Vehicle posture adjustment method and system based on lane line compensation based on lighting curve

Abstract

The present invention belongs to the field of intelligent driving technology, and specifically discloses a vehicle posture adjustment method and system based on lane line compensation by lighting curve. In view of the situation that lane line is incomplete or lane line recognition is incomplete due to obstruction by the front vehicle, the present invention first uses a vehicle-mounted camera to obtain an image containing lighting and lane lines in front of the vehicle according to the lighting layout rules in tunnels and various night driving scenes, and then processes and curve fits the image to obtain the lighting light source curve and lane line curve respectively, and uses the lighting light source curve to compensate for the lane line curve, and obtains the angle between the vehicle axis and the lane line, that is, the angle that the vehicle should adjust to drive correctly along the lane line, thereby achieving vehicle posture adjustment and finally achieving the lane keeping function.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent driving technology, and in particular relates to a vehicle posture adjustment method and system based on lane line compensation based on lighting curves. Background Art

[0002] Lane keeping is a basic function of smart driving cars and also a guarantee for the safe and reliable driving of smart driving vehicles. Lane line recognition is the prerequisite for lane keeping. How to accurately recognize lane lines plays an important role in timely and accurate adjustment of vehicle posture. At present, lane line recognition mainly uses computer vision to process and recognize lane line images. This method uses the on-board camera to capture the image data in front of the vehicle, recognizes the lane line through image processing, and then calculates the angle between the vehicle axis and the lane line, further adjusts the control heading, and finally realizes the lane keeping function.

[0003] The above method has high requirements for the integrity of lane lines. When lane lines are incomplete or blocked by the front vehicle, only a short range of lane lines can be identified. In environments with poor lighting conditions such as night and tunnels, insufficient or unstable lighting will result in incomplete lane line recognition using computer vision, and only partial lane line fragments can be obtained. The inventors analyzed the layout of lighting in scenes such as tunnels and found that the axis of the lighting equipment is basically consistent with the axis of the lane.

[0004] Based on this, the present invention considers proposing a solution to compensate for lane line recognition by using the lighting curve in tunnels and various nighttime driving scenes, so as to make up for the lack of lane line recognition in tunnels and various nighttime driving scenes, and facilitate timely and accurate adjustment of vehicle posture, thereby realizing the lane keeping function. However, there is no relevant technology to solve this problem. Summary of the invention

[0005] The purpose of the present invention is to propose a vehicle posture adjustment method based on lane line compensation based on lighting curve. According to the lighting layout rules in tunnels and various night driving scenes, the method uses the obtained lighting light source fitting curve to identify and compensate for lane lines, thereby accurately adjusting the vehicle posture and ultimately achieving the lane keeping function.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme:

[0007] The vehicle posture adjustment method based on lane line compensation of lighting curve includes the following steps:

[0008] Step 1. Obtain an image containing lights and lane lines in front of the vehicle;

[0009] Step 2. Preprocess the acquired image and perform lane feature detection and lane curve fitting;

[0010] Step 3. Determine whether the lane line is missing based on the lane line feature detection and lane line curve fitting; if the lane line is missing, execute steps 4 to 6; otherwise, if the lane line is not missing, go directly to step 7;

[0011] Step 4. Based on the multiple lighting light sources contained in the image obtained in step 1, the outline of the lighting light source is fitted using the ellipse fitting principle, and the center point position coordinates of each lighting light source are determined;

[0012] Step 5. Use the least square method to perform curve fitting on the center points of the multiple lighting light sources obtained in step 4 to obtain a lighting light source fitting curve;

[0013] Step 6. Use the lighting light source fitting curve obtained in step 5 to compensate the lane line curve obtained by lane line curve fitting in step 2 to obtain the compensated lane line, and then go to step 7;

[0014] Step 7. Calculate the angle between the vehicle axis and the lane line, that is, the angle that needs to be adjusted for normal vehicle driving.

