CN102622582A - Road pedestrian event detection method based on video - Google Patents

Road pedestrian event detection method based on video Download PDF

Info

Publication number
CN102622582A
CN102622582A CN2012100395539A CN201210039553A CN102622582A CN 102622582 A CN102622582 A CN 102622582A CN 2012100395539 A CN2012100395539 A CN 2012100395539A CN 201210039553 A CN201210039553 A CN 201210039553A CN 102622582 A CN102622582 A CN 102622582A
Authority
CN
China
Prior art keywords
target
piece
frame
field picture
pedestrian
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
Application number
CN2012100395539A
Other languages
Chinese (zh)
Other versions
CN102622582B (en
Inventor
宋焕生
付洋
朱小平
杨孟拓
陈艳
刘童
施春宁
赵倩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changan University
Original Assignee
Changan University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Changan University filed Critical Changan University
Priority to CN201210039553.9A priority Critical patent/CN102622582B/en
Publication of CN102622582A publication Critical patent/CN102622582A/en
Application granted granted Critical
Publication of CN102622582B publication Critical patent/CN102622582B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Image Analysis (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a road pedestrian event detection method based on a video. The road pedestrian event detection method mainly comprises three steps as follows: based on binary segmentation of blocks, separating a target background in each frame of image in the video to be processed; based on the joint domain marks of the blocks, separating pedestrian targets through the profile characteristics of the marked targets, and recording the gravity center position information of the pedestrian targets at the same time; and based on the gravity center position characteristics, matching and calculating the speed of the pedestrian targets so as to judge whether the pedestrians pass through the road or not. Compared with the prior art, the road pedestrian event detection method can detect all the pedestrian targets in the video range and judge the real-time video, has the advantages of no environmental limit, short detection time, easiness in realization, higher accuracy and wide application prospect, and is suitable for real-time pedestrian event detection.

