CN104331910A - Track obstacle detection system based on machine vision - Google Patents

Abstract

The invention discloses a track obstacle detection system based on machine vision, and belongs to the field of railway safety. Black and white video images are obtained by an on-board camera installed at the head of a train, and the track is similarly linear or bent is judged according to that whether the camera is over travel. Manual detection of bend states is achieved by fixing a high definition camera and a wireless transmitting device at a bend for receiving wireless images. A similar straightway analyzes the obtained real-time image sequence, and divides forward obstacles into a non-dangerous class (including static small obstacles, moving objects quickly crossing the track) and a dangerous class (static large obstacles, moving obstacles influencing pass of the train) by adopting a track edge extraction algorithm based on hood conversion and Otsu threshold value, combining an inter-frame difference method based on mathematical morphology improvement with a background difference method and adopting an angular point feature matching tracking algorithm. The track obstacle detection system based on machine vision can quickly process track images, more effectively and accurately extract track edges, and is high in detection precision of track obstacles.

Description

A kind of track obstacle detection system based on machine vision

Technical field

The invention belongs to railway security field, be specifically related to a kind of track obstacle detection system based on machine vision.

Background technology

In recent years, along with train raising speed by a large scale, the change of train operation pattern, passenger-cargo freight volume significantly improves, and has higher requirement to the safety and reliability of transportation by railroad.In track obstacle research, although the product of comparative maturity has been had external at present, but the design concept of most products is all the signal by sending certain form to orientation to be detected (mainly comprises laser, radar, magnetic induction, ultrasound wave etc.), and analysis detects and the signal reflected, as the foundation judging cognitive disorders thing through sensor.In these detection methods, ultrasound wave is such as utilized to carry out railway track detection, the position identifying target obstacle can be detected more exactly, but still exist comparatively large for volume and to have the target obstacle Detection results of certain altitude better, there will be the problem of undetected flat little barrier; Laser and detections of radar have the shortcoming that spatial coverage is limited and resolution is not high.Meanwhile, these class methods belong to infringement formula and detect, and inevitably increase neighbourhood noise, and also can produce interference between sensor.These shortcoming and defect, none can not affect barrier detection and Identification accurately and effectively.

China's patent of invention, publication number is " locomotive ground signal and the barrier automatic recognition system " of CN201825066U, proposition car body is installed electronic image recognition system, analyzes the figure run on forward box.Judged the colour light signal on figure, switch location and track switch open and-shut mode, blind siding soil shelves and standing car by system identification, remind driver or control locomotive Braking mode and carry out Accident prevention generation.But said system also just has good result for the detection of indivedual predetermined substance, automatically detect identify train operation ahead pedestrian, falling rocks and vehicle field in, still cannot play its effect.

Summary of the invention

The present invention is directed to the deficiencies in the prior art and shortcoming, provide a kind of track obstacle detection system based on machine vision, it can fast processing orbital image, and rail flanges is extracted more accurate, higher to the accuracy of track detection of obstacles.

The technical scheme that the present invention proposes is a kind of track obstacle detection system based on machine vision, and obtain black and white video image by the vehicle-mounted vidicon being arranged on train head, according to car, at video camera, whether the excess of stroke judges that track is class straight way or bend.Bend adopts fixing high-definition camera and wireless launcher to receive wireless image and realizes manual detection bend situation.The real-time image sequences got is analyzed by class straight way, adopt the rail flanges extraction algorithm based on top cap conversion and Otsu threshold value, the frame differential method improved based on mathematical morphology combines and Corner Feature Matching pursuitalgorithm with background subtraction, is divided into by preceding object thing in real time without dangerous (static the small-scale obstacle thing, fast across the moving obstacle of track) and danger (static large obstacle, affect the moving obstacle that train passes through) two classes.Circulating a notice of to driver and conductor by detecting the rear result analyzing identification, reaching the object effectively avoiding judging by accident or traffic hazard occurs.Concrete steps are as follows:

1, realtime graphic is gathered

Adopt the B/W camera of monocular-camera mode, optical anti-vibration, super focal length far away, real-time image acquisition sequence in train traveling process.

