A lane line matching method, device, equipment and storage medium

Abstract

The application provides a lane line matching method, obtains multiple groups of to-be-tested lane line data and multiple groups of true value lane line data of a target lane line at the same time, performs matching calculation on the to-be-tested lane line data and the true value lane line data, obtains matching error data, determines minimum matching error data in the multiple groups of to-be-tested lane line data and the multiple groups of true value lane line data, and obtains an optimal matching pair of the target lane line according to to-be-tested lane line data and true value lane line data corresponding to the minimum matching error data. The application also provides a matching device, a matching equipment and a storage medium. The technical scheme of the application can obtain multiple true value lane lines and multiple to-be-tested lane lines at the same time, and solves the technical problem that the current technical scheme cannot pair and screen the multiple true value lane lines and the multiple to-be-tested lane lines to obtain an optimal matching pair.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a lane line matching method and device, equipment and a storage medium. BACKGROUND

[0002] In the field of automatic driving, an important research direction is to realize automatic driving through visual perception, that is, to obtain image information of the surrounding environment through a camera installed on the vehicle, to perceive the information in the image through a visual perception algorithm, and to provide necessary "vision" for automatic driving regulation control. In the research and development stage of the perception algorithm, a large number of tests need to be carried out to ensure the correctness and accuracy of the perception algorithm. At present, the test of lane line perception results is an important part of algorithm testing. When testing the lane line output by the algorithm, an optimal true value lane line needs to be matched for the to-be-tested lane line, and then the true value lane line is referred to for evaluating the recognition accuracy of the to-be-tested lane line. The true value lane line can be obtained by manually observing and measuring the actual test scene, and then compared with the to-be-tested lane line data obtained by the to-be-tested camera on the vehicle to determine whether the lane line data obtained by the to-be-tested camera on the vehicle is accurate.

[0003] At present, in order to reduce manpower, a radar sensor is generally used to quickly obtain a true value lane line, and the radar sensor and the to-be-tested camera synchronously obtain lane lines of the same time and the same scene, and then the lane lines are compared. However, multiple true value lane lines and multiple to-be-tested lane lines can be obtained at the same time, and the current technical solution cannot pair and screen the optimal matching pair from the multiple true value lane lines and the multiple to-be-tested lane lines. SUMMARY

[0004] In view of the above-mentioned shortcomings of the prior art, the present application provides a lane line matching method, device, equipment and storage medium. To solve the above technical problems.

[0005] The lane line matching method provided by the present application comprises:

[0006] Obtaining multiple groups of to-be-tested lane line data and multiple groups of true value lane line data of a target lane line at the same time;

[0007] Matching and calculating the to-be-tested lane line data and the true value lane line data to obtain matching error data, so as to determine the minimum matching error data in the multiple groups of to-be-tested lane line data and the multiple groups of true value lane line data;

[0008] According to the to-be-tested lane line data and the true value lane line data corresponding to the minimum matching error data, an optimal matching pair of the target lane line is obtained.

[0009] In an embodiment of the present application, the matching calculation of the to-be-tested lane line data and the true value lane line data to obtain the matching error data comprises:

[0010] Based on the two-dimensional coordinate information of each point contained in the to-be-tested lane line data and the true value lane line data, curve fitting is performed in the image coordinate system to obtain a fitting curve of the to-be-tested lane line and a fitting curve of the true value lane line, respectively,

[0011] The matching calculation is performed according to the fitting curve of the to-be-tested lane line and the fitting curve of the true value lane line to obtain the matching error data.

[0012] In an embodiment of the present application, the matching calculation according to the fitting curve of the to-be-tested lane line and the fitting curve of the true value lane line to obtain the matching error data comprises:

[0013] n sampling points are taken in the x direction of the image coordinate system, and the absolute error data of the to-be-tested lane line data and the true value lane line data in the y direction of the image coordinate system corresponding to each sampling point is matched and calculated,

[0014] The average value of the absolute error data is calculated and taken as the matching error data.

[0015] In an embodiment of the present application, the taking of n sampling points in the x direction of the image coordinate system comprises:

[0016] According to the real zero point segmentation method, the segment between the starting point and the ending point in the x direction of the image coordinate system is divided into at least one sub-interval;

[0017] The sampling points are collected in the x direction of the image coordinate system at a fixed step, and the sampling points belonging to the same sub-interval are divided into the same group.