Description

A kind of road pedestrian event detecting method based on video
Technical field
The invention belongs to the video detection technology field, be specifically related to a kind of road pedestrian event detecting method based on traffic video.
Background technology
Road pedestrian incident is meant that the pedestrian gets under the situation that has no safeguard measure on the car lane, the behavior of jammer motor-car cruising.Though traffic control department takes measures, the situation that the pedestrian swarms into car lane happens occasionally, and particularly in urban transportation, this phenomenon is particularly evident.The danger of this traffic behavior is very big, causes traffic congestion easily, even leads to traffic hazard, makes troubles with dangerous for people's life.Traditional pedestrian's event detecting method mainly contains temperature checking method, electronic coil detection method, digital video detection method.Wherein temperature checking method receives the vehicle interference easily; The electronic coil poor expandability must suspend traffic, destroy the road surface during installation and maintenance, these methods can not be used widely in real life.
Present new project adopts installation more and more, safeguard need not destroy roadbed, surveyed area big, implement convenient, flexible transport information detection technique based on video.Become the focus of research based on the pedestrian detection method of video, existing method mainly contains based on the neural network pedestrian detection, based on template matches detection method of wavelet transformation etc.Though these methods can realize pedestrian's affair alarm, the complex disposal process of video data, poor reliability can not satisfy the real-time requirement of detection, can't satisfy requirement of actual application.
Summary of the invention
Defective or deficiency to prior art the objective of the invention is to, and a kind of road pedestrian event detecting method based on video is provided, and this method can realize in real time all pedestrian's incidents in the range of video, reliable detection.
In order to realize above-mentioned task, the present invention takes following technical solution:
A kind of road pedestrian event detecting method based on video is characterized in that this method is implemented according to the following step:
Step 1 adopts a kind of video camera geometric calibration method, sets up the mapping relations of image pixel actual range to the road surface, i.e. mapping table;
Step 2 all is divided into a plurality of with background image with first two field picture under identical piece coordinate system;
Step 3 to each piece of first two field picture, finds the background piece identical with this piece position in background image, and calculates the absolute value sum of the gray scale difference value of each same pixel position between its corresponding background piece of this piece;
When the absolute value sum of gained greater than preset threshold, then this piece is an object block, and the gray-scale value that inner all pixels of this piece are set is 255;
When the absolute value sum of gained is less than or equal to preset threshold, then this piece is the background piece, and the gray-scale value that inner all pixels of this piece are set is 0;
At last background in first two field picture and target are separated, obtained the binary image of first two field picture;
Step 4, according to from left to right, order from top to bottom is unit scanning with the piece to the binary image of first two field picture; Adjacent object block is labeled as same target; Calculate the height and the width value of each target-marking simultaneously, when value that this value satisfies height over width is in certain threshold range, be object construction body of this target-marking dynamic creation; Write down its border, upper and lower, left and right in this target; Current centre of gravity place and original center of gravity position, coupling lock-on counter information, the coupling lock-on counter is initialized as zero for the first time.
Step 5; Second two field picture is handled according to step 2, step 3 step 4; And be foundation with the centre of gravity place of first frame recording, do comparison with the centre of gravity place of the target of record in second frame, when both centre of gravity place absolute less than certain threshold value; The target of just thinking this first frame is mated in second frame again; With the border, upper and lower, left and right of the target of present frame and the record that current centre of gravity place is replaced first frame, the original center of gravity invariant position matees lock-on counter simultaneously and adds 1;
When not finding the target that to mate, abandon the record of first frame at second frame.
Step 6, to the 3rd two field picture ..., the m two field picture, repeating step two, step 3, step 4 and step 5 are handled;
Step 7; When the coupling lock-on counter of this structure record during greater than certain threshold value; Through the mapping table of setting up in the finding step three, can obtain the corresponding actual road surface distance in current centre of gravity place and original center of gravity position, calculate the displacement of this target; Coupling lock-on counter statistical value is total time frame, can be in the hope of the speed of this target; When the speed of this target is in certain threshold range, can judge that this target is the pedestrian.
Wherein:
Threshold value described in the step 3 is the area of the area～20 * piece of 10 * piece.
Threshold range described in the step 4 is 2～10.
Threshold value under in the step 5 is 5 block lengths.
M described in the step 6 is the natural number of 40≤m≤60.
Coupling lock-on counter threshold value described in the step 7 is 40 frames, and the threshold speed scope is 0.3m/s～2.0m/s.
Road pedestrian event detecting method based on video of the present invention; Compared with prior art, can detect, not receive environmental restraint all pedestrian's targets in the range of video; Can detect real-time video; And detection time is short, be easy to realize, accuracy is higher, is well suited for real-time detection pedestrian incident, has broad application prospects.
Description of drawings
Fig. 1 is first frame video image;
Fig. 2 is together with the field mark synoptic diagram;
Fig. 3 is the first frame binaryzation marking image, and white portion is the binaryzation target-marking of present frame among the figure, and white box is the border of this target-marking;
Fig. 4 is second frame video image;
Fig. 5 is the second frame binaryzation signature, and the white box around this binaryzation target-marking is the border of this target-marking of present frame, and another white box is the border of the first frame flag target;
Fig. 6 is the 20 frame video image;
Fig. 7 is the 40th frame binaryzation signature, and the white box around this binaryzation target-marking is the border of this target-marking of present frame, and all the other white box are the border of past 39 frame flag targets.
Below in conjunction with accompanying drawing and embodiment the present invention is done further detailed description.
Embodiment
Road pedestrian event detecting method based on video of the present invention, in the process handled image be in the video positive seasonal effect in time series first two field picture in edge, second two field picture, the 3rd two field picture ..., m (m is a natural number) two field picture.
