analysis method is present in intelligent analysis module, comprises: legacy detection, camera occlusion detection, human body aggressive behavior detection, suspicion face detect and identify, personnel hover analyzing and testing, not operation personnel cross yellow line and report to the police, peep behavior detection, atm card mouth and keyboard modification detection, ATM shock detection, video quality method for detecting abnormality;
The diagrammatically shown legacy testing process of Fig. 7: first the N two field picture of input is carried out to difference (703), judge image scene whether change (704), if there is no scene changes, transfer respectively realtime graphic and prefabricated bit image to gray level image (705), two images carry out difference (707) again, carry out successively filtering (709), binaryzation (711), morphology processing (713), need look for connected region (704), if connected region area is less than threshold value T1(716), using present image as new prefabricated bit image (718); Otherwise, if image Scene changes, then get N two field picture and carry out difference (706), if changing does not appear in image scene, again get N two field picture and carry out difference (703); After 708 judgement scenes change, successively realtime graphic and prefabricated bit image are carried out to difference (710), binaryzation (712), the result of result and last registration is carried out with operation (715), found connected region (717), if connected region area is greater than threshold value T2(719), search out legacy (720);
The diagrammatically shown camera occlusion detection of Fig. 8 flow process: first input image to be tested (803), successively image is carried out to binaryzation (804), intercept region of interest ROI (805), to the gradient absolute value of ROI image calculation X/Y direction, get larger one of gradient absolute value in both direction and carry out binaryzation, ask the entropy (810) of this matrix, with default entropy threshold value M1 make comparisons (811), if this matrix entropy is greater than M1, think that camera is blocked (812), otherwise think camera be not blocked (813);
The diagrammatically shown aggressive behavior testing process of Fig. 9: the frame of video (903) of first inputting some, carry out moving region detection (904), movement velocity estimation (905), carry out motion ordery analysis (906), judge whether it is too fierce behavior (907), if not again input picture is carried out to moving region detection (904), otherwise think too fierce behavior (908) occurs, report to the police;
The diagrammatically shown suspicion face of Figure 10 detects and the doubtful testing process of peeping: first ask input video frame (1003), carry out successively moving region detection (1004), Face Detection (1005), full figure traversal wicket (1005), whether be face (1006), if face is preserved facial image (1007) if detecting, detect whether suspicion face (1009) of this face, if carry out suspect's warning (1011); Preserve facial image (1007) afterwards, image detection to face number add one (1008), when having judged whether that in ATM operating area multiple faces appear at (1010) in same piece image, if so, carry out the doubtful warning (1012) of peeping;
The diagrammatically shown pedestrian of Figure 11 testing process of hovering: first get N1 frame realtime graphic (1102), carry out pedestrian detection (1103), doubling-up goes out pedestrian (1104), pedestrian is followed the tracks of to (1105), record pedestrian's movement locus (1106), pedestrian's movement locus is analyzed to (1107), utilize the HMM model training in advance to judge (1108) to track, hover if be judged as, by the pedestrian who hovers and out (1109) of historical movement Trajectories Toggle thereof, otherwise requested image detects again;
The diagrammatically shown yellow line testing process of crossing of Figure 12: first get N1 frame consecutive image (1202), detect whether there is pedestrian (1203), iris out pedestrian (1204) if having, measure the distance of pedestrian apart from yellow line by photogrammetric technology; Then input the distance signal result that distance measuring sensor is measured, if result is consistent, judge whether this distance has crossed yellow line (1208), cross yellow line alarm signal if crossed output; Otherwise again obtaining image detects;
The diagrammatically shown atm card mouth of Figure 13 and keyboard modification testing process: in advance at keyboard, go out bayonet socket etc. and locate to smear the coating of special wave band, first will monitor that camera switches to the corresponding modes (1302) of corresponding special wave band, in the time of unattended ATM, obtain piece image (1303), intercept the image (1304) of bayonet socket and keyboard area according to the region of interest ROI of configuration, extract the feature (1305) of cut-away view picture, do poor (1306) with pre-stored area image or its feature, if feature difference is excessive or image and pre-stored image difference excessive, think that bayonet socket and keyboard were reequiped, output alarm signal (1307),
The diagrammatically shown ATM shock detection of Figure 14 flow process: first get N1 frame realtime graphic (1403), judge whether image rocks (1404), if image does not rock, again get N1 two field picture and detect (1403); Otherwise the ATM vibration signal value M1(1405 that input pickup records), judge whether M1 is greater than default vibrations threshold value T1(1406), if judge that ATM rocks, export corresponding alarm signal (1407);
The diagrammatically shown video quality abnormality detection of Figure 15 flow process: first input frame image to be detected (1503), then the parts of images (1504) between the word that sectional drawing image to be detected above and below marks, the image intercepting out is divided into 9 (1505) by 3*3, extract feature (1506) to every respectively, finally utilize svm grader to classify (1507), divide into respectively image excessively bright (1508), no signal (1509), image normal (1510), blue screen (1511), snowflake screen (1512).
