CN103136511A - Behavior detection method and behavior detection device - Google Patents
Behavior detection method and behavior detection device Download PDFInfo
- Publication number
- CN103136511A CN103136511A CN2013100216497A CN201310021649A CN103136511A CN 103136511 A CN103136511 A CN 103136511A CN 2013100216497 A CN2013100216497 A CN 2013100216497A CN 201310021649 A CN201310021649 A CN 201310021649A CN 103136511 A CN103136511 A CN 103136511A
- Authority
- CN
- China
- Prior art keywords
- staff
- behavior
- shoulder
- foreground image
- module
- 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.)
- Granted
Links
Images
Abstract
The invention provides a behavior detection method and a behavior detection device. The behavior detection method comprises the following steps: extracting a foreground image through a Gaussian background modeling method; extracting the positions of arms and hands of a human body in the foreground image; judging whether a running behavior occurs according to the positions of the arms and the hands. By means of the behavior detection method and the behavior detection device, the accuracy of behavior monitoring is improved.
Description
Technical field
The present invention relates to the machine vision technique field, particularly a kind of behavior detection method and device.
Background technology
Along with the needs of social development and intelligent city, video monitoring system has been installed in increasing public place.Such class functional requirement is arranged in some video monitoring system, whether the people of running is fast namely arranged in video.This demand is behavioural analysis problem in video monitoring, belongs to intelligent video monitoring higher level processing target.
Summary of the invention
In order to achieve the above object, the present invention proposes a kind of behavior detection method and device.
According to an aspect of the present invention, behavior detection method comprises: use the Gaussian Background modeling to extract foreground image; Extract the position of human body shoulder and staff in described foreground image; According to the behavior of whether running of the position judgment of the position of described staff and shoulder.
Preferably, using the Gaussian Background modeling to extract foreground image comprises: with each image as unit in foreground image as the stochastic variable of sampling and obtaining from mixed Gaussian distribution sample; According to preset value, each pixel is that the prior probability of prospect or background carries out valuation.
Preferably, the position of extraction human body shoulder and staff comprises in described foreground image: use three kinds of different positive and negative sample trainings to detect son: human body, head shoulder and staff; Use described human detection that the moving region is detected; Make use the same method detection head shoulder and staff in described human region and in preset range.
Preferably, describedly judge whether that the method for the behavior of running also comprises: extract staff center hand1 in a people, hand2, the head shoulder detects the left and right inferior horn corner1 of son, corner2, and the height height1 of head shoulder; Judge hand1 or during greater than threshold value thr1, judge the behavior of running than upper height1 with the distance of corner1 or corner2.
According to an aspect of the present invention, a kind of behavior pick-up unit comprises: the first extraction module is used for using the Gaussian Background modeling to extract foreground image; The second extraction module is used for the position at described foreground image extraction human body shoulder and staff; Judge module is used for according to the behavior of whether running of the position judgment of the position of described staff and shoulder.
Preferably, described the first extraction module comprises:
The first processing module is used for each image as unit with foreground image as the stochastic variable of sampling and obtaining from mixed Gaussian distribution sample;
The second processing module is used for according to preset value, and each pixel is that the prior probability of prospect or background carries out valuation.
Preferably, described the second extraction module comprises:
Training module is used for using three kinds of different positive and negative sample trainings to detect son: human body, head shoulder and staff; First detection module is used for using described human detection that the moving region is detected; The second detection module is used for making use the same method detection head shoulder and staff in described human region and in preset range.
Preferably, described judge module comprises: extraction module, be used for extracting people's staff center hand1, and hand2, the head shoulder detects the left and right inferior horn corner1 of son, corner2, and the height height1 of head shoulder; The behavior determination module is used for judging hand1 or during greater than threshold value thr1, judges the behavior of running than upper height1 with the distance of corner1 or corner2.
Description of drawings
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, the below will do one to the accompanying drawing of required use in embodiment or description of the Prior Art and introduce simply, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is the process flow diagram according to the behavior detection method of the embodiment of the present invention;
Fig. 2 is the structured flowchart according to the behavior pick-up unit of the embodiment of the present invention;
Fig. 3 is the process flow diagram of running and detecting according to the embodiment of the present invention.