The concrete following steps that adopt realize:
Step 1; Adopt a kind of video camera geometric calibration method, take out geometric model, the functional relation that corresponding road surface actual range changes when extrapolating the pixel fragment variation according to the video camera imaging principle; Thereby set up the mapping relations of image pixel actual range, i.e. mapping table to the road surface;
Step 2 all is divided into a plurality of with background image with first two field picture under identical piece coordinate system, promptly first two field picture and background image adopt identical piece coordinate system, and then the piece number T that divided of first two field picture is: T=(W/w) * (H/h); The size that is two field picture is W * H, and the area of piece is w * h;
Wherein W is the pixel of the horizontal direction of image, and H is the pixel of image vertical direction, and w is the width in piece zone, and h is the height of piece.
Step 3, to each piece of first two field picture, in background image, finding identical with this piece position is the identical background piece of coordinate, and calculates the absolute value sum of the gray scale difference value of each same pixel position between its corresponding background piece of this piece;
When the absolute value sum of gained greater than preset threshold, then this piece is an object block, and the gray-scale value that inner all pixels of this piece are set is 255, threshold value span wherein is the area of the area～20 * piece of 10 * piece, promptly 10 * (w * h)～20 * (w * h);
When the absolute value sum of gained is less than or equal to preset threshold, then this piece is the background piece, and the gray-scale value that inner all pixels of this piece are set is 0;
At last background in first two field picture and target are separated, obtained the binary image of first two field picture;
Step 4 is done together with field mark binary image
According to from left to right, order from top to bottom is the unit passing marker first frame binary image with the piece, and adjacent object block is labeled as same target, calculates the height h of each target-marking simultaneously 0With width w 0, as this width and highly satisfied 2≤(h 0/ w 0)≤10 o'clock are that this target-marking is created a target-marking structure, write down the current centre of gravity place (x of this target 1, y 1) and original center of gravity position (x 0, y 0), be coupling lock-on counter of this Target Setting simultaneously, and the coupling lock-on counter is initialized as zero for the first time;
Step 5 is handled according to step 2, step 2 and step 4 second two field picture, and with the centre of gravity place (x of first frame recording 1, y 1) be foundation, with the centre of gravity place (x of the target of record in second frame 2, y 2) do poor, when both centre of gravity place absolute values with satisfy
Figure BDA0000137179830000051
The time, the target of just thinking this first frame flag realizes that again coupling follows the tracks of in second frame, with the centre of gravity place (x of the target of present frame 2, y 2) replacement (x 1, y 1), original center of gravity position (x 0, y 0) constant, mate lock-on counter simultaneously and add 1;
When not finding the target that to mate, abandon the record of first frame at second frame.
Step 6 is to the 3rd two field picture ... The m two field picture is handled according to step 2, step 3, step 4 and step 5;
Step 7 when the coupling lock-on counter of target-marking structure record adds up when equaling 40 frames, is searched mapping table and is obtained current centre of gravity place (x 40, y 40) and original center of gravity position (x 1, y 1) corresponding actual range L1 and L2; Calculate the displacement S=|L1-L2| of this target; Coupling lock-on counter statistical value is 40 frames, and normal video is 25fps, then the average velocity V=S/ (40*1/25) of this target-marking in 40 frames; When the satisfied 0.3≤V of the speed of this target-marking≤2.0 (units: in the time of m/s), can judge that this target is pedestrian's incident.
In conjunction with Fig. 2, to explaining together with field mark in the above-mentioned steps, Far Left and rightmost are respectively image from coordinate and horizontal ordinate among the figure; Two object branches are arranged in the binary image, and according to from left to right, order from top to bottom is block scan one by one to binary image; Adopt 8 together with the territory method of discrimination; The object block that the space is adjacent is labeled as same target, like target-marking a and b among the figure, can obtain height, width and the centre of gravity place information of target-marking through mark; Wherein marking objects b satisfies height over width greater than 2 less than 10 condition, explains that this target-marking possibly be pedestrian's target.
In conjunction with Fig. 3 and Fig. 5; Tracking is explained to the coupling in the above-mentioned steps; White box among Fig. 3 around the binaryzation target-marking is represented the border of the binaryzation target of mark in first two field picture; White box among Fig. 5 around the binaryzation target-marking is represented the binaryzation object boundary of mark in second frame, and the another one white box is the border of the binaryzation target of mark in first two field picture, and the border centre of gravity place of binaryzation target-marking is (x among Fig. 3 1, y 1), the border centre of gravity place of binaryzation target-marking is (x among Fig. 5 2, y 2), when both centre of gravity place satisfies
Figure BDA0000137179830000061
The time, binaryzation target-marking realization coupling among binaryzation target-marking and Fig. 3 in the key diagram 5, both are same target-markings, the centre of gravity place of present frame target-marking is (x 2, y 2), successively at the 3rd frame picture ... Occur target-marking in the m two field picture and seek the coupling target of former frame target-marking, can realize that so the coupling of target is followed the tracks of.
It below is the specific embodiment that the inventor provides.
Embodiment:
Known video positive sowing time, complete the appearing in the 1st two field picture for the first time of pedestrian's target, as shown in Figure 1, Fig. 4 is second two field picture, Fig. 6 is the 40th two field picture.Among the embodiment in the processing procedure SF of video be 25 frame per seconds; The two field picture size is 720 * 288; The size in every zone is 8 * 6; Two field picture is divided into 90 * 48 piece zones, and target area binaryzation segmentation threshold is 576, successively first frame to the, 40 two field pictures is handled according to method of the present invention.
As can beappreciated from fig. 7 the white box among the figure is followed successively by the border of pedestrian's target-marking in first frame to the, 40 frame two field pictures; The white box that wherein comprises the binaryzation target-marking is the border of target-marking in the 40 two field picture; To pedestrian's realization of goal 39 couplings follow the tracks of; Current centre of gravity place through the original center of gravity position that obtains in its first two field picture and the 40 frame obtain can be tried to achieve its average velocity; If average every speed satisfies pedestrian's velocity characteristic, explain that the coupling tracking target is the pedestrian.

