CN102867414A - Vehicle queue length measurement method based on PTZ (Pan/Tilt/Zoom) camera fast calibration - Google Patents

Abstract

The invention discloses a vehicle queue length measurement method based on PTZ (Pan/Tilt/Zoom) camera fast calibration. The vehicle queue length measurement method based on the PTZ camera fast calibration comprises the following steps of choosing two vertically-crossed traffic markings to form a T-shaped scaling reference and establishing a conversion relation between coordinates of pixels in an image and coordinates of roadway corresponding points in a world coordinate system according to the defined models of the image coordinate system and the world coordinate system; acquiring video images of a traffic monitoring scene by adopting a PTZ camera, setting an ROI (Region Of Interests) of a lane, detecting the vehicle queue state in the ROI by the adoption of an adaptive background update algorithm and textural features, and acquiring the pixels and pixel coordinates of the tails of the vehicle queues; converting the detected pixel coordinates of the tails of the vehicle queues into the world coordinate and finally computing the length of the vehicle queues. The tail position of the vehicle queues is judged according to the textural features, and the measurement of length of the vehicle queues is finished by the combination of the camera, so that the vehicle queue length measurement method based on the PTZ camera fast calibration, disclosed by the invention, has the advantages of low cost, strong embedded type, and the like.

Description

A kind of vehicle queue length measuring method based on the Pan/Tilt/Zoom camera Fast Calibration

Technical field

The present invention relates to a kind of vehicle queue length measuring method, particularly a kind of vehicle queue length measuring method based on the Pan/Tilt/Zoom camera Fast Calibration.

Background technology

Along with the fast development of economy, the city automobile owning amount is more and more, and traffic congestion is one of difficult problem of urban development always.Intelligent transportation system is one of effective way of solving urban traffic blocking.Most domestic traffic intersection all is to adopt the timing controlled traffic lights at present, and the time span that traffic lights switch is changeless.Because complicacy and randomness that vehicle flowrate changes, the defective of this fixed allocation mode more highlights, and therefore, has progressively carried out the research of fixed allocation time to Intelligent time distribution transition.The urban traffic signal command system carries out Intelligent time to the intersection signal and divides timing, need to obtain the telecommunication flow information of road.Wherein the intersection vehicle queue length is one of important parameter in the intelligent transportation system.

The mode of obtaining telecommunication flow information mainly contains the modes such as ground induction coil, video identification, Floating Car estimation.Because ground induction coil places the fixed position of road, although accurately measuring vehicle how much, error is larger aspect the measuring vehicle queue length.Publication No. be CN102024323A patent disclosure a kind of method of extracting vehicle queue length based on floating car data, the method is at first by the highway section matching technique, ordinary queue waits for that the Floating Car vehicle GPS that passes through obtains the halt position before extracting the crossing, highway section, then the Floating Car halt is added up apart from the position distribution variation of crossing, estimated queue length.

Based on the intelligent traffic monitoring system of video analysis, have the advantages such as the transport information of obtaining is many, monitoring range large, simple installation, more domestic and international researcher tends to carry out Vehicle length by computer vision technique and automatically extracts.The people such as Zhu Xiaoshan propose to improve the vehicle queue length detection method of Canny edge detection algorithm.Rourke and Bell have proposed a kind of traffic queue detection method based on FFT.The people such as Li Weibin utilize gradient difference and colour-difference to separately win a complete information of picking up the car, and adopt the telescopic window length detection of ranking.Publication No. is method and the device that a kind of vehicle queue length of the patent disclosure of CN101936730A detects, and adopts daytime and adopts the car light characteristic to detect respectively the queuing vehicle platoon at three frame difference methods and morphology, night.

Chinese scholars mainly lays particular emphasis on the Pixel Information by vehicle queue in the video analysis detected image, but less for the research in conjunction with the vehicle platoon length computation of camera calibration, PTZ (Pan/Tilt/Zoom) video camera particularly, because of its inside and outside parameter frequent variations, calculate the more aobvious difficulty of vehicle queue queue length.

In existing scaling method, traditional camera marking method will be used specific calibrating block usually, and the calibration point setting up procedure is loaded down with trivial details.Self-calibrating method need to be controlled rig camera and do for several times rigid motion, and the image under the different visual angles is carried out the characteristic parameter coupling, is not suitable for the normally fixing application scenario of rig camera in the traffic scene.

Characteristics for the traffic monitoring scene, Nelson, the people such as Granttham and George adopts the traffic video monitoring system camera marking method based on simple imaging model, directly utilizes the rectangle realization focal length of camera of road surface lane line angle point composition in the traffic scene and the demarcation of direction parameter.Invention CN1564581A has announced a kind of urban transportation and has monitored and adopt on the road surface several special straight lines as spotting under the environment, the method for calibrating camera focal length and space external parameter.Said method is based upon on the three-dimensional mapping model basis, needs to solidify camera model partial interior parameter, and needed known conditions is more, has reduced the usable range of calibration algorithm.