Embodiment
For the purpose, technical scheme and the advantage that make the embodiment of the present invention clearer, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment in the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that obtains under the creative work prerequisite.
The present embodiment provides a kind of behavior detection method, and Fig. 1 is according to the process flow diagram of the behavior detection method of the embodiment of the present invention, as shown in Figure 1, comprises the steps:
Step S102: use the Gaussian Background modeling to extract foreground image.
Step S104: the position of extracting human body shoulder and staff in this foreground image.
Step S106: according to the behavior of whether running of the position judgment of the position of this staff and shoulder.
Preferably, using the Gaussian Background modeling to extract foreground image comprises: with each image as unit in foreground image as the stochastic variable of sampling and obtaining from mixed Gaussian distribution sample; According to preset value, each pixel is that the prior probability of prospect or background carries out valuation.
Preferably, the position of extraction human body shoulder and staff comprises in this foreground image: use three kinds of different positive and negative sample trainings to detect son: human body, head shoulder and staff; Use this human detection that the moving region is detected; Make use the same method detection head shoulder and staff in this human region and in preset range.
Preferably, this method that judges whether the behavior of running also comprises: extract staff center hand1 in a people, and hand2, the head shoulder detects the left and right inferior horn corner1 of son, corner2, and the height height1 of head shoulder; Judge hand1 or during greater than threshold value thr1, judge the behavior of running than upper height1 with the distance of corner1 or corner2.
According to an aspect of the present invention, a kind of behavior pick-up unit, Fig. 2 are the structured flowcharts according to the behavior pick-up unit of the embodiment of the present invention, and as shown in Figure 2, this device comprises: the first extraction module 22 is used for using the Gaussian Background modeling to extract foreground image; The second extraction module 24 is used for the position at this foreground image extraction human body shoulder and staff; Judge module 26 is used for according to the behavior of whether running of the position judgment of the position of this staff and shoulder.
Preferably, this first extraction module 22 comprises:
The first processing module is used for each image as unit with foreground image as the stochastic variable of sampling and obtaining from mixed Gaussian distribution sample;
The second processing module is used for according to preset value, and each pixel is that the prior probability of prospect or background carries out valuation.
Preferably, this second extraction module 24 comprises:
Training module is used for using three kinds of different positive and negative sample trainings to detect son: human body, head shoulder and staff; First detection module is used for using this human detection that the moving region is detected; The second detection module is used for making use the same method detection head shoulder and staff in this human region and in preset range.
Preferably, this judge module comprises: extraction module, be used for extracting people's staff center hand1, and hand2, the head shoulder detects the left and right inferior horn corner1 of son, corner2, and the height height1 of head shoulder; The behavior determination module is used for judging hand1 or during greater than threshold value thr1, judges the behavior of running than upper height1 with the distance of corner1 or corner2.
Preferred embodiment one
This preferred embodiment proposes a kind of detection method of running based on the metering of arm angle.Utilize mixed Gaussian background modeling method to extract the foreground image of motion.Again human region is extracted in the moving region, then human region is extracted the position of head shoulder and hand.At last according to the behavior of whether running of the position judgment of same human body following and hand.
Preferred embodiment two
This preferred embodiment provides a kind of behavior monitoring method, and the method comprises:
(1) extract movement human:
Use the mixed Gaussian background modeling to send out and extract the human region that moves in scene.
Single Gaussian Background is modeled as
The mixed Gaussian background modeling
1) initialization mixture model parameter at first comprises:
The shared weight of each Gauss model
The average of each Gauss model and standard deviation.
Wherein the initialization of weight is exactly the distribution of background to be carried out the valuation of prior probability, initialized the time, generally the weight of first Gauss model is got greatlyr, and other just corresponding values are less, that is:
Wherein the average of first Gauss model equal the first frame of input video corresponding pixel value or process the mean value of unit, that is:
The variance v of K Gauss model:
σ
k 2(x,y,1)=var k=1,2,...,K
The initial variance of all Gauss models all equates, that is: σ
k 2(x, y, 1)=var k=1,2 ..., K
The var value is directly relevant to the dynamic perfromance of this video.