Claims (2)

1. the road pedestrian event detecting method based on video is characterized in that, this method realizes through the following step:
Step 1 adopts video camera geometric calibration method, sets up the mapping relations of image pixel actual range to the road surface, i.e. mapping table;
Step 2 all is divided into a plurality of with background image with first two field picture under identical piece coordinate system;
Step 3 to each piece of first two field picture, finds the background piece identical with this piece position in background image, and calculates the absolute value sum of the gray scale difference value of each same pixel position between its corresponding background piece of this piece;
When the absolute value sum of gained greater than preset threshold, then this piece is an object block, and the gray-scale value that inner all pixels of this piece are set is 255;
When the absolute value sum of gained is less than or equal to preset threshold, then this piece is the background piece, and the gray-scale value that inner all pixels of this piece are set is 0;
At last background in first two field picture and target are separated, obtained the binary image of first two field picture;
Step 4, according to from left to right, order from top to bottom is unit scanning with the piece to the binary image of first two field picture; Adjacent object block is labeled as same target; Calculate the height and the width value of each target-marking simultaneously, when value that this value satisfies height over width is in certain threshold range, be object construction body of this target-marking dynamic creation; Write down its border, upper and lower, left and right in this target; Current centre of gravity place and original center of gravity position, coupling lock-on counter information, the coupling lock-on counter is initialized as zero for the first time;
Step 5; Second two field picture is handled according to step 2, step 3 step 4; And be foundation with the centre of gravity place of first frame recording, do comparison with the centre of gravity place of the target of record in second frame, when both centre of gravity place absolute less than certain threshold value; The target of just thinking this first frame is mated in second frame again; With the border, upper and lower, left and right of the target of present frame and the record that current centre of gravity place is replaced first frame, the original center of gravity invariant position matees lock-on counter simultaneously and adds 1;
When not finding the target that to mate, abandon the record of first frame at second frame;
Step 6, to the 3rd two field picture ..., the m two field picture, repeating step two, step 3, step 4 and step 5 are handled;
Step 7; When the coupling lock-on counter of this structure record during greater than certain threshold value; Through the mapping table of setting up in the finding step three, can obtain the corresponding actual road surface distance in current centre of gravity place and original center of gravity position, calculate the displacement of this target; Coupling lock-on counter statistical value is total time frame, tries to achieve the speed of this target; When the speed of this target is in certain threshold range, can judge that this target is the pedestrian.
2. the method for claim 1 is characterized in that:
Threshold value described in the step 3 is the area of the area～20 * piece of 10 * piece;
Threshold range described in the step 4 is 2～10;
Threshold value under in the step 5 is 5 block lengths;
M described in the step 6 is the natural number of 40≤m≤60;
Coupling lock-on counter threshold value described in the step 7 is 40 frames, and the threshold speed scope is 0.3m/s～2.0m/s.
CN201210039553.9A 2012-02-21 2012-02-21 Road pedestrian event detection method based on video Expired - Fee Related CN102622582B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210039553.9A CN102622582B (en) 2012-02-21 2012-02-21 Road pedestrian event detection method based on video

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210039553.9A CN102622582B (en) 2012-02-21 2012-02-21 Road pedestrian event detection method based on video

Publications (2)

Publication Number Publication Date
CN102622582A true CN102622582A (en) 2012-08-01
CN102622582B CN102622582B (en) 2014-04-30

Family

ID=46562492

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210039553.9A Expired - Fee Related CN102622582B (en) 2012-02-21 2012-02-21 Road pedestrian event detection method based on video

Country Status (1)

