CN103324913B - A kind of pedestrian event detection method of Shape-based interpolation characteristic sum trajectory analysis - Google Patents

Abstract

The invention provides a kind of pedestrian event detection method of Shape-based interpolation characteristic sum trajectory analysis, foreground target is obtained by using the Target Segmentation of background subtraction, block-based method is adopted to mark to the connected domain of same target, record the boundary rectangle of this connected domain simultaneously and extract its geometric characteristic and complete target identification, the angle point of target is extracted after identifying class pedestrian target, utilize corner location information to angle point tracking and matching, repeat said process, the movement locus of target can be obtained, segmentation flex point is asked to this track, linear analysis is done respectively in each segmentation that flex point is formed, asking for of realize target speed, analyze pedestrian's state information of event on this basis, complete traffic safety early warning.Detection method of the present invention is applicable to traffic scene complicated and changeable, and accurately can identify the pedestrian occurred within the scope of monitor video, follow the tracks of and early warning, practical value is high, has broad application prospects.

Description

A kind of pedestrian event detection method of Shape-based interpolation characteristic sum trajectory analysis

Technical field

The invention belongs to field of video detection, be specifically related to a kind of pedestrian event detection method of Shape-based interpolation characteristic sum trajectory analysis.

Background technology

Along with the development that road traffic is built, the contradiction of pedestrian and vehicle is more and more outstanding, causes traffic hazard constantly to occur.Pedestrians disobeying traffic rule event is the major reason causing traffic hazard, such as, make a dash across the red light, jaywalk, swarm into highway etc., therefore the monitoring of pedestrians disobeying traffic rule event is become to a pith of traffic monitoring.Current traffic monitoring is maked an inspection tour mainly through artificial checking monitoring video and road and is realized, and this mode efficiency is low, can not accomplish real-time monitoring, also cause significant wastage to resource.At intelligent transportation field, traditional pedestrian detection method mainly comprises temperature detection, inductive coil detection, sound detection etc.Temperature detection is subject to the interference of the numerous thermal source target of traffic scene, causes flase drop.Inductive coil detection sensitivity is not high, installation is inconvenient, maintainability is poor.Because traffic scene noise is a lot of, Detection accuracy is not high yet for sound detection.

In recent years, based on the detection technique of video because its sensing range is large, can meet real-time, can provide the advantage widespread uses such as a lot of supplementarys.But due to traffic scene more complicated, background and moving target are easily because the factor such as light, weather changes, although there is the method for a lot of pedestrian detection, as based on human parameters model method, pedestrian's affair alarm can be realized based on the method etc. of body local feature, but cannot meet to environmental factor adaptability and obtain in real time, the requirement of traffic detection information accurately.

Summary of the invention

For shortcomings and deficiencies of the prior art, the object of the invention is to, a kind of pedestrian event detection method of Shape-based interpolation characteristic sum trajectory analysis is provided, the method can overcome traffic route scene factor complicated and changeable, realize detecting in real time, accurately to the pedestrian's event in surveyed area, and to its danger classes early warning.

In order to realize above-mentioned task, the present invention adopts following technical scheme to be achieved:

A pedestrian event detection method for Shape-based interpolation characteristic sum trajectory analysis, the method is carried out according to following steps:

Step one, sets up the mapping relations of image pixel to road surface actual range, i.e. mapping table, is divided into by road image in road and curb two parts simultaneously;

Step 2,1st two field picture is all divided into multiple pieces of regions with background image under identical block coordinate system, the size of background is W*H, the block size divided is w*h, the block areal T divided is T=(W/w) * (H/h), subtracts each other, obtain the frame difference image that size is all W*H with current 1st two field picture and background image respective pixel, frame difference image is divided into the block that T size is all w*h, the number of pixels being greater than gray threshold A in a note jth block is N _jif, N _jbe greater than threshold value B, then in this block, all pixel values are composed is 255, otherwise tax is 0, wherein:

W is image level direction number of pixels;

