CN102164270A - Intelligent video monitoring method and system capable of exploring abnormal events - Google Patents
Intelligent video monitoring method and system capable of exploring abnormal eventsDownload PDFInfo
- Publication number
- CN102164270A CN102164270ACN2011100255346ACN201110025534ACN102164270ACN 102164270 ACN102164270 ACN 102164270ACN 2011100255346 ACN2011100255346 ACN 2011100255346ACN 201110025534 ACN201110025534 ACN 201110025534ACN 102164270 ACN102164270 ACN 102164270A
- Authority
- CN
- China
- Prior art keywords
- anomalous event
- moving target
- video camera
- target
- video
- 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
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
Abstract
Translated fromChinese
Description
Technical field
The present invention relates to field of video monitoring, especially a kind of video frequency monitoring method and system.
Background technology
Along with the growth of social economy and development of electronic technology and people's awareness of safety, the video monitoring technology is rapidly developed, and the intellectuality of video monitoring system is the inevitable demand of monitoring technique development.
At present, traditional artificial video monitoring mode is widely adopted, but it is not so reliable.For most of people, stare at monitoring screen and only see after 20 minutes, the details that takes place during the intensity of attentiveness just is not enough to find to record a video.Moreover, the incident that most times do not have us to pay close attention in the monitoring video takes place, even the monitor staff can focus one's attention on for a long time, also can cause the human resources serious waste.And traditional no supervision video recording mode then not only must manually be finished the task of searching when needed, and can only assist investigation as legal argument after incident takes place, and has lost the effect that helps us to take real-time measure, stop malignant event to take place.
This shows, find and analyze anomalous event (being that anomalous event is excavated) automatically in video monitoring, in time send and report to the police and processing signals, is the problem that very presses for solution.
Summary of the invention
In order to overcome not having automatic discovery and analyzing the relatively poor deficiency of real-time that anomalous event function, intelligent degree are low, report to the police of existing video monitoring mode, the invention provides a kind of intelligent video monitoring method and system that anomalous event is excavated function that have that has automatic discovery and analyze anomalous event function, intelligent degree height, in time give the alarm and carry out information processing.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of intelligent video monitoring processing method with anomalous event excavation function, this method may further comprise the steps:
Abnormal conditions around the step 1, camera supervised this video camera of passive type, the video data in the acquisition monitoring scene;
Step 2, the moving target that occurs in detection and the tracing and monitoring scene is demarcated moving target, and the position and the size parameter of moving target reached active video camera;
Step 3, active video camera according to the parameter of setting, judge whether that being necessary to transfer active video camera obtains the local feature of target according to behind the position and size parameter that obtain; If reach the requirement of transferring active video camera, then adjust the parameter and the attitude of active video camera, provide the close shot feature of the moving target that occurs in the monitoring scene adaptively; According to the transfer condition of setting, judge whether to stop to transfer equally; If still satisfy the transfer condition, then return the parameter and the attitude that continue to adjust active video camera; If reach the condition that stops to transfer active video camera, then active video camera turns back to initial setting up, monitors Same Scene with the passive type video camera with same focal length;
Step 4, detected moving target is correctly classified: differentiating target is pedestrian or other objects that enter monitoring scene, according to the object edge profile information that obtains in the tracing process and variation characteristic thereof as main classification foundation;
Step 5 is carried out behavior to sorted moving target and is understood, and extracts the behavioural characteristic of movement human target itself, and abnormal behaviour is discerned and judged whether to be to the behavior sample that comparison is trained to its behavior;
Step 6 is set the abnormal behaviour standard, according to the standard that sets, judges whether to take place anomalous event, if no abnormal incident takes place, then returns and continues to gather video data; If anomalous event has taken place, then trigger the alarm setting at once.
Further, in the described step 6,,, check evidence obtaining in order to the staff with unusual condition video recording storage if anomalous event has taken place in the future.
Further again, in the described step 4, after differentiating target and being the pedestrian, distinguishing out what enter again is single or many people of motion together.
Further, in the step 6, should have different abnormal behaviour definition for different application scenarioss.
A kind of intelligent video monitoring treatment system with anomalous event excavation function, described system comprises:
Video acquisition module is used for the collection to the guarded region video, adopts the mode of a pair of principal and subordinate's video camera collaborative work to come anomalous event in the monitoring scene;
The Intelligent Measurement module is used for guarded region motion target detection and tracking, obtains the real time position and the size parameter of moving target;
Anomalous event is excavated module, being used for that sorted moving target is carried out behavior understands, extract the behavioural characteristic of movement human target itself, the behavior sample that comparison is trained, abnormal behaviour is discerned and judged whether to be in its behavior, and the abnormal behaviour standard according to setting judges whether to take place anomalous event, if no abnormal incident takes place, then return and continue to gather video data; If anomalous event has taken place, then trigger the alarm setting at once.
Further, described system also comprises: human-computer interaction module is used for trigger condition, the mode of alarm and the storage of key video sequence and the playback of alarm.
Further again, in the described video acquisition module, the passive type video camera is used for obtaining the video data of fixed monitoring scene, Data Source as the needs processing, attitude and parameter that active video camera is dynamically adjusted video camera according to the moving target position that obtains and size parameter provide the close shot close-up shot of moving target adaptively.
Further, described anomalous event is excavated in the module, according to the speed of moving target, and acceleration, the position, shape facility is discerned moving object and human body.
Described anomalous event is excavated in the module, carries out recognition of face in moving target profile inside, carries out distinguishing single and many people.
Described anomalous event is excavated in the module, by using character description methods such as Hu square and R conversion to extract the behavioural characteristic of movement human, use the similarity of hidden Markov model calculating and training sample then, identify the concrete behavior of human body, excavate out the anomalous event in the scene at last.
Again further, in the described human-computer interaction module, if abnormal behaviour reaches the unusual parameter that sets, then system triggers the anomalous event alarm at once, and the alarm mode comprises that system produces warning information, sends SMS and mail for relevant director.
