CN107623842A - A kind of video monitoring image processing system and method - Google Patents
A kind of video monitoring image processing system and method Download PDFInfo
- Publication number
- CN107623842A CN107623842A CN201710872730.4A CN201710872730A CN107623842A CN 107623842 A CN107623842 A CN 107623842A CN 201710872730 A CN201710872730 A CN 201710872730A CN 107623842 A CN107623842 A CN 107623842A
- Authority
- CN
- China
- Prior art keywords
- unit
- data
- moving object
- image
- detection
- 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
Landscapes
- Closed-Circuit Television Systems (AREA)
- Burglar Alarm Systems (AREA)
Abstract
The invention discloses a kind of video monitoring image processing system, including：Image pre-processing unit, moving object detection unit, obtain moving region unit, data processing unit and abnormity early warning unit；Image pre-processing unit is used to give the multiple image data transfer after processing to moving object detection unit；Moving object detection unit, which is used to testing result being sent to, obtains moving region unit；Moving region unit is obtained to be used to moving object zone information data being sent to data processing unit；Data processing unit is used to detect motion intrusion target, and sends alarm command to abnormity early warning unit；The system can in real time, active analysis monitoring function, intelligent monitor system based on video image, people is freed from prolonged, uninteresting heavy monitoring operation.
Description
Technical field
The present invention relates to security monitoring technology, more particularly to a kind of video monitoring image processing system and method.
Background technology
With the development of science and technology, the scope of activities of the mankind becomes increasing to neodymium, and all the more complicated social environment makes
It is more and more to obtain various emergencies and anomalous event, monitoring becomes all the more important and difficulty also increases therewith.It is important at some
Occasion such as transformer station, warehouse, parking lot, bank etc. be mounted various video monitoring equipments, so as to prevent to steal, break
The generation of the behaviors such as bad, personnel's injury, detection does not provide foundation afterwards.
However, video camera is simply connected to televimonitor and video recording by most of these monitoring systems used at present
On machine, monitored and recorded a video a long way off, although making the working environment of staff be improved and can obtain correlation
Video recording, if but continual monitoring analysis is carried out to monitoring scene without personnel, abnormal conditions at that time can not be entered in real time
Row early warning, it is difficult to ensure safety.To improve security just necessarily has staff to watch monitor attentively double tides, not only
Workload is heavy, and when control point is more, monitoring personnel is also difficult to complete monitoring.Therefore, people can be replaced by being badly in need of one kind
Brain play in real time, active analysis monitoring function, intelligent monitor system based on video image, with people from prolonged, withered
Freed in dry heavy monitoring operation.
The content of the invention
It is an object of the invention to provide a kind of video monitoring image processing system and method, to solve in above-mentioned background technology
The problem of proposition.
The invention provides a kind of video monitoring image processing system, including：Image pre-processing unit, moving object detection
Unit, obtain moving region unit, data processing unit and abnormity early warning unit；Described image pretreatment unit is used for video
The image of collection carries out image gray processing processing and the processing of E value filterings, and by the multiple image data transfer after processing to described
Moving object detection unit；The moving object detection unit is used to receive the multiframe figure transmitted by described image pretreatment unit
Motion detection is carried out as data and to it, judges whether there is the object of motion in the multiple image data, and by testing result
It is sent to the acquisition moving region unit；The acquisition moving region unit is used to receive the moving object detection unit institute
The testing result of transmission and the region for determining moving object in current frame image data, while by moving object zone information data
It is sent to the data processing unit；The data processing unit is used to receive the fortune transmitted by the acquisition moving region unit
Animal body area data information simultaneously first carries out small resolution ratio detection to it, detection motion intrusion target, utilizes particle filter algorithm
Target is tracked, preserves the movement locus of intrusion target, and alarm command is sent to abnormity early warning unit；At the data
Reason unit can carry out big resolution ratio detection to the moving object area data received simultaneously, and detection stands intrusion target, preserves
Intrusion target frame image data, and send alarm command to abnormity early warning unit；The abnormity early warning unit is described for receiving
Alarm command transmitted by data processing unit simultaneously sends alarm.