[0015] In addition, based on the vehicle posture adjustment method based on the compensation of the lighting curve for the lane line, the present invention also proposes a corresponding vehicle posture adjustment system based on the compensation of the lighting curve for the lane line, which adopts the following scheme:

[0016] The vehicle posture adjustment system based on the lane line compensation of the lighting curve includes the following modules:

[0017] An image acquisition module is used to acquire an image including lights and lane lines in front of the vehicle;

[0018] The lane feature detection and curve fitting module is used to pre-process the acquired image, perform lane feature detection and lane curve fitting, and obtain the lane curve;

[0019] The lane line missing judgment module is used to judge whether the lane line is missing based on the lane line feature detection and curve fitting;

[0020] A light source fitting module is used to fit the contour of the lighting light source based on the multiple lighting light sources contained in the obtained image using the ellipse fitting principle, and determine the center point position coordinates of each lighting light source;

[0021] The lighting light source fitting module is used to perform curve fitting on the central points of the obtained multiple lighting light sources using the least square method to obtain a lighting light source fitting curve;

[0022] The lane line compensation module is used to compensate the lane line curve by fitting the curve of the lighting light source;

[0023] And the posture adjustment module is used to calculate the angle between the vehicle axis and the lane line, that is, the angle that needs to be adjusted for normal driving of the vehicle.

[0024] The present invention has the following advantages:

[0025] As described above, in view of the deficiencies in the prior art of incomplete lane line recognition due to incomplete lane lines or obstruction by the vehicle in front, as well as the inability to fully recognize lane lines in environments with poor lighting conditions such as at night and in tunnels, the present invention proposes a vehicle posture adjustment method and system based on lane line compensation based on lighting curves. The present invention makes full use of the characteristic that the axis of the lighting equipment is basically consistent with the axis of the lane, and can relatively easily extract the lighting contour, and obtain the lighting light source fitting curve by curve fitting. The lighting light source fitting curve is then used to identify and compensate for the missing lane lines, thereby making up for the deficiencies in lane line recognition in tunnels and various nighttime driving scenarios. After the lane lines are accurately identified through curve compensation, the vehicle posture is further adjusted in a timely and accurate manner according to the identified lane lines, which is ultimately conducive to realizing the lane keeping function. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a vehicle posture adjustment method based on lane line compensation of a lighting curve in an embodiment of the present invention;

[0027] Figure 2 This is a schematic diagram after curve fitting in an embodiment of the present invention;

[0028] Figure 3 Schematic diagram of the angle between the vehicle axis and the lane line in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments:

[0030] Example 1

[0031] In view of the technical problems in the prior art that lane line recognition is incomplete due to incomplete lane line or obstruction by the front vehicle, and lane line recognition is inaccurate due to light changes in tunnels or various night driving scenes, the present invention analyzes the layout of lighting lamps in tunnels and various night driving scenes, and finds that the axis of the lighting equipment is basically consistent with the axis of the lane. On this basis, the present invention proposes a vehicle posture adjustment method based on lane line compensation based on lighting lamp curve. First, an image containing lighting lamps and lane lines in front of the vehicle is obtained by using an ordinary vehicle-mounted camera. After image processing and curve fitting, the lighting lamp layout curve and lane lines are obtained respectively. The lane line is compensated by using the lighting lamp curve, and the angle between the vehicle axis and the lane line axis is calculated. In environments with poor lighting conditions such as night and tunnels, it is difficult to use computer vision to recognize lane lines, but it is easier to extract the outline of lighting lamps from such environments; compared with the situation where the lane line is easily obstructed by the front vehicle, the position of the lighting lamp is higher and is not easily obstructed by the front vehicle. Therefore, the present invention can compensate for the lack of lane line recognition in tunnels and various night driving scenes by using the lighting lamp layout rules in the tunnel, and achieve good results.

[0032] like Figure 1 As shown, the vehicle posture adjustment method based on the lane line compensation of the lighting curve includes the following steps:

[0033] Step 1. Get an image containing lights and lane lines in front of the vehicle.

