CN101221663A - Intelligent monitoring and alarming method based on movement object detection - Google Patents
Intelligent monitoring and alarming method based on movement object detection Download PDFInfo
- Publication number
- CN101221663A CN101221663A CNA2008100259792A CN200810025979A CN101221663A CN 101221663 A CN101221663 A CN 101221663A CN A2008100259792 A CNA2008100259792 A CN A2008100259792A CN 200810025979 A CN200810025979 A CN 200810025979A CN 101221663 A CN101221663 A CN 101221663A
- Authority
- CN
- China
- Prior art keywords
- background
- threshold value
- frame
- foreground point
- value
- 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
An intelligent monitoring and alarm method based on moving object detection has the following steps: step 1, picking up the grey scale information of a video signal; step 2, initializing a background matrix; step 3, carrying out background-based object detection; step 4, updating the background. The invention detects an initial sequence through a frame difference method and establishes the initial background according to the detection result; after the initial background is established, a background method is used to detect a moving object; the background model adopts a mean-based difference comparison method instead of a probability threshold value comparison method; the background updating is carried out in two parts, namely a foreground point part and a background point part. The method capable of automatically updating the background can detect the moving object in time with effectiveness and timeliness, thereby avoiding a 'ghost shadow' to a great extent. Furthermore, the invention can meet the requirements of multi-path real-time monitoring with simple operation and high speed.
Description
[technical field]
The invention belongs to field of intelligent monitoring, be used for motion target detection and the warning of camera when static.
[background technology]
Video monitoring system is with its directly perceived, convenient, the full and accurate occasions such as production management, security personnel that are widely used in of the information content, become finance, traffic, commerce, electric power, public security, customs, national defence, so the important means of field safety precaution monitoring such as dwelling house community.
In order to realize intelligent monitoring, the motion target detection technology occupies important status in system.In recent decades, people have done a large amount of and deep research to the Detection for Moving Target in the image sequence, for compressed video, can carry out target detection by the motion vector of macroblock/block, also can carry out target detection by traditional method based on pixel.By studies have shown that, the former arithmetic speed is faster, and the latter detects better effects if.At present, the motion target detection technology is rather ripe, is three kinds of relatively classic methods below:
(1) optical flow method
One of three kinds of traditional moving object detection algorithms.When object of which movement, the luminance patterns of corresponding object is also being moved on image, thereby claims that light stream is the apparent movement of image brightness pattern.Optical flow method detects and has adopted the time dependent light stream characteristic of target.Utilize optical flow method to come the profile of initialization target, thereby make track algorithm detection and tracking target effectively based on profile by displacement calculating optical flow vector field.
The major advantage of characteristic light stream method is can handle big interframe displacement to the less-restrictive of target in the motion of interframe; Major defect is that most of optical flow computation methods are quite complicated, and noiseproof feature is poor, if there is not specific hardware supported, generally is difficult to be applied to the real-time operation of moving target in the sequence image.Optical flow method is referring to document: Sasa G, Lonoario S.Spalic-temporal image segmentationusing optical flow and clustering algorithm[A] .First Int ' Workshopon Image and Signal Processing Analysis[C] .Pula.Crotia.2000.63-38.
(2) frame-to-frame differences point-score
One of three kinds of traditional moving object detection algorithms.Inter-frame difference is to detect simple, the most direct method that changes between adjacent two frame images, and it is the difference that has directly compared the gray-scale value of the corresponding picture elements of two frame images, and passing threshold comes the moving region in the abstraction sequence image then, k frame image f
k(x is y) with k+1 frame image f
K+1(x, y) the available two-value difference image D of the variation between (x, y) represent:
T is the threshold value of difference image binaryzation in the formula.The place of (owing to motion produces) variation does not take place in the pixel correspondence that in the binary picture is " 0 " between two frame images of front and back, the place that changes between corresponding two frame images of pixel for " 1 ", and this is often produced by target travel.Frame difference method is referring to document: Foresti GL.Object reconnition and trackinn for remote videosurveillance[J] .IEEE Transactions On Circuits and Systems for VideoTechnology, 1999,9 (7): 1045-1062.
(3) background subtraction method
One of three kinds of traditional moving object detection algorithms.Under the situation that camera is fixed, the background subtraction method is the moving target detecting method of using always.Its basic thought is that present frame image and the background model of storing in advance or obtain are in real time compared, and judges according to result relatively whether this picture element belongs to motion target area.The background subtraction method is referring to document: Stringna E, Renazzoni C S.Realtime Video-shotdetection for scene svreillance applications[J] .IEEE Transactions onImage Processing, 2000,9 (): 69-79.