Claims (3)
1. the contactless self-help bank based on machine vision and a self-help teller machine intelligent monitor system, is characterized in that, described intelligent monitoring and controlling device comprises:
Transducer and sensing data processing module, be made up of shock sensor, infrared range-measurement system, one chip microcomputer; This shock sensor is measured the vibrations of ATM, and this infrared range-measurement system is measured the distance of human body distance A TM machine;
IMAQ and processing module, be made up of digital camera, digital hard disc video recorder; This digital camera comprise embed the fisheye camera that gathers facial image in ATM, be positioned over ATM human oriented skew back top capture ATM keyboard screen and operator infrared/the changeable camera of visible ray, be positioned over the wide-angle camera in indoor corner, ATM place; This digital hard disc video recorder is configured to DVR and NVR as required;
Alarm module, is made up of gate control system, video record equipment and alarm lamp and alarming horn; This gate control system is arranged on the porch in room, ATM place; This alarm lamp and alarming horn are used for pointing out user to have abnormal behaviour to occur;
Intelligent analysis module is deployed in computer system; The hardware of this computer system comprises image pick-up card, display, video card and order input equipment.
2. intelligent monitor system as claimed in claim 1, is characterized in that:
1) by IMAQ and processing module acquisition monitoring scene San road live video stream, the video flowing of yuv format is converted to rgb format in real time, sends into intelligent analysis module analysis;
2) by the distance signal of sensing data sampling and processing module Real-time Collection ATM vibrations and human body position distance A TM machine, send into intelligent analysis module analysis;
3) intelligent analysis module detects whether anomalous event occurs, if the event of noting abnormalities intercepts the relevant informations such as alarm picture, segment warning video, abnormal event alarming signal and information is delivered to alarm module;
4) alarm module receives abnormal event alarming signal, first be stored in the database in the machine, then according to the character of anomalous event, determine whether carry out anomalous event processing by serial port drive warning lamp, gate inhibition, stereo set etc., by Ethernet, warning message is sent to Surveillance center simultaneously.