It is preferred that described image pretreatment unit is handled image gray processing by weighted mean method.
It is preferred that the moving object detection unit includes inter-frame difference detection and background Differential Detection.
It is preferred that the data processing unit uses TMS320C5502 chips.
It is preferred that the TMS320C5502 chip signals are connected with internal storage, the internal storage uses
CY7C1011CV33 high-speed cmos static memories.
A kind of video monitoring image processing method, comprises the following steps：
Step 1：The video monitoring data that camera is provided is obtained in real time, and the video monitoring data is by multiple image number
Image gray processing processing and the processing of E value filterings are carried out according to composition, while to the frame image data of acquisition；
Step 2：Frame image data after being handled in detecting step 1, judges whether there is fortune in the current frame image data
Dynamic object；
Step 3：When having the object of motion in the current frame image data, moving object in current frame image data is determined
The region of body；
Step 4：First carrying out small resolution ratio detection respectively to the moving object area data, intrusion target is moved in detection,
Target is tracked using particle filter algorithm, preserves the movement locus of intrusion target, and report is sent to abnormity early warning unit
Alert instruction；Big resolution ratio detection is carried out to moving object area data again, detection stands intrusion target, preserves invasion target frame figure
As data, and alarm command is sent to abnormity early warning unit；
Step 5：The instruction that abnormity early warning unit is sent according to step 4 sounds the alarm.
Compared to the prior art the present invention, the advantage is that：
A kind of video monitoring image processing system provided by the invention, it is used for by image pre-processing unit to video acquisition
Image carry out image gray processing processing and the processing of E value filterings, and by the multiple image data transfer after processing to moving target
Detection unit；Moving object detection unit is used to receive the multiple image data transmitted by image pre-processing unit and carry out it
Motion detection, judge whether there is the object of motion in multiple image data, and testing result is sent to and obtains moving region list
Member；Moving region unit is obtained to be used to receive the testing result transmitted by moving object detection unit and determine current frame image number
Data processing unit is sent to according to the region of middle moving object, while by moving object zone information data；Data processing unit
For receiving the moving object area data information obtained transmitted by the unit of moving region and small resolution ratio detection first being carried out to it,
Detection motion intrusion target, is tracked to target using particle filter algorithm, preserves the movement locus of intrusion target, and to different
Normal prewarning unit sends alarm command；Data processing unit can be differentiated greatly to the moving object area data received simultaneously
Rate detects, and detection stands intrusion target, preserves invasion target frame view data, and send alarm command to abnormity early warning unit；
Abnormity early warning unit is used to receive the alarm command transmitted by data processing unit and sends alarm.The system can in real time,
Active analysis monitoring function, intelligent monitor system based on video image, people is made from prolonged, uninteresting heavy monitoring
Freed in industry.
Brief description of the drawings
Fig. 1 is systematic schematic diagram provided by the invention.
Embodiment
Below in conjunction with the accompanying drawings, the specific embodiment of the present invention is described in detail, it is to be understood that of the invention
Protection domain do not limited by embodiment.
As shown in figure 1, the embodiments of the invention provide a kind of video monitoring image processing system, including：Image preprocessing
Unit, moving object detection unit, obtain moving region unit, data processing unit and abnormity early warning unit；Image preprocessing
Unit is used to carry out image gray processing processing to the image of video acquisition and E value filterings are handled, and by the multiple image after processing
Data transfer gives moving object detection unit；Moving object detection unit is used to receive the multiframe transmitted by image pre-processing unit
View data simultaneously carries out motion detection to it, judges whether there is the object of motion in multiple image data, and testing result is sent out
Give and obtain moving region unit；Moving region unit is obtained to be used to receive the testing result transmitted by moving object detection unit
And the region of moving object in current frame image data is determined, while moving object zone information data is sent to data processing
Unit；Data processing unit is used to receive the moving object area data information transmitted by acquisition moving region unit and to its elder generation
Small resolution ratio detection is carried out, detection motion intrusion target, target is tracked using particle filter algorithm, preserves intrusion target
Movement locus, and send alarm command to abnormity early warning unit；Data processing unit while moving object that can be to receiving
Area data carries out big resolution ratio detection, and detection stands intrusion target, preserves invasion target frame view data, and to abnormity early warning
Unit sends alarm command；Abnormity early warning unit is used to receive the alarm command transmitted by data processing unit and sends alarm
Sound.