[0018] In an embodiment of the present application, the calculation of the average value of the absolute error data comprises:

[0019] The error data of the to-be-tested lane line data and the true value lane line data in the y direction of the image coordinate system corresponding to each sampling point in the same sub-interval is obtained, and the error data is summed to obtain the sum of the sub-interval error data;

[0020] The sum of the absolute values of each sub-interval error data is summed and divided by the total number of sampling points of each sub-interval to obtain the average value of the absolute error data.

[0021] In an embodiment of the present application, the obtaining of the to-be-tested lane line data set and the true value lane line data set of the target lane line at the same time comprises:

[0022] All target lane line images of the target lane line at the same time are obtained by two groups of sensors, respectively,

[0023] all the target lane line images acquired by the first group of sensors are processed to obtain a lane line data set as a to-be-tested lane line data set,

[0024] all the target lane line images acquired by the second group of sensors are processed to obtain a lane line data set as a true value lane line data set.

[0025] In an embodiment of the present application, the first group of sensors are to-be-tested sensors; and the second group of sensors are reference sensors and are used to provide evaluation reference data for the to-be-tested sensors.

[0026] Also provided is a lane line matching device, which is characterized by comprising:

[0027] a data acquisition module, configured to acquire a to-be-tested lane line data set and a true value lane line data set of a target lane line at the same time,

[0028] a matching module, configured to respectively match each to-be-tested lane line data in the to-be-tested lane line data set with each true value lane line data in the true value lane line data set, respectively obtain matching error data, select the smallest matching error data from the matching error data, and determine that a corresponding true value lane line and to-be-tested lane line are an optimal matching pair of the target lane line based on a pair of to-be-tested lane line data and true value lane line data mapped by the smallest matching error data.

[0029] Also provided is an electronic device, which is characterized by comprising:

[0030] one or more processors;

[0031] a storage device, configured to store one or more programs, when the one or more programs are executed by the one or more processors, the electronic device is caused to implement the steps of the matching method provided in each of the above embodiments.

[0032] Also provided is a computer readable storage medium, which is characterized by storing computer readable instructions thereon, when the computer readable instructions are executed by a processor of a computer, the computer is caused to execute the steps of the matching method for quickly matching a true value lane line for a to-be-tested lane line according to any one of claims 1 to 7.

[0033] The present application has the following beneficial effects: in the present application, all to-be-tested lane lines and true value lane lines at the same time are acquired, then the to-be-tested lane lines and the true value lane lines are traversed, the best matching true value lane line is selected for the to-be-tested lane line, and finally a matching pair is formed, so that the optimal matching pair is screened out from multiple to-be-tested lane lines and multiple true value lane lines.

[0034] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application, as claimed. BRIEF DESCRIPTION OF DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and serve to explain the principles of the application. It is readily apparent to one skilled in the art that the following figures are merely some embodiments of the present application, and other figures can be obtained by those of ordinary skill in the art without any creative effort, based on these figures. In the drawings:

[0036] Figure 1 is a step flow chart of a lane line matching method according to an exemplary embodiment of the present application;

[0037] Figure 2 is a step flow chart of obtaining the to-be-tested lane line data set and the true value lane line data set of the target lane line at the same time according to step S1 of an exemplary embodiment of the present application;

[0038] Figure 3 is a step flow chart of performing matching calculation on the to-be-tested lane line data and the true value lane line data according to step S2 of an exemplary embodiment of the present application;

[0039] Figure 4 is a step flow chart of performing matching calculation according to the fitting curve of the to-be-tested lane line and the fitting curve of the true value lane line according to step S23 of an exemplary embodiment of the present application;

[0040] Figure 5 is a step flow chart of taking n sampling points in the x direction of the image coordinate system according to step S231 of an exemplary embodiment of the present application;

[0041] Figure 6 is a step flow chart of calculating the average value of the absolute error data according to step S233 of an exemplary embodiment of the present application;

[0042] Figure 7 is a schematic diagram of an image coordinate system according to an exemplary embodiment of the present application;

[0043] Figure 8 is a detailed step flow chart of a matching algorithm according to an exemplary embodiment of the present application;

[0044] Figure 9 is a block diagram of a matching device according to an exemplary embodiment of the present application;

[0045] Figure 10A structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application is shown. DETAILED DESCRIPTION

[0046] Other advantages and effects of the present application can be easily understood by those skilled in the art from the description of the embodiments of the present application. The present application can also be implemented or applied in other different specific embodiments, and the details in the description can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, but not for limiting the protection scope of the present application.