3. one group of ATM intelligent control method based on machine vision, is characterized in that, comprises following accident detection method:
Legacy detects: at set intervals, judge when scene immobilizes, frame of video is automatically updated into background frames; Present frame and background frames are made difference, binaryzation, searching connected region, if connected region area is greater than certain threshold value, are judged as legacy;
Camera occlusion detection: first input image to be tested, successively image is carried out to binaryzation, intercept region of interest ROI, to the gradient absolute value of ROI image calculation X/Y direction, get larger one of gradient absolute value in both direction and carry out binaryzation, ask the entropy of this matrix, make comparisons with default entropy threshold value M1, if this matrix entropy is greater than M1, thinks that camera is blocked, otherwise think that camera is not blocked;
Aggressive behavior detects: the frame of video of first inputting some, carry out moving region detection, movement velocity estimation, carry out motion ordery analysis, according to the result of ordery analysis, judge whether it is too fierce behavior, if not again input picture is carried out to moving region detection, otherwise think too fierce behavior occurs, report to the police;
Suspicion face detects and doubtfully peeps detection: first ask input video frame, carry out successively moving region detection, Face Detection, full figure traversal wicket, whether be face, if face if detecting, preserve facial image, detect whether suspicion face of this face, if carry out suspect's warning; Preserve after facial image, image detection to face number add one, when having judged whether that in ATM operating area multiple faces appear in same piece image, if so, carry out the doubtful warning of peeping;
Pedestrian's detection of hovering: first get N1 frame real time video image, carry out pedestrian detection, doubling-up goes out pedestrian, pedestrian is followed the tracks of, record pedestrian's movement locus, pedestrian's movement locus is analyzed, utilize the HMM model training in advance to judge track, hover if be judged as, by the pedestrian who hovers and historical movement Trajectories Toggle thereof out, otherwise requested image detects again;
Crossing yellow line detects: first get N1 frame consecutive image, detect whether there is pedestrian, iris out pedestrian if having, measure the distance of pedestrian apart from yellow line by photogrammetric technology; Then input the distance signal result that distance measuring sensor is measured, if result is consistent, judge whether this distance has crossed yellow line, cross yellow line alarm signal if crossed output; Otherwise again obtaining image detects;
Atm card mouth and keyboard modification detect: in advance at keyboard, go out bayonet socket etc. and locate to smear the coating of special wave band, supervision camera is switched to corresponding wave band pattern, obtain piece image, intercept the image of bayonet socket and keyboard area according to the region of interest ROI of configuration, extract the feature of cut-away view picture, compare with the feature of the image in pre-stored two regions, if feature difference is excessive or image and pre-stored image difference excessive, think that bayonet socket and keyboard were reequiped, output alarm signal;
ATM shock detection: first get N1 frame realtime graphic, judge whether image rocks, if image does not rock, again get N1 two field picture and detect; Otherwise the ATM vibration signal value M1 that input pickup records, judges that whether M1 is greater than default vibrations threshold value T1, if judge that ATM rocks, exports corresponding alarm signal;