[0034] Specifically, in this embodiment, an on-board camera is used to obtain an image including the lighting and lane lines in front of the vehicle. The on-board camera is fixed in front of the vehicle and is located on the symmetry axis of the vehicle.

[0035] Step 2. Perform preprocessing operations on the acquired image, including grayscale processing and binarization processing, and perform lane line feature detection and lane line curve fitting to obtain the lane line curve.

[0036] The specific steps of step 2 are:

[0037] Step 2.1. Grayscale processing;

[0038] For each pixel of the image, calculate its grayscale value according to formula (1) to obtain a grayscale image;

[0039] (1)

[0040] in, are the pixel coordinates, , , are the brightness values ​​of the red, green, and blue channels of the pixel, respectively. is the calculated grayscale value.

[0041] Step 2.2. Binarization processing.

[0042] The graythresh function is used to determine the grayscale threshold of the image.

[0043] Traverse each pixel of the image and compare its grayscale value with the grayscale threshold; if the grayscale value is greater than the grayscale threshold, set the grayscale value to white; if the grayscale value is less than the grayscale threshold, set it to black to obtain a binary image.

[0044] Step 2.3. Use the Canny edge detection algorithm to extract the edge, then filter the lane feature points, and use the least squares method to fit the lane curve to obtain the lane curve, such as Figure 2 The curve in shown.

[0045] Step 3. Determine whether the lane line is missing based on the lane line feature detection and lane line curve fitting; if the lane line is missing, execute steps 4 to 6; otherwise, if the lane line is not missing, go directly to step 7.

[0046] Specifically, the conditions for determining lane line missing are as follows:

[0047] The lane line is considered missing when any of the following conditions I to II is met:

[0048] I. The lane line is incomplete, resulting in incomplete lane line detection;

[0049] II. The lane line is blocked by the front vehicle, resulting in incomplete lane line detection.

[0050] Step 4. Based on the multiple lighting sources contained in the image obtained in step 1, the outline of the lighting source is fitted using the ellipse fitting principle, and the center point position coordinates of each lighting source are determined.

[0051] Step 4.1. Assume the ellipse equation of the i-th lighting lamp contour as shown in equation (2):

[0052] (2)

[0053] Among them, A i , B i , C i , D i 、E i 、F i represent the ellipse fitting coefficients respectively.

[0054] set up is the pixel point on the i-th lighting contour; where j=1,2,…,N, N is the number of pixel points on the i-th lighting contour, N>5; according to the least squares principle, the following objective function is established :

[0055] (3).

[0056] Will Simplified to f, to minimize the objective function f, we need to make:

[0057] (4).

[0058] Step 4.2. Solve the ellipse fitting coefficient A according to equations (3) and (4): i , B i , C i , D i 、E i 、F i , Substitute each ellipse fitting coefficient into formula (2) to obtain the ellipse equation of the i-th lighting lamp profile.

[0059] Step 4.3. Based on the definition of the ellipse, calculate the coordinates of the center point of the i-th lighting source according to equation (5).

[0060] (5)

[0061] in, Represents the center point coordinates of the i-th lighting source.

[0062] Step 4.4. Obtain the coordinates of the center point of each light source of each lighting lamp in sequence according to steps 4.1 to 4.3.

[0063] Step 5. Use the least squares method to perform curve fitting on the center points of the multiple lighting sources obtained in step 4 to obtain the lighting source fitting curve, such as Figure 2 The curve in shown.

[0064] Step 5.1. Assume that the expression of the fitting curve of the lighting source is as shown in formula (6):

[0065] (6)

[0066] Among them, (x, y) represents the point on the fitting curve of the lighting source. , , represents the fitting coefficients of the least squares method.

[0067] The center point position coordinates of the lighting source obtained in step 4 Substituting into equation (6), we get equation (7):

[0068] (7)

[0069] Wherein, i=1,2,…,M, M is the number of light source center points, M>3.