In the described human-computer interaction module, system will record a video to preserve to current unusual condition automatically and check to be used for the user afterwards when the anomalous event alarm is triggered; The user also can record interested scene at any time and preserve.
Beneficial effect of the present invention mainly shows: the mode that adopts the collaborative work of master-slave mode video camera, passive type camera acquisition video data is also analyzed, active video camera provides important area close shot feature adaptively, can more clearly observe the local feature of moving target; By obtaining the accurate edge contour information of moving target, extract its behavioural characteristic, excavate out the anomalous event that occurs in the monitoring scene according to the behavior database of having set up.
Description of drawings
Fig. 1 is the functional block diagram with intelligent video monitoring system of anomalous event excavation function of the present invention;
Fig. 2 is the process chart that anomalous event is excavated the intelligent video monitoring system of function that has based on the parking lot scene of the present invention.
Embodiment
Below in conjunction with accompanying drawing the present invention is further described.
Embodiment 1
See figures.1.and.2, a kind of intelligent video monitoring processing method with anomalous event excavation function, this method may further comprise the steps:
Abnormal conditions around the step 1, camera supervised this video camera of passive type, the video data in the acquisition monitoring scene;
Step 2, the moving target that occurs in detection and the tracing and monitoring scene is demarcated moving target, and the position and the size parameter of moving target reached active video camera;
Step 3, active video camera according to the parameter of setting, judge whether that being necessary to transfer active video camera obtains the local feature of target according to behind the position and size parameter that obtain; If reach the requirement of transferring active video camera, then adjust the parameter and the attitude of active video camera, provide the close shot feature of the moving target that occurs in the monitoring scene adaptively; According to the transfer condition of setting, judge whether to stop to transfer equally; If still satisfy the transfer condition, then return the parameter and the attitude that continue to adjust active video camera; If reach the condition that stops to transfer active video camera, then active video camera turns back to initial setting up, monitors Same Scene with the passive type video camera with same focal length;
Step 4, detected moving target is correctly classified: differentiating target is pedestrian or other objects that enter monitoring scene, according to the object edge profile information that obtains in the tracing process and variation characteristic thereof as main classification foundation;
Step 5 is carried out behavior to sorted moving target and is understood, and extracts the behavioural characteristic of movement human target itself, and abnormal behaviour is discerned and judged whether to be to the behavior sample that comparison is trained to its behavior;
Step 6 is set the abnormal behaviour standard, according to the standard that sets, judges whether to take place anomalous event, if no abnormal incident takes place, then returns and continues to gather video data; If anomalous event has taken place, then trigger the alarm setting at once.
In the described step 6,,, check evidence obtaining in order to the staff with unusual condition video recording storage if anomalous event has taken place in the future.
In the described step 4, after differentiating target and being the pedestrian, distinguishing out what enter again is single or many people of motion together.
In the step 6, should have different abnormal behaviour definition for different application scenarioss.
Be example with the parking lot monitoring below, further set forth the intelligent video monitoring system processing method that anomalous event is excavated function that has of the present invention.Fig. 2 is the process chart that anomalous event is excavated the intelligent video monitoring system of function that has based on the parking lot scene of the present invention.
After in the parking lot, installing active video camera and passive type video camera, two class video camera display frames are transferred to same focal length monitoring Same Scene.
Step 210, the video data in the passive type camera acquisition monitoring scene is as the Data Source of needs processing.
Step 220 detects and also to follow the tracks of the moving target that occurs in the parking lot, demarcates moving target, and with the position of target, parameters such as size reach active video camera.
Step 230, active video camera according to target components such as position that obtains and sizes after, according to the parameter of setting, as moving target whether in the monitoring scene center, whether moving target is less than normal etc., judges whether that being necessary to transfer active video camera obtains the local feature of target.
Step 231 if reach the requirement of transferring active video camera, is then adjusted the parameter and the attitude of active video camera, provides the close shot feature of the moving target that occurs in the parking lot adaptively.
Step 232 equally according to the transfer condition of setting, judges whether to stop to transfer.If still satisfy the transfer condition, then return the parameter and the attitude that continue to adjust active video camera.
Step 233, if reach the condition that stops to transfer active video camera, then active video camera turns back to initial setting up, monitors Same Scene with the passive type video camera with same focal length.
Step 240 is classified to detected moving target, and differentiating target is pedestrian or the vehicle that enters the parking lot, if the people, then should distinguish out what enter is single or many people.
Step 250, the behavioural characteristic of extraction movement human target itself, the behavior sample that comparison is trained, the concrete behavior of identification human body.
Step 260 is set the abnormal behaviour standard, the normal walking of definition here, and trotting to wait belongs to normal behaviour, and jumps, and being trapped in other grade of certain car for a long time is abnormal behaviour.According to the standard that sets, judge whether to be abnormal behaviour, if no abnormal behavior takes place, then return and continue to gather video data.
Step 270 if abnormal behaviour has taken place, then triggers the alarm setting, and with unusual condition video recording storage, checks evidence obtaining in order to the staff at once in the future.
Embodiment 2
See figures.1.and.2, a kind of intelligent video monitoring treatment system with anomalous event excavation function, described system comprises:
Video acquisition module is used for the collection to the guarded region video, adopts the mode of a pair of principal and subordinate's video camera collaborative work to come anomalous event in the monitoring scene;
The Intelligent Measurement module is used for guarded region motion target detection and tracking, obtains the real time position and the size parameter of moving target;
Anomalous event is excavated module, being used for that sorted moving target is carried out behavior understands, extract the behavioural characteristic of movement human target itself, the behavior sample that comparison is trained, abnormal behaviour is discerned and judged whether to be in its behavior, and the abnormal behaviour standard according to setting judges whether to take place anomalous event, if no abnormal incident takes place, then return and continue to gather video data; If anomalous event has taken place, then trigger the alarm setting at once.