Video quality abnormality detection: first input frame image to be detected, then the parts of images between the word that sectional drawing image to be detected above and below marks, the image intercepting out is divided into 9 by 3*3, extract feature to every respectively, finally utilize svm grader to classify, divide into respectively that image is excessively bright, no signal, image are normal, blue screen, snowflake screen.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410072225.8A CN103873825A (en) | 2014-02-28 | 2014-02-28 | ATM (automatic teller machine) intelligent monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410072225.8A CN103873825A (en) | 2014-02-28 | 2014-02-28 | ATM (automatic teller machine) intelligent monitoring system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103873825A true CN103873825A (en) | 2014-06-18 |
Family
ID=50911906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410072225.8A Pending CN103873825A (en) | 2014-02-28 | 2014-02-28 | ATM (automatic teller machine) intelligent monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103873825A (en) |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104883538A (en) * | 2015-05-04 | 2015-09-02 | 黄河科技学院 | Intelligent monitoring system and method for automatic teller machine |
| CN104915655A (en) * | 2015-06-15 | 2015-09-16 | 西安电子科技大学 | Multi-path monitor video management method and device |
| CN105761378A (en) * | 2016-01-29 | 2016-07-13 | 广州御银科技股份有限公司 | Device and method for automatically identifying abnormal transactions and reducing losses |
| CN106056079A (en) * | 2016-05-31 | 2016-10-26 | 中国科学院自动化研究所 | Image acquisition device and facial feature occlusion detection method |
| CN106131564A (en) * | 2016-07-28 | 2016-11-16 | 广东西奥物联网科技股份有限公司 | A kind of method and device that camera video stream is processed |
| WO2016180272A1 (en) * | 2015-05-12 | 2016-11-17 | 杭州海康威视数字技术股份有限公司 | Image acquisition method and device, and video monitoring method and system |
| CN106210636A (en) * | 2016-07-18 | 2016-12-07 | 四川君逸数码科技股份有限公司 | Wisdom gold eyeball people based on intelligent video technology and thing Activity recognition instrument |
| CN106303397A (en) * | 2015-05-12 | 2017-01-04 | 杭州海康威视数字技术股份有限公司 | Image-pickup method and system, video frequency monitoring method and system |
| CN106331646A (en) * | 2016-09-09 | 2017-01-11 | 北京高地信息技术有限公司 | Artificial intelligence safety monitoring system |
| CN106778901A (en) * | 2016-12-30 | 2017-05-31 | 广州视源电子科技股份有限公司 | Indoor article loses reminding method and device |
| WO2017128954A1 (en) * | 2016-01-29 | 2017-08-03 | 广州广电运通金融电子股份有限公司 | Security association method and system for self-service terminal security and protection system |
| CN107113542A (en) * | 2014-09-29 | 2017-08-29 | 泰科消防及安全有限公司 | The shop intelligent platform sensed using the degree of approach |
| CN107341445A (en) * | 2017-06-07 | 2017-11-10 | 武汉大千信息技术有限公司 | The panorama of pedestrian target describes method and system under monitoring scene |
| CN107545702A (en) * | 2017-08-28 | 2018-01-05 | 北京工业大学 | The security system and implementation method of the too high attention rate of intelligent early-warning crowd |
| CN107734303A (en) * | 2017-10-30 | 2018-02-23 | 北京小米移动软件有限公司 | Video labeling method and device |
| CN107948597A (en) * | 2017-11-29 | 2018-04-20 | 合肥寰景信息技术有限公司 | Behavioural analysis and alarm embedded device based on specific region |
| CN108734055A (en) * | 2017-04-17 | 2018-11-02 | 杭州海康威视数字技术股份有限公司 | A kind of exception personnel detection method, apparatus and system |
| CN108961540A (en) * | 2018-06-14 | 2018-12-07 | 合肥美的智能科技有限公司 | Unmanned vending machine and alarm method |
| WO2019036964A1 (en) * | 2017-08-23 | 2019-02-28 | 深圳企管加企业服务有限公司 | Machine room vibration alarm system based on internet of things |
| CN109951682A (en) * | 2019-02-25 | 2019-06-28 | 广东协安机电工程有限公司 | A kind of bank safety video monitoring system |
| CN110134676A (en) * | 2019-06-03 | 2019-08-16 | 西安电子科技大学 | A kind of monitoring method of sensing data quality |
| CN110446015A (en) * | 2019-08-30 | 2019-11-12 | 北京青岳科技有限公司 | A kind of abnormal behaviour monitoring method based on computer vision and system |