The background subtraction method is simple to operate, and the detection position is accurate and speed is fast.But common background subtraction method is very responsive to the variation of illumination conditions such as light, weather.The shade of moving target also usually is detected as the part of moving target.This will influence the accuracy of testing result.Therefore, in non-control environment, need to add the update mechanism of background images.Common background model has single Gaussian distribution background model and many Gaussian distribution background model, the former has set up a Gaussian distribution model for each picture element, the latter then is according to the common color distribution of describing on the picture element of a plurality of Gaussian distribution, list of references: C Stauffer, WELGrimson.Learning Patters of Activity Using Real-Time Tracking, IEEETrans.PAMI, 2000,22 (8): 747~757 and RT Collins, AJ Lipton, T Kanade.ASystem for Video Surveillance and Monitoring.Proc Am.Nuclear Soc. (ANS) English Int ' l Topical Meeting Robotic and Remote Systems, Apr.1999
Traditional background method based on statistical model, owing to need set up statistical model to each picture element, calculated amount is big, and carries out moving object detection by this model, can't eliminate " ghost " that moving target brings at short notice.
[summary of the invention]
The objective of the invention is to overcome the deficiencies in the prior art part, provide a kind of and effectively in time can avoid the generation of " ghost ", computing is simple, and speed is fast, and can realize the multichannel alarm method of monitoring in real time.
The object of the present invention is achieved like this:
The half-tone information of step 1, extraction vision signal
In decoder module, the color space of video output is set to yuv format, and Y-signal is stored as a matrix in addition, handles for subsequent step;
Step 2, initialization background matrix
The background indicia initial value is " 0 ", when new forward one frame is visual, at first detects this background indicia, if this is masked as " 0 ", then carries out motion target detection by frame difference method, and concrete step is:
At first that each pixel gray-scale value of this frame image is corresponding with background frames pixel gray-scale value subtracts each other, if this result, then is designated as " 1 " greater than certain threshold value to be expressed as the foreground point; If less than threshold value, then be designated as " 0 " to be expressed as background dot, produce two values matrix thus;
Then this two values matrix is carried out morphology and handle, promptly earlier the foreground point is carried out opening operation one time, and then this result is done a closed operation continuously, respectively in order to remove because noise forms isolated foreground point and cavity with structural element SE;
Then add up morphology and handle later two-value calculating, calculate the quantity of prospect picture element, value that obtains and alarm threshold value are compared, determine whether to report to the police,, then report to the police if greater than threshold value; If less than threshold value, then do not report to the police;
If continuous three frames all do not have alerting signal to produce, illustrate that this sequence does not temporarily have moving target at this moment, the gray average of this three frame as the initial background image, and is set at " 1 " with background indicia, at this moment, the background initialization finishes;
Step 3, based on the target detection of background
After the background indicia set, then adopt the background method to carry out motion target detection, experience present frame and background frames compares, binaryzation, morphology are handled and whether judgement reports to the police several stages;
The renewal of step 4, background
For background dot, adopt Bn+1 (x, y)=(1-a) Bn (x, y)+(x y) upgrades aVn, and wherein (x y) is the background dot of n frame to Bn, and (x is the arithmetic mean of corresponding background dot in nearest three frames y) to Vn, and a is a renewal rate; For the foreground point, it is carried out accumulation calculating as the number of times of foreground point continuously, when being accumulated to a certain threshold value, incorporate this foreground point into background dot to upgrade background.
Moving target detecting method of the present invention uses frame difference method to carry out the detection of initiation sequence, and sets up initial background according to testing result; After initial background is set up, utilize the background method to detect moving target; Background model adopts based on the difference relative method of average and replaces the probability threshold value relative method; Context update branch foreground point and background dot two parts are handled respectively.Can upgrade background automatically, in time detect moving target, effectively in time, avoid the generation of " ghost " to a great extent.And computing is simple, and speed is fast, can satisfy the multichannel requirement of monitoring in real time.
[description of drawings]
Fig. 1 is the process flow diagram of alarm module of the present invention;
Fig. 2 is the detection effect (gray-scale map, background, moving target) of the 72nd frame;
Fig. 3 is the detection effect (gray-scale map, background, moving target) of the 82nd frame.