2) upgrade the Gauss model parameter
Travel through each Gauss model, relatively following formula:
(I(x,y,l,f)-μ
k(x,y,l,f-1))
2<c*σ
k(x,y,f-1)
2
If all set up for all color components, so just this pixel is attributed to B Gauss model, otherwise, just not belonging to any one Gauss model, this just is equivalent to occur wild point.Below either way need to do corresponding renewal.
Situation 1 is upgraded accordingly:
The value of the pixel that situation 1 expression is current satisfies B Gaussian distribution, and this pixel might not belong to background so, needs to judge whether this B Gaussian distribution meets the following conditions:
Illustrate that this pixel belongs to background dot, otherwise just belong to the foreground point.
If this pixel belongs to background dot, so just illustrate that B background distributions exported a sampled value, at this moment all distribute and all need to carry out parameter and upgrade.
B corresponding Gauss model parameter upgraded as follows:
w
B(x,y,f)=(1-α)*w
B(x,y,f-1)+α
μ
B(x,y,l,f)=(1-β)*μ
B(x,y,l,f-1)+β*I(x,y,l,f)
σ
B 2(x,y,f)=(1-β)*σ
B 2(x,y,f-1)+β*(I(:)-μ
B(:))T*(I(:)-μ
B(:))
Remaining Gauss model only changes weights, and average and variance all remain unchanged, that is:
w
k(x,y,f)=(1-α)*w
k(x,y,f-1) k≠B
β=αη(I(x,y,:,f)|μ
B,σ
B)
Wild point refers to this pixel value and does not meet any one Gaussian distribution, this moment, we regarded this pixel as the new situation that occurs in video, replace K Gaussian distribution with this new situation, its weight and average and variance are all determined according to the initialization thinking, namely distribute a less weight, with a larger variance, that is:
w
K(x,y,f)=(1-W)/(K-1)
μ
K(x,y,l,f)=I(x,y,l,f)
σ
K(x,y,l,f)=var
Determine that simultaneously this point is the foreground point.
(2) human body, head shoulder and staff
Human body, head shoulder and staff:
At first use the support vector machine method to carry out human detection.
Training: choose suitable kernel function, k(xi, xj).
Minimize w, at ω
i(wx
i-b) 〉=1-ξ
iCondition under.
Only store the α of non-zero
iWith corresponding x
i(they are support vectors).
Image is zoomed to different scale by a certain percentage, use the window scan image of 8*16 size under each yardstick.And then the image under each window is classified.
(3) classification: for pattern X, use support vector x
iWith corresponding weight α
iThe computational discrimination functional expression
The symbol of this function determines that this zone is human body.
The human region that detects is used said method detection head shoulder and staff respectively
(4) detection is run:
Under same human body, determine the left and right inferior horn corner1 of head shoulder, corner2, the height height of head shoulder, and the center of staff, hand1, hand2.Distance() for calculating the function of bright spot Euclidean distance.Thr1 is artificial adjustable threshold value.
Work as Distance(hand1, corner1)/height〉Thr1
Or
Distance(hand2,corner2)/height>Thr1
Or
Distance(hand1,corner2)/height>Thr1
Or
Distance(hand2, corner1)/height〉during Thr1, judge that the behavior of running occurs.
Preferred embodiment three
This preferred embodiment provides a kind of behavior monitoring method, and Fig. 3 is the process flow diagram that detects according to running of the embodiment of the present invention, and as shown in Figure 3, the method comprising the steps of S302 is to step S316.
Step S302: obtain image.
Step S304: extract the moving region.
Step S306: extract human region.
Step S308: positioning head shoulder, staff.
Step S310: calculate staff shoulder distance.
Step S312: distance is greater than threshold value.
Step S314: run.
Step S316: non-running.
Need to prove, the present invention is not subjected to the impact of illumination variation, can detect more accurately fast the event of running in video.