The people such as Fathy utilize the method for camera calibration to set up the 2D image coordinate is calculated formation to the transformation model of 3D world coordinates length.For the parameter to video camera is demarcated, the method needs in advance coordinate and corresponding point the coordinate in image coordinate system of known four points in world coordinate system.Coordinate points obtain inconvenience, practical application bothers, and is not easy to obtain such coordinate points in actual scene, and needs the extra scaling reference of placing.The people such as Fung utilize existing lane line to finish camera calibration, only need to know the width in track, that although lane width is followed certain standard and obtain easily, traffic marking must possess rectangular characteristic in this algorithm, and also there is certain limitation in adaptability.The people such as Li Bo propose to adopt two line segments of conllinear in the pavement strip and another parallel lines as demarcating masterplate, but the height of video camera must be known.Said method exists the witness marker thing of particular geometric feature to choose difficulty, constraint condition and the defective such as is difficult for obtaining, and has certain limitation in practical application.

Summary of the invention

Above-mentioned technical matters for the length measurement method that solves existing vehicle queue formation exists the invention provides a kind of vehicle queue length measuring method based on the Pan/Tilt/Zoom camera Fast Calibration.

The technical scheme that the present invention solves the problems of the technologies described above may further comprise the steps:

1) video image of usefulness PTZ video camera Real-time Obtaining traffic monitoring scene;

2) two traffic marking choosing square crossing in image consist of T-shaped camera calibration reference substance, obtain the pixel coordinate of four end points in the T-shaped scaling reference, measure the wherein between any two distance of three points of conllinear, and measure the distance that a bit arrives in addition this straight line;

3) set up model and the corresponding relation thereof of image coordinate system and world coordinate system, solve the inside and outside parameter of video camera, set up the conversion relation between the coordinate of the coordinate of image slices vegetarian refreshments and world coordinate system road surface corresponding point;

4) in image, choose stop line from the track to the lane detection district that presets as vehicle queue information detection zone, i.e. interest domain ROI, follow-up processing procedure is limited in the ROI; For any pixel (x, y), adopt the Tamura textural characteristics of its place neighborhood image piece to weigh the degree of roughness of this pixel, be designated as F _Crs(x, y) is with F _Crs(x, y) is as the pixel gray-scale value of grain background image; Go through all over the neighborhood roughness value F that calculates each pixel _Crs(x, y) forms the background image B that a width of cloth characterizes textural characteristics _Crs, and background image with sunshine light change can adaptive updates;

5) textural characteristics of realtime graphic and the textural characteristics of background image are compared, extract foreground image, obtain the smooth of the edge, complete imperforate binaryzation foreground image through the morphology processing, be vehicle queue information, from the stop line of track to track queuing direction, adopt the algorithm search formation tail position of mobile detection window, obtain the image coordinate of tail of the queue pixel N;

6) the coordinate system conversion relation of setting up according to camera calibration is scaled the road surface corresponding point at the coordinate figure of world coordinate system, the queue length of vehicle queue when calculating traffic jam with the image coordinate of tail of the queue pixel N.

The present invention is by extracting static background in video, adopt textural characteristics, in video, isolate non-target context or moving target, in differentiating the track after the vehicle queue state, obtain inside and outside parameter according to camera calibration, set up the conversion relation of corresponding point in world coordinate system and the image coordinate system, finally realize the vision measurement of vehicle queue length.The characteristics such as the present invention has the camera calibration target and chooses easily, additionally places scaling reference, and robustness easy and simple to handle, the vehicle queue state recognition that scaling method has is good.

The present invention has the following advantages:

1. need not video camera sign reference substance additionally is set in monitoring scene, take full advantage of geometric properties and the dimensional data of existing traffic marking, the scaling method of camera parameters is simple and convenient.

2. the present invention adopts the vehicle queue information in the texture feature extraction background image, causes the transient change of illumination when having avoided vehicle to cross video camera, and the method that adopts background automatically to upgrade, and can adapt to the variation of difference light at sunshine period.

3. the present invention takes full advantage of the video image information that the existing rig camera of traffic intersection gathers, and is embedded into easily the traffic information management platform, has low, the embedded strong advantage of cost.

Description of drawings

Fig. 1 is process flow diagram of the present invention.

Fig. 2 gets traffic marking as the synoptic diagram of camera calibration reference substance among the present invention.

Fig. 3 is the camera model figure among the present invention.

Fig. 4 be scaling reference of the present invention and in camera model the synoptic diagram of position relationship.

Fig. 5 is boost line synoptic diagram in the camera calibration of the present invention.

Fig. 6 is the synoptic diagram of the embodiment of the invention.