Country Link
CN (1) CN102622582B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103150550A (en) * 2013-02-05 2013-06-12 长安大学 Road pedestrian event detecting method based on movement trajectory analysis
CN104112118A (en) * 2014-06-26 2014-10-22 大连民族学院 Lane departure early-warning system-based lane line detection method
CN104217419A (en) * 2013-05-31 2014-12-17 三星Sds株式会社 People detection apparatus and method and people counting apparatus and method
TWI656511B (en) * 2017-07-27 2019-04-11 鴻海精密工業股份有限公司 Surveillance method, computing device, and non-transitory storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101388145A (en) * 2008-11-06 2009-03-18 北京汇大通业科技有限公司 Auto alarming method and device for traffic safety
CN101799968A (en) * 2010-01-13 2010-08-11 任芳 Detection method and device for oil well intrusion based on video image intelligent analysis
KR101030257B1 (en) * 2009-02-17 2011-04-22 한남대학교 산학협력단 Method and System for Vision-Based People Counting in CCTV

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101388145A (en) * 2008-11-06 2009-03-18 北京汇大通业科技有限公司 Auto alarming method and device for traffic safety
KR101030257B1 (en) * 2009-02-17 2011-04-22 한남대학교 산학협력단 Method and System for Vision-Based People Counting in CCTV
CN101799968A (en) * 2010-01-13 2010-08-11 任芳 Detection method and device for oil well intrusion based on video image intelligent analysis

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
姚亚夫等: "基于位置特征的运动行人检测与跟踪方法", 《广西大学学报：自然科学版》 *
常好丽等: "基于单目视觉的运动行人检测与跟踪方法", 《交通运输工程学报》 *
胡建华等: "交通监控***中车辆和行人的检测与识别", 《电子测量技术》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103150550A (en) * 2013-02-05 2013-06-12 长安大学 Road pedestrian event detecting method based on movement trajectory analysis
CN103150550B (en) * 2013-02-05 2015-10-28 长安大学 A kind of road pedestrian event detection method based on gripper path analysis
CN104217419A (en) * 2013-05-31 2014-12-17 三星Sds株式会社 People detection apparatus and method and people counting apparatus and method
CN104217419B (en) * 2013-05-31 2018-04-17 三星Sds株式会社 Human body detection device and method and human body counting device and method
CN104112118A (en) * 2014-06-26 2014-10-22 大连民族学院 Lane departure early-warning system-based lane line detection method
CN104112118B (en) * 2014-06-26 2017-09-05 大连民族学院 Method for detecting lane lines for Lane Departure Warning System
TWI656511B (en) * 2017-07-27 2019-04-11 鴻海精密工業股份有限公司 Surveillance method, computing device, and non-transitory storage medium

Also Published As

Publication number Publication date
CN102622582B (en) 2014-04-30

Similar Documents

Publication Publication Date Title
CN102622886B (en) Video-based method for detecting violation lane-changing incident of vehicle
CN103778786B (en) A kind of break in traffic rules and regulations detection method based on remarkable vehicle part model
CN103117005B (en) Lane deviation warning method and system
CN101916383B (en) Vehicle detecting, tracking and identifying system based on multi-camera
CN102867417B (en) Taxi anti-forgery system and taxi anti-forgery method
CN104575003B (en) A kind of vehicle speed detection method based on traffic surveillance videos
CN102915433B (en) Character combination-based license plate positioning and identifying method
CN110379168B (en) Traffic vehicle information acquisition method based on Mask R-CNN
CN103425764B (en) Vehicle matching method based on videos
CN104239867A (en) License plate locating method and system
CN104392224A (en) Crack detection method for road surface
CN101105893A (en) Automobile video frequency discrimination speed-testing method
CN103150550B (en) A kind of road pedestrian event detection method based on gripper path analysis
EP2813973B1 (en) Method and system for processing video image
JP4946175B2 (en) Road boundary detection device and road boundary detection method
CN109828267A (en) The Intelligent Mobile Robot detection of obstacles and distance measuring method of Case-based Reasoning segmentation and depth camera
CN103150908A (en) Average vehicle speed detecting method based on video
CN112084900A (en) Underground garage random parking detection method based on video analysis
CN103164958B (en) Method and system for vehicle monitoring
CN107705577B (en) Real-time detection method and system for calibrating illegal lane change of vehicle based on lane line
Lee et al. Clustering learning model of CCTV image pattern for producing road hazard meteorological information
CN102622582B (en) Road pedestrian event detection method based on video
Nguyen et al. Real-time validation of vision-based over-height vehicle detection system
CN103440785A (en) Method for rapid lane departure warning
Janda et al. Road boundary detection for run-off road prevention based on the fusion of video and radar

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: 20140430

Termination date: 20160221

CF01 Termination of patent right due to non-payment of annual fee