One of ordinary skill in the art will appreciate that: all or part of step that realizes said method embodiment can be completed by the hardware that programmed instruction is correlated with, aforesaid program can be stored in a computer read/write memory medium, this program is carried out the step that comprises said method embodiment when carrying out; And aforesaid storage medium comprises: the various media that can be program code stored such as ROM, RAM, magnetic disc or CD.
It should be noted that at last: above embodiment only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to previous embodiment, the present invention is had been described in detail, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme that aforementioned each embodiment puts down in writing, and perhaps part technical characterictic wherein is equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution break away from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (8)
1. a behavior detection method, is characterized in that, comprising:
Use the Gaussian Background modeling to extract foreground image;
Extract the position of human body shoulder and staff in described foreground image;
According to the behavior of whether running of the position judgment of the position of described staff and shoulder.
2. method according to claim 1, is characterized in that, uses the Gaussian Background modeling to extract foreground image and comprise:
With each image as unit in foreground image as the stochastic variable that obtains of sampling from mixed Gaussian distribution sample;
According to preset value, each pixel is that the prior probability of prospect or background carries out valuation.
3. method according to claim 1, is characterized in that, the position of extracting human body shoulder and staff in described foreground image comprises:
Use three kinds of different positive and negative sample trainings to detect son: human body, head shoulder and staff;
Use described human detection that the moving region is detected;
Then make use the same method detection head shoulder and staff in described human region and in preset range.
4. method described according to right 1, is characterized in that, describedly judges whether that the method for the behavior of running also comprises:
Extract staff center hand1 in a people, hand2, the head shoulder detects the left and right inferior horn corner1 of son, corner2, and the height height1 of head shoulder;
Judge hand1 or during greater than threshold value thr1, judge the behavior of running than upper height1 with the distance of corner1 or corner2.
5. a behavior pick-up unit, is characterized in that, comprising:
The first extraction module is used for using the Gaussian Background modeling to extract foreground image;
The second extraction module is used for the position at described foreground image extraction human body shoulder and staff;
Judge module is used for according to the behavior of whether running of the position judgment of the position of described staff and shoulder.
6. device according to claim 5, is characterized in that, described the first extraction module comprises:
The first processing module is used for each image as unit with foreground image as the stochastic variable of sampling and obtaining from mixed Gaussian distribution sample;
The second processing module is used for according to preset value, and each pixel is that the prior probability of prospect or background carries out valuation.
7. device according to claim 5, is characterized in that, described the second extraction module comprises:
Training module is used for using three kinds of different positive and negative sample trainings to detect son: human body, head shoulder and staff;
First detection module is used for using described human detection that the moving region is detected;
The second detection module is used for making use the same method detection head shoulder and staff in described human region and in preset range.
8. device described according to right 5, is characterized in that, described judge module comprises:
Extraction module is used for extracting people's staff center hand1, hand2, and the head shoulder detects the left and right inferior horn corner1 of son, corner2, and the height height1 of head shoulder;
The behavior determination module is used for judging hand1 or during greater than threshold value thr1, judges the behavior of running than upper height1 with the distance of corner1 or corner2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310021649.7A CN103136511B (en) | 2013-01-21 | 2013-01-21 | Behavioral value method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310021649.7A CN103136511B (en) | 2013-01-21 | 2013-01-21 | Behavioral value method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103136511A true CN103136511A (en) | 2013-06-05 |
CN103136511B CN103136511B (en) | 2016-06-29 |
Family
ID=48496319