2, classification of track is judged

When the vehicle-mounted vidicon excess of stroke, be judged as bend (wide-angle turning track, right angle track); Then adopt fixing high-definition camera and wireless launcher to receive wireless image and realize manual detection bend track condition;

If when vehicle-mounted vidicon does not have an excess of stroke, be then judged to be class straight way (rectilinear orbit, little radian turning track), continue to adopt vehicle-mounted vidicon to obtain realtime graphic, enter next step process image.

3, Image semantic classification

First, image is done and strengthens process, adopt diameter be 4 " diamond " structural element do top cap computing, image X is designated as X ° of B about the top cap computing of structural element B, is defined as highlight double track part, the highlighted part of Background suppression;

Then, Otsu threshold calculations optimal threshold T is adopted to the image after strengthening, by image binaryzation, obtains bianry image; Image after Threshold segmentation comprises multiple discontinuity zone;

Finally, check that in discontinuity zone, each pixel is adjacent the connectedness of pixel, marker extraction region, retains double track characteristic straight line by connected component labeling.

4, detection window is set up

Retain double track characteristic straight line according to connected component labeling, utilize fitting a straight line, adopt least square method to realize extracting edge local to track, by two rail linear, obtain straight-line equation; With the position of the particular location determination detection window window of rail, size and dimension, rail portion is confined within the scope of it by detection window.

5, barrier has been judged whether

Got rid of the feature of background based on image in class straight way track rule unchangeability and detection window, can ignore orbital motion, when there being suspicious barrier intrusion detection window, characteristics of image will certainly be caused to change, and this method chooses histogram feature.

Define threshold value T based on experience value ₁and T ₂for differentiating histogram variances variation delta σ _k ²with the value changing condition of histogram burr number BurrNum, by two-value monochrome pixels ratio r ati o, Δ σ _k ²with the monitoring of BurrNum tri-parameters, determining whether barrier invasion may.Algorithm is as follows:

Histogram average: $\stackrel{\‾}{r_k}=\underset{r_k=0}{\overset{L-1}{\mathrm{\Σ}}}{r}_k{p}_k\left(r_k\right)$

(wherein r _kfor histogram feature data, p _kprobability corresponding to it, L is the number of characteristic)

Histogram variances: ${\mathrm{\σ}}_k^2=\underset{r_k=0}{\overset{L-1}{\mathrm{\Σ}}}{(r_k-\stackrel{\‾}{r_k})}^2{p}_k\left(r_k\right)$

Two-value monochrome pixels ratio:

(n _bfor the quantity of black pixel, n _kquantity for white pixel)

From significance level and fiduciary level, ratio n _b/ n _kmore directly perceived, more can show actual conditions, therefore enumerate basis for estimation:

(1) during ratio<4.5, no matter Δ σ _k ²with the value of BurrNum how, all judge there is invasion barrier;

(2) during ratio>4.5, then Δ σ is observed _k ²how to change with the value of BurrNum, if both exceed threshold value, then judge there is invasion barrier;

(3) during ratio>4.5, and Δ σ _k ²all do not exceed threshold value with the value of BurrNum or one of them exceeds threshold value, then judging do not have barrier, may be the impact of the external interference such as illumination condition.

If there is no barrier, then return and start anew; If there is barrier, then carry out next step.

6, detection of obstacles

Stationary obstruction also has relative motion to train, so differentiate static or moving obstacle by movement locus and motion feature.

Adopt the frame differential method improved through mathematical morphology, calculus of differences is carried out to the image in detection window, extract segmentation moving target; Frame differential method is exactly in sequence of video images, extracts adjacent two frame three frame or multiple images, and carries out to the two field picture extracted the image operation that pixel subtracts each other.If the difference of neighbor is less than the threshold value of setting, then think that this pixel is static background, otherwise, then extract this pixel as moving target, according to this principle, all pixels meeting moving target threshold value to be joined together the moving target that just can extract in scene, and remove jamming pattern, reach with this object extracting segmentation moving target.