| CN110533328A (en) * | 2019-08-30 | 2019-12-03 | 广州广电城市服务集团股份有限公司 | A kind of project scene traffic control method, apparatus, medium and terminal device |
| CN110704284A (en) * | 2019-09-27 | 2020-01-17 | 高新兴科技集团股份有限公司 | Alarm processing method and system in video monitoring scene and electronic equipment |
| RU2713876C1 (en) * | 2019-02-12 | 2020-02-07 | Публичное Акционерное Общество "Сбербанк России" (Пао Сбербанк) | Method and system for detecting alarm events when interacting with self-service device |
| CN111507216A (en) * | 2017-11-03 | 2020-08-07 | 阿里巴巴集团控股有限公司 | Method and device for identifying illegal behaviors in unattended scene |
| CN111542866A (en) * | 2017-12-21 | 2020-08-14 | 株式会社木村技研 | Toilet management system and toilet management method |
| CN111583539A (en) * | 2020-04-17 | 2020-08-25 | 温州大学 | Automatic goods placing and network selling system |
| CN112150758A (en) * | 2019-06-28 | 2020-12-29 | 张伟民 | Self-service bank intelligent security device |
| WO2021012603A1 (en) * | 2019-07-23 | 2021-01-28 | Zhejiang Xinsheng Electronic Technology Co., Ltd. | Surveillance systems and methods |
| CN113112618A (en) * | 2020-01-10 | 2021-07-13 | 北京汇星导航技术有限公司 | Automatic ticket checking method based on smart phone Bluetooth |
| CN113160500A (en) * | 2021-02-24 | 2021-07-23 | 滕州京腾鑫汇新材料科技有限公司 | Visual intelligent cabinet |
| CN114664036A (en) * | 2020-12-24 | 2022-06-24 | 航天信息股份有限公司 | Tax self-service terminal alarm system and method |
| CN114724316A (en) * | 2022-05-12 | 2022-07-08 | 中国银行股份有限公司 | Alarm method and device for automatic teller machine |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201084225Y (en) * | 2007-05-31 | 2008-07-09 | 北京华景创智科技有限公司 | An ATM digital video monitoring evidence-taking device |
| KR20090068550A (en) * | 2007-12-24 | 2009-06-29 | 노틸러스효성 주식회사 | Watching system of atm |
| US7574038B1 (en) * | 2005-03-31 | 2009-08-11 | Adobe Systems Incorporated | Method and apparatus for determining the background of an image sequence |
| CN201611507U (en) * | 2010-02-03 | 2010-10-20 | 赵毅 | Full-intelligent security device of bank ATM |
| CN101894428A (en) * | 2010-05-12 | 2010-11-24 | 北京海鑫智圣技术有限公司 | ATM (Automated Teller Machine) intelligent monitoring system |
| CN102622818A (en) * | 2011-01-26 | 2012-08-01 | 北京海鑫智圣技术有限公司 | All-directional intelligent monitoring method for bank ATMs |
-
2014
- 2014-02-28 CN CN201410072225.8A patent/CN103873825A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7574038B1 (en) * | 2005-03-31 | 2009-08-11 | Adobe Systems Incorporated | Method and apparatus for determining the background of an image sequence |
| CN201084225Y (en) * | 2007-05-31 | 2008-07-09 | 北京华景创智科技有限公司 | An ATM digital video monitoring evidence-taking device |
| KR20090068550A (en) * | 2007-12-24 | 2009-06-29 | 노틸러스효성 주식회사 | Watching system of atm |
| CN201611507U (en) * | 2010-02-03 | 2010-10-20 | 赵毅 | Full-intelligent security device of bank ATM |
| CN101894428A (en) * | 2010-05-12 | 2010-11-24 | 北京海鑫智圣技术有限公司 | ATM (Automated Teller Machine) intelligent monitoring system |
| CN102622818A (en) * | 2011-01-26 | 2012-08-01 | 北京海鑫智圣技术有限公司 | All-directional intelligent monitoring method for bank ATMs |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107113542B (en) * | 2014-09-29 | 2020-07-17 | 泰科消防及安全有限公司 | Store intelligent platform using proximity sensing |
| CN107113542A (en) * | 2014-09-29 | 2017-08-29 | 泰科消防及安全有限公司 | The shop intelligent platform sensed using the degree of approach |
| CN104883538A (en) * | 2015-05-04 | 2015-09-02 | 黄河科技学院 | Intelligent monitoring system and method for automatic teller machine |
| WO2016180272A1 (en) * | 2015-05-12 | 2016-11-17 | 杭州海康威视数字技术股份有限公司 | Image acquisition method and device, and video monitoring method and system |
| CN106303397B (en) * | 2015-05-12 | 2019-03-22 | 杭州海康威视数字技术股份有限公司 | Image-pickup method and system, video monitoring method and system |