In embodiments of the present invention, image pre-processing unit is handled image gray processing by weighted mean method.Move mesh
Marking detection unit includes inter-frame difference detection and background Differential Detection.Data processing unit uses TMS320C5502 chips.
TMS320C5502 chip signals are connected with internal storage, and internal storage is deposited using CY7C1011CV33 high-speed cmos static state
Reservoir.
A kind of video monitoring image processing method, comprises the following steps：
Step 1：The video monitoring data that camera is provided is obtained in real time, and the video monitoring data is by multiple image number
Image gray processing processing and the processing of E value filterings are carried out according to composition, while to the frame image data of acquisition；
Step 2：Frame image data after being handled in detecting step 1, judges whether there is fortune in the current frame image data
Dynamic object；
Step 3：When having the object of motion in the current frame image data, moving object in current frame image data is determined
The region of body；
Step 4：First carrying out small resolution ratio detection respectively to the moving object area data, intrusion target is moved in detection,
Target is tracked using particle filter algorithm, preserves the movement locus of intrusion target, and report is sent to abnormity early warning unit
Alert instruction；Big resolution ratio detection is carried out to moving object area data again, detection stands intrusion target, preserves invasion target frame figure
As data, and alarm command is sent to abnormity early warning unit；
Step 5：The instruction that abnormity early warning unit is sent according to step 4 sounds the alarm.
In summary, a kind of video monitoring image processing system provided in an embodiment of the present invention, passes through image preprocessing list
Member is used to carry out image gray processing processing to the image of video acquisition and E value filterings are handled, and by the multiple image number after processing
According to passing to moving object detection unit；Moving object detection unit is used to receive the multiframe figure transmitted by image pre-processing unit
Motion detection is carried out as data and to it, judges whether there is the object of motion in multiple image data, and testing result is sent
Give acquisition moving region unit；Moving region unit is obtained for receiving the testing result transmitted by moving object detection unit simultaneously
The region of moving object in current frame image data is determined, while moving object zone information data is sent to data processing list
Member；Data processing unit is used to receive the moving object area data information and advanced to its obtained transmitted by the unit of moving region
The small resolution ratio detection of row, detection motion intrusion target, is tracked to target using particle filter algorithm, preserves intrusion target
Movement locus, and send alarm command to abnormity early warning unit；Data processing unit simultaneously can be to the moving object area that receives
Numeric field data carries out big resolution ratio detection, and detection stands intrusion target, preserves invasion target frame view data, and to abnormity early warning list
Member sends alarm command；Abnormity early warning unit is used to receive the alarm command transmitted by data processing unit and sends alarm.
The system can in real time, active analysis monitoring function, intelligent monitor system based on video image, people from it is prolonged,
Freed in uninteresting heavy monitoring operation.
Disclosed above is only several specific embodiments of the present invention, and still, the embodiment of the present invention is not limited to this, is appointed
What what those skilled in the art can think change should all fall into protection scope of the present invention.
Claims (6)
- A kind of 1. video monitoring image processing system, it is characterised in that including：Image pre-processing unit, moving object detection list Member, obtain moving region unit, data processing unit and abnormity early warning unit；Described image pretreatment unit is used to carry out image gray processing processing to the image of video acquisition and E value filterings are handled, and Give the multiple image data transfer after processing to the moving object detection unit；The moving object detection unit is used to receive the multiple image data transmitted by described image pretreatment unit and to it Motion detection is carried out, judges whether there is the object of motion in the multiple image data, and testing result is sent to described obtain Take moving region unit；The moving region unit that obtains is used to receive the testing result transmitted by the moving object detection unit and determines to work as The region of moving object in prior image frame data, while moving object zone information data is sent to the data processing list Member；The data processing unit is used to receive the moving object area data information transmitted by the acquisition moving region unit And small resolution ratio detection is first carried out to it, detection motion intrusion target, target is tracked using particle filter algorithm, preserved The movement locus of intrusion target, and send alarm command to abnormity early warning unit；The data processing unit simultaneously can be to receiving The moving object area data arrived carries out big resolution ratio detection, and detection stands intrusion target, preserves invasion target frame view data, And send alarm command to abnormity early warning unit；The abnormity early warning unit is used to receive the alarm command transmitted by the data processing unit and sends alarm.