Frame differential method principle is as follows:

D _k(x,y)＝|F _k(x,y)-F _k-1(x,y)|

F _k(x, y) represents continuous print image in video, D _k(x, y) represents the error image that two continuous frames image subtraction obtains, then by D _k(x, y) does following process:

$R_k(x,y)=\left\{\begin{array}{cc}1& D_k(x,y)>P\\ 0& D_k(x,y)<P\end{array}\right.$ (P is setting threshold value, and simulation obtains repeatedly by experiment)

R _k(x, y) is for judge the foundation whether target moves: if 1, then target discrimination is motion; Otherwise, for static.

Meanwhile, utilize background subtraction, the detected image in detection window and background image are carried out difference, then detects moving region by threshold value.If b (x, y) is background image, definition image sequence f (x, y, i), wherein (x, y) is image position coordinates, and i is number of image frames.The gray-scale value of the gray-scale value subtracting background of each two field picture is obtained error image:

id(x,y,i)＝f(x,y,i)-b(x,y)

A binaryzation difference image can be obtained by arranging threshold value T:

(threshold value T simulates by experiment and obtains)

Finally, pixel is carried out to the image of two kinds of algorithm gained and gets common factor, more accurately target is extracted, obtain the size of target, the shape facility of target.

7, the identification of barrier and classification

Corner Feature Matching pursuitalgorithm is adopted to carry out barrier size, speed and direction discernment, feature extraction adopts Harris Corner Detection Algorithm, it is a kind of interest point detect operator based on signal, in this method, the point enough large with adjoint point brightness contrast (intensity contrast of pixel neighborhoods point) is defined as angle point.

Pixel related function used is as follows:

$E(x,y)=\underset{u,v}{\mathrm{\&Sigma;}}w(u,v){[I(x+u,x+v)-I(x,y)]}^2=[u,v]M\left[\begin{array}{c}u\\ v\end{array}\right]$

$M=\underset{u,v}{\mathrm{\&Sigma;}}w(u,v)\left[\begin{array}{cc}{I}_x^2& I_x{I}_y\\ I_x{I}_y& I_y^2\end{array}\right]$

Wherein, w is the smoothing windows of carrying out noise reduction process, and (u, v) is offset coordinates, and I is the pixel value of image pixel matrix, I (x, y) value image mid point (x, y).I _xand I _ythe respectively single order partial differential of representative image pixel in the horizontal direction, in vertical direction, I _x ²and I _y ²then be respectively the second order Grad in both direction.Then the angle point in image just can be detected by calculating angle point response function:

R＝det(M)-k*tr ²(M)

Wherein, tr (M) and det (M) represents mark and the determinant of matrix M respectively, and Harris Corner Detection Algorithm recommends k to get 0.04.

Characteristic matching adopts based on the relevant Feature Points Matching algorithm of gray scale, is extracted as example with three frames:

First, for each unique point p _i∈ E ₁, p _j∈ E ₃, respectively centered by unique point, the window of structure N × N size, is designated as W respectively _i, W _j, then calculate the related function of each window respectively

$C_{\mathrm{cor}}(i,j)=\frac{\underset{n=1}{\overset{N\&times;N}{\mathrm{\&Sigma;}}}\left(W_i{W}_j\right)}{\underset{n=1}{\overset{N\&times;N}{\mathrm{\&Sigma;}}}{W}_i\underset{n=1}{\overset{N\&times;N}{\mathrm{\&Sigma;}}}{W}_j}$

Can according to C _corthe value of (i, j) can judge the correlation of individual features point, and this value is larger, and corresponding unique point neighborhood gray scale is more close.In the process of looking for match point, the mode of mutually coupling is adopted to mate, namely when the optimal match point of the unique point pi in E1 is the p in E3 _i, p simultaneously _joptimal match point be also p _itime, just think (p _ip _j) be a pair optimum matching unique point.Obtain final corners Matching result accordingly.

The type of preceding object thing is judged, for without dangerous (static the small-scale obstacle thing, fast across the moving obstacle of track) or dangerous (static large obstacle, affect the moving obstacle that train passes through) with this.

The present invention has following beneficial effect compared with existing system:

Because algorithm is relatively simple, complexity reduces, shorten the processing time, can fast processing orbital image; Rail flanges extraction algorithm based on top cap conversion and Otsu threshold value more effectively can extract rail flanges more accurately; Adopt and carry out target detection based on the mixed method of morphological transformation, effectively improve the shortcoming of frame difference method adjoint much noise and breakpoint because of the limitation chosen in the time interval, frame difference method result is had to the effect of denoising and horizontal sliding wheel exterior feature, overcome background subtraction judge object by quiet to dynamic moving time, there is " ghost " defect, optimize the effect of moving object detection; So also higher to the accuracy of track detection of obstacles.