H is image vertical direction number of pixels;

W is the pixel wide of block;

H is the pixels tall of block;

j＝1,2,3...T；

The value of described threshold value A is 30;

The span of described threshold value B is 0.5 ~ 0.75 times of sum of all pixels in block;

Step 3, scans in units of block to binary image from left to right from top to bottom successively, is marked with identical label to the connected domain of same target, obtains the minimum enclosed rectangle of this connected domain simultaneously, calculates the height R of this boundary rectangle _h, width R _w, depth-width ratio R _awith rectangular degree R _j, work as R _avalue within the scope of threshold value C, and R _jvalue within the scope of threshold value D time, retain this target, work as R _aor R _jtime not within the scope of threshold value C and D, remove this target, wherein:

Described threshold value C scope is 1.5 ~ 8;

Described threshold value D scope is 0.5 ~ 1;

Step 4, finds best angle point to the jth foreground target that the 1st two field picture marks, and chooses this target pixel P _icentered by (m, n), setting up a size is the window of a*a, respectively calculated central pixel point P _iin horizontal, longitudinal and two diagonals of (m, n), the quadratic sum of neighbor gray scale difference, gets the minimum value g in its result _minif, g _minbe greater than threshold value E, then this point is angle point, if g _minbe less than or equal to threshold value E, then this point is not angle point and casts out, wherein:

Described a is the pixel wide of the window length of side;

The span of described threshold value E is 180 ~ 220;

Step 5, the positional information of angle point and matched jamming number information are recorded in the structure of a newly-built sky, object matching is followed the tracks of number of times and is initialized as zero;

Step 6, to the second frame, the 3rd frame ..., the i-th two field picture, the method for step 2, step 3 and step 4 of repetition obtains the corner location of target in present frame, then with the corner location of last frame recording for foundation, compare with the corner location of the target of the record in present frame, then have:

When both positions, absolute value difference is greater than threshold value F, just determines that the target at this angle point place in present frame is target new in present frame, then process according to the method for step 5;

When both positions, absolute value difference is less than or equal to threshold value F, then replace the corner location information of former frame as new benchmark foundation by the corner location information of present frame, matched jamming number of times adds 1, wherein:

I is positive integer;

The span of described threshold value F is 1 ~ 5;

Step 7, when matching times is more than or equal to threshold value G, then follows the tracks of complete, obtains pursuit path and is: Track={P _i, P _i+1... P _i+n, perform step 8, wherein:

The span of described threshold value G is 50 ~ 70;

Step 8, searches mapping table, obtains track Track={P _i, P _i+1... P _i+nin actual range corresponding to each angle point, i.e. actual motion track Track ^,={ (s _i, 0), (s _i+1, 1) ..., (s _i+n, n) }, wherein:

S _i+nrepresent pixel P _i+ncorresponding actual range, n represents subscript a little;

Step 9, by actual motion geometric locus first point P _iwith tail point P _i+nobtain the straight-line equation through this straight line of 2: y=kx+b, on this track, any point to the distance of this straight line is:

$d_r=\frac{|k{S}_{i+r}-r+b|}{\sqrt{k^2+1}}$

In formula: k is the slope of straight line, b is intercept, and (x, y) represents any point on this straight line, (s _i+r, r) represent any point on this track, d _rrepresent (s _i+r, r) to the distance of straight line;

To all d _rcarrying out sorts finds out maximum d _maxif be greater than threshold value H, then this point is the flex point of target trajectory, preserves this point (s _i+r, r), perform step 10, wherein:

The value of described threshold value H is 70cm;

Step 10, flex point (s _i+r, r) by path curves segmentation, with (s ₀, 0) and (s _i+r, be r) segment of curve that head and the tail are put, and with point (s _i+r, r) with (s _i+n, be n) segment of curve that head and the tail are put, in these two segment of curve, perform step 9 respectively, continue the flex point asking for each section of track, until all distance between beeline and dot d on this track _rtill during≤H, obtain one group of flex point { (s like this _i+r0, r ₀), (s _i+r1, r ₁) ..., (s _i+rm, r _m);

