CN105913689A - Pre-warning method for motor vehicle driving safety - Google Patents

Abstract

The invention provides a pre-warning method for motor vehicle driving safety. The method comprises the following steps: in a vehicle running process, performing vehicle distance detection on an image captured by a vehicle-mounted camera; sending out an alarm when the distance between a vehicle and another vehicle in front of the vehicle is shorter than a safe distance. According to the pre-warning method for motor vehicle driving safety, safety detection for a motor vehicle is realized in an embedded chip, so that the driving safety pre-warning performance is improved, and a task processing quantity can be calculated to realize real-time calculation and pre-warning.

Description

Motor vehicle running safe early warning method

Technical field

The present invention relates to intelligent transportation, particularly to a kind of motor vehicle running safe early warning method.

Background technology

In recent years, along with global traffic demand increases, all kinds of urban highway traffic facility resource-constraineds, traffic Supply and demand is uneven, brings huge pressure to urban transportation.In China, drive, no without card is violating the regulations On qualified vehicle, road travels, driver fatigue is driven, drives when intoxicated, overloaded, hypervelocity etc. is to cause traffic thing Therefore reason.Existing road traffic accident analysis shows, the accident percentage relevant with driver's subjective factors Rate accounts for nearly 95%.The reason really causing serious accident is the most still attributed to traffic participant itself, thus A set of comprehensive traffic safety aid system is just particularly important.In recent years, computer technology develops rapidly, Using photographic head objectively to differentiate that concrete environment is possibly realized, digital image processing techniques are the completeest Kind, use the visual information acquired in digital computer process more and more accurately quickly.Traditional automobile chip In manufacture, use Single-chip Controlling.Software in single-chip microcomputer still uses first degree assembler language.Adopt Using the single-threaded method of operation, resource utilization is low.The introducing of intelligent transportation system, running safe early warning Effect increasingly come into one's own, from strength to strength, bring is also task treating capacity to function simultaneously, calculate The increase of amount.The most only the chip controls by single-chip microcomputer does not the most adapt to the safe manufacturing of automobile.

Summary of the invention

For solving the problem existing for above-mentioned prior art, it is pre-that the present invention proposes a kind of motor vehicle running safety Alarm method, including:

In vehicle travel process, the image being captured vehicle-mounted vidicon carries out spacing detection；When vehicle with Warning is sent when the spacing of front truck is less than safe distance.

Preferably, the detection of described spacing farther includes:

Carry out rim detection initially with sub-circular sliding window, will sub-circular sliding window in gray scale to be detected Slide on image, inside sliding window, give the ash of gray value and the sliding window center pixel of each pixel of numbering Angle value compares, if gray value of certain some pixel is less than, with the difference of center gray scale, the threshold set in sliding window Value t, it is determined that this point and sliding window central point have identical gray scale, all in sliding window have same grayscale with center The summation of value constitutes similar area；

By coordinate (x_c, y_c) represent sliding window centre coordinate, use similar comparison function as follows:

C (x, y)=exp [-[[I (x, y)-I (x_c,y_c)]/2]⁶]

(x, y) is coordinate x to I, the gray scale of y；

Then the size of similar area is calculated as:

Under different contrast adaptively selected to t value, i.e. in circular sliding window, by picture in cumulative sliding window Element value determines pixel and threshold value t of sliding window center pixel difference in sliding window:

For given sub-circular sliding window, represent accumulated variables, img with sum_{(i, j)}K () represents center pixel The i-th row jth row in source images, k represents the kth pixel in sliding window, the then threshold value of kth pixel T is:

T=sum/n (x_c, y_c)

$sum=\underset{s=1}{\overset{k}{\Σ}}{\mathrm{img}}_{(i,j)}\left(s\right)$

Sum makes t value in response to local contrast by cumulative sliding window pixel；

Obtain the difference of kth pixel and center pixel, make comparisons with t, if less than or equal to t, similar Region adds 1, finally judges the size of similar area and threshold value g, if less than g, then current pixel is marginal point, Current pixel value is set to 255, and otherwise, current pixel is not marginal point, it is set to 0.

Preferably, before described rim detection, returning method also includes: candidate marginal is only done edge inspection Surveying, screening technique is as follows:

First, centered by central pixel point, the pixel calculating vertical segment two ends is poor, and with pre-set Difference threshold Th compares, the gray-scale pixels point more than Th as candidate marginal, otherwise, less than Th Point be considered as then that interior pixels point is ready to remove.

The present invention compared to existing technology, has the advantage that

The present invention proposes a kind of motor vehicle running safe early warning method, achieves motor-driven in embedded chip Car safety detection, improves traffic safety early warning performance, it is possible to real by realizing under amount of calculation in task treating capacity Time calculate and early warning.