Described system also comprises: human-computer interaction module is used for trigger condition, the mode of alarm and the storage of key video sequence and the playback of alarm.
In the described video acquisition module, the passive type video camera is used for obtaining the video data of fixed monitoring scene, Data Source as the needs processing, attitude and parameter that active video camera is dynamically adjusted video camera according to the moving target position that obtains and size parameter provide the close shot close-up shot of moving target adaptively.
Described anomalous event is excavated in the module, according to the speed of moving target, and acceleration, the position, shape facility is discerned moving object and human body.
Described anomalous event is excavated in the module, carries out recognition of face in moving target profile inside, carries out distinguishing single and many people.
Described anomalous event is excavated in the module, by using character description methods such as Hu square and R conversion to extract the behavioural characteristic of movement human, use the similarity of hidden Markov model calculating and training sample then, identify the concrete behavior of human body, excavate out the anomalous event in the scene at last.
In the described human-computer interaction module, if abnormal behaviour reaches the unusual parameter that sets, then system triggers the anomalous event alarm at once, and the alarm mode comprises that system produces warning information, sends SMS and mail for relevant director.
In the described human-computer interaction module, system will record a video to preserve to current unusual condition automatically and check to be used for the user afterwards when the anomalous event alarm is triggered; The user also can record interested scene at any time and preserve.
Fig. 1 is the functional block diagram with intelligent video monitoring system of anomalous event excavation function of the present invention.This system mainly comprises video acquisition module 110, Intelligent Measurement module 120, and anomalous event is excavated module 130 and human-computer interaction module 140.
Video acquisition module 110 is mainly used in the collection to the guarded region video, it is characterized in that adopting the collaborative work of a pair of principal and subordinate's video camera.Comprise passive type camara module 111 and active camara module 112.
Passive type camara module 111 is used for obtaining the video data of fixed monitoring scene, as the Data Source of needs processing.
Attitude and parameter that active camara module 112 is dynamically adjusted video camera according to the moving target position that obtains and size parameter provide the close shot close-up shot of moving target adaptively.
Intelligent Measurement module 120 is mainly used in guarded region motion target detection and tracking, obtains the real time position and the size parameter of moving target.Comprise moving object detection module 121 and motion target tracking module 122.
Moving object detection module 121 is used for the video data that collects is carried out moving object detection, demarcates detected moving target.Because this intelligent video monitoring system is mainly monitored some complex scenes, so code book is a kind of suitable moving target detecting method, its basic thought is to adopt the method that quantizes cluster, from long observation sequence, set up background model, when detecting, measure test pixel and the distance of background pixel on color and intensity simultaneously, with this differentiation prospect and background, As time goes on the background model of estimation is upgraded.
Motion target tracking module 122 is used for detected moving target is accurately followed the tracks of, and obtains moving target position and size parameter.Target following at first relates to forecasting problem, the present invention uses particle filter technology solution the forecasting problem here, and the method that employing is chosen principal character according to ambient conditions improves robustness, information such as the gray scale of target, colourity, texture and yardstick are compared with the scenery of the certain limit at its place, find out feature with the biggest gap principal character as target.Like this, occur complicated or overlap for a long time, block or just be difficult for producing trail-and-error when staggered in multiple target.
Anomalous event excavation module 130 is mainly used in the classification to moving target in the monitoring scene, and the understanding analysis of human body behavior and the definition of abnormal behaviour etc. comprise target classification module 131, behavior Understanding Module 132 and abnormal behaviour definition module 133.
Target classification module 131 is used for the classification to moving object and movement human, and distinguishing to single and many people, use close-up image that active video camera obtains to increase resolution capability, combine as classification foundation with edge that obtains in the tracing process and profile information, speed according to moving target, acceleration, the position, features such as shape are discerned moving object and human body.Carry out recognition of face in moving target profile inside, carry out distinguishing single and many people.
Behavior Understanding Module 132 is mainly used in the understanding of moving target behavior, utilize the character of target itself and the position relation between a plurality of target, motion relevance etc. to extract the moving target behavioural characteristic, to different state classification standards, need to adopt different characteristics combination, judge whether it is abnormal behaviour.Common feature extracting methods such as R conversion extract the behavioural characteristic of movement human by using the Hu square, use the similarity of hidden Markov model (HMM) calculating and training sample then, identify the concrete behavior of human body, excavate out the anomalous event in the scene at last.
Abnormal behaviour definition module 133 is mainly used in the definition of abnormal behaviour, different behaviors should have different abnormal behaviour definition for different application scenarioss, as to run this action can be normal at some, but can be defined as abnormal behaviour in some occasion.
Human-computer interaction module 140 is mainly used in man-machine interaction, comprises the definite condition and the triggering of alarm, and the mode of alarm and the storage of key video sequence and playback etc. comprise Realtime Alerts module 141 and video storage and playback module 142.
Realtime Alerts module 141 comprises the setting of abnormal behaviour parameter and sends the anomalous event alarm that if abnormal behaviour reaches the unusual parameter that sets, then system triggers the anomalous event alarm at once.The alarm mode comprises that system produces warning information, sends note and mail etc. for relevant director.
Video storage and playback module 142 are used to record abnormal behaviour video and playback.On the one hand, system is checked to be used for the user recording a video to preserve to current unusual condition automatically afterwards when the anomalous event alarm is triggered; On the other hand, the user also can record interested scene at any time and preserve.
Of the present invention have anomalous event and excavate in the intelligent video monitoring method of function and the intelligent monitoring environment that system can be applied to various situations, as large parking lot, and museum etc.Method and system of the present invention can alleviate the workload of monitor staff in this type of scene significantly, and can effectively increase its fail safe, reduce unnecessary loss.
Obviously, under the prerequisite that does not depart from true spirit of the present invention and scope, the present invention described here can have many variations.Therefore, the change that all it will be apparent to those skilled in the art that all should be included within the scope that these claims contain.The present invention's scope required for protection is only limited by described claims.