Accompanying drawing explanation

In order to be illustrated more clearly in the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, to those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.

Fig. 1 is straight way of the present invention, class straight way systems axiol-ogy process flow diagram;

Fig. 2 is bend system framework process flow diagram of the present invention;

Fig. 3 is bend monitoring model schematic diagram;

Fig. 4 is that straight way, class straight way are static, moving obstacle skimulated motion track schematic diagram;

Fig. 5 frame differential method and mathematical morphology blending algorithm block diagram;

Fig. 6 moving object detection algorithm block diagram.

Embodiment

Referring to Fig. 1-Fig. 6, a kind of track obstacle detection system based on machine vision, this system obtains black and white video image by the vehicle-mounted vidicon being arranged on train head, judges that track is class straight way or bend.Bend adopts fixing high-definition camera and wireless launcher to receive wireless image and realizes manual detection bend situation.The real-time image sequences got is analyzed by class straight way, adopt the rail flanges extraction algorithm based on top cap conversion and Otsu threshold value, the frame differential method improved based on mathematical morphology combines and Corner Feature Matching pursuitalgorithm with background subtraction, is divided into by preceding object thing in real time without dangerous (static the small-scale obstacle thing, fast across the moving obstacle of track) and danger (static large obstacle, affect the moving obstacle that train passes through) two classes.Circulating a notice of to driver and conductor by detecting the rear result analyzing identification, reaching the object effectively avoiding judging by accident or traffic hazard occurs.Concrete steps are as follows:

1, realtime graphic is gathered

Adopt the B/W camera of monocular-camera mode, optical anti-vibration, super focal length far away, real-time image acquisition sequence in train traveling process.Adopt grand electric H3225A-K-G MDVR car video recorder in the present embodiment, there is optical anti-vibration, the B/W camera of super focal length far away can apply.The image memory device gathered is vehicle-mounted industrial computer: the safe two 19 cun of panel computer P1903 of Beijing China.

2, classification of track is judged

When the vehicle-mounted vidicon excess of stroke, be judged as bend (wide-angle turning track, right angle track); Then adopt fixing high-definition camera and wireless launcher to receive wireless image and realize manual detection bend track condition, referring to figs. 2 and 3; Fix high-definition camera in the present embodiment and adopt bend high-definition probe, brand Ansky model Ask-3510-67, wireless launcher adopts radio transmission device: technical grade wireless simulation amount Signal transmissions DTD110FC.Bend high-definition probe fixed position can be other position except Fig. 3.

If when vehicle-mounted vidicon does not have an excess of stroke, then be judged to be class straight way (rectilinear orbit, little radian turning track), continue to adopt vehicle-mounted vidicon to obtain realtime graphic, enter next step, adopt vehicle-mounted industrial computer: the safe two 19 cun of panel computer P1903 process images of Beijing China.

3, Image semantic classification

First, image is done and strengthens process, adopt diameter be 4 " diamond " structural element do top cap computing, image X is designated as X ° of B about the top cap computing of structural element B, is defined as highlight double track part, the highlighted part of Background suppression;

Then, Otsu threshold calculations optimal threshold T is adopted to the image after strengthening, by image binaryzation, obtains bianry image; Image after Threshold segmentation comprises multiple discontinuity zone;

Finally, check that in discontinuity zone, each pixel is adjacent the connectedness of pixel, marker extraction region, retains double track characteristic straight line by connected component labeling.

4, detection window is set up

Retain double track characteristic straight line according to connected component labeling, utilize fitting a straight line, adopt least square method to realize extracting edge local to track, by two rail linear, obtain straight-line equation; With the position of the particular location determination detection window window of rail, size and dimension, rail portion is confined within the scope of it by detection window.