[embodiment]
Intelligent alarm method of the present invention comprises following steps:
The half-tone information of step 1, extraction vision signal
In decoder module, we are set to yuv format in the color space of video output, and Y-signal is stored as a matrix in addition, handle for subsequent step;
Step 2, initialization background matrix
The background indicia initial value is " 0 ", when new forward one frame is visual, at first detects this background indicia, if this is masked as " 0 ", then carries out motion target detection by frame difference method, and concrete step is:
At first that each pixel gray-scale value of this frame image is corresponding with background frames pixel gray-scale value subtracts each other, if this result, then is designated as " 1 " greater than certain threshold value to be expressed as the foreground point; If less than threshold value, then be designated as " 0 " to be expressed as background dot, produce two values matrix thus;
Then this two values matrix is carried out morphology and handle, promptly earlier the foreground point is carried out opening operation one time, and then this result is done a closed operation continuously with structural element SE.Respectively in order to remove because noise forms isolated foreground point and cavity;
Then add up morphology and handle later two-value calculating, calculate the quantity of prospect picture element, value that obtains and alarm threshold value are compared, determine whether to report to the police.If greater than threshold value, then report to the police; If less than threshold value, then do not report to the police;
If continuous three frames all do not have alerting signal to produce, illustrate that this sequence does not temporarily have moving target at this moment, the gray average of this three frame as the initial background image, and is set at " 1 " with background indicia, at this moment, the background initialization finishes;
Step 3, based on the target detection of background
After the background indicia set, then adopt the background method to carry out motion target detection, the step of the method for concrete step and frame difference is similar, experience comparison, binaryzation, morphology processing and judge the several stages of whether reporting to the police, the difference of the two is comparing liking present frame and background frames of comparing this moment;
The renewal of step 4, background
For background dot, we adopt Bn+1 (x, y)=(1-a) Bn (x, y)+(x y) upgrades aVn, and wherein (x y) is the background dot of n frame to Bn, and (x is the arithmetic mean of corresponding background dot in nearest three frames y) to Vn, and a is a renewal rate; For the foreground point, we carry out accumulation calculating as the number of times of foreground point continuously to it, and when being accumulated to a certain threshold value, we just incorporate this foreground point into background dot to upgrade background.The setting of this threshold value can be adjusted as the case may be: if the foreground point movement velocity is slower, then need this threshold setting greatlyyer, otherwise the foreground point can be updated to background mistakenly; If the foreground point movement velocity is very fast, then this threshold value can be set at less value.
Need to prove:
Morphology in step 3 and the step 4 is handled, and what our structural element adopted is:
SE=1,1,1
1,1,1
1,1,1。
Claims (1)
1. intelligent monitoring and alarming method based on moving object detection is characterized in that may further comprise the steps:
The half-tone information of step 1, extraction vision signal
In decoder module, the color space of video output is set to yuv format, and Y-signal is stored as a matrix in addition, handles for subsequent step;
Step 2, initialization background matrix
The background indicia initial value is " 0 ", when new forward one frame is visual, at first detects this background indicia, if this is masked as " 0 ", then carries out motion target detection by frame difference method, and concrete step is:
At first that each pixel gray-scale value of this frame image is corresponding with background frames pixel gray-scale value subtracts each other, if this result is greater than certain threshold value, then be designated as " 1 " to be expressed as the foreground point:, then be designated as " 0 " if less than threshold value to be expressed as background dot, produce two values matrix thus;