Claims (10)
1. one kind has the intelligent video monitoring processing method that anomalous event is excavated function, it is characterized in that:
This method may further comprise the steps:
Abnormal conditions around the step 1, camera supervised this video camera of passive type, the video data in the acquisition monitoring scene;
Step 2, the moving target that occurs in detection and the tracing and monitoring scene is demarcated moving target, and the position and the size parameter of moving target reached active video camera;
Step 3, active video camera according to the parameter of setting, judge whether that being necessary to transfer active video camera obtains the local feature of target according to behind the position and size parameter that obtain; If reach the requirement of transferring active video camera, then adjust the parameter and the attitude of active video camera, provide the close shot feature of the moving target that occurs in the monitoring scene adaptively; According to the transfer condition of setting, judge whether to stop to transfer equally; If still satisfy the transfer condition, then return the parameter and the attitude that continue to adjust active video camera; If reach the condition that stops to transfer active video camera, then active video camera turns back to initial setting up, monitors Same Scene with the passive type video camera with same focal length;
Step 4, detected moving target is correctly classified: differentiating target is pedestrian or other objects that enter monitoring scene, according to the object edge profile information that obtains in the tracing process and variation characteristic thereof as main classification foundation;
Step 5 is carried out behavior to sorted moving target and is understood, and extracts the behavioural characteristic of movement human target itself, and abnormal behaviour is discerned and judged whether to be to the behavior sample that comparison is trained to its behavior;
Step 6 is set the abnormal behaviour standard, according to the standard that sets, judges whether to take place anomalous event, if no abnormal incident takes place, then returns and continues to gather video data; If anomalous event has taken place, then trigger the alarm setting at once.
2. the intelligent video monitoring processing method with anomalous event excavation function as claimed in claim 1 is characterized in that: in the described step 6, if anomalous event has taken place, with unusual condition video recording storage, check evidence obtaining in order to the staff in the future.
3. as claimed in claim 1 or 2 have an intelligent video monitoring processing method that anomalous event is excavated function, it is characterized in that: in the described step 4, after differentiating target and being the pedestrian, distinguishing out what enter again is single or many people of motion together.
4. the intelligent video monitoring processing method with anomalous event excavation function as claimed in claim 1 or 2 is characterized in that: in the step 6, should have different anomalous event definition for different application scenarioss.
5. one kind is used to realize the described system that anomalous event is excavated the intelligent video monitoring processing method of function that has, and it is characterized in that: described system comprises:
Video acquisition module is used for the collection to the guarded region video, adopts the mode of a pair of principal and subordinate's video camera collaborative work to come anomalous event in the monitoring scene;
The Intelligent Measurement module is used for guarded region motion target detection and tracking, obtains the real time position and the size parameter of moving target;
Anomalous event is excavated module, being used for that sorted moving target is carried out behavior understands, extract the behavioural characteristic of movement human target itself, the behavior sample that comparison is trained, abnormal behaviour is discerned and judged whether to be in its behavior, and the abnormal behaviour standard according to setting judges whether to take place anomalous event, if no abnormal behaviour part takes place, then return and continue to gather video data; If anomalous event has taken place, then trigger the alarm setting at once.
6. system as claimed in claim 5 is characterized in that: described system also comprises: human-computer interaction module is used for trigger condition, the mode of alarm and the storage of key video sequence and the playback of alarm.
7. as claim 5 or 6 described systems, it is characterized in that: in the described video acquisition module, the passive type video camera is used for obtaining the video data of fixed monitoring scene, Data Source as the needs processing, attitude and parameter that active video camera is dynamically adjusted video camera according to the moving target position that obtains and size parameter provide the close shot close-up shot of moving target adaptively.
8. as claim 5 or 6 described systems, it is characterized in that: described anomalous event is excavated in the module, according to the speed of moving target, and acceleration, the position, shape facility is discerned moving object and human body.
9. system as claimed in claim 8 is characterized in that: described anomalous event is excavated in the module, carries out recognition of face in moving target profile inside, carries out distinguishing single and many people.