5, barrier has been judged whether

Got rid of the feature of background based on image in class straight way track rule unchangeability and detection window, can ignore orbital motion, when there being suspicious barrier intrusion detection window, characteristics of image will certainly be caused to change, and this step chooses histogram feature

Define threshold value T based on experience value ₁and T ₂for differentiating histogram variances variation delta σ _k ²with the value changing condition of histogram burr number BurrNum, by two-value monochrome pixels ratio r ati o, Δ σ _k ²with the monitoring of BurrNum tri-parameters, determining whether barrier invasion may.Algorithm is as follows:

Histogram average: $\stackrel{\&OverBar;}{r_k}=\underset{r_k=0}{\overset{L-1}{\mathrm{\&Sigma;}}}{r}_k{p}_k\left(r_k\right)$

(wherein r _kfor histogram feature data, p _kprobability corresponding to it, L is the number of characteristic)

Histogram variances: ${\mathrm{\&sigma;}}_k^2=\underset{r_k=0}{\overset{L-1}{\mathrm{\&Sigma;}}}{(r_k-\stackrel{\&OverBar;}{r_k})}^2{p}_k\left(r_k\right)$

Two-value monochrome pixels ratio:

(n _bfor the quantity of black pixel, n _kquantity for white pixel)

From significance level and fiduciary level, ratio n _b/ n _kmore directly perceived, more can show actual conditions, therefore enumerate basis for estimation:

(1) during ratio<4.5, no matter Δ σ _k ²with the value of BurrNum how, all judge there is invasion barrier;

(2) during ratio>4.5, then Δ σ is observed _k ²how to change with the value of BurrNum, if both exceed threshold value, then judge there is invasion barrier;

(3) during ratio>4.5, and Δ σ _k ²all do not exceed threshold value with the value of BurrNum or one of them exceeds threshold value, then judging do not have barrier, may be the impact of the external interference such as illumination condition.

If there is no barrier, then return and start anew; If there is barrier, then carry out next step.

6, detection of obstacles

Stationary obstruction also has relative motion to train, so differentiate static or moving obstacle by movement locus and motion feature.With reference to figure 3.

With reference to figure 5, adopt the frame differential method improved through mathematical morphology, calculus of differences is carried out to the image in detection window, extract segmentation moving target; Frame differential method is exactly in sequence of video images, extracts adjacent two frame three frame or multiple images, and carries out to the two field picture extracted the image operation that pixel subtracts each other.If the difference of neighbor is less than the threshold value of setting, then think that this pixel is static background, otherwise, then extract this pixel as moving target, according to this principle, all pixels meeting moving target threshold value to be joined together the moving target that just can extract in scene, and remove jamming pattern, reach with this object extracting segmentation moving target.

Frame differential method principle is as follows:

D _k(x,y)＝|F _k(x,y)-F _k-1(x,y)|

F _k(x, y) represents continuous print image in video, D _k(x, y) represents the error image that two continuous frames image subtraction obtains, then by D _k(x, y) does following process:

$R_k(x,y)=\left\{\begin{array}{cc}1& D_k(x,y)>P\\ 0& D_k(x,y)<P\end{array}\right.$ (P is setting threshold value, and simulation obtains repeatedly by experiment)

R _k(x, y) is for judge the foundation whether target moves: if 1, then target discrimination is motion; Otherwise, for static.

Meanwhile, with reference to figure 6, utilize background subtraction, the detected image in detection window and background image are carried out difference, then detects moving region by threshold value.If b (x, y) is background image, definition image sequence f (x, y, i), wherein (x, y) is image position coordinates, and i is number of image frames.The gray-scale value of the gray-scale value subtracting background of each two field picture is obtained error image:

id(x,y,i)＝f(x,y,i)-b(x,y)

A binaryzation difference image can be obtained by arranging threshold value T:

(threshold value T simulates by experiment and obtains)

Finally, pixel is carried out to the image of two kinds of algorithm gained and gets common factor, more accurately target is extracted, obtain the size of target, the shape facility of target.