Accompanying drawing explanation

Fig. 1 is the flow chart of motor vehicle running safe early warning method according to embodiments of the present invention.

Detailed description of the invention

Hereafter provide one or more embodiment of the present invention together with the accompanying drawing of the diagram principle of the invention is detailed Thin description.Describe the present invention in conjunction with such embodiment, but the invention is not restricted to any embodiment.This Bright scope is limited only by the appended claims, and the present invention contains many replacements, amendment and equivalent.? Middle elaboration many detail is described below to provide thorough understanding of the present invention.For exemplary purposes And these details are provided, and can also be according to right without some in these details or all details Claim realizes the present invention.

An aspect of of the present present invention provides a kind of motor vehicle running safe early warning method.Fig. 1 is according to the present invention The motor vehicle running safe early warning method flow chart of embodiment.

The present invention is vehicle detection in vehicle travel process, real time distance.First embedded OS is entered Row is cut out, and then compiled system is transplanted by load driver.Loading third-party image software processes Behind storehouse, carry out writing and carry of application software, be then transplanted in embedded chip.Use adaptive thresholding The method of value is to candidate marginal Detection and Extraction vehicle edge and then extracts vehicle, thus calculates spacing.

The present invention installs cross compilation environment at server end, first sets, and enters at server end Binary image is write and generated to line program, and carry out the operation of application program at embedded board end.Cause The auxiliary of this present invention is driven the program of early warning system and is added corresponding hardware on embedded board and drive Dynamic.

The auxiliary of the present invention is driven early warning system and is used camera collection image, then on the basis of operating system On, carry out application and write, including with lower module:

Image collection module: obtain image from photographic head, then carry out color space conversion and the pretreatment of image, The image detected is sent to other modules.

Lane detection module: identify the traffic lane line in image, it is judged that self is whether in the range of safe track, If it is not, then send warning.

Spacing detection module: by obtain frame of video, image is carried out a series of process, determine front truck or Barrier position in the picture, adjusts the distance and judges, if less than safe distance, then sends alarm.

Car alarming module: when the function of this module is that aforementioned functional module is occurred unsafe condition, send report Alert.

Image display: provide distance prompt from image, provide the user with visible results.

Wherein spacing detection module and lane detection module use same video streaming image source, therefore use Multi-thread programming realizes.The present invention uses timer class to open thread.A letter is produced when timer triggers Number, the timer class run by this way, use incompatible lock mechanism to achieve the communication between thread.As Fruit has a thread to have mutual exclusion lock, then it now can not be accessed by other threads, can be only in dormancy shape State, until lock release is unlocked by this thread.

For lane detection, the detection method that the present invention proposes utilizes known to track color and direction both Feature, is weighted color characteristic processing, bonding position significant characteristics, jointly splits lane position, Then extract lane markings characteristic point, candidate point is fitted, obtains region, track.

Due to Perspective Principles, track obtained in road imaging process always intersects at certain point, and real Border is that two tracks of parallel lines can be rendered as π/3 and 2 π/3 two intersecting lens, in the picture according to this feature Travel direction is retrained, makes notable figure Direction of superposition feature, can more clearly from represent the notable special of track Levy.

For direction α and yardstick β, define filtering core function:

$W_{\mathrm{\α},\mathrm{\β}}(x,y)=\mathrm{\β}/\left(\sqrt{2\mathrm{\π}}c\right)-\exp (-a^2(4a^2+b^2)/(8c^2\left)\right)\left(\exp \right(ia\mathrm{\β})-\exp (-c^2/2\left)\right)$

Wherein a=xcos α+ysin α, b=-xsin α+ycos α, c=2.2.For track, choose π/3 and 2 π/3 Kernel function under two yardsticks of both direction carries out convolution, if (x y) is (x, y) value put, I and side in figure to I To being the kernel function convolution under β for α and yardstick, it is defined as:

$G_{\mathrm{\α},\mathrm{\β}}=I\⊗W_{\mathrm{\α},\mathrm{\β}}$

At z=, (x, y) convolution results put is divided into real part and imaginary part two parts, response value is taken as real part with empty The quadratic sum in portion:

I_α,β(z)=Re (G_α,β(z)²)+Im(G_α,β(z)²)

Response value under a direction α is defined as the fusion of the transformation results of direction different scale β, for uniformly Obtain the information of two yardsticks, take the meansigma methods of different scale result, the fusion results finally obtained, for The region response of each different directions is different, and the region response identical with image texture direction is relatively strong, And it is relatively weak with the region response that image texture direction is runed counter to.

According to track, there is known significantly color characteristic, to appointment during color is significantly schemed to generate Colored pixels carries out significance enhancing, then carries out region on the basis of the notable figure strengthened through color characteristic Contrast compares, and obtains notable figure based on region contrast.I.e. on color space, to some pixel, Calculate it and arrive the distance summation between other all pixels, just obtain this pixel showing under overall situation resolution Write figure.