Then this two values matrix is carried out morphology and handle, promptly earlier the foreground point is carried out opening operation one time, and then this result is done a closed operation continuously, respectively in order to remove because noise forms isolated foreground point and cavity with structural element SE;
Then add up morphology and handle later two-value calculating, calculate the quantity of prospect picture element, value that obtains and alarm threshold value are compared, determine whether to report to the police,, then report to the police if greater than threshold value; If less than threshold value, then do not report to the police;
If continuous three frames all do not have alerting signal to produce, illustrate that this sequence does not temporarily have moving target at this moment, the gray average of this three frame as the initial background image, and is set at " 1 " with background indicia, at this moment, the background initialization finishes;
Step 3, based on the target detection of background
After the background indicia set, then adopt the background method to carry out motion target detection, experience present frame and background frames compares, binaryzation, morphology are handled and whether judgement reports to the police several stages;
The renewal of step 4, background
For background dot, adopt Bn+1 (x, y)=(1-a) Bn (x, y)+(x y) upgrades aVn, and wherein (x y) is the background dot of n frame to Bn, and (x is the arithmetic mean of corresponding background dot in nearest three frames y) to Vn, and a is a renewal rate; For the foreground point, it is carried out accumulation calculating as the number of times of foreground point continuously, when being accumulated to a certain threshold value, incorporate this foreground point into background dot to upgrade background.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2008100259792A CN101221663A (en) | 2008-01-18 | 2008-01-18 | Intelligent monitoring and alarming method based on movement object detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2008100259792A CN101221663A (en) | 2008-01-18 | 2008-01-18 | Intelligent monitoring and alarming method based on movement object detection |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101221663A true CN101221663A (en) | 2008-07-16 |
Family
ID=39631478
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNA2008100259792A Pending CN101221663A (en) | 2008-01-18 | 2008-01-18 | Intelligent monitoring and alarming method based on movement object detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101221663A (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101847204A (en) * | 2010-03-30 | 2010-09-29 | 北京蓝色星河软件技术发展有限公司 | Abnormal face detecting method for embedded digital video recorder (DVR) system |
CN101980300A (en) * | 2010-10-29 | 2011-02-23 | 杭州电子科技大学 | 3G smart phone-based motion detection method |
CN101635852B (en) * | 2009-08-26 | 2011-08-31 | 北京航空航天大学 | Method for detecting real-time moving object based on adaptive background modeling |
CN102244776A (en) * | 2011-07-06 | 2011-11-16 | 浙江浙大华是科技有限公司 | Automatic tracking laser thermal imaging monitoring system |
CN102254396A (en) * | 2011-07-06 | 2011-11-23 | 北京国铁华晨通信信息技术有限公司 | Intrusion detection method and device based on video |
CN101777186B (en) * | 2010-01-13 | 2011-12-14 | 西安理工大学 | Multimodality automatic updating and replacing background modeling method |
CN102663362A (en) * | 2012-04-09 | 2012-09-12 | 宁波中科集成电路设计中心有限公司 | Moving target detection method t based on gray features |
CN103002195A (en) * | 2011-09-09 | 2013-03-27 | 中怡(苏州)科技有限公司 | Motion detecting method and motion detecting device |
CN103280052A (en) * | 2013-05-15 | 2013-09-04 | 重庆大学 | Intrusion detection method applied in intelligent video monitoring of long-distance railway lines |
CN103426181A (en) * | 2012-05-25 | 2013-12-04 | 信帧电子技术(北京)有限公司 | Automatic frame rate changing wire-mixing detection method |
CN103442209A (en) * | 2013-08-20 | 2013-12-11 | 北京工业大学 | Video monitoring method of electric transmission line |
CN103700116A (en) * | 2012-09-27 | 2014-04-02 | 中国航天科工集团第二研究院二O七所 | Background modeling method for movement target detection |
CN103810703A (en) * | 2014-01-22 | 2014-05-21 | 安徽科力信息产业有限责任公司 | Picture processing based tunnel video moving object detection method |
CN101751670B (en) * | 2009-12-17 | 2014-09-10 | 北京中星微电子有限公司 | Method and device for detecting foreground object |
CN104063878A (en) * | 2013-03-20 | 2014-09-24 | 富士通株式会社 | Motion object detection device, motion object detection method and electronic device |