[0070] Step 5.2. To simplify the calculation, the following definitions are made:

[0071] , T = ,X= ;

[0072] Using the least squares method, we transform equation (7) into a determinant and obtain equation (8). , , .

[0073] ;

[0074] ;

[0075] ;

[0076] (8)

[0077] The parameters , , Substituting the fitting curve equation into formula (6), the lighting light source fitting curve is obtained.

[0078] Step 6. Use the lighting light source fitting curve to compensate the lane line curve to obtain the compensated lane line.

[0079] Step 6.1. Assume that the fitting curve of the lighting source is , the lane curve segment is ; On the two curves, the fitting curve of the lighting source and lane curve segments Take points evenly on the top;

[0080] set up Obtained points with coordinates , , , ,set up Obtained points with coordinates , , , , because the lane line is missing, here Less than .

[0081] Step 6.2. In the scenario faced by this embodiment, the axis of the lighting source layout of the lighting lamp is consistent with the axis of the lane line, so the lighting source curve can be used to compensate for the missing lane line curve segment.

[0082] First, it is necessary to compare the lane line curve segment with the different positions of the lighting light source curve to find the position where the curve features of the lane line curve segment and the lighting light source curve are consistent.

[0083] In this embodiment, the vector difference between two adjacent points on the curve is used as the comparison object.

[0084] Fitting the lighting source to the curve Subtract the adjacent points on the graph, and assume that the vector obtained is:

[0085] , , , .

[0086] Lane curve segment Make a difference between adjacent points on the graph, and assume that the vector obtained is:

[0087] , , , .

[0088] Step 6.3. Convert the vector ( ) and vector ( ) are compared at different positions, and the similarity of different positions is obtained by using the difference method. The calculation formula is as follows:

[0089] ; in .beg The minimum value point indicates that the lane line curve segment is most similar to the lighting fitting curve at this position.

[0090] Step 6.4. At the position where the lane curve segment is most similar to the lighting light source curve, a total of m points are aligned.

[0091] Add the remaining nm points in the lighting source curve to the front or back of the lane line segment according to their positions. Lane curve points are expanded to Lane curve points.

[0092] Step 7. Calculate the angle between the vehicle axis and the lane line, that is, the angle that needs to be adjusted for normal vehicle driving.

[0093] like Figure 3 As shown, in order to achieve lane keeping and lane line following, it is necessary to determine the angle between the vehicle's driving direction and the lane line to achieve vehicle heading control. In this embodiment, the angle between the vehicle's head direction and the tangent of the lane line curve is calculated. , which is the angle between the vehicle's direction of travel and the lane line According to formula (9), we get value;

[0094] (9)

[0095] in is the unit vector of the vehicle head direction, is the tangent direction vector of the lane curve, It is the angle between the front of the vehicle and the tangent of the lane line, that is, the angle that needs to be adjusted for the vehicle to maintain lane.

[0096] After adjusting the above angle, it is convenient to complete the vehicle posture adjustment in a timely and accurate manner, and finally realize the lane keeping function.

[0097] The method of the present invention is easy to implement, and is particularly suitable for scenes such as tunnels where the axis of the light source layout of the lighting lamp is consistent with the axis of the lane line, and is suitable for situations where the lane line is incomplete or blocked by the front vehicle, or where the lane line recognition is incomplete due to poor light.

[0098] Example 2

[0099] This embodiment 2 describes a vehicle posture adjustment system based on lane line compensation by lighting curve, which is based on the same inventive concept as the vehicle posture adjustment method based on lane line compensation by lighting curve described in the above embodiment 1.