Pixel I in image I_kCalculate utilizing the color contrast saliency value as significance measure method As follows:

S(I_k)=∑_1≤j≤nf_jD(I_k, I_j)

Wherein D (I_k, I_j) it is pixel I_kAnd I_jColor distance in Luv color space.N is to wrap in image The sum of all kinds of colors contained, f_jIt is that there is pixel I_kThe quantity of all pixels of color.

If color significantly figure is S, the notable figure in direction is set to R, for highlighting track further, need to color be shown The notable figure of work figure and direction blends.The notable figure of figure notable to color and direction does Regularization respectively.

N (S)=(S-min (S))/(max (S)-min (S))

Max (S) in formula, min (S) represent the maximum and minimum value in notable figure respectively.

On this basis, both do fusion treatment obtain always significantly scheming SR.

SR=N (S) × N (R)

Notable figure is carried out binary conversion treatment, obtains splitting image.So starting retrieval from picture centre line, Choose at notable figure close shot 1/3 for ROI, extract two track characteristic points, be set to (x_i,y_i) (i=0,1,2 ..., n). If the parametric equation that function y=F (x) is corresponding is y=kx+b, to arbitrary characteristics point (x_i,y_i) corresponding target line Error is ε=F (x_i)-y_i, the error sum of squares of the most all Feature point correspondence is as follows:

$f(k,b)=min\underset{i=1}{\overset{n}{\Σ}}{\[{\mathrm{kx}}_i+b-y_i\]}^2$

Above formula obtains the function of minima and is required straight line parameter.

Spacing is detected, first has to the front vehicles in identification extraction image.The present invention uses a kind of approximation Circular sliding window carries out rim detection.Approximation concentric stroking window is slided, in sliding window on gray level image to be detected The gray value of each pixel that portion gives numbering will compare with the gray value of sliding window center pixel.As Really in sliding window gray value of certain some pixel and the difference of center gray scale less than threshold value t set, it is determined that this point with Sliding window central point has identical gray scale, and in sliding window, the summation of all values having same grayscale to center constitutes similar Region.

By coordinate (x_c, y_c) represent sliding window centre coordinate.Use similar comparison function as follows:

C (x, y)=exp [-[[I (x, y)-I (x_c,y_c)]/2]⁶]

(x, y) is coordinate x to I, the gray scale of y；

Then the size of similar area is calculated as:

Generally, threshold value t determines the feature quantity of the characteristic point that can extract.The present invention is in difference Under contrast adaptively selected to t value: in circular sliding window, determine sliding window by pixel value in cumulative sliding window Interior pixel and threshold value t of sliding window center pixel difference.Computational methods are as follows:

For given sub-circular sliding window, sum represents accumulated variables, img_{(i, j)}K () represents that center pixel exists The i-th row jth row in source images, k represents the kth pixel in sliding window.

Then threshold value t of kth pixel is:

T=sum/n (x_c, y_c)

$sum=\underset{s=1}{\overset{k}{\Σ}}{\mathrm{img}}_{(i,j)}\left(s\right)$

Sum makes t value calculate by the method for cumulative sliding window pixel the response characteristic of local contrast, right Pixel in sliding window, t value is increasing, and can remove the complex background that major part contrast is less, retain mesh Mark, well separates target and background, and refines edge, therefore can accurate reservation vehicle edge.

Obtain the difference of kth pixel and center pixel, make comparisons with t, if less than or equal to t, similar Region adds 1, finally judges the size of similar area and threshold value g, if less than g, then current pixel is marginal point, Current pixel value is set to 255, and otherwise, current pixel is not marginal point, it is set to 0.

Before above-mentioned rim detection, first carry out Preliminary screening, only candidate marginal is done rim detection, screening Method is as follows:

First, centered by central pixel point, the pixel calculating vertical segment two ends is poor, and with pre-set Difference threshold Th compares, and edge occurs in the pixel that grey-scale contrast is big, the therefore ash more than Th Degree pixel as candidate marginal, otherwise, the point less than Th is considered as then that interior pixels point is ready to remove.

Vehicle in video image shape in the picture presents certain rule, the most proportional length Square, therefore the present invention uses shape facility as detection vehicle foundation.Vehicle is the rule having lines, Top and bottom portion horizontal line, both sides vertical edges etc. the most after treatment, all can present certain straight line etc. Feature.

For complicated environment, selected shape feature of the present invention and boundary characteristic as extracting vehicle location Feature.Image is cut out by the first present invention, only close shot is carried out vehicle detection, then carries out image Enhancement process, including expanding, corrodes scheduling algorithm.In order to further determine that vehicle location, use the shape of vehicle Shape feature, gets rid of the mistake survey that background causes.