CN104125436A (en) * | 2014-08-01 | 2014-10-29 | 昆明联诚科技股份有限公司 | Early warning method and system for traffic accident detection |
CN104463905A (en) * | 2014-11-04 | 2015-03-25 | 江苏省南京市公路管理处公路科学研究所 | Method for monitoring vehicles in construction site |
CN104700429A (en) * | 2014-10-05 | 2015-06-10 | 安徽工程大学 | Motion detection method of airborne display |
CN104700430A (en) * | 2014-10-05 | 2015-06-10 | 安徽工程大学 | Method for detecting movement of airborne displays |
CN104836959A (en) * | 2015-05-15 | 2015-08-12 | 华南师范大学 | FPGA-based Multi-mode automatic switchover collection system of array CMOS image sensor |
CN106023259A (en) * | 2016-05-26 | 2016-10-12 | 史方 | Method and device for detecting moving target frequency |
WO2016184431A1 (en) * | 2015-05-20 | 2016-11-24 | 王向恒 | Local calculation-based video monitoring method and terminal thereof |
CN106878668A (en) * | 2015-12-10 | 2017-06-20 | 微软技术许可有限责任公司 | Mobile detection to object |
CN107798689A (en) * | 2016-08-28 | 2018-03-13 | 淮安信息职业技术学院 | Traffic video image background extracting method |
CN108259904A (en) * | 2016-12-29 | 2018-07-06 | 乐视汽车(北京)有限公司 | For the method for coded image data, encoder and electronic equipment |
CN110517435A (en) * | 2019-09-08 | 2019-11-29 | 天津大学 | The portable instant fire prevention early warning of one kind and Information Collecting & Processing early warning system and method |
CN112906646A (en) * | 2021-03-23 | 2021-06-04 | 中国联合网络通信集团有限公司 | Human body posture detection method and device |
-
2008
- 2008-01-18 CN CNA2008100259792A patent/CN101221663A/en active Pending
Cited By (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101635852B (en) * | 2009-08-26 | 2011-08-31 | 北京航空航天大学 | Method for detecting real-time moving object based on adaptive background modeling |
CN101751670B (en) * | 2009-12-17 | 2014-09-10 | 北京中星微电子有限公司 | Method and device for detecting foreground object |
CN101777186B (en) * | 2010-01-13 | 2011-12-14 | 西安理工大学 | Multimodality automatic updating and replacing background modeling method |
CN101847204A (en) * | 2010-03-30 | 2010-09-29 | 北京蓝色星河软件技术发展有限公司 | Abnormal face detecting method for embedded digital video recorder (DVR) system |
CN101980300A (en) * | 2010-10-29 | 2011-02-23 | 杭州电子科技大学 | 3G smart phone-based motion detection method |
CN102244776A (en) * | 2011-07-06 | 2011-11-16 | 浙江浙大华是科技有限公司 | Automatic tracking laser thermal imaging monitoring system |
CN102254396A (en) * | 2011-07-06 | 2011-11-23 | 北京国铁华晨通信信息技术有限公司 | Intrusion detection method and device based on video |
CN102244776B (en) * | 2011-07-06 | 2013-03-20 | 浙江浙大华是科技有限公司 | Automatic tracking laser thermal imaging monitoring system |
CN103002195B (en) * | 2011-09-09 | 2016-03-30 | 中磊电子(苏州)有限公司 | Method for testing motion and motion detection apparatus |
CN103002195A (en) * | 2011-09-09 | 2013-03-27 | 中怡(苏州)科技有限公司 | Motion detecting method and motion detecting device |
US9214031B2 (en) | 2011-09-09 | 2015-12-15 | Sernet (Suzhou) Technologies Corporation | Motion detection method and associated apparatus |
CN102663362A (en) * | 2012-04-09 | 2012-09-12 | 宁波中科集成电路设计中心有限公司 | Moving target detection method t based on gray features |
CN103426181A (en) * | 2012-05-25 | 2013-12-04 | 信帧电子技术(北京)有限公司 | Automatic frame rate changing wire-mixing detection method |
CN103700116A (en) * | 2012-09-27 | 2014-04-02 | 中国航天科工集团第二研究院二O七所 | Background modeling method for movement target detection |
CN103700116B (en) * | 2012-09-27 | 2017-02-22 | 中国航天科工集团第二研究院二O七所 | Background modeling method for movement target detection |
CN104063878A (en) * | 2013-03-20 | 2014-09-24 | 富士通株式会社 | Motion object detection device, motion object detection method and electronic device |
CN104063878B (en) * | 2013-03-20 | 2017-08-08 | 富士通株式会社 | Moving Objects detection means, Moving Objects detection method and electronic equipment |
CN103280052B (en) * | 2013-05-15 | 2015-08-19 | 重庆大学 | Be applied to the intrusion detection method of long distance track circuit intelligent video monitoring |
CN103280052A (en) * | 2013-05-15 | 2013-09-04 | 重庆大学 | Intrusion detection method applied in intelligent video monitoring of long-distance railway lines |
CN103442209A (en) * | 2013-08-20 | 2013-12-11 | 北京工业大学 | Video monitoring method of electric transmission line |
CN103442209B (en) * | 2013-08-20 | 2017-02-22 | 北京工业大学 | Video monitoring method of electric transmission line |
CN103810703A (en) * | 2014-01-22 | 2014-05-21 | 安徽科力信息产业有限责任公司 | Picture processing based tunnel video moving object detection method |
CN103810703B (en) * | 2014-01-22 | 2016-09-21 | 安徽科力信息产业有限责任公司 | A kind of tunnel based on image procossing video moving object detection method |