7, the identification of barrier and classification

Corner Feature Matching pursuitalgorithm is adopted to carry out barrier size, speed and direction discernment, feature extraction adopts Harris Corner Detection Algorithm, it is a kind of interest point detect operator based on signal, in this method, the point enough large with adjoint point brightness contrast (intensity contrast of pixel neighborhoods point) is defined as angle point, and pixel related function used is as follows:

$E(x,y)=\underset{u,v}{\mathrm{\&Sigma;}}w(u,v){[I(x+u,x+v)-I(x,y)]}^2=[u,v]M\left[\begin{array}{c}u\\ v\end{array}\right]$

$M=\underset{u,v}{\mathrm{\&Sigma;}}w(u,v)\left[\begin{array}{cc}{I}_x^2& I_x{I}_y\\ I_x{I}_y& I_y^2\end{array}\right]$

Wherein, w is the smoothing windows of carrying out noise reduction process, and (u, v) is offset coordinates, and I is the pixel value of image pixel matrix, I (x, y) value image mid point (x, y).I _xand I _ythe respectively single order partial differential of representative image pixel in the horizontal direction, in vertical direction, I _x ²and I _y ²then be respectively the second order Grad in both direction.Then the angle point in image just can be detected by calculating angle point response function:

R＝det(M)-k*tr ²(M)

Wherein, tr (M) and det (M) represents mark and the determinant of matrix M respectively, and Harris Corner Detection Algorithm recommends k to get 0.04.

Characteristic matching adopts based on the relevant Feature Points Matching algorithm of gray scale, is extracted as example with three frames:

First, for each unique point p _i∈ E ₁, p _j∈ E ₃, respectively centered by unique point, the window of structure N × N size, is designated as W respectively _i, W _j, then calculate the related function of each window respectively

$C_{\mathrm{cor}}(i,j)=\frac{\underset{n=1}{\overset{N\&times;N}{\mathrm{\&Sigma;}}}\left(W_i{W}_j\right)}{\underset{n=1}{\overset{N\&times;N}{\mathrm{\&Sigma;}}}{W}_i\underset{n=1}{\overset{N\&times;N}{\mathrm{\&Sigma;}}}{W}_j}$

Can according to C _corthe value of (i, j) can judge the correlation of individual features point, and this value is larger, and corresponding unique point neighborhood gray scale is more close.In the process of looking for match point, the mode of mutually coupling is adopted to mate, namely when the optimal match point of the unique point pi in E1 is the p in E3 _i, p simultaneously _joptimal match point be also p _itime, just think (p _ip _j) be a pair optimum matching unique point.Obtain final corners Matching result accordingly.

The type of preceding object thing is judged, for without dangerous (static the small-scale obstacle thing, fast across the moving obstacle of track) or dangerous (static large obstacle, affect the moving obstacle that train passes through) with this.According to detection recognition result adjustment train operation.

Claims (6)

1., based on a track obstacle detection system for machine vision, it is characterized in that: concrete steps are as follows:

Step 1: gather realtime graphic: obtain black and white video image by the vehicle-mounted vidicon being arranged on train head, adopt the B/W camera of monocular-camera mode, optical anti-vibration, super focal length far away;

Step 2: judge classification of track: whether the excess of stroke judges that track is class straight way or bend according to vehicle-mounted vidicon; Bend track adopts fixing high-definition camera and wireless launcher to receive wireless image and realizes manual detection bend situation; Class straight way track enters step 3;

Step 3: Image semantic classification: the real-time image sequences got is analyzed by class straight way, adopts the rail flanges extraction algorithm based on top cap conversion and Otsu threshold value, obtains track double track characteristic straight line;

Step 4: set up detection window: utilize fitting a straight line, adopts least square method to extract edge local to track, by rail linear, obtains straight-line equation; With rail concrete till determine detection window, rail is confined within the scope of it by detection window;

Step 5: judged whether barrier: based on histogram feature change in detection window, define threshold value T based on experience value ₁and T ₂for differentiating histogram variances variation delta σ _k ²with the value changing condition of histogram burr number BurrNum, by two-value monochrome pixels ratio r atio, Δ σ _k ²with the monitoring of BurrNum tri-parameters, determining whether barrier invasion may;

Step 6: detection of obstacles: the frame differential method improved based on mathematical morphology combines with background subtraction, extracts, obtain the size of barrier, shape facility to barrier feature;

Step 7: the identification of barrier and classification: adopt Corner Feature Matching pursuitalgorithm to carry out barrier speed and direction discernment, is divided into preceding object thing in real time without dangerous (static the small-scale obstacle thing, fast across the moving obstacle of track) and danger (static large obstacle, affect the moving obstacle that train passes through) two classes.