Step 11, movement locus is divided into path curves section by flex point, uses least square method to carry out linear fit obtain correlation coefficient r, then have each section of path curves section:

When r >=0.5, retain this section of path curves section;

As r < 0.5, remove this section of path curves section;

Finally obtain one group of path curves section;

Step 12, utilize the first point of each path curves section that obtains and the actual range of tail point and mistiming after step 11 screening to ask for segmentation internal object speed v, expression formula is:

$v=\frac{|s_f-s_s|}{\mathrm{N\&Delta;t}}$

In formula:

N represents the interval hop count of tracing point in one section of path curves section;

S _frepresent the tail point actual range of one section of path curves section;

S _srepresent the first point actual range of one section of path curves section;

Δ t represents the time interval of adjacent two tracing points in one section of path curves section;

When the speed in all segmentations all meets 0.3m/s < v < 2m/s, can determine that this target is for pedestrian;

Step 13, according to the coordinate points P of target at present frame _i+nposition judgment pedestrian event danger classes:

(1) as a P _i+nwhen being in road inside, this pedestrian's event danger classes is high;

(2) as a P _i+nwhen being in curb, if the direction of pedestrian movement's track vector and road correctly exercise angular separation be greater than 30 degree, then during this pedestrian's event danger classes is;

(3) as a P _i+nwhen being in curb, if the direction of pedestrian movement's track vector and road correctly exercise angular separation be less than or equal to 30 degree, then this pedestrian's event danger classes is low.

The pedestrian event detection method of Shape-based interpolation characteristic sum trajectory analysis of the present invention, compared with prior art, the feature of the Target Segmentation difficulty that this method causes for the polytrope comparatively far away and pedestrian's attitude of traffic scene monitor video sighting distance, the geometric characteristic of pedestrian is utilized to complete Target Segmentation and preliminary identification in conjunction with background subtraction, and Objective extraction is stablized, single angle point, utilize matching algorithm to obtain target following track.Due to the randomness of pedestrian movement, gained pedestrian track has nonlinear feature, if directly to whole section of geometric locus linear fit, larger error will be had, therefore the present invention adopts the method for segmentation, find flex point to target trajectory curve, geometric locus can be divided into several to have the line segment of linear relationship by these flex points, then uses least square method to carry out linear fit to the line segment between each adjacent comers.After this kind of process, target speed information more accurately can be obtained, improve the accuracy rate of pedestrian's event detection.In addition, the present invention, by calculating and analyzing pedestrian position information and direction of motion, can realize the judgement of pedestrian's event danger classes, complete the function that gives warning in advance.

Accompanying drawing explanation

Fig. 1 is the 1st two field picture.

Fig. 2 is that road zones of different divides, and white represents in road.

Fig. 3 is the class pedestrian that Shape-based interpolation feature identifies, and in figure, white box is target boundary rectangle.

Fig. 4 is target signature point schematic diagram, and wherein white round dot is this clarification of objective angle point.

Fig. 5 is stencil matching searching method, angle point institute black round dot representation feature angle point in the picture, outside stain, little square is template, in image to be searched, dash area is region of search, with template traversal search region in region of search, find the match block making MAD value minimum, as new masterplate, its center is new angle point.

Fig. 6 is target following track schematic diagram in video, and wherein white wire represents the feature angle point movement locus in the picture of pedestrian.

Fig. 7 is target actual motion trajectory diagram, and the position in each moment represents with white round dot, and in figure, horizontal ordinate is the time, and unit is 0.04s; Ordinate is actual range, and unit is cm.

Fig. 8 finds segmentation flex point to actual path curve, and flex point place grey cross marks.

Fig. 9 is the early warning of pedestrian's event danger classes, display pedestrian position and direction of motion, and judges pedestrian's event danger classes.