10. as claim 5 or 6 described systems, it is characterized in that: described anomalous event is excavated in the module, by using character description methods such as Hu square and R conversion to extract the behavioural characteristic of movement human, use the similarity of hidden Markov model calculating and training sample then, identify the concrete behavior of human body, excavate out the anomalous event in the scene at last.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100255346ACN102164270A (en) | 2011-01-24 | 2011-01-24 | Intelligent video monitoring method and system capable of exploring abnormal events |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100255346ACN102164270A (en) | 2011-01-24 | 2011-01-24 | Intelligent video monitoring method and system capable of exploring abnormal events |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102164270Atrue CN102164270A (en) | 2011-08-24 |
Family
ID=44465198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100255346APendingCN102164270A (en) | 2011-01-24 | 2011-01-24 | Intelligent video monitoring method and system capable of exploring abnormal events |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102164270A (en) |
Cited By (55)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102938058A (en)* | 2012-11-14 | 2013-02-20 | 南京航空航天大学 | Method and system for video driving intelligent perception and facing safe city |
| CN103260007A (en)* | 2012-02-21 | 2013-08-21 | 清华大学 | Intelligent monitoring system based on on-chip multi-port memory controller |
| CN103295358A (en)* | 2013-05-10 | 2013-09-11 | 西安祥泰软件设备系统有限责任公司 | Warning method for access control system and embedded mainboard for implementing warning method |
| CN103533311A (en)* | 2013-10-22 | 2014-01-22 | 北京汉邦高科数字技术股份有限公司 | High-definition network camera device |
| CN103761748A (en)* | 2013-12-31 | 2014-04-30 | 北京邮电大学 | Method and device for detecting abnormal behaviors |
| CN103945171A (en)* | 2013-01-17 | 2014-07-23 | 上海快视信息技术有限公司 | Criminal investigation video analyzing system and method |
| CN104038733A (en)* | 2014-05-21 | 2014-09-10 | 天津市亚安科技股份有限公司 | Sentinel early warning monitoring system |
| CN104268594A (en)* | 2014-09-24 | 2015-01-07 | 中安消技术有限公司 | Method and device for detecting video abnormal events |
| CN104301686A (en)* | 2014-10-27 | 2015-01-21 | 青岛宝微视控信息技术有限公司 | Intelligent video analyzing system and method |
| CN104516295A (en)* | 2014-12-15 | 2015-04-15 | 成都凌感科技有限公司 | Device for automatically recognizing human body malignant violent terrorism actions and emitting violence preventing substances |
| CN105279485A (en)* | 2015-10-12 | 2016-01-27 | 江苏精湛光电仪器股份有限公司 | Detection method for monitoring abnormal behavior of target under laser night vision |
| CN105405150A (en)* | 2015-10-21 | 2016-03-16 | 东方网力科技股份有限公司 | Abnormal behavior detection method and abnormal behavior detection device based fused characteristics |
| CN105657372A (en)* | 2016-02-04 | 2016-06-08 | 韩贵杰 | Method and system for realizing intelligent detection and early warning of on-duty guard posts by videos |
| CN105678211A (en)* | 2015-12-03 | 2016-06-15 | 广西理工职业技术学院 | Human body dynamic characteristic intelligent identification system |
| CN105812725A (en)* | 2015-01-21 | 2016-07-27 | 富士施乐株式会社 | Surveillance system |
| CN105825198A (en)* | 2016-03-29 | 2016-08-03 | 深圳市佳信捷技术股份有限公司 | Pedestrian detection method and device |
| CN105979232A (en)* | 2016-07-12 | 2016-09-28 | 湖北誉恒科技有限公司 | Video monitoring system for closed school |
| CN106303403A (en)* | 2015-06-12 | 2017-01-04 | 中国人民公安大学 | Supervising device presetting bit setting, changing method and system |
| CN106815960A (en)* | 2017-02-15 | 2017-06-09 | 山东科技大学 | A kind of method for reducing Forest Fire Alarm rate of false alarm |
| CN106851229A (en)* | 2017-04-01 | 2017-06-13 | 山东瀚岳智能科技股份有限公司 | A kind of method and system of the security protection intelligent decision based on image recognition |
| CN106878666A (en)* | 2015-12-10 | 2017-06-20 | 杭州海康威视数字技术股份有限公司 | The methods, devices and systems of destination object are searched based on CCTV camera |
| CN107005679A (en)* | 2014-07-11 | 2017-08-01 | 王向恒 | A kind of intelligent Target identifying device based on cloud service, system and method |
| CN107820048A (en)* | 2017-10-25 | 2018-03-20 | 桐城市闲产网络服务有限公司 | A kind of intelligent network Video Supervision Technique |
| CN108509889A (en)* | 2018-03-27 | 2018-09-07 | 哈尔滨工业大学深圳研究生院 | A kind of close shot anomaly detection method and device based on skin color segmentation |
| CN108537190A (en)* | 2018-04-17 | 2018-09-14 | 智慧互通科技有限公司 | A kind of parking lot order managing device based on image |
| CN108717521A (en)* | 2018-04-17 | 2018-10-30 | 智慧互通科技有限公司 | A kind of parking lot order management method and system based on image |
| CN108898717A (en)* | 2018-06-29 | 2018-11-27 | 仁怀市云侠网络科技有限公司 | A kind of intelligent safety defense monitoring system |
| CN109165634A (en)* | 2018-09-21 | 2019-01-08 | 深圳市九洲电器有限公司 | A kind of intelligent identification Method, apparatus and system |
| CN109212520A (en)* | 2018-09-29 | 2019-01-15 | 河北德冠隆电子科技有限公司 | The road conditions perception accident detection alarm system and method for comprehensive detection radar |
| CN109308778A (en)* | 2018-09-11 | 2019-02-05 | 深圳市智美达科技股份有限公司 | Mobile detection alarm method, device, acquisition equipment and storage medium |
| CN109389794A (en)* | 2018-07-05 | 2019-02-26 | 北京中广通业信息科技股份有限公司 | A kind of Intellectualized Video Monitoring method and system |
| CN109407601A (en)* | 2018-10-29 | 2019-03-01 | 孙宜美 | Development of intelligent laboratory monitoring and alarming system based on data analysis |