2. a kind of track obstacle detection system based on machine vision according to claim 1, it is characterized in that, the detailed process of step 3 is as follows:

First, image is done and strengthens process, adopt diameter be 4 " diamond " structural element do top cap computing, image X is designated as X ° of B about the top cap computing of structural element B, is defined as highlight double track part, the highlighted part of Background suppression;

Then, Otsu threshold calculations optimal threshold T is adopted to the image after strengthening, by image binaryzation, obtains bianry image; Image after Threshold segmentation comprises multiple discontinuity zone;

Finally, check that in discontinuity zone, each pixel is adjacent the connectedness of pixel, marker extraction region, retains double track characteristic straight line by connected component labeling.

3. a kind of track obstacle detection system based on machine vision according to claim 1, it is characterized in that, the detailed process of step 4 is: retain double track characteristic straight line according to connected component labeling, utilize fitting a straight line, least square method is adopted to realize extracting edge local to track, by two rail linear, obtain straight-line equation; With the position of the particular location determination detection window window of rail, size and dimension, rail portion is confined within the scope of it by detection window.

4. a kind of track obstacle detection system based on machine vision according to claim 1, it is characterized in that, the detailed process of step 5 is as follows:

Got rid of the feature of background based on image in class straight way track rule unchangeability and detection window, can ignore orbital motion, when there being suspicious barrier intrusion detection window, characteristics of image will certainly be caused to change, and this method chooses histogram feature;

Define threshold value T based on experience value ₁and T ₂for differentiating histogram variances variation delta σ _k ²with the value changing condition of histogram burr number BurrNum, by two-value monochrome pixels ratio r atio, Δ σ _k ²with the monitoring of BurrNum tri-parameters, determining whether barrier invasion may; Algorithm is as follows:

Histogram average: $\stackrel{\&OverBar;}{r_k}=\underset{r_k=0}{\overset{L-1}{\mathrm{\&Sigma;}}}{r}_k{p}_k\left(r_k\right)$

(wherein r _kfor histogram feature data, p _kprobability corresponding to it, L is the number of characteristic)

Histogram variances: ${\mathrm{\&sigma;}}_k^2=\underset{r_k=0}{\overset{L-1}{\mathrm{\&Sigma;}}}{(r_k-\stackrel{\&OverBar;}{r_k})}^2{p}_k\left(r_k\right)$

Two-value monochrome pixels ratio: $\mathrm{ratio}=\frac{n_b}{n_k}$

(n _bfor the quantity of black pixel, n _kquantity for white pixel)

From significance level and fiduciary level, ratio n _b/ n _kmore directly perceived, more can show actual conditions, therefore enumerate basis for estimation:

(1) during ratio<4.5, no matter Δ σ _k ²with the value of BurrNum how, all judge there is invasion barrier;

(2) during ratio>4.5, then Δ σ is observed _k ²how to change with the value of BurrNum, if both exceed threshold value, then judge there is invasion barrier;

(3) during ratio>4.5, and Δ σ _k ²all do not exceed threshold value with the value of BurrNum or one of them exceeds threshold value, then judging do not have barrier, may be the impact of the external interference such as illumination condition;

If there is no barrier, then return and start anew; If there is barrier, then carry out next step.

5. a kind of track obstacle detection system based on machine vision according to claim 1, it is characterized in that, the detailed process of step 6 is as follows:

Stationary obstruction also has relative motion to train, so differentiate static or moving obstacle by movement locus and motion feature;

Adopt the frame differential method improved through mathematical morphology, calculus of differences is carried out to the image in detection window, extract segmentation moving target; Frame differential method is exactly in sequence of video images, extracts adjacent two frame three frame or multiple images, and carries out to the two field picture extracted the image operation that pixel subtracts each other; If the difference of neighbor is less than the threshold value of setting, then think that this pixel is static background, otherwise, then extract this pixel as moving target, according to this principle, all pixels meeting moving target threshold value to be joined together the moving target that just can extract in scene, and remove jamming pattern, reach with this object extracting segmentation moving target;