[0047] It should be noted that the diagrams provided in the following embodiments only schematically illustrate the basic concept of the present application, and only the components related to the present application are shown in the diagrams, but not the number, shape and size of the components in actual implementation. The shape, number and ratio of the components in actual implementation can be arbitrarily changed, and the layout pattern of the components can be more complex.

[0048] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application, however, it is obvious for those skilled in the art that the embodiments of the present application can be implemented without these specific details, and in other embodiments, the known structures and devices are shown in the form of block diagrams instead of details, to avoid making the embodiments of the present application difficult to understand.

[0049] First of all, it should be noted that the curve fitting of the lane line is performed by collecting the lane line linear data, analyzing the curve parameters, and selecting the applicable fitting method to identify the linear shape of the lane line to be fitted. The specific method used for curve fitting includes Lagrange interpolation method, piecewise interpolation method, spline fitting method and least square method, etc.

[0050] Figure 1 A step flowchart of a lane line matching method shown for an exemplary embodiment of the present application is shown in FIG. 1, and the steps of the lane line matching method are as follows: Figure 1

[0051] Step S1, obtaining a plurality of sets of to-be-tested lane line data and a plurality of sets of true value lane line data of the target lane line at the same time.

[0052] Step S2, performing matching calculation on the to-be-tested lane line data and the true value lane line data to obtain matching error data. The matching error data is used to describe the similarity of two lane lines, and the smaller the matching error is, the higher the similarity of the two lane lines is.

[0053] ​Step S3, determining the minimum matching error data in the multiple sets of to-be-tested lane line data and the multiple sets of true value lane line data.

[0054] Step S4, obtaining the optimal matching pair of the target lane line according to the to-be-tested lane line data and the true value lane line data corresponding to the minimum matching error data.

[0055] Figure 2 The step flow chart of the step S1 shown in an exemplary embodiment of the present application for obtaining the to-be-tested lane line data set and the true value lane line data set of the target lane line at the same time. As shown in Figure 2 , the step of obtaining the to-be-tested lane line data set and the true value lane line data set of the target lane line at the same time can include the following steps:

[0056] Step S11, obtaining all target lane line images of the target lane line at the same time by two groups of sensors.

[0057] Step S12, obtaining the lane line data set obtained after image processing of all target lane line images obtained by the first group of sensors as the to-be-tested lane line data set.

[0058] Step S13, obtaining the lane line data set obtained after image processing of all target lane line images obtained by the second group of sensors as the true value lane line data set.

[0059] The first group of sensors is used as the to-be-tested sensor; the second group of sensors is used as the reference sensor and is used to provide evaluation reference data for the to-be-tested sensor.

[0060] Figure 3 The step flow chart of the step S2 shown in an exemplary embodiment of the present application for matching calculation of the to-be-tested lane line data and the true value lane line data, as shown in Figure 3 , the matching calculation of the to-be-tested lane line data and the true value lane line data can include the following steps:

[0061] Step S21, based on the two-dimensional coordinate information of each point contained in the to-be-tested lane line data and the true value lane line data.

[0062] Step S22, as shown in Figure 7 , curve fitting is performed in the image coordinate system to obtain the fitting curve of the to-be-tested lane line and the fitting curve of the true value lane line, respectively.

[0063] Step S23, performing matching calculation according to the fitting curve of the to-be-tested lane line and the fitting curve of the true value lane line to obtain the matching error data.

[0064] Figure 4A flowchart illustrating step S23, which involves performing a matching calculation based on the fitted curve of the lane line to be tested and the fitted curve of the true lane line, is shown in an exemplary embodiment of this application. Figure 4 As shown, the matching calculation based on the fitted curve of the lane line to be tested and the fitted curve of the true lane line to obtain the matching error data may include the following steps:

[0065] Step S231: Take n sampling points in the x direction of the image coordinate system.

[0066] Step S232: Match and calculate the absolute error data between the lane line data to be tested and the true lane line data corresponding to each sampling point in the y-direction of the image coordinate system.