| CN106303397A (en) * | 2015-05-12 | 2017-01-04 | 杭州海康威视数字技术股份有限公司 | Image-pickup method and system, video frequency monitoring method and system |
| CN104915655A (en) * | 2015-06-15 | 2015-09-16 | 西安电子科技大学 | Multi-path monitor video management method and device |
| WO2017128954A1 (en) * | 2016-01-29 | 2017-08-03 | 广州广电运通金融电子股份有限公司 | Security association method and system for self-service terminal security and protection system |
| CN105761378A (en) * | 2016-01-29 | 2016-07-13 | 广州御银科技股份有限公司 | Device and method for automatically identifying abnormal transactions and reducing losses |
| CN107025737A (en) * | 2016-01-29 | 2017-08-08 | 广州广电运通金融电子股份有限公司 | A kind of self-service terminal safety-protection system safety interaction method and system |
| CN106056079B (en) * | 2016-05-31 | 2019-07-05 | 中国科学院自动化研究所 | A kind of occlusion detection method of image capture device and human face five-sense-organ |
| CN106056079A (en) * | 2016-05-31 | 2016-10-26 | 中国科学院自动化研究所 | Image acquisition device and facial feature occlusion detection method |
| CN106210636A (en) * | 2016-07-18 | 2016-12-07 | 四川君逸数码科技股份有限公司 | Wisdom gold eyeball people based on intelligent video technology and thing Activity recognition instrument |
| CN106131564A (en) * | 2016-07-28 | 2016-11-16 | 广东西奥物联网科技股份有限公司 | A kind of method and device that camera video stream is processed |
| CN106331646A (en) * | 2016-09-09 | 2017-01-11 | 北京高地信息技术有限公司 | Artificial intelligence safety monitoring system |
| CN106778901A (en) * | 2016-12-30 | 2017-05-31 | 广州视源电子科技股份有限公司 | Indoor article loses reminding method and device |
| CN108734055B (en) * | 2017-04-17 | 2021-03-26 | 杭州海康威视数字技术股份有限公司 | Abnormal person detection method, device and system |
| CN108734055A (en) * | 2017-04-17 | 2018-11-02 | 杭州海康威视数字技术股份有限公司 | A kind of exception personnel detection method, apparatus and system |
| CN107341445A (en) * | 2017-06-07 | 2017-11-10 | 武汉大千信息技术有限公司 | The panorama of pedestrian target describes method and system under monitoring scene |
| WO2019036964A1 (en) * | 2017-08-23 | 2019-02-28 | 深圳企管加企业服务有限公司 | Machine room vibration alarm system based on internet of things |
| CN107545702A (en) * | 2017-08-28 | 2018-01-05 | 北京工业大学 | The security system and implementation method of the too high attention rate of intelligent early-warning crowd |
| CN107734303A (en) * | 2017-10-30 | 2018-02-23 | 北京小米移动软件有限公司 | Video labeling method and device |
| US10810439B2 (en) | 2017-10-30 | 2020-10-20 | Beijing Xiaomi Mobile Software Co., Ltd. | Video identification method and device |
| CN111507216A (en) * | 2017-11-03 | 2020-08-07 | 阿里巴巴集团控股有限公司 | Method and device for identifying illegal behaviors in unattended scene |
| CN107948597A (en) * | 2017-11-29 | 2018-04-20 | 合肥寰景信息技术有限公司 | Behavioural analysis and alarm embedded device based on specific region |
| CN111542866B (en) * | 2017-12-21 | 2022-03-08 | 株式会社木村技研 | Toilet management system and toilet management method |
| CN111542866A (en) * | 2017-12-21 | 2020-08-14 | 株式会社木村技研 | Toilet management system and toilet management method |
| CN108961540A (en) * | 2018-06-14 | 2018-12-07 | 合肥美的智能科技有限公司 | Unmanned vending machine and alarm method |
| RU2713876C1 (en) * | 2019-02-12 | 2020-02-07 | Публичное Акционерное Общество "Сбербанк России" (Пао Сбербанк) | Method and system for detecting alarm events when interacting with self-service device |
| EA038293B1 (en) * | 2019-02-12 | 2021-08-05 | Публичное Акционерное Общество "Сбербанк России" (Пао Сбербанк) | Method and system for detecting troubling events during interaction with a self-service device |
| WO2020167155A1 (en) * | 2019-02-12 | 2020-08-20 | Публичное Акционерное Общество "Сбербанк России" | Method and system for detecting troubling events during interaction with a self-service device |
| CN109951682A (en) * | 2019-02-25 | 2019-06-28 | 广东协安机电工程有限公司 | A kind of bank safety video monitoring system |
| CN110134676A (en) * | 2019-06-03 | 2019-08-16 | 西安电子科技大学 | A kind of monitoring method of sensing data quality |