Embodiment

Measuring principle of the present invention is as follows:

(1) two traffic marking choosing square crossing form T-shaped scaling reference, and through measure known collinear three points in twos between distance, with the outer vertical range that a bit arrives this straight line of line, obtain the pixel coordinate of four unique points in image, solve again the inside and outside parameter of camera calibration, set up the conversion relation of point coordinate and image coordinate system pixel coordinate in the world coordinate system;

(2) in the monitor video of traffic scene, extract image sequence, extract the textural characteristics of background image in the zone, track, set up the grain background image; The interest domain in track is set in image, extracts the textural characteristics of track interest domain in the realtime graphic, carry out automatic comparison with the textural characteristics of respective regions in the background image and differentiate, search and obtain the position of vehicle queue afterbody in image;

(3) according to the location of pixels of the vehicle platoon afterbody of searching, subscript conversion is the point coordinate of world coordinate system, finally calculates the length of queuing vehicle platoon in the world coordinate system.

The concrete steps of above-mentioned measuring principle are:

(1) Fast Calibration of video camera

The present invention adopts pinhole camera modeling, suppose in the traffic monitoring scene traffic be smooth, without curling, and ignore the distortion of video camera.The inside and outside parameter of video camera comprises focal distance f, tiltangleθ, rotationangleφ and track and world coordinate system transverse axis angle α etc.

Step 1 is set up the model of image coordinate system and world coordinate system.

World coordinate system X _W-Y _W: X _WAxle was defined as the cam lens center and was parallel to the intersection on plane and the ground of ccd sensor, Y _WAxle was defined as camera optical axis and perpendicular to the intersection on plane and the ground on ground, Y _WThe axle positive dirction is along road surface directed forward, X _WThe axle positive dirction is that level is pointed to right-hand; Its initial point O _WBe defined as X _WAxle and Y _WThe point of crossing of axle, as shown in Figure 3.

Image coordinate system XOY: in image, establish image and be of a size of M * N, initial point is defined as image geometry center [(M-1)/2, (N-1)/2].The X-axis level is pointed to left in the image, and Y-axis is vertically pointed to the below, as shown in Figure 3.

When video camera was overlooked in the traffic scene scaling reference, the angle on optical axis and plane, road was θ.The angle of lane line and world coordinate system is α.The rotation angle of its optical axis of camera intrinsic is φ, when the video camera level is installed, and rotationangleφ=0.Install when the non-level of video camera, there are angle in bottom and the horizontal line of video camera CCD, and namely rotationangleφ is not 0, need to be with image rotation φ angle, and the error of bringing when installing with the non-level of correcting camera.

Step 2 is chosen with reference to demarcating thing.Because the traffic marking such as driveway edge line and driveway separatrix have specific dimensions and geometric configuration, therefore, the traffic marking in traffic scene is chosen three conllinear terminal A, B, the C on the track boundary dotted line, supposes at world coordinate system X _WY _WIn coordinate be respectively (X _A, Y _A), (X _B, Y _B) and (X _C, Y _C).Measure end points distance between any two, terminal A B spacing is h ₁, terminal A C spacing is h ₂Cross certain end points pick up the car the boundary dotted line perpendicular line on certain 1 D, and measure this between the point of crossing apart from d ₁According to standard criterion, h ₁, h ₂And d ₁But value both can from handbook, find also actual measurement.

In image, obtain three terminal A, B, C and the pixel corresponding to vertical point D of lane line, be respectively a, b, c and d, the coordinate in image coordinate system XY be respectively (x ' _a, y ' _a), (x ' _b, y ' _b), (x ' _c, y ' _c) and (x ' _d, y ' _d).

Step 3 is made boost line in image, obtain the required data of camera calibration.

When the non-level of video camera is installed, there is rotationangleφ between the bottom of ccd sensor and the horizontal line.The value of angle φ can be calculated by the described formula in back and obtain.In view of the impact of rotationangleφ, for satisfying method described in the invention, need to correct the non-level of video camera the error of bringing be installed with the corresponding rotation of the image that obtains φ angle before calibrating camera, namely the postrotational coordinate figure of a, b, c and d is

$\left[\begin{array}{c}{x}_i\\ y_i\end{array}\right]=\left[\begin{array}{cc}\cos \mathrm{\φ}& -\sin \mathrm{\φ}\\ \sin \mathrm{\φ}& \cos \mathrm{\φ}\end{array}\right]\left[\begin{array}{c}{x}_i^{\′}\\ x_i^{\′}\end{array}\right](i=a,b,c,d)---\left(1\right)$

Calculate intermediate variable $Y_A^{\′}=\frac{h_1{h}_2(y_b-y_c)}{(y_a-y_b)h_2-(y_a-y_c)h_1}---\left(2\right)$

$\mathrm{\λ}=\frac{(Y_A^{\′}+h_1)\·y_b-Y_A^{\′}\·y_a}{h_1}---\left(3\right)$

In world coordinate system, cross the C point of lane line and do parallel and X _wAxle is made parallel lines, crosses the A point of lane line and does parallel and Y _wAxle is made parallel lines, and both meet at A ' point.A ' spot projection is a ' to the point in the image, and its coordinate is (x _a', y _c), wherein

$x_{a^{\′}}=\frac{\mathrm{\λ}-y_c}{\mathrm{\λ}-y_a}{x}_a---\left(4\right)$

In image, cross the d point and make horizontal line, with the intersection point of a, b, c place straight line be the e point.E point pixel coordinate is (x _e, y _e), as shown in Figure 5.