CN104125436A (en) * | 2014-08-01 | 2014-10-29 | 昆明联诚科技股份有限公司 | Early warning method and system for traffic accident detection |
CN104700429A (en) * | 2014-10-05 | 2015-06-10 | 安徽工程大学 | Motion detection method of airborne display |
CN104700430A (en) * | 2014-10-05 | 2015-06-10 | 安徽工程大学 | Method for detecting movement of airborne displays |
CN104463905B (en) * | 2014-11-04 | 2017-07-04 | 江苏省南京市公路管理处公路科学研究所 | Job site vehicle monitoring method |
CN104463905A (en) * | 2014-11-04 | 2015-03-25 | 江苏省南京市公路管理处公路科学研究所 | Method for monitoring vehicles in construction site |
CN104836959B (en) * | 2015-05-15 | 2018-01-23 | 华南师范大学 | Face array CMOS image sensor multimode automatic switching acquisition system based on FPGA |
CN104836959A (en) * | 2015-05-15 | 2015-08-12 | 华南师范大学 | FPGA-based Multi-mode automatic switchover collection system of array CMOS image sensor |
WO2016184431A1 (en) * | 2015-05-20 | 2016-11-24 | 王向恒 | Local calculation-based video monitoring method and terminal thereof |
US10460456B2 (en) | 2015-12-10 | 2019-10-29 | Microsoft Technology Licensing, Llc | Motion detection of object |
CN106878668A (en) * | 2015-12-10 | 2017-06-20 | 微软技术许可有限责任公司 | Mobile detection to object |
CN106023259B (en) * | 2016-05-26 | 2018-12-07 | 史方 | A kind of moving target frequency detecting method and device |
CN106023259A (en) * | 2016-05-26 | 2016-10-12 | 史方 | Method and device for detecting moving target frequency |
CN107798689A (en) * | 2016-08-28 | 2018-03-13 | 淮安信息职业技术学院 | Traffic video image background extracting method |
CN108259904A (en) * | 2016-12-29 | 2018-07-06 | 乐视汽车(北京)有限公司 | For the method for coded image data, encoder and electronic equipment |
CN108259904B (en) * | 2016-12-29 | 2022-04-05 | 法法汽车(中国)有限公司 | Method, encoder and electronic device for encoding image data |
CN110517435A (en) * | 2019-09-08 | 2019-11-29 | 天津大学 | The portable instant fire prevention early warning of one kind and Information Collecting & Processing early warning system and method |
CN112906646A (en) * | 2021-03-23 | 2021-06-04 | 中国联合网络通信集团有限公司 | Human body posture detection method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101221663A (en) | Intelligent monitoring and alarming method based on movement object detection | |
WO2018130016A1 (en) | Parking detection method and device based on monitoring video | |
CN101303727B (en) | Intelligent management method based on video human number Stat. and system thereof | |
CN101751677B (en) | Target continuous tracking method based on multi-camera | |
CN106952474B (en) | Traffic flow statistical method based on moving vehicle detection | |
CN106204586B (en) | A kind of moving target detecting method under complex scene based on tracking | |
CN105678803A (en) | Video monitoring target detection method based on W4 algorithm and frame difference | |
CN103258332B (en) | A kind of detection method of the moving target of resisting illumination variation | |
CN100555348C (en) | Intelligent video monitoring system of bank self-aid apparatus | |
Cheng et al. | Scene analysis for object detection in advanced surveillance systems using Laplacian distribution model | |
CN110040595B (en) | Elevator door state detection method and system based on image histogram | |
CN101635835A (en) | Intelligent video monitoring method and system thereof | |
CN103714325A (en) | Left object and lost object real-time detection method based on embedded system | |
CN101957997A (en) | Regional average value kernel density estimation-based moving target detecting method in dynamic scene | |
CN102663362B (en) | Moving target detection method based on gray features | |
Miller et al. | A hidden Markov model for vehicle detection and counting | |
CN105894530A (en) | Detection and tracking solution scheme aiming at motion target in video | |
CN102254394A (en) | Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis | |
CN109948474A (en) | AI thermal imaging all-weather intelligent monitoring method | |
Chen et al. | Research on moving object detection based on improved mixture Gaussian model | |
Miranto et al. | Adaptive background subtraction for monitoring system | |
CN101877135B (en) | Moving target detecting method based on background reconstruction | |
CN107665325B (en) | Video abnormal event detection method and system based on atomic feature bag model | |
Fu et al. | An effective background subtraction method based on pixel change classification | |
Wang et al. | A new approach for real-time detection of abandoned and stolen objects |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Open date: 20080716 |