| CN110134676B (en) * | 2019-06-03 | 2021-01-29 | 西安电子科技大学 | Method for monitoring data quality of sensor |
| CN112150758A (en) * | 2019-06-28 | 2020-12-29 | 张伟民 | Self-service bank intelligent security device |
| WO2021012603A1 (en) * | 2019-07-23 | 2021-01-28 | Zhejiang Xinsheng Electronic Technology Co., Ltd. | Surveillance systems and methods |
| US20220130151A1 (en) * | 2019-07-23 | 2022-04-28 | Zhejiang Xinsheng Electronic Technology Co., Ltd. | Surveillance systems and methods |
| CN110533328A (en) * | 2019-08-30 | 2019-12-03 | 广州广电城市服务集团股份有限公司 | A kind of project scene traffic control method, apparatus, medium and terminal device |
| CN110446015A (en) * | 2019-08-30 | 2019-11-12 | 北京青岳科技有限公司 | A kind of abnormal behaviour monitoring method based on computer vision and system |
| CN110704284A (en) * | 2019-09-27 | 2020-01-17 | 高新兴科技集团股份有限公司 | Alarm processing method and system in video monitoring scene and electronic equipment |
| CN113112618A (en) * | 2020-01-10 | 2021-07-13 | 北京汇星导航技术有限公司 | Automatic ticket checking method based on smart phone Bluetooth |
| CN111583539B (en) * | 2020-04-17 | 2022-04-01 | 温州大学 | Automatic goods placing and network selling system |
| CN111583539A (en) * | 2020-04-17 | 2020-08-25 | 温州大学 | Automatic goods placing and network selling system |
| CN114664036A (en) * | 2020-12-24 | 2022-06-24 | 航天信息股份有限公司 | Tax self-service terminal alarm system and method |
| CN113160500A (en) * | 2021-02-24 | 2021-07-23 | 滕州京腾鑫汇新材料科技有限公司 | Visual intelligent cabinet |
| CN114724316A (en) * | 2022-05-12 | 2022-07-08 | 中国银行股份有限公司 | Alarm method and device for automatic teller machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103873825A (en) | ATM (automatic teller machine) intelligent monitoring system and method | |
| Adam et al. | Robust real-time unusual event detection using multiple fixed-location monitors | |
| US7646401B2 (en) | Video-based passback event detection | |
| CN201965714U (en) | Home intelligent early-warning security system based on human face recognition | |
| US7751647B2 (en) | System and method for detecting an invalid camera in video surveillance | |
| US20180115749A1 (en) | Surveillance system and surveillance method | |
| CN102859565B (en) | Method and system for security system tampering detection | |
| CN106650584B (en) | Flame detecting method and system | |
| US20110228984A1 (en) | Systems, methods and articles for video analysis | |
| US8086088B2 (en) | Digital video recording method in an audio detection mode | |
| KR102195706B1 (en) | Method and Apparatus for Detecting Intruder | |
| CN105184258A (en) | Target tracking method and system and staff behavior analyzing method and system | |
| JPH10285581A (en) | Automatic monitoring device | |
| CN106127292B (en) | Flow method of counting and equipment | |
| CN105516652B (en) | A kind of intelligent campus street lamp illumination system | |
| CN212208379U (en) | Automatic attendance temperature measuring system | |
| CN110490126B (en) | Safe deposit box safety control system based on artificial intelligence | |
| KR20170058827A (en) | Security system and security process and security controller of throw trash, by detected humans action or shape image | |
| CN105592301A (en) | Image capturing apparatus, method of controlling the same, monitoring camera system | |
| KR101033238B1 (en) | Video surveillance system and recording medium recording in which video surveillance program is recorded | |
| CN112102574B (en) | Intelligent alarm system for security room | |
| KR20160093253A (en) | Video based abnormal flow detection method and system | |
| CN201717988U (en) | All-in-one machine with intelligent office monitoring system | |
| KR100779858B1 (en) | picture monitoring control system by object identification and the method thereof | |
| CN111144181A (en) | Risk detection method, device and system based on background collaboration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140618 |