Step 4 is found the solution lane line and world coordinate system transverse axis angle α.

The coordinate figure that a, the b that tries to achieve according to image rotation φ angle, c and d are 4 obtains lane line and world coordinate system transverse axis angle α satisfies following expression.

$\sin 2\mathrm{\α}=\frac{\mathrm{\λ}-y_a}{\mathrm{\λ}-y_c}\frac{{2d}_1(x_c-x_{a^{\′}})}{h_2|x_e-x_a|}$

In the following formula x _eThe horizontal ordinate that e is ordered in the plane of delineation, x _aBe the horizontal ordinate that A is ordered, h ₂Be AC distance between two points, d ₁Spacing for road surface two parallel lines.

Then

So basis $\sin \mathrm{\α}=\sqrt{\frac{1-\cos 2\mathrm{\α}}{2}},$ $\mathrm{\α}=\arcsin \left(\sqrt{\frac{1-\cos 2\mathrm{\α}}{2}}\right)---\left(5\right)$

Step 5 is found the solution the rotationangleφ of external parameters of cameras.

After the angle α that calculates lane line and world coordinate system transverse axis, be the coordinate of world coordinate system with scaling reference D point respective pixel coordinate transformation in image, computing formula is as follows.

$Y_d=\frac{\mathrm{\λ}-y_a}{\mathrm{\λ}-y_d}\·\frac{h_1{h}_2(y_b-y_c)}{(y_a-y_b)h_2-(y_a-y_c)h_1}\sin \mathrm{\α}---\left(6\right)$

$X_d=\frac{\mathrm{\λ}-y_c}{\mathrm{\λ}-y_d}\frac{h_2\cos \mathrm{\α}}{x_c-x_{a^{\′}}}{x}_d---\left(7\right)$

Supposed straight line and straight line L that D is ordered ₁Vertically meet at the B point, in like manner the coordinate transformation with pixel b is the coordinate of world coordinate system.Calculating at last | the distance of DB| is the D point to A, B, 3 places of C straight line L ₁Distance.

In order to find the solution φ, interval according to formula (1) image rotating, repeating step three, four, five at φ ∈ [15 °, 15 °].Adopt in Levenberg-Marquardt algorithm search φ ∈ [15 °, the 15 °] interval, so that

φ=argmin(|DB|) (8)

Step 6 is found the solution the depression angle θ of external parameters of cameras

After solving rotationangleφ, obtain the coordinate figure (x of 4 of a, b behind the image rotation φ, c and d _a, y _a), (x _b, y _b), (x _c, y _c) and (x _d, y _d).

Calculate $\sin \mathrm{\θ}=\mathrm{\λ}\frac{d_1}{\sin \mathrm{\α}}\frac{1}{x_e-x_a}\frac{1}{Y_{A^{\′}}\sin \mathrm{\α}},$ Therefore the depression angle θ of video camera can find the solution according to following formula.

$\mathrm{\θ}=\arcsin \left[\frac{d_1\·\mathrm{\λ}}{{\sin }^2\mathrm{\α}\·(x_e-x_a)\·Y_{A^{\′}}}\right]---\left(9\right)$

Step 7 is found the solution the focal distance f of video camera

According to the value of the depression angle θ that tries to achieve and intermediate variable λ, can calculate the focal distance f of video camera, have

$f=\frac{\mathrm{\λ}}{\tan \mathrm{\θ}}---\left(10\right)$

(2) video image analysis of vehicle queue situation

In order to extract track vehicle queue situation in video, the present invention adopts textural characteristics to extract moving target from background image, and concrete step is as follows:

Step 1 arranges the vehicle queue surveyed area in image, i.e. interest domain ROI, choose from the track traffic stop line to predetermined lane detection district as the vehicle queue detection zone.For every two field picture of video, only the surveyed area that arranges is carried out the calculating of view data.

Step 2, the roughness of each neighborhood of pixels in the computed image.If the neighborhood of pixel G (x, y) is 2 in the image ^k* 2 ^kThe window of individual pixel adopts Tamura textural characteristics method to calculate the roughness of this neighborhood image piece, is designated as F _Crs(x, y), and calculate one by one the roughness of the neighborhood image piece of each pixel in the surveyed area, with the neighborhood roughness value F of each pixel _Crs(x, y) forms the new image of a width of cloth as textural characteristics background image B _Crs

Step 3 adopts the Gauss model analysis, extracts foreground image F from background image _Img

B in the top publicity _CrsThe roughness value of pixel (x, y) in (x, y) expression grain background image, F _CrsThe roughness of (x, y) expression current pixel (x, y) neighborhood piece of living in.If it is foreground pixel that the gaussian probability of this pixel, represents this point greater than threshold value T.