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310021649.7A Expired - Fee Related CN103136511B (en) | 2013-01-21 | 2013-01-21 | Behavioral value method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103136511B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104866841A (en) * | 2015-06-05 | 2015-08-26 | 中国人民解放军国防科学技术大学 | Human body object running behavior detection method |
CN107735813A (en) * | 2015-06-10 | 2018-02-23 | 柯尼卡美能达株式会社 | Image processing system, image processing apparatus, image processing method and image processing program |
CN111461036A (en) * | 2020-04-07 | 2020-07-28 | 武汉大学 | Real-time pedestrian detection method using background modeling enhanced data |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007028121A (en) * | 2005-07-15 | 2007-02-01 | Fujitsu Access Ltd | Alarm monitor control system and alarm monitor control method |
CN101355449A (en) * | 2008-09-19 | 2009-01-28 | 武汉噢易科技有限公司 | Intelligent analysis system and analysis method for computer user behaviors |
-
2013
- 2013-01-21 CN CN201310021649.7A patent/CN103136511B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007028121A (en) * | 2005-07-15 | 2007-02-01 | Fujitsu Access Ltd | Alarm monitor control system and alarm monitor control method |
CN101355449A (en) * | 2008-09-19 | 2009-01-28 | 武汉噢易科技有限公司 | Intelligent analysis system and analysis method for computer user behaviors |
Non-Patent Citations (2)
Title |
---|
张传金: "基于视频序列的人体肢体标定研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 15 July 2010 (2010-07-15) * |
陈雪莹: "基于混合高斯的背景建模与更新算法的研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 15 June 2012 (2012-06-15) * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104866841A (en) * | 2015-06-05 | 2015-08-26 | 中国人民解放军国防科学技术大学 | Human body object running behavior detection method |
CN104866841B (en) * | 2015-06-05 | 2018-03-09 | 中国人民解放军国防科学技术大学 | A kind of human body target is run behavioral value method |
CN107735813A (en) * | 2015-06-10 | 2018-02-23 | 柯尼卡美能达株式会社 | Image processing system, image processing apparatus, image processing method and image processing program |
CN111461036A (en) * | 2020-04-07 | 2020-07-28 | 武汉大学 | Real-time pedestrian detection method using background modeling enhanced data |
CN111461036B (en) * | 2020-04-07 | 2022-07-05 | 武汉大学 | Real-time pedestrian detection method using background modeling to enhance data |
Also Published As
Publication number | Publication date |
---|---|
CN103136511B (en) | 2016-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107704805B (en) | Method for detecting fatigue driving, automobile data recorder and storage device | |
CN103400105B (en) | Method identifying non-front-side facial expression based on attitude normalization | |
CN101404086A (en) | Target tracking method and device based on video | |
CN110020592A (en) | Object detection model training method, device, computer equipment and storage medium | |
CN108710865A (en) | A kind of driver's anomaly detection method based on neural network | |
CN105354986A (en) | Driving state monitoring system and method for automobile driver | |
CN102609682B (en) | Feedback pedestrian detection method for region of interest | |
CN103985137B (en) | It is applied to the moving body track method and system of man-machine interaction | |
CN106650688A (en) | Eye feature detection method, device and recognition system based on convolutional neural network | |
CN104680144A (en) | Lip language recognition method and device based on projection extreme learning machine | |
CN105512640A (en) | Method for acquiring people flow on the basis of video sequence | |
CN103150019A (en) | Handwriting input system and method | |
CN103593672A (en) | Adaboost classifier on-line learning method and Adaboost classifier on-line learning system | |
CN106203385A (en) | A kind of driver's hand-held phone behavioral value method and device | |
CN105046197A (en) | Multi-template pedestrian detection method based on cluster | |
CN103079117A (en) | Video abstract generation method and video abstract generation device | |
CN104484644A (en) | Gesture identification method and device | |
CN106503710A (en) | A kind of automobile logo identification method and device | |
CN107483813A (en) | A kind of method, apparatus and storage device that recorded broadcast is tracked according to gesture | |
CN108805902A (en) | A kind of space-time contextual target tracking of adaptive scale | |
CN103136511B (en) | Behavioral value method and device | |
CN103258216A (en) | Regional deformation target detection method and system based on online learning | |
CN105809713A (en) | Object tracing method based on online Fisher discrimination mechanism to enhance characteristic selection | |
CN105427339B (en) | A kind of Fast Compression tracking of binding characteristic screening and secondary positioning | |
CN104268595A (en) | General object detecting method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160629 Termination date: 20200121 |
|
CF01 | Termination of patent right due to non-payment of annual fee |