[0100] The vehicle posture adjustment system based on the lane line compensation of the lighting curve includes the following modules:

[0101] An image acquisition module is used to acquire an image including lights and lane lines in front of the vehicle;

[0102] The lane feature detection and curve fitting module is used to pre-process the acquired image, perform lane feature detection and lane curve fitting, and obtain the lane curve;

[0103] The lane line missing judgment module is used to judge whether the lane line is missing based on the lane line feature detection and curve fitting;

[0104] A light source fitting module is used to fit the contour of the lighting light source based on the multiple lighting light sources contained in the obtained image using the ellipse fitting principle, and determine the center point position coordinates of each lighting light source;

[0105] The lighting light source fitting module is used to perform curve fitting on the central points of the obtained multiple lighting light sources using the least square method to obtain a lighting light source fitting curve;

[0106] The lane line compensation module is used to compensate the lane line curve by fitting the curve of the lighting light source;

[0107] And the posture adjustment module is used to calculate the angle between the vehicle axis and the lane line, that is, the angle that needs to be adjusted for normal driving of the vehicle.

[0108] It should be noted that in the vehicle posture adjustment system of the present embodiment 2, the implementation process of the functions and effects of each functional module is specifically described in the implementation process of the corresponding steps in the method of the above embodiment 1, and will not be repeated here.

[0109] Example 3

[0110] This embodiment 3 describes a computer device, which includes a memory and one or more processors. The memory stores executable code. When the processor executes the executable code, it is used to implement the vehicle posture adjustment method based on the lighting curve to compensate the lane line in the above embodiment 1.

[0111] In this embodiment, the computer device is any device or apparatus with data processing capability, which will not be described in detail here.

[0112] Example 4

[0113] This embodiment 4 describes a computer-readable storage medium on which a program is stored. When the program is executed by a processor, it is used to implement the vehicle posture adjustment method based on lane line compensation based on lighting curve in the above-mentioned embodiment 1.

[0114] The computer-readable storage medium may be an internal storage unit of any device or apparatus with data processing capabilities, such as a hard disk or memory, or an external storage device of any device with data processing capabilities, such as a plug-in hard disk, a smart media card (SMC), an SD card, a flash card, etc., equipped on the device.

[0115] Of course, the above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiments. It should be noted that all equivalent substitutions and obvious deformation forms made by any technician familiar with the field under the guidance of this specification fall within the essential scope of this specification and should be protected by the present invention.

Claims

1. A vehicle posture adjustment method based on lane line compensation using lighting curves, characterized in that: The steps include: Step 1. Obtain an image containing lights and lane lines in front of the vehicle; In step 1, the image of the front of the vehicle including the lighting and the lane line is obtained from a vehicle-mounted camera; wherein the vehicle-mounted camera is fixed in front of the vehicle and is located on the axis of symmetry of the vehicle; Step 2: Preprocess the acquired image and perform lane feature detection and lane curve fitting; Step 3. Determine whether the lane line is missing based on the lane line feature detection and lane line curve fitting; if the lane line is missing, execute steps 4 to 6; otherwise, if the lane line is not missing, go directly to step 7; Step 4. Based on the multiple lighting light sources contained in the image obtained in step 1, the outline of the lighting light source is fitted using the ellipse fitting principle, and the center point position coordinates of each lighting light source are determined; Step 5. Use the least square method to perform curve fitting on the center points of the multiple lighting light sources obtained in step 4 to obtain a lighting light source fitting curve; Step 6. Use the lighting light source fitting curve obtained in step 5 to compensate the lane line curve obtained by lane line curve fitting in step 2 to obtain the compensated lane line, and then go to step 7; Step 7. Calculate the angle between the vehicle axis and the lane line, that is, the angle that needs to be adjusted for normal vehicle driving.

2. The vehicle posture adjustment method based on lane line compensation by lighting curve according to claim 1, characterized in that: The step 2 is specifically as follows: Step 2.

1. Grayscale processing; For each pixel of the image, calculate its grayscale value according to formula (1) to obtain a grayscale image; Gray(p,q)=0.3*R(p,q)+0.59*G(p,q)+0.11*B(p,q) (1) Among them, Gray(p,q) is the calculated gray value, (p,q) is the coordinate of the pixel, R(p,q), G(p,q), and B(p,q) are the brightness values ​​of the red, green, and blue channels of the pixel respectively; Step 2.