If have some isolated points and local hole, then adopt the morphology disposal route to remake expansion process do corrosion treatment first, obtain the smooth of the edge, complete foreground image, i.e. the vehicle queue binary image.

Step 4 to track queuing direction, adopts the algorithm search formation tail position of mobile detection window from the stop line of track, acquisition tail of the queue pixel coordinate N (x ' _n, y ' _n).

Step 5 is got present frame f ₁And front cross frame image f ₂And f ₃Carry out frame difference and analyse, computing method are as follows.

$f_{12}(x,y)=\left\{\begin{array}{cc}1& |f_1(x,y)-f_2(x,y)|>\mathrm{<figure-callout\; id="0"\; label="T"\; filenames="HDA00002029130300021.png"\; state="\{\{state\}\}">T</figure-callout>}\\ 0& \mathrm{otherwise}\end{array}\right.$

$f_{23}(x,y)=\left\{\begin{array}{cc}1& |f_3(x,y)-f_2(x,y)|>\mathrm{<figure-callout\; id="0"\; label="T"\; filenames="HDA00002029130300021.png"\; state="\{\{state\}\}">T</figure-callout>}\\ 0& \mathrm{otherwise}\end{array}\right.$

$f(x,y)=\left\{\begin{array}{cc}1& f_{12}(x,y)=1\mathrm{and}{f}_{23}(x,y)=1\\ 0& \mathrm{otherwise}\end{array}\right.$

By the difference between the image, obtain the binaryzation frame difference image.Because what the poor binary image of frame usually obtained is contour of object, certainly exist some isolated points during the moving target of extraction, the local tiny area that noise etc. cause, hole or the problem such as discontinuous.In image is processed, adopt the morphology disposal route to do a corrosion treatment, remove local tiny area and isolated point in the video image.And then carry out twice expansion process and make foreground target thing marginal portion obtain smoothly finally obtaining complete moving target.

Step 6, because the traffic monitoring background can slowly change with factors such as sunshines, therefore, the textural characteristics background image carries out slowly upgrading in real time according to formula (11), namely

$B_{\mathrm{crs}}(t+1,x,y)=\left\{\begin{array}{cc}a\&CenterDot;B_{\mathrm{crs}}(t,x,y)+(1-a)\&CenterDot;F_{\mathrm{crs}}(t,x,y)& f(x,y)=1\mathrm{or}{F}_{\mathrm{img}}(x,y)=0\\ B_{\mathrm{crs}}(t,x,y)& F_{\mathrm{img}}(x,y)=1\end{array}\right.---\left(11\right)$

Wherein, a is undated parameter, the speed of expression change of background.B _Crs(t, x, y) is the value of pixel (x, y) in the t frame grain background image, F _Crs(t, x, y) is the neighborhood image piece roughness value of pixel (x, y) in the current frame image, B _Crs(t+1, x, y) is the grain background image after upgrading.If the f (x, y) in bulk zone is 1, then represent to exist in the track moving vehicle, the vehicle in track is not to be in queueing condition, need to be to the background real-time update.If F _Img(x, y)=1, vehicle has formed queue queue in the expression track, can not upgrade background, being upgraded by publicity (11) by foreground image when avoiding the long-time static queuing of vehicle becomes background, and to have produced frame poor when the vehicle setting in motion, i.e. f (x, y) become 1 after, real-time update background image again.

(3) measurement of vehicle queue length

By the image of Traffic Surveillance Video is processed obtain vehicle queue tail of the queue position (x ' _n, y ' _n), obtained the rotationangleφ of lane line and world coordinate system transverse axis angle α and video camera by camera calibration.

At first, find the solution the rotationangleφ of video camera, make it satisfy image coordinate system that the present invention sets up and the conversion relation of world coordinate system.Coordinate (x according to rotationangleφ pixel n _n, y _n) be

$\left[\begin{array}{c}{x}_n\\ y_n\end{array}\right]=\left[\begin{array}{cc}\cos \mathrm{\&phi;}& -\sin \mathrm{\&phi;}\\ \sin \mathrm{\&phi;}& \cos \mathrm{\&phi;}\end{array}\right]\left[\begin{array}{c}{x}_n^{\&prime;}\\ y_n^{\&prime;}\end{array}\right]$

Secondly, with (the x of the coordinate of pixel n in the image coordinate system _n, y _n) be scaled (X of world coordinate system corresponding point N _n, Y _n), reduction formula is as follows:

$Y_n=\frac{\mathrm{\&lambda;}-y_a}{\mathrm{\&lambda;}-y_n}\&CenterDot;\frac{h_1{h}_2(y_b-y_c)}{(y_a-y_b)h_2-(y_a-y_c)h_1}\sin \mathrm{\&alpha;}$

$X_n=\frac{\mathrm{\&lambda;}-y_c}{\mathrm{\&lambda;}-y_n}\frac{h_2\cos \mathrm{\&alpha;}}{x_c-x_{a^{\&prime;}}}{x}_n$

At last, calculate vehicle queue length

The present invention uses digital camera to obtain the video image of traffic monitoring scene, detects the traffic intersection vehicle queue length in conjunction with video camera quick calibrating method and digital image processing techniques, reaches the collection of arithmetic for real-time traffic flow parameter.