Frame differential method principle is as follows:

D _k(x,y)＝|F _k(x,y)-F _k-1(x,y)|

F _k(x, y) represents continuous print image in video, D _k(x, y) represents the error image that two continuous frames image subtraction obtains, then by D _k(x, y) does following process:

$R_k(x,y)=\left\{\begin{array}{cc}1& D_k(x,y)>P\\ 0& D_k(x,y)<P\end{array}\right.$ (P is setting threshold value, and simulation obtains repeatedly by experiment)

R _k(x, y) is for judge the foundation whether target moves: if 1, then target discrimination is motion; Otherwise, for static;

Meanwhile, utilize background subtraction, the detected image in detection window and background image are carried out difference, then detects moving region by threshold value; If b (x, y) is background image, definition image sequence f (x, y, i), wherein (x, y) is image position coordinates, and i is number of image frames; The gray-scale value of the gray-scale value subtracting background of each two field picture is obtained error image:

id(x,y,i)＝f(x,y,i)-b(x,y)

A binaryzation difference image can be obtained by arranging threshold value T:

(threshold value T simulates by experiment and obtains)

Finally, carry out pixel and get common factor, extract more accurately to target the image of two kinds of algorithm gained, obtain the size of target, the shape of target, differentiation is static or motion.

6. a kind of track obstacle detection system based on machine vision according to claim 1, it is characterized in that, the detailed process of step 7 is as follows:

Corner Feature Matching pursuitalgorithm is adopted to carry out barrier size, speed and direction discernment, feature extraction adopts Harris Corner Detection Algorithm, it is a kind of interest point detect operator based on signal, in this method, the point enough large with adjoint point brightness contrast (intensity contrast of pixel neighborhoods point) is defined as angle point, pixel related function used is as follows:

$E(x,y)=\underset{u,v}{\mathrm{\&Sigma;}}w(u,v){[I(x+u,x+v)-I(x,y)]}^2=[u,v]M\left[\begin{array}{c}u\\ v\end{array}\right]$

$M=\underset{u,v}{\mathrm{\&Sigma;}}w(u,v)\left[\begin{array}{cc}{I}_x^2& I_x{I}_y\\ I_x{I}_y& I_y^2\end{array}\right]$

Wherein, w is the smoothing windows of carrying out noise reduction process, and (u, v) is offset coordinates, and I is the pixel value of image pixel matrix, I (x, y) value image mid point (x, y); I _xand I _ythe respectively single order partial differential of representative image pixel in the horizontal direction, in vertical direction, I _x ²and I _y ²then be respectively the second order Grad in both direction; Then the angle point in image just can be detected by calculating angle point response function:

R＝det(M)-k*tr ²(M)

Wherein, tr (M) and det (M) represents mark and the determinant of matrix M respectively, and Harris Corner Detection Algorithm recommends k to get 0.04;

Characteristic matching adopts based on the relevant Feature Points Matching algorithm of gray scale, is extracted as example with three frames:

First, for each unique point p _i∈ E ₁, p _j∈ E ₃, respectively centered by unique point, the window of structure N × N size, is designated as W respectively _i, W _j, then calculate the related function of each window respectively

$C_{\mathrm{cor}}(i,j)=\frac{\underset{n=1}{\overset{N\&times;N}{\mathrm{\&Sigma;}}}\left(W_i{W}_j\right)}{\underset{n=1}{\overset{N\&times;N}{\mathrm{\&Sigma;}}}{W}_i\underset{n=1}{\overset{N\&times;N}{\mathrm{\&Sigma;}}}{W}_j}$

Can according to C _corthe value of (i, j) can judge the correlation of individual features point, and this value is larger, and corresponding unique point neighborhood gray scale is more close; In the process of looking for match point, the mode of mutually coupling is adopted to mate, namely when the optimal match point of the unique point pi in E1 is the p in E3 _i, p simultaneously _joptimal match point be also p _itime, just think (p _ip _j) be a pair optimum matching unique point; Obtain final corners Matching result accordingly;

The type of preceding object thing is judged, for without dangerous (static the small-scale obstacle thing, fast across the moving obstacle of track) or dangerous (static large obstacle, affect the moving obstacle that train passes through) with this.