- A kind of 2. video monitoring image processing system as claimed in claim 1, it is characterised in that described image pretreatment unit By weighted mean method to image gray processing processing.
- A kind of 3. video monitoring image processing system as claimed in claim 1, it is characterised in that the moving object detection list Member includes inter-frame difference detection and background Differential Detection.
- 4. a kind of video monitoring image processing system as claimed in claim 1, it is characterised in that the data processing unit is adopted With TMS320C5502 chips.
- A kind of 5. video monitoring image processing system as claimed in claim 4, it is characterised in that the TMS320C5502 cores Piece signal is connected with internal storage, and the internal storage uses CY7C1011CV33 high-speed cmos static memories.
- 6. a kind of video monitoring image processing method, it is characterised in that comprise the following steps：Step 1：The video monitoring data that camera is provided is obtained in real time, and the video monitoring data is by multiple image data group Into, while image gray processing processing and the processing of E value filterings are carried out to the frame image data of acquisition；Step 2：Frame image data after being handled in detecting step 1, judges whether there is motion in the current frame image data Object；Step 3：When having the object of motion in the current frame image data, moving object in current frame image data is determined Region；Step 4：First carry out small resolution ratio detection respectively to the moving object area data, detection motion intrusion target, utilize Particle filter algorithm is tracked to target, preserves the movement locus of intrusion target, and send alarm to abnormity early warning unit and refer to Order；Big resolution ratio detection is carried out to moving object area data again, detection stands intrusion target, preserves invasion target frame picture number According to, and send alarm command to abnormity early warning unit；Step 5：The instruction that abnormity early warning unit is sent according to step 4 sounds the alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710872730.4A CN107623842A (en) | 2017-09-25 | 2017-09-25 | A kind of video monitoring image processing system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710872730.4A CN107623842A (en) | 2017-09-25 | 2017-09-25 | A kind of video monitoring image processing system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107623842A true CN107623842A (en) | 2018-01-23 |
Family
ID=61090478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710872730.4A Pending CN107623842A (en) | 2017-09-25 | 2017-09-25 | A kind of video monitoring image processing system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107623842A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112532917A (en) * | 2020-10-21 | 2021-03-19 | 深圳供电局有限公司 | Integrated intelligent monitoring platform based on streaming media |
| CN112770090A (en) * | 2020-12-28 | 2021-05-07 | 杭州电子科技大学 | Monitoring method based on transaction detection and target tracking |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1233336A (en) * | 1996-08-22 | 1999-10-27 | 富特福尔有限公司 | Video imaging systems |
| CN101295405A (en) * | 2008-06-13 | 2008-10-29 | 西北工业大学 | Portrait and vehicle recognition alarming and tracing method |
| CN101699862A (en) * | 2009-11-16 | 2010-04-28 | 上海交通大学 | High-resolution region-of-interest image acquisition method of PTZ camera |
| CN101971620A (en) * | 2008-02-29 | 2011-02-09 | 慧视科技有限公司 | A method of recording quality images |
| CN201773466U (en) * | 2009-09-09 | 2011-03-23 | 深圳辉锐天眼科技有限公司 | Video monitoring and pre-warning device for detecting, tracking and identifying object detention/stealing event |
| CN101996410A (en) * | 2010-12-07 | 2011-03-30 | 北京交通大学 | Method and system of detecting moving object under dynamic background |
| CN202435528U (en) * | 2012-01-17 | 2012-09-12 | 深圳辉锐天眼科技有限公司 | Video monitoring system |
| CN103826109A (en) * | 2014-03-25 | 2014-05-28 | 龙迅半导体科技(合肥)有限公司 | Video monitoring image data processing method and system |