2. Binarization processing; Use the graythresh function to determine the grayscale threshold of the image; Traverse each pixel of the image and compare its grayscale value with the grayscale threshold; if the grayscale value is greater than the grayscale threshold, set the grayscale value to white; if the grayscale value is less than the grayscale threshold, set it to black to obtain a binary image; Step 2.

3. Use the Canny edge detection algorithm to extract edges, then screen the lane feature points, and use the least squares method to fit the lane curve to obtain the lane curve.

3. The vehicle posture adjustment method based on lane line compensation by lighting curve according to claim 1, characterized in that: In step 3, the conditions for determining whether the lane line is missing are as follows: The lane line is considered missing when any of the following conditions I to II is met: I. The lane line is incomplete, resulting in incomplete lane line detection; II. The lane line is blocked by the front vehicle, resulting in incomplete lane line detection.

4. The vehicle posture adjustment method based on lane line compensation by lighting curve according to claim 1, characterized in that: The step 4 is specifically as follows: Step 4.

1. Assume the ellipse equation of the i-th lighting lamp contour as shown in equation (2): A i x 2 +B i xy+C i y 2 +D i x+E i y+F i =0 (2) Among them, A i , B i , C i , D i 、E i 、F i They represent the ellipse fitting coefficients respectively; Assume (x ij ,y ij ) is the pixel point on the i-th lighting lamp contour; where j = 1, 2, ..., N, N is the number of pixel points on the i-th lighting lamp contour, N > 5; according to the least squares principle, the following objective function f(A i ,B i ,C i ,D i ,E i ,F i ): f(A i ,B i ,C i ,D i ,E i ,F i ) is simplified to f. To minimize the objective function f, we need to make: Step 4.

2. Solve the ellipse fitting coefficient A according to equations (3) and (4): i , B i , C i , D i 、E i 、F i , Substitute each ellipse fitting coefficient into formula (2) to obtain the ellipse equation of the i-th lighting lamp profile; Step 4.

3. According to the definition of the ellipse, calculate the position coordinates of the center point of the i-th lighting source according to formula (5); Among them, (x ic ,y ic ) represents the center point position coordinates of the i-th lighting source; Step 4.

4. Obtain the coordinates of the center point of the light source of each lighting lamp in sequence according to steps 4.1 to 4.

3.

5. The vehicle posture adjustment method based on lane line compensation by lighting curve according to claim 1, characterized in that: The step 5 is specifically as follows: Step 5.

1. Assume that the equation of the fitting curve of the lighting source is expressed as shown in equation (6): y=a2x 2 +a1x+a0 (6) Among them, a0, a1, and a2 represent the fitting coefficients of the least squares method; The center point position coordinates (x ic ,y ic ) into equation (6), we get equation (7): Wherein, i=1,2,…,M, M is the number of light source center points, M>3; Step 5.

2. To simplify the calculation, the following definitions are made: Use the least square method to transform the determinant of equation (7) to obtain equation (8), and find a0, a1, and a2; HX = T; H T HX=H T T; (H T H) -1 H T HX=(H T H) -1 H T T; X=(H T H) -1 H T T (8) Substitute the parameters a0, a1, and a2 into the fitting curve equation in formula (6) to obtain the lighting light source fitting curve.

6. The vehicle posture adjustment method based on lane line compensation by lighting curve according to claim 1, characterized in that: The step 6 is specifically as follows: Step 6.

1. Assume that the lighting light source fitting curve is l1 and the lane line curve segment is l2, and evenly select points on the lighting light source fitting curve l1 and the lane line curve l2; Suppose we have n points on l1, with coordinates (a1,b1), (a2,b2), ..., (a n ,b n ), suppose m points are obtained on l2, with coordinates (c1, d1), (c2, d2), ..., (c m ,d m ), where m is less than n due to the missing lane line; Step 6.