Below in conjunction with drawings and Examples, content of the present invention is described in further detail.

Embodiment

The present embodiment provides a kind of pedestrian event detection method of Shape-based interpolation characteristic sum trajectory analysis, by using the Target Segmentation of background subtraction, block-based connected component labeling, the target identification based on geometric characteristic, angle point grid, target trajectory is followed the tracks of and the segmentation flex point that seeks trajectory, linear analysis realize target speed must be asked for, complete pedestrian's event state analysis on this basis, complete traffic safety early warning.

It should be noted that, image handled in procedure of the present invention be in video along positive seasonal effect in time series first two field picture, the second two field picture, the 3rd two field picture ..., i-th (i is positive integer) two field picture.

It should be noted that the mapping table in the present embodiment adopts the video camera geometric calibration method described in patent of invention " a kind of video camera geometric calibration method under linear model " (open (bulletin) number: CN102222332A) to obtain.

If the size of each frame video image is W*H, the size of each piece is w*h, and wherein W is the pixel of each frame video image horizontal direction, and H is the pixel of each frame video image vertical direction, and w is the width in each piece of region, and h is the height in each piece of region.

The method of the present embodiment specifically adopts following steps to realize:

Step one, sets up the mapping relations of image pixel to road surface actual range, i.e. mapping table, is divided into by road image in road and curb two parts simultaneously;

Step 2,1st two field picture is all divided into multiple pieces of regions with background image under identical block coordinate system, the size of background is W*H, the block size divided is w*h, the block areal T divided is T=(W/w) * (H/h), subtracts each other, obtain the frame difference image that size is all W*H with current 1st two field picture and background image respective pixel, frame difference image is divided into the block that T size is all w*h, the number of pixels being greater than gray threshold A in a note jth block is N _jif, N _jbe greater than threshold value B, then in this block, all pixel values are composed is 255, otherwise tax is 0, wherein:

W is image level direction number of pixels;

H is image vertical direction number of pixels;

W is the pixel wide of block;

H is the pixels tall of block;

j＝1,2,3...T；

The value of described threshold value A is 30;

The span of described threshold value B is 0.5 ~ 0.75 times of sum of all pixels in block;

Step 3, scans in units of block to binary image from left to right from top to bottom successively, is marked with identical label to the connected domain of same target, obtains the minimum enclosed rectangle of this connected domain simultaneously, calculates the height R of this boundary rectangle _h, width R _w, depth-width ratio R _awith rectangular degree R _j, work as R _avalue within the scope of threshold value C, and R _jvalue within the scope of threshold value D time, retain this target, work as R _aor R _jtime not within the scope of threshold value C and D, remove this target, wherein:

Described threshold value C scope is 1.5 ~ 8;

Described threshold value D scope is 0.5 ~ 1;

Step 4, finds best angle point to the jth foreground target that the 1st two field picture marks, and chooses this target pixel P _icentered by (m, n), setting up a size is the window of a*a, respectively calculated central pixel point P _iin horizontal, longitudinal and two diagonals of (m, n), the quadratic sum of neighbor gray scale difference, gets the minimum value g in its result _minif, g _minbe greater than threshold value E, then this point is angle point, if g _minbe less than or equal to threshold value E, then this point is not angle point and casts out, wherein:

Described a is the pixel wide of the window length of side;

The span of described threshold value E is 180 ~ 220;

Step 5, the positional information of angle point and matched jamming number information are recorded in the structure of a newly-built sky, object matching is followed the tracks of number of times and is initialized as zero;

Step 6, to the second frame, the 3rd frame ..., the i-th two field picture, the method for step 2, step 3 and step 4 of repetition obtains the corner location of target in present frame, then with the corner location of last frame recording for foundation, compare with the corner location of the target of the record in present frame, then have:

When both positions, absolute value difference is greater than threshold value F, just determines that the target at this angle point place in present frame is target new in present frame, then process according to the method for step 5;