| CN109657626A (en)* | 2018-12-23 | 2019-04-19 | 广东腾晟信息科技有限公司 | A kind of analysis method by procedure identification human body behavior |
| CN109788257A (en)* | 2016-09-20 | 2019-05-21 | 张玲花 | In video the recognition methods of target and can recognition of face video monitoring Skynet system |
| CN110009928A (en)* | 2019-03-01 | 2019-07-12 | 上海涛尔信息技术有限公司 | A kind of smart city parking management method and system |
| CN110198471A (en)* | 2018-02-27 | 2019-09-03 | 北京猎户星空科技有限公司 | Abnormality recognition method, device, smart machine and storage medium |
| TWI672595B (en)* | 2018-04-09 | 2019-09-21 | 宏碁股份有限公司 | Monitering method and electronic device using the same |
| CN110335432A (en)* | 2019-06-24 | 2019-10-15 | 安徽和润智能工程有限公司 | A kind of exhibition room security system based on recognition of face |
| CN110443977A (en)* | 2019-08-29 | 2019-11-12 | 张玉华 | The dynamic early-warning method and dynamic early-warning system of human body behavior |
| CN110599721A (en)* | 2018-06-13 | 2019-12-20 | 杭州海康威视数字技术股份有限公司 | Monitoring method, device and system and monitoring equipment |
| CN110996043A (en)* | 2019-10-25 | 2020-04-10 | 上海飞宽通信技术有限公司 | Intelligent police service inspection management system |
| CN111325048A (en)* | 2018-12-13 | 2020-06-23 | 杭州海康威视数字技术股份有限公司 | Personnel gathering detection method and device |
| CN112053563A (en)* | 2020-09-16 | 2020-12-08 | 北京百度网讯科技有限公司 | Event detection method, device, device and storage medium for cloud control platform |
| CN112211496A (en)* | 2019-07-09 | 2021-01-12 | 杭州萤石软件有限公司 | Monitoring method and system based on intelligent door lock and intelligent door lock |
| CN112307916A (en)* | 2020-10-21 | 2021-02-02 | 山东神戎电子股份有限公司 | Alarm monitoring method based on visible light camera |
| WO2021022456A1 (en)* | 2019-08-05 | 2021-02-11 | 唐山哈船科技有限公司 | Monitoring system and monitoring method for reducing vagrant conflicts |
| CN112365740A (en)* | 2020-11-30 | 2021-02-12 | 北京停简单信息技术有限公司 | Alarm display method and device |
| CN112560547A (en)* | 2019-09-10 | 2021-03-26 | 中兴通讯股份有限公司 | Abnormal behavior judgment method and device, terminal and readable storage medium |
| CN112770081A (en)* | 2019-11-01 | 2021-05-07 | 杭州海康威视数字技术股份有限公司 | Parameter adjusting method and device for monitoring equipment, electronic equipment and storage medium |
| CN112866654A (en)* | 2021-03-11 | 2021-05-28 | 福建环宇通信息科技股份公司 | Intelligent video monitoring system |
| CN112861572A (en)* | 2019-11-27 | 2021-05-28 | 杭州萤石软件有限公司 | Pedestrian detection method, computer-readable storage medium and electronic device |
| CN113538515A (en)* | 2021-07-19 | 2021-10-22 | 安徽炬视科技有限公司 | High-voltage switch cabinet abnormal movement detection algorithm based on combination of semantic segmentation and target detection tracking |
| CN114913663A (en)* | 2021-02-08 | 2022-08-16 | 腾讯科技（深圳）有限公司 | Anomaly detection method and device, computer equipment and storage medium |
| CN115294519A (en)* | 2022-07-22 | 2022-11-04 | 山东浪潮科学研究院有限公司 | An abnormal event detection and early warning method based on lightweight network |
| WO2025060454A1 (en)* | 2023-09-21 | 2025-03-27 | 深圳感臻智能股份有限公司 | Video playback method and system for monitoring device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101533548A (en)* | 2009-04-03 | 2009-09-16 | 浙江工业大学 | Device for protecting property based on omnibearing computer visual sense |
| CN101557506A (en)* | 2009-05-19 | 2009-10-14 | 浙江工业大学 | Intelligent detecting device for violent behavior in elevator car based on computer vision |
| WO2009146970A1 (en)* | 2008-05-29 | 2009-12-10 | Siemens Aktiengesellschaft | Method for identifying anomalies in object streams using the phenomenon of group speed |
- 2011
- 2011-01-24CNCN2011100255346Apatent/CN102164270A/enactivePending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009146970A1 (en)* | 2008-05-29 | 2009-12-10 | Siemens Aktiengesellschaft | Method for identifying anomalies in object streams using the phenomenon of group speed |
| CN101533548A (en)* | 2009-04-03 | 2009-09-16 | 浙江工业大学 | Device for protecting property based on omnibearing computer visual sense |
| CN101557506A (en)* | 2009-05-19 | 2009-10-14 | 浙江工业大学 | Intelligent detecting device for violent behavior in elevator car based on computer vision |
Cited By (72)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103260007A (en)* | 2012-02-21 | 2013-08-21 | 清华大学 | Intelligent monitoring system based on on-chip multi-port memory controller |
| CN103260007B (en)* | 2012-02-21 | 2016-02-24 | 清华大学 | Based on the intelligent monitor system of multiport storage controller on sheet |
| CN102938058A (en)* | 2012-11-14 | 2013-02-20 | 南京航空航天大学 | Method and system for video driving intelligent perception and facing safe city |
| CN103945171B (en)* | 2013-01-17 | 2017-10-10 | 上海快视信息技术有限公司 | A kind of criminal investigation video analytic system and method |
| CN103945171A (en)* | 2013-01-17 | 2014-07-23 | 上海快视信息技术有限公司 | Criminal investigation video analyzing system and method |
| CN103295358A (en)* | 2013-05-10 | 2013-09-11 | 西安祥泰软件设备系统有限责任公司 | Warning method for access control system and embedded mainboard for implementing warning method |
| CN103533311A (en)* | 2013-10-22 | 2014-01-22 | 北京汉邦高科数字技术股份有限公司 | High-definition network camera device |
| CN103533311B (en)* | 2013-10-22 | 2017-01-11 | 北京汉邦高科数字技术股份有限公司 | High-definition network camera device |
| CN103761748A (en)* | 2013-12-31 | 2014-04-30 | 北京邮电大学 | Method and device for detecting abnormal behaviors |
| CN104038733A (en)* | 2014-05-21 | 2014-09-10 | 天津市亚安科技股份有限公司 | Sentinel early warning monitoring system |