| CN106128032A (en) * | 2016-07-05 | 2016-11-16 | 北京理工大学珠海学院 | A kind of fatigue state monitoring and method for early warning and system thereof |
-
2017
- 2017-09-25 CN CN201710872730.4A patent/CN107623842A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1233336A (en) * | 1996-08-22 | 1999-10-27 | 富特福尔有限公司 | Video imaging systems |
| CN101971620A (en) * | 2008-02-29 | 2011-02-09 | 慧视科技有限公司 | A method of recording quality images |
| CN101295405A (en) * | 2008-06-13 | 2008-10-29 | 西北工业大学 | Portrait and vehicle recognition alarming and tracing method |
| CN201773466U (en) * | 2009-09-09 | 2011-03-23 | 深圳辉锐天眼科技有限公司 | Video monitoring and pre-warning device for detecting, tracking and identifying object detention/stealing event |
| CN101699862A (en) * | 2009-11-16 | 2010-04-28 | 上海交通大学 | High-resolution region-of-interest image acquisition method of PTZ camera |
| CN101996410A (en) * | 2010-12-07 | 2011-03-30 | 北京交通大学 | Method and system of detecting moving object under dynamic background |
| CN202435528U (en) * | 2012-01-17 | 2012-09-12 | 深圳辉锐天眼科技有限公司 | Video monitoring system |
| CN103826109A (en) * | 2014-03-25 | 2014-05-28 | 龙迅半导体科技(合肥)有限公司 | Video monitoring image data processing method and system |
| CN106128032A (en) * | 2016-07-05 | 2016-11-16 | 北京理工大学珠海学院 | A kind of fatigue state monitoring and method for early warning and system thereof |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112532917A (en) * | 2020-10-21 | 2021-03-19 | 深圳供电局有限公司 | Integrated intelligent monitoring platform based on streaming media |
| CN112770090A (en) * | 2020-12-28 | 2021-05-07 | 杭州电子科技大学 | Monitoring method based on transaction detection and target tracking |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101942808B1 (en) | Apparatus for CCTV Video Analytics Based on Object-Image Recognition DCNN | |
| EP4105101A1 (en) | Monitoring system, monitoring method, and monitoring device for railway train | |
| CN103067740B (en) | Video monitoring equipment intelligent fault detection method and detection system thereof | |
| CN105208343B (en) | Can be used for intelligent monitor system and the method for video monitoring equipment | |
| CN100585656C (en) | An all-weather intelligent video analysis monitoring method based on a rule | |
| CN102164270A (en) | Intelligent video monitoring method and system capable of exploring abnormal events | |
| CN111432179A (en) | Intelligent coal conveying belt inspection system and method based on computer vision | |
| CN107818312A (en) | A kind of embedded system based on abnormal behaviour identification | |
| CN103108159A (en) | Electric power intelligent video analyzing and monitoring system and method | |
| KR102149832B1 (en) | Automated Violence Detecting System based on Deep Learning | |
| CN110867046A (en) | Intelligent car washer video monitoring and early warning system based on cloud computing | |
| CN113223046B (en) | Method and system for identifying prisoner behaviors | |
| CN108583592A (en) | A kind of subway service on buses or trains job information acquisition intelligent detecting method | |
| CN103929592A (en) | All-dimensional intelligent monitoring equipment and method | |
| KR20190035187A (en) | Sound alarm broadcasting system in monitoring area | |
| CN109040711A (en) | A kind of image-pickup method, monitoring method and imaging sensor | |
| CN107623842A (en) | A kind of video monitoring image processing system and method | |
| CN104363414A (en) | Intelligent video analyzing method | |
| CN108809886A (en) | A kind of computer network security guard system | |
| CN106341658A (en) | Intelligent city security state monitoring system | |
| CN201717988U (en) | All-in-one machine with intelligent office monitoring system | |
| CN203279057U (en) | Multi-target intelligent tracking locking and monitoring system | |
| KR20220113631A (en) | Dangerous situation detection device and dangerous situation detection method | |
| CN106710303A (en) | Parking space monitoring system | |
| TWI720500B (en) | Smart monitoring system and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180123 |
|
| RJ01 | Rejection of invention patent application after publication |