When both positions, absolute value difference is less than or equal to threshold value F, then replace the corner location information of former frame as new benchmark foundation by the corner location information of present frame, matched jamming number of times adds 1, wherein:

I is positive integer;

The span of described threshold value F is 1 ~ 5;

Step 7, when matching times is more than or equal to threshold value G, then follows the tracks of complete, obtains pursuit path and is: Track={P _i, P _i+1... P _i+n, perform step 8, wherein:

The span of described threshold value G is 50 ~ 70;

Step 8, searches mapping table, obtains track Track={P _i, P _i+1... P _i+nin actual range corresponding to each angle point, i.e. actual motion track Track '={ (s _i, 0), (s _i+1, 1) ..., (s _i+n, n) }, wherein:

S _i+nrepresent pixel P _i+ncorresponding actual range, n represents subscript a little;

Step 9, by actual motion geometric locus first point P _iwith tail point P _i+nobtain the straight-line equation through this straight line of 2: y=kx+b, on this track, any point to the distance of this straight line is:

$d_r=\frac{|k{S}_{i+r}-r+b|}{\sqrt{k^2+1}}$

In formula: k is the slope of straight line, b is intercept, and (x, y) represents any point on this straight line, (s _i+r, r) represent any point on this track, d _rrepresent (s _i+r, r) to the distance of straight line;

To all d _rcarrying out sorts finds out maximum d _maxif be greater than threshold value H, then this point is the flex point of target trajectory, preserves this point (s _i+r, r), perform step 10, wherein:

The value of described threshold value H is 70cm;

Step 10, flex point (s _i+r, r) by path curves segmentation, with (s ₀, 0) and (s _i+r, be r) segment of curve that head and the tail are put, and with point (s _i+r, r) with (s _i+n, be n) segment of curve that head and the tail are put, in these two segment of curve, perform step 9 respectively, continue the flex point asking for each section of track, until all distance between beeline and dot d on this track _rtill during≤H, obtain one group of flex point { (s like this _i+r0, r ₀), (s _i+r1, r ₁) ..., (s _i+rm, r _m);

Step 11, movement locus is divided into path curves section by flex point, uses least square method to carry out linear fit obtain correlation coefficient r, then have each section of path curves section:

When r >=0.5, retain this section of path curves section;

As r < 0.5, remove this section of path curves section;

Finally obtain one group of path curves section;

Step 12, utilize the first point of each path curves section that obtains and the actual range of tail point and mistiming after step 11 screening to ask for segmentation internal object speed v, expression formula is:

$v=\frac{|s_f-s_s|}{\mathrm{N\&Delta;t}}$

In formula:

N represents the interval hop count of tracing point in one section of path curves section;

S _frepresent the tail point actual range of one section of path curves section;

S _srepresent the first point actual range of one section of path curves section;

Δ t represents the time interval of adjacent two tracing points in one section of path curves section;

When the speed in all segmentations all meets 0.3m/s < v < 2m/s, can determine that this target is for pedestrian;

Step 13, according to the coordinate points P of target at present frame _i+nposition judgment pedestrian event danger classes:

(2) as a P _i+nwhen being in road inside, this pedestrian's event danger classes is high;

(2) as a P _i+nwhen being in curb, if the direction of pedestrian movement's track vector and road correctly exercise angular separation be greater than 30 degree, then during this pedestrian's event danger classes is;

(3) as a P _i+nwhen being in curb, if the direction of pedestrian movement's track vector and road correctly exercise angular separation be less than or equal to 30 degree, then this pedestrian's event danger classes is low.

Below provide specific embodiments of the invention, it should be noted that the present invention is not limited to following specific embodiment, all equivalents done on technical scheme basis all fall into protection scope of the present invention.