| CN107005679A (en)* | 2014-07-11 | 2017-08-01 | 王向恒 | A kind of intelligent Target identifying device based on cloud service, system and method |
| CN104268594B (en)* | 2014-09-24 | 2017-12-19 | 中安消技术有限公司 | A kind of video accident detection method and device |
| CN104268594A (en)* | 2014-09-24 | 2015-01-07 | 中安消技术有限公司 | Method and device for detecting video abnormal events |
| CN104301686A (en)* | 2014-10-27 | 2015-01-21 | 青岛宝微视控信息技术有限公司 | Intelligent video analyzing system and method |
| CN104516295A (en)* | 2014-12-15 | 2015-04-15 | 成都凌感科技有限公司 | Device for automatically recognizing human body malignant violent terrorism actions and emitting violence preventing substances |
| CN105812725A (en)* | 2015-01-21 | 2016-07-27 | 富士施乐株式会社 | Surveillance system |
| CN106303403B (en)* | 2015-06-12 | 2019-03-12 | 中国人民公安大学 | Monitoring device presetting bit setting, switching method and system |
| CN106303403A (en)* | 2015-06-12 | 2017-01-04 | 中国人民公安大学 | Supervising device presetting bit setting, changing method and system |
| CN105279485B (en)* | 2015-10-12 | 2018-12-07 | 江苏精湛光电仪器股份有限公司 | The detection method of monitoring objective abnormal behaviour under laser night vision |
| CN105279485A (en)* | 2015-10-12 | 2016-01-27 | 江苏精湛光电仪器股份有限公司 | Detection method for monitoring abnormal behavior of target under laser night vision |
| CN105405150B (en)* | 2015-10-21 | 2019-04-30 | 东方网力科技股份有限公司 | Anomaly detection method and device based on fusion feature |
| CN105405150A (en)* | 2015-10-21 | 2016-03-16 | 东方网力科技股份有限公司 | Abnormal behavior detection method and abnormal behavior detection device based fused characteristics |
| CN105678211A (en)* | 2015-12-03 | 2016-06-15 | 广西理工职业技术学院 | Human body dynamic characteristic intelligent identification system |
| CN106878666A (en)* | 2015-12-10 | 2017-06-20 | 杭州海康威视数字技术股份有限公司 | The methods, devices and systems of destination object are searched based on CCTV camera |
| CN105657372A (en)* | 2016-02-04 | 2016-06-08 | 韩贵杰 | Method and system for realizing intelligent detection and early warning of on-duty guard posts by videos |
| CN105825198A (en)* | 2016-03-29 | 2016-08-03 | 深圳市佳信捷技术股份有限公司 | Pedestrian detection method and device |
| CN105979232B (en)* | 2016-07-12 | 2019-05-07 | 湖北誉恒科技有限公司 | Video monitoring system for closed school |
| CN105979232A (en)* | 2016-07-12 | 2016-09-28 | 湖北誉恒科技有限公司 | Video monitoring system for closed school |
| CN109788257A (en)* | 2016-09-20 | 2019-05-21 | 张玲花 | In video the recognition methods of target and can recognition of face video monitoring Skynet system |
| CN106815960A (en)* | 2017-02-15 | 2017-06-09 | 山东科技大学 | A kind of method for reducing Forest Fire Alarm rate of false alarm |
| CN106815960B (en)* | 2017-02-15 | 2018-10-02 | 山东科技大学 | A method of reducing Forest Fire Alarm rate of false alarm |
| CN106851229A (en)* | 2017-04-01 | 2017-06-13 | 山东瀚岳智能科技股份有限公司 | A kind of method and system of the security protection intelligent decision based on image recognition |
| CN107820048A (en)* | 2017-10-25 | 2018-03-20 | 桐城市闲产网络服务有限公司 | A kind of intelligent network Video Supervision Technique |
| CN110198471A (en)* | 2018-02-27 | 2019-09-03 | 北京猎户星空科技有限公司 | Abnormality recognition method, device, smart machine and storage medium |
| CN108509889A (en)* | 2018-03-27 | 2018-09-07 | 哈尔滨工业大学深圳研究生院 | A kind of close shot anomaly detection method and device based on skin color segmentation |
| TWI672595B (en)* | 2018-04-09 | 2019-09-21 | 宏碁股份有限公司 | Monitering method and electronic device using the same |
| CN108717521A (en)* | 2018-04-17 | 2018-10-30 | 智慧互通科技有限公司 | A kind of parking lot order management method and system based on image |
| CN108537190A (en)* | 2018-04-17 | 2018-09-14 | 智慧互通科技有限公司 | A kind of parking lot order managing device based on image |
| CN110599721A (en)* | 2018-06-13 | 2019-12-20 | 杭州海康威视数字技术股份有限公司 | Monitoring method, device and system and monitoring equipment |
| CN108898717A (en)* | 2018-06-29 | 2018-11-27 | 仁怀市云侠网络科技有限公司 | A kind of intelligent safety defense monitoring system |
| CN108898717B (en)* | 2018-06-29 | 2021-02-26 | 仁怀市云侠网络科技有限公司 | An intelligent security monitoring system |
| CN109389794A (en)* | 2018-07-05 | 2019-02-26 | 北京中广通业信息科技股份有限公司 | A kind of Intellectualized Video Monitoring method and system |
| CN109308778A (en)* | 2018-09-11 | 2019-02-05 | 深圳市智美达科技股份有限公司 | Mobile detection alarm method, device, acquisition equipment and storage medium |
| CN109308778B (en)* | 2018-09-11 | 2020-08-18 | 深圳市智美达科技股份有限公司 | Mobile detection alarm method, device, acquisition equipment and storage medium |
| CN109165634A (en)* | 2018-09-21 | 2019-01-08 | 深圳市九洲电器有限公司 | A kind of intelligent identification Method, apparatus and system |
| CN109212520A (en)* | 2018-09-29 | 2019-01-15 | 河北德冠隆电子科技有限公司 | The road conditions perception accident detection alarm system and method for comprehensive detection radar |
| CN109212520B (en)* | 2018-09-29 | 2021-04-27 | 河北德冠隆电子科技有限公司 | Road condition sensing abnormal event detection alarm system and method for omnibearing detection radar |
| CN109407601A (en)* | 2018-10-29 | 2019-03-01 | 孙宜美 | Development of intelligent laboratory monitoring and alarming system based on data analysis |
| CN111325048A (en)* | 2018-12-13 | 2020-06-23 | 杭州海康威视数字技术股份有限公司 | Personnel gathering detection method and device |
| CN111325048B (en)* | 2018-12-13 | 2023-05-26 | 杭州海康威视数字技术股份有限公司 | Personnel gathering detection method and device |
| CN109657626A (en)* | 2018-12-23 | 2019-04-19 | 广东腾晟信息科技有限公司 | A kind of analysis method by procedure identification human body behavior |