As shown in Figure 1, the present invention adopts the PTZ video camera to obtain the video image that road traffic monitors scene, the interest domain ROI on road surface is set, adopt the vehicle queue state in the interest domain on the textural characteristics detection background image, set up the corresponding conversion relation of image coordinate system and world coordinate system by the Fast Calibration of video camera, the tail of the queue pixel coordinate that detects is converted into the world coordinates value, calculates the length of vehicle queue.Pan/Tilt/Zoom camera, i.e. Pan (translation), Tilt (inclination), Zoom (zoom) can level, vertically change the video camera of visual angle and zoom, is used for video monitoring system.

In sum, implementation process brief overview of the present invention is following steps:

1) the PTZ video camera of installing by traffic intersection, Real-time Obtaining road conditions video image information;

2) from the image information that video camera obtains, choose the traffic marking with particular geometric feature and dimensional data, as shown in Figure 2.In the traffic marking on road surface, to choose three conllinear terminal A, B, C on the track boundary dotted line, and obtain these three end points distance between any two, terminal A B spacing is h ₁, terminal A C spacing is h ₂Cross certain end points pick up the car the boundary dotted line perpendicular line on certain 1 D, and measure this between the point of crossing apart from d ₁

According to coordinate system synoptic diagram shown in Figure 3, the coordinate of above-mentioned four end points in image be respectively (x ' _a, y ' _a), (x ' _b, y ' _b), (x ' _c, y ' _c) and (x ' _d, y ' _d).

Video camera be not complete level when installing, the base of ccd sensor supposes that along having the anglec of rotation with horizontal line rotation angle is φ, then at first a, b, c and four pixel coordinates of d is rotated, and has

$\left[\begin{array}{c}{x}_i\\ y_i\end{array}\right]=\left[\begin{array}{cc}\cos \mathrm{\&phi;}& -\sin \mathrm{\&phi;}\\ \sin \mathrm{\&phi;}& \cos \mathrm{\&phi;}\end{array}\right]\left[\begin{array}{c}{x}_i^{\&prime;}\\ y_i^{\&prime;}\end{array}\right]$ (wherein i=a, b, c, d) (1)

Calculate intermediate variable $Y_A^{\&prime;}=\frac{h_1{h}_2(y_b-y_c)}{(y_a-y_b)h_2-(y_a-y_c)h_1}---\left(2\right)$

$\mathrm{\&lambda;}=\frac{(Y_A^{\&prime;}+h_1)\&CenterDot;y_b-Y_A^{\&prime;}\&CenterDot;y_a}{h_1}---\left(3\right)$

As shown in Figure 4 auxiliary point A ' in world coordinate system, pixel corresponding in image is a ', then pixel is that the horizontal ordinate of a ' is

$x_{a^{\&prime;}}=\frac{\mathrm{\&lambda;}-y_c}{\mathrm{\&lambda;}-y_a}{x}_a---\left(4\right)$

In image, cross the d point and make horizontal line, with the intersection point of a, b, c place straight line be the e point.E point pixel coordinate is (x _e, y _e), known straight line L ₁Slope be k, intercept is b, as shown in Figure 5.The horizontal ordinate x that e is ordered in the plane of delineation _eBe calculated as by following formula

$x_e=\frac{y_b-b}{k}$

Foundation again $\sin 2\mathrm{\&alpha;}=\frac{\mathrm{\&lambda;}-y_a}{\mathrm{\&lambda;}-y_c}\frac{{2d}_1(x_c-x_{a^{\&prime;}})}{h_2|x_e-x_a|},$ Obtain the angle α of lane line and world coordinate system transverse axis.

Be the coordinate of world coordinate system with scaling reference D point respective pixel coordinate transformation in image, computing formula is as follows.

$Y_d=\frac{\mathrm{\&lambda;}-y_a}{\mathrm{\&lambda;}-y_d}\&CenterDot;\frac{h_1{h}_2(y_b-y_c)}{(y_a-y_b)h_2-(y_a-y_c)h_1}\sin \mathrm{\&alpha;}---\left(6\right)$

$X_d=\frac{\mathrm{\&lambda;}-y_c}{\mathrm{\&lambda;}-y_d}\frac{h_2\cos \mathrm{\&alpha;}}{x_c-x_{a^{\&prime;}}}{x}_d---\left(7\right)$

Supposed straight line and straight line L that D is ordered ₁Vertically meet at the B point, in like manner the coordinate transformation with pixel b is the coordinate of world coordinate system, calculates | the distance of DB| is the D point to A, B, 3 places of C straight line L ₁Distance.