2. Use the lighting light source curve to compensate for the missing lane line curve segment. The process is as follows: Firstly, the lane line curve segment is compared with different positions of the lighting light source curve, and the position where the curve features of the lane line curve segment and the lighting light source curve are consistent is found, and the vector difference between two adjacent points on the curve is used as the comparison object; Subtract the adjacent points on the lighting source fitting curve l1, and assume the obtained vector is: <h2 style=";text-align:left;direction:ltr">μ1 = (a1,b1) - (a2,b2) μ2 = (a2,b2) - (a3,b3) μ1 = (a1,b1) - (a2,b2) μ2 = (a3,b3) μ1 = (a3,b1 ...<h2 style=";text-align:left;direction:ltr"> n-1 <h2 style=";text-align:left;direction:ltr"> (a)<h2 style=";text-align:left;direction:ltr"> n-1 <h2 style=";text-align:left;direction:ltr"> ,b<h2 style=";text-align:left;direction:ltr"> n-1 <h2 style=";text-align:left;direction:ltr"> )-(a<h2 style=";text-align:left;direction:ltr"> n <h2 style=";text-align:left;direction:ltr"> ,b<h2 style=";text-align:left;direction:ltr"> n <h2 style=";text-align:left;direction:ltr"> ); Subtract the adjacent points on the lane curve segment l2, and assume that the obtained vector is: ν1=(c1,d1)-(c2,d2),ν2=(c2,d2)-(c3,d3),...,ν m-1 =(c m-1 ,d m-1 )-(c m ,d m ); Step 6.

3. Substitute the vector (μ1,μ2,...,μ m-1 ) and the vector (ν1,ν2,...,ν n-1 ) are compared at different positions, and the similarity of different positions is obtained by using the difference method. The calculation formula is as follows: ω k =(μ k -ν1)+(μ k+1 -ν2)+...+(μ k+m-2 -ν m-1 ), where k = 1, 2, 3, ..., n-m + 1; find ω k The minimum value point of , which indicates that the lane curve segment and the lighting fitting curve are most similar at this position; Step 6.

4. At the position where the lane curve segment is most similar to the light source curve of the lighting lamp, a total of m points are aligned; The remaining nm points in the lighting light source curve are added to the front or back of the lane line segment according to their positions, so as to expand the m lane line curve points to n lane line curve points.

7. The vehicle posture adjustment method based on lane line compensation by lighting curve according to claim 1, characterized in that: The step 7 is specifically as follows: Solve the angle between the vehicle head direction and the tangent line of the lane curve, that is, the angle between the vehicle driving direction and the lane line, so as to realize the vehicle heading control; according to formula (9), the δ value is obtained; Among them, α is the unit vector of the vehicle head direction, β is the tangent direction vector of the lane line curve, and δ is the angle between the vehicle head and the lane line tangent, that is, the angle that needs to be adjusted for the vehicle to keep the lane.

8. A vehicle posture adjustment system based on lane line compensation using lighting curves, characterized in that: Includes the following modules: An image acquisition module, used to acquire an image including lighting and lane lines in front of the vehicle; The image including the lighting and lane lines in front of the vehicle is obtained from a vehicle-mounted camera; wherein the vehicle-mounted camera is fixed in front of the vehicle and located on the symmetry axis of the vehicle; The lane feature detection and curve fitting module is used to pre-process the acquired image, perform lane feature detection and lane curve fitting, and obtain a lane curve; The lane line missing judgment module is used to judge whether the lane line is missing based on the lane line feature detection and curve fitting; A light source fitting module is used to fit the contour of the lighting source based on the multiple lighting sources contained in the obtained image using the ellipse fitting principle, and determine the center point position coordinates of each lighting source; The lighting light source fitting module is used to perform curve fitting on the central points of the obtained multiple lighting light sources using the least square method to obtain a lighting light source fitting curve; The lane line compensation module is used to compensate the lane line curve by fitting the curve of the lighting light source; And the posture adjustment module is used to calculate the angle between the vehicle axis and the lane line, that is, the angle that needs to be adjusted for normal driving of the vehicle.

Images