Alternatively, spacing detect in, by the size of each light stream vectors mould be grouped into driving Segmentation, obtains front vehicle position.

ROI can be divided on the basis of detecting track, set up pattern mask, if in image two The straight line in track is y=k₁x+b₁And y=k₂x+b₂, for N × M dimension image I, (x y), arranges pattern mask (x, y) is similarly the bianry image of N × M to M, for all 1's matrix.Its create-rule is as follows.

M (x, y)=1 y ＜ k₁x+b₁And y ＞ k₂x+b₂

M (x, y)=0 other

Vehicle area coverage in the picture is far longer than a block of pixels, so image is carried out vector block Dividing, setup algorithm obtains I_i=I (x_i,y_i) 5 × 5 neighborhood light stream vectors put are V_i=(u_i,v_i), then can obtain (x, y), each field direction covers 5 × 5 neighborhoods of correspondence position in original image to image light flow field Y. As M (x_i,y_iDuring)=1, Y (x_i,y_i)=(u_i,v_i)

In order to carry out single Threshold segmentation, light stream vectors is melted at component u, v of x, y both direction Close, obtain merge scalar figure P (x, y):

$P(x_i,y_i)=\sqrt{u_i^2+v_i^2}$

To P (x_i,y_i) carry out region division, obtain vehicle motion contrast district in image, for early warning meter afterwards Calculate and reliable guarantee is provided.

In sum, the present invention proposes a kind of motor vehicle running safe early warning method, in embedded chip Achieve information of safety inspection for motor vehicles, improve traffic safety early warning performance, it is possible to will calculate in task treating capacity The lower realization of amount calculates and early warning in real time.

Obviously, it should be appreciated by those skilled in the art, each module or each step of the above-mentioned present invention are permissible Realizing by general calculating system, they can concentrate in single calculating system, or is distributed in many On the network that individual calculating system is formed, alternatively, they can use the executable program code of calculating system Realize, it is thus possible to be stored in storage system being performed by calculating system.So, this Bright be not restricted to any specific hardware and software combine.

It should be appreciated that the above-mentioned detailed description of the invention of the present invention is used only for exemplary illustration or explains this The principle of invention, and be not construed as limiting the invention.Therefore, without departing from the spirit and scope of the present invention In the case of any modification, equivalent substitution and improvement etc. done, should be included in protection scope of the present invention Within.Additionally, claims of the present invention be intended to fall into scope and border or Whole in the equivalents on this scope of person and border change and modifications example.

Claims (3)

1. a motor vehicle running safe early warning method, it is characterised in that including:

In vehicle travel process, the image being captured vehicle-mounted vidicon carries out spacing detection；When vehicle with Warning is sent when the spacing of front truck is less than safe distance.

Method the most according to claim 1, it is characterised in that the detection of described spacing farther includes:

Carry out rim detection initially with sub-circular sliding window, will sub-circular sliding window in gray scale to be detected Slide on image, inside sliding window, give the ash of gray value and the sliding window center pixel of each pixel of numbering Angle value compares, if gray value of certain some pixel is less than, with the difference of center gray scale, the threshold set in sliding window Value t, it is determined that this point and sliding window central point have identical gray scale, all in sliding window have same grayscale with center The summation of value constitutes similar area；

By coordinate (x_c, y_c) represent sliding window centre coordinate, use similar comparison function as follows:

C (x, y)=exp [-[[I (x, y)-I (x_c,y_c)]/2]⁶]

(x, y) is coordinate x to I, the gray scale of y；

Then the size of similar area is calculated as:

Under different contrast adaptively selected to t value, i.e. in circular sliding window, by picture in cumulative sliding window Element value determines pixel and threshold value t of sliding window center pixel difference in sliding window:

For given sub-circular sliding window, represent accumulated variables, img with sum_{(i, j)}K () represents center pixel The i-th row jth row in source images, k represents the kth pixel in sliding window, the then threshold value of kth pixel T is:

T=sum/n (x_c, y_c)

$sum=\underset{s=1}{\overset{k}{\Σ}}{\mathrm{img}}_{(i,j)}\left(s\right)$

Sum makes t value in response to local contrast by cumulative sliding window pixel；

Obtain the difference of kth pixel and center pixel, make comparisons with t, if less than or equal to t, similar Region adds 1, finally judges the size of similar area and threshold value g, if less than g, then current pixel is marginal point, Current pixel value is set to 255, and otherwise, current pixel is not marginal point, it is set to 0.

Method the most according to claim 2, it is characterised in that before described rim detection, returning method Also include: only candidate marginal being done rim detection, screening technique is as follows:

First, centered by central pixel point, the pixel calculating vertical segment two ends is poor, and with pre-set Difference threshold Th compares, the gray-scale pixels point more than Th as candidate marginal, otherwise, less than Th Point be considered as then that interior pixels point is ready to remove.