Embodiment:

In the processing procedure of the present embodiment, the sample frequency of video is that 25 frames are per second, every two field picture size is 720 × 288, the block size that frame difference image carries out block process is 8 × 6, image be divide into 90 × 48 block regions, gray threshold A when carrying out background subtraction is 30, threshold value B is 36, the scope meeting the length breadth ratio threshold value C of pedestrian's feature is 1.5 ~ 8, rectangular degree threshold value D scope is 0.5 ~ 1, the value choosing the threshold value E of angle point is 180 ~ 220, the threshold value F of corners Matching distance is 3, corners Matching frequency threshold value G gets 50, to actual motion track find segmentation flex point time judging distance threshold value H get 70cm, as shown in Figures 1 to 9, use said method from the first frame, to defer to said method successively to process video image.

In figure, white wire is pedestrian movement's track as can be seen from Figure 6, and when video image runs to the 51st frame, corners Matching number of times reaches 50 times, therefore trajectory is ended from the 1st frame to the 51st frame.The lower end of this track enters scene, the characteristic point position found for pedestrian first time, puts the unique point for finding at the 50th frame topmost.

Fig. 7 is the actual range curve map that target following track is corresponding, and use the method in step 9 and step 10 to ask for flex point to this geometric locus, as shown in Figure 8, flex point place cross symbol is marked result.Then adopt least square method to the track fitting in each segmentation, the actual motion speed 0.71m/s of pedestrian can be tried to achieve, so can judge that this target is as pedestrian.Now according to position and the direction of this pedestrian, judge the danger classes that this pedestrian's event causes traffic safety to realize traffic safety early warning.

Claims (1)

1. a pedestrian event detection method for Shape-based interpolation characteristic sum trajectory analysis, is characterized in that, the method is carried out according to following steps:

Step one, sets up the mapping relations of image pixel to road surface actual range, i.e. mapping table, is divided into by road image in road and curb two parts simultaneously;

Step 2,1st two field picture is all divided into multiple pieces of regions with background image under identical block coordinate system, the size of background is W*H, the block size divided is w*h, the block areal T divided is T=(W/w) * (H/h), subtracts each other, obtain the frame difference image that size is all W*H with current 1st two field picture and background image respective pixel, frame difference image is divided into the block that T size is all w*h, the number of pixels being greater than gray threshold A in a note jth block is N _jif, N _jbe greater than threshold value B, then in this block, all pixel values are composed is 255, otherwise tax is 0, wherein:

W is image level direction number of pixels;

H is image vertical direction number of pixels;

W is the pixel wide of block;

H is the pixels tall of block;

j＝1,2,3...T；

The value of described threshold value A is 30;

The span of described threshold value B is 0.5 ~ 0.75 times of sum of all pixels in block;

Step 3, scans in units of block to binary image from left to right from top to bottom successively, is marked with identical label to the connected domain of same target, obtains the minimum enclosed rectangle of this connected domain simultaneously, calculates the height R of this boundary rectangle _h, width R _w, depth-width ratio R _awith rectangular degree R _j, work as R _avalue within the scope of threshold value C, and R _jvalue within the scope of threshold value D time, retain this target, work as R _aor R _jtime not within the scope of threshold value C and D, remove this target, wherein:

Described threshold value C scope is 1.5 ~ 8;

Described threshold value D scope is 0.5 ~ 1;

Step 4, finds best angle point to the jth foreground target that the 1st two field picture marks, and chooses this target pixel P _icentered by (m, n), setting up a size is the window of a*a, respectively calculated central pixel point P _iin horizontal, longitudinal and two diagonals of (m, n), the quadratic sum of neighbor gray scale difference, gets the minimum value g in its result _minif, the g of certain point in window _minbe greater than threshold value E, then this point in window is angle point, if g _minbe less than or equal to threshold value E, then this point is not angle point and casts out, wherein:

Described a is the pixel wide of the window length of side;

The span of described threshold value E is 180 ~ 220;

Step 5, the positional information of angle point and matched jamming number information are recorded in the structure of a newly-built sky, object matching is followed the tracks of number of times and is initialized as zero;