Find the solution in the process of φ, repetition, is obtained to formula (7) again according to formula (1) in φ ∈ [15 °, 15 °] interval | the value of DB|.Adopt in Levenberg-Marquardt algorithm search φ ∈ [15 °, the 15 °] interval, so that

φ=argmin(|DB|) (8)

(2) video image analysis of vehicle queue situation

At first, the vehicle queue surveyed area is set in image, i.e. interest domain ROI, choose from the track traffic stop line to predetermined lane detection district as the vehicle queue detection zone.As shown in Figure 6.

Secondly, the Tamura texture value of employing pixel (x, y) place neighborhood image piece is weighed the roughness of this dot image, is designated as F _Crs(x, y) is with the neighborhood roughness value F of each pixel _Crs(x, y) forms the new image of a width of cloth as textural characteristics background image B _Crs

Then, because the traffic monitoring background can slowly change with factors such as sunshines, for example the grain background image on daytime is with regard to obviously different nights, and therefore, the textural characteristics background image carries out in real time slowly renewal according to formula (11).But

$B_{\mathrm{crs}}(t+1,x,y)=\left\{\begin{array}{cc}a\&CenterDot;B_{\mathrm{crs}}(t,x,y)+(1-a)\&CenterDot;F_{\mathrm{crs}}(t,x,y)& f(x,y)=1\mathrm{or}{F}_{\mathrm{img}}(x,y)=0\\ B_{\mathrm{crs}}(t,x,y)& F_{\mathrm{img}}(x,y)=1\end{array}\right.---\left(11\right)$

The employing Gauss model is analyzed, and extracts foreground image F from background image _Img

Through the morphology disposal route, obtain the smooth of the edge, complete foreground image, i.e. the vehicle queue binary image.

At last, from the stop line of track, to track queuing direction, adopt the algorithm search formation tail position of mobile detection window, acquisition tail of the queue pixel coordinate N (x ' _n, y ' _n), as shown in Figure 6.

(3) measurement of vehicle queue length

After obtaining accurate φ angle, through image process obtain vehicle queue tail of the queue position n (x ' _n, y ' _n), at first according to formula (1) pixel n is rotated rectification.Coordinate (x according to rotationangleφ pixel n _n, y _n) be

$\left[\begin{array}{c}{x}_n\\ y_n\end{array}\right]=\left[\begin{array}{cc}\cos \mathrm{\&phi;}& -\sin \mathrm{\&phi;}\\ \sin \mathrm{\&phi;}& \cos \mathrm{\&phi;}\end{array}\right]\left[\begin{array}{c}{x}_n^{\&prime;}\\ y_n^{\&prime;}\end{array}\right]$

Secondly, with (the x of the coordinate of pixel n in the image coordinate system _n, y _n) be scaled (X of world coordinate system corresponding point N _n, Y _n), reduction formula is as follows:

$Y_n=\frac{\mathrm{\&lambda;}-y_a}{\mathrm{\&lambda;}-y_n}\&CenterDot;\frac{h_1{h}_2(y_b-y_c)}{(y_a-y_b)h_2-(y_a-y_c)h_1}\sin \mathrm{\&alpha;}$

$X_n=\frac{\mathrm{\&lambda;}-y_c}{\mathrm{\&lambda;}-y_n}\frac{h_2\cos \mathrm{\&alpha;}}{x_c-x_{a^{\&prime;}}}{x}_n$

At last, calculate vehicle queue length, $L=\sqrt{{\left(X_n\right)}^2+{\left(Y_n\right)}^2}.$

Claims (6)

1. vehicle queue length measuring method based on the Pan/Tilt/Zoom camera Fast Calibration may further comprise the steps:

1) video image of usefulness PTZ video camera Real-time Obtaining traffic monitoring scene;

2) two traffic marking choosing square crossing in image consist of T-shaped camera calibration reference substance, obtain the pixel coordinate of four end points in the T-shaped scaling reference, measure the wherein between any two distance of three points of conllinear, and measure the distance that a bit arrives in addition this straight line;

3) set up model and the corresponding relation thereof of image coordinate system and world coordinate system, solve the inside and outside parameter of video camera, set up the conversion relation between the coordinate of the coordinate of image pixel and world coordinate system road surface corresponding point;

4) in image, choose stop line from the track to the lane detection district that presets as vehicle queue information detection zone, i.e. interest domain ROI, follow-up processing procedure is limited in the ROI; For any pixel (x, y), adopt the textural characteristics of its place neighborhood image piece to weigh the degree of roughness of this pixel, be designated as F _Crs(x, y) is with F _Crs(x, y) is as the pixel gray-scale value of grain background image; Go through all over the neighborhood roughness value F that calculates each pixel _Crs(x, y) forms the background image B that a width of cloth characterizes textural characteristics _Crs, and background image with sunshine light change can adaptive updates;