| CN110009928A (en)* | 2019-03-01 | 2019-07-12 | 上海涛尔信息技术有限公司 | A kind of smart city parking management method and system |
| CN110335432A (en)* | 2019-06-24 | 2019-10-15 | 安徽和润智能工程有限公司 | A kind of exhibition room security system based on recognition of face |
| CN112211496A (en)* | 2019-07-09 | 2021-01-12 | 杭州萤石软件有限公司 | Monitoring method and system based on intelligent door lock and intelligent door lock |
| WO2021022456A1 (en)* | 2019-08-05 | 2021-02-11 | 唐山哈船科技有限公司 | Monitoring system and monitoring method for reducing vagrant conflicts |
| CN110443977A (en)* | 2019-08-29 | 2019-11-12 | 张玉华 | The dynamic early-warning method and dynamic early-warning system of human body behavior |
| CN112560547A (en)* | 2019-09-10 | 2021-03-26 | 中兴通讯股份有限公司 | Abnormal behavior judgment method and device, terminal and readable storage medium |
| CN110996043A (en)* | 2019-10-25 | 2020-04-10 | 上海飞宽通信技术有限公司 | Intelligent police service inspection management system |
| CN112770081A (en)* | 2019-11-01 | 2021-05-07 | 杭州海康威视数字技术股份有限公司 | Parameter adjusting method and device for monitoring equipment, electronic equipment and storage medium |
| CN112861572B (en)* | 2019-11-27 | 2024-05-28 | 杭州萤石软件有限公司 | Pedestrian detection method, computer-readable storage medium, and electronic device |
| CN112861572A (en)* | 2019-11-27 | 2021-05-28 | 杭州萤石软件有限公司 | Pedestrian detection method, computer-readable storage medium and electronic device |
| CN112053563A (en)* | 2020-09-16 | 2020-12-08 | 北京百度网讯科技有限公司 | Event detection method, device, device and storage medium for cloud control platform |
| CN112307916A (en)* | 2020-10-21 | 2021-02-02 | 山东神戎电子股份有限公司 | Alarm monitoring method based on visible light camera |
| CN112365740A (en)* | 2020-11-30 | 2021-02-12 | 北京停简单信息技术有限公司 | Alarm display method and device |
| CN114913663A (en)* | 2021-02-08 | 2022-08-16 | 腾讯科技（深圳）有限公司 | Anomaly detection method and device, computer equipment and storage medium |
| CN114913663B (en)* | 2021-02-08 | 2024-08-23 | 腾讯科技（深圳）有限公司 | Abnormality detection method, abnormality detection device, computer device, and storage medium |
| CN112866654B (en)* | 2021-03-11 | 2023-02-28 | 福建环宇通信息科技股份公司 | Intelligent video monitoring system |
| CN112866654A (en)* | 2021-03-11 | 2021-05-28 | 福建环宇通信息科技股份公司 | Intelligent video monitoring system |
| CN113538515A (en)* | 2021-07-19 | 2021-10-22 | 安徽炬视科技有限公司 | High-voltage switch cabinet abnormal movement detection algorithm based on combination of semantic segmentation and target detection tracking |
| CN113538515B (en)* | 2021-07-19 | 2024-06-07 | 安徽炬视科技有限公司 | High-voltage switch cabinet abnormal state detection method based on combination of semantic segmentation and target detection tracking |
| CN115294519A (en)* | 2022-07-22 | 2022-11-04 | 山东浪潮科学研究院有限公司 | An abnormal event detection and early warning method based on lightweight network |
| WO2025060454A1 (en)* | 2023-09-21 | 2025-03-27 | 深圳感臻智能股份有限公司 | Video playback method and system for monitoring device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102164270A (en) | Intelligent video monitoring method and system capable of exploring abnormal events | |
| CN100487739C (en) | Multi-layer real time forewarning system based on the intelligent video monitoring | |
| CN102811343B (en) | Intelligent video monitoring system based on behavior recognition | |
| CN101854516B (en) | Video monitoring system, video monitoring server and video monitoring method | |
| CN201773466U (en) | Video monitoring and pre-warning device for detecting, tracking and identifying object detention/stealing event | |
| CN105426820B (en) | More people's anomaly detection methods based on safety monitoring video data | |
| CN112232211A (en) | An intelligent video surveillance system based on deep learning | |
| CN101266710A (en) | A rule-based all-weather intelligent video analysis and monitoring method | |
| CN103049459A (en) | Feature recognition based quick video retrieval method | |
| CN110867046A (en) | Intelligent car washer video monitoring and early warning system based on cloud computing | |
| CN102917207A (en) | Motion sequence based abnormal motion vision monitoring system | |
| CN102065275A (en) | Multi-target tracking method in intelligent video monitoring system | |
| CN119131699B (en) | Intelligent video monitoring method and system | |
| CN111814510A (en) | Detection method and device for remnant body | |
| CN119399446A (en) | A smart community target recognition and tracking method based on big data | |
| CN105227918B (en) | A kind of intelligent control method | |
| CN117830053A (en) | Perimeter security alarm system and method | |
| CN110516600A (en) | A kind of bus passenger flow detection method based on Face datection | |
| CN210666820U (en) | A pedestrian abnormal behavior detection system based on DSP edge computing | |
| Andersson et al. | Fusion of acoustic and optical sensor data for automatic fight detection in urban environments | |
| CN105095891A (en) | Human face capturing method, device and system | |
| KR101547255B1 (en) | Object-based Searching Method for Intelligent Surveillance System | |
| CN114973135A (en) | A head-and-shoulders-based time-series video sleeping post identification method, system and electronic device | |
| CN202904792U (en) | Intelligent visualized alarm system | |
| CN104966264A (en) | Security big data based on text serving as transformation basic state of heterogeneous data for fusion processing |
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:20110824 |