Step 6, to the second frame, the 3rd frame ..., the i-th two field picture, the method for step 2, step 3 and step 4 of repetition obtains the corner location of target in present frame, then with the corner location of last frame recording for foundation, compare with the corner location of the target of the record in present frame, then have:

When both positions, absolute value difference is greater than threshold value F, just determines that the target at this angle point place in present frame is target new in present frame, then process according to the method for step 5;

When both positions, absolute value difference is less than or equal to threshold value F, then replace the corner location information of former frame as new benchmark foundation by the corner location information of present frame, matched jamming number of times adds 1, wherein:

I is positive integer;

The span of described threshold value F is 1 ~ 5;

Step 7, when matching times is more than or equal to threshold value G, then follows the tracks of complete, obtains pursuit path and is: Track={P _i, P _i+1... P _i+n, perform step 8, wherein:

The span of described threshold value G is 50 ~ 70;

Step 8, searches mapping table, obtains track Track={P _i, P _i+1... P _i+nin actual range corresponding to each angle point, i.e. actual motion track Track '={ (s _i, 0), (s _i+1, 1) ..., (s _i+n, n) }, wherein:

S _i+nrepresent pixel P _i+ncorresponding actual range, n represents subscript a little;

Step 9, by actual motion geometric locus first point P _iwith tail point P _i+nobtain the straight-line equation through this straight line of 2: y=kx+b, on this track, any point to the distance of this straight line is:

$d_r=\frac{|{\mathrm{kS}}_{i+r}-r+b|}{\sqrt{k^2+1}}$

In formula: k is the slope of straight line, b is intercept, and (x, y) represents any point on this straight line, (s _i+r, r) represent any point on this track, d _rrepresent (s _i+r, r) to the distance of straight line;

To all d _rcarrying out sorts finds out maximum d _maxif be greater than threshold value H, then this point on actual motion geometric locus is the flex point of target trajectory, preserves this point (s _i+r, r), perform step 10, wherein:

The value of described threshold value H is 70cm;

Step 10, flex point (s _i+r, r) by path curves segmentation, with (s ₀, 0) and (s _i+r, be r) segment of curve that head and the tail are put, and with point (s _i+r, r) with (s _i+n, be n) segment of curve that head and the tail are put, in these two segment of curve, perform step 9 respectively, continue the flex point asking for each section of track, until all distance between beeline and dot d on this track _rtill during≤H, H is threshold value, and the value of described threshold value H is 70cm, obtains one group of flex point { (s like this _i+r0, r ₀), (s _i+r1, r ₁) ..., (s _i+rm, r _m);

Step 11, movement locus is divided into path curves section by flex point, uses least square method to carry out linear fit obtain correlation coefficient r, then have each section of path curves section:

When r >=0.5, retain this section of path curves section;

As r < 0.5, remove this section of path curves section;

Finally obtain one group of path curves section;

Step 12, utilize the first point of each path curves section that obtains and the actual range of tail point and mistiming after step 11 screening to ask for segmentation internal object speed v, expression formula is:

$v=\frac{|s_f-s_s|}{N\mathrm{\&Delta;}t}$

In formula:

N represents the interval hop count of tracing point in one section of path curves section;

S _frepresent the tail point actual range of one section of path curves section;

S _srepresent the first point actual range of one section of path curves section;

Δ t represents the time interval of adjacent two tracing points in one section of path curves section;

When the speed in all segmentations all meets 0.3m/s < v < 2m/s, can determine that this target is for pedestrian;

Step 13, according to the coordinate points P of target at present frame _i+nposition judgment pedestrian event danger classes:

(1) as a P _i+nwhen being in road inside, this pedestrian's event danger classes is high;

(2) as a P _i+nwhen being in curb, if the direction of pedestrian movement's track vector and road correctly exercise angular separation be greater than 30 degree, then during this pedestrian's event danger classes is;

(3) as a P _i+nwhen being in curb, if the direction of pedestrian movement's track vector and road correctly exercise angular separation be less than or equal to 30 degree, then this pedestrian's event danger classes is low.