5) textural characteristics of realtime graphic and the textural characteristics of background image are compared, extract foreground image, after processing, morphology obtains the smooth of the edge, complete imperforate binaryzation foreground image, be vehicle queue information, from the stop line of track, search for to track queuing direction, adopt the algorithm search formation tail position of mobile detection window, obtain the image coordinate of tail of the queue pixel N;

6) the coordinate system conversion relation of setting up according to camera calibration is scaled the road surface corresponding point at the coordinate figure of world coordinate system, the queue length of vehicle queue when calculating traffic jam with the image coordinate of tail of the queue pixel N.

2. the camera calibration reference substance the vehicle queue length measuring method based on the Pan/Tilt/Zoom camera Fast Calibration according to claim 1, described step 2) is chosen track boundary dotted line L ₁The A of upper conllinear, B, 3 end points of C, and known these three end points distance between any two, terminal A B spacing is h ₁, terminal A C spacing is h ₂, the line L of outer another D of certain end points among A, B, the C and line ₂Perpendicular to L ₁, the D point is to straight line L ₁Distance be d ₁And known A, B, C, the D coordinate in image are respectively a(x ^' _a, y ^' _a), b(x ' _b, y ^' _b), c(x ^' _c, y ^' _c) and d(x ^' _d, y ^' _d).

3. the vehicle queue length measuring method based on the Pan/Tilt/Zoom camera Fast Calibration according to claim 1, the image coordinate system in the described step 3) and the model of world coordinate system and corresponding relation thereof, world coordinate system X _W-Y _W: X _WAxle was defined as the cam lens center and was parallel to the intersection on plane and the ground of ccd sensor, Y _WAxle was defined as camera optical axis and perpendicular to the intersection on plane and the ground on ground, Y _WThe axle positive dirction is along camera directed forward, X _WThe axle positive dirction is that level is pointed to right-hand; Its initial point O _WBe defined as X _WAxle and Y _WThe point of crossing of axle; Image coordinate system XOY: in image, establish image and be of a size of M * N, initial point is defined as image geometry center [(M-1)/2, (N-1)/2], and the X-axis level is pointed to left in the image, and Y-axis is vertically pointed to the below; When video camera was overlooked in the traffic scene scaling reference, the angle on optical axis and plane, road was θ, and the angle of lane line and world coordinate system is α, and the rotation angle of its optical axis of camera intrinsic is φ.

4. the vehicle queue length measuring method based on the Pan/Tilt/Zoom camera Fast Calibration according to claim 1, the camera calibration step in the described step 3) is:

When the non-complete level of video camera was installed, there were the anglec of rotation in bottom and the horizontal line of ccd sensor, suppose that rotation angle is φ, then at first a, b, c and four pixel coordinates of d are rotated, and have

(wherein i=a, b, c, d) (1)

And ask intermediate variable

The horizontal ordinate of auxiliary point a ' in the computed image

In image, cross the d point and make horizontal line, with a, b, c place straight line L ₁Intersection point be the e point, e point pixel coordinate is (x _e, y _e), the horizontal ordinate x that e is ordered in the plane of delineation _eFor

Foundation again

, obtain the angle α of lane line and world coordinate system transverse axis;

Be the coordinate of world coordinate system with the coordinate transformation of pixel d in the image, computing formula is as follows,

Suppose in world coordinate system, to cross straight line and the straight line L that D is ordered ₁Vertically meet at the B point, then the coordinate of corresponding point pixel b can be scaled according to formula (6), (7) coordinate of world coordinate system in image, calculates | and the distance of DB| is the D point to A, B, 3 places of C straight line L ₁Distance;

Adopt in Levenberg-Marquardt algorithm search φ ∈ [15 °, the 15 °] interval, so that

。

5. the vehicle queue length measuring method based on the Pan/Tilt/Zoom camera Fast Calibration according to claim 1, described step 4) uses the textural characteristics value of each neighborhood of pixels image block to set up the grain background image, and namely the gray-scale value of certain pixel is the roughness value of this neighborhood of pixels image block in the grain background image.

6. the vehicle queue length measuring method based on the Pan/Tilt/Zoom camera Fast Calibration according to claim 1, the step of described step 6) is:

After obtaining rotationangleφ, obtain to get vehicle queue tail of the queue position n (x through image processing and range searching ^' _n, y ^' _n), at first according to formula (9) pixel n is rotated rectification, the pixel n (x after the rectification _n, y _n) be

Secondly, with (the x of the coordinate of pixel n in the image coordinate system _n, y _n) be scaled (X of world coordinate system corresponding point N _n, Y _n), reduction formula is as follows:

At last, calculate vehicle queue length,

Images