[0067] Step S233: Calculate the average value of the absolute error data and use it as the matching error data.

[0068] Figure 5 A flowchart illustrating step S231, which involves taking n sampling points in the x-direction of the image coordinate system, as shown in an exemplary embodiment of this application, is as follows: Figure 5 As shown, taking n sampling points in the x-direction of the image coordinate system may include the following steps:

[0069] Step S2311: According to the real number zero-point segmentation method, the segment between the starting point and the ending point in the x-direction of the image coordinate system is divided into at least one sub-interval.

[0070] Step S2312: Collect the sampling points in the x-direction of the image coordinate system at a fixed step size, and divide the sampling points belonging to the same sub-interval into the same group.

[0071] For example, with Figure 7 Taking six points in the image coordinate system as an example, sampling is performed in the overlapping area of ​​the two lane lines in the x direction. Starting from the initial x value x1, x is taken at a fixed step size to obtain x1, x2, x3, x4, x5, and x6. The true y value of the lane line and the y value of the lane line to be measured are taken at each point. The error of each point is represented by the deviation of the y value dy1, dy2, etc.

[0072] The smaller the step size of x, the more sampling points there are. The absolute values ​​of dy1 to dy6 are the lane line errors at each point. The average of the errors of all sampling points is the matching error between the two lane lines. In general, when there are n sampling points, the matching error is: (|y1|+|y2|+…+|y…) n However, the overall process of lane line evaluation is inherently large in terms of data volume and computation. In addition, comparing multiple ground truth lane line data and multiple lane line data to be tested, and then taking the absolute value of each point for recalculation, will further increase the lane line evaluation time and reduce the evaluation efficiency.

[0073] The embodiment can group each sampling point according to the real zero point segmentation method, and a simple expression is that the signs of dy1, dy2, dy3, dy4, dy5 and dy6 are grouped, and continuous data with the same sign is grouped as a group. For example, dy1 and dy2 are positive numbers, dy3 and dy4 are negative numbers, and dy5 and dy6 are positive numbers, then the data is divided into three groups, dy1 and dy2 are divided into a group, dy3 and dy4 are divided into a group, and dy5 and dy6 are divided into a group.

[0074] Therefore, the application does not directly obtain the values of dy1, dy2 and the like, but groups dy1, dy2 and the like according to the functional properties of the lane line, calculates the sum of each group of data using a simple formula after grouping is completed, and thus the time for calculating the point error of dy1, dy2 and the like each time is omitted, thereby saving time.

[0075] Figure 6 The step flow chart for calculating the average value of the absolute error data in step S233 shown for an exemplary embodiment of the application is shown in FIG. 13, and the calculation of the average value of the absolute error data can include the following steps: Figure 6

[0076] In step S2331, the error data of the to-be-tested lane line data and the true value lane line data in the y direction of the image coordinate system corresponding to each sampling point of the same sub-interval is obtained, and the error data is summed to obtain the sum of the sub-interval error data.

[0077] In step S2332, the sum of the error data of each sub-interval is taken as an absolute value, and then summed and divided by the total number of sampling points of each sub-interval to obtain the average value of the absolute error data.

[0078] Figure 8 The detailed step flow chart of the matching algorithm shown for an exemplary embodiment of the application is shown in FIG. 14, and the matching algorithm can include the following specific steps: Figure 7

[0079] Step one: obtaining multiple groups of to-be-tested lane line data and multiple groups of true value lane line data of the target lane line at the same time; the to-be-tested lane line data are lane_1, lane_2, …, lane_n, and the true value lane line data are Lane_1, Lane_2, …, Lane_N.

[0080] Step two: traversing the to-be-tested lane line data, taking lane_i (1<=i<=n) from the to-be-tested lane line data, obtaining the cubic equation y1(x)=a1+b1x+c1x 2 +d1x 3 . ​​

[0081] Step three: traverse the true value lane line data, take Lane_j (1<=j<=N) from the true value lane line data, get the cubic equation y2(x)=a2+b2x+c2x 2 +d2x 3 .

[0082] Step four: calculate the matching error data of lane_i and Lane_j, the fast calculation method of matching error data is as follows:

[0083] 1) subtract the equation y1(x) of lane_i from the equation y2(x) of Lane_j to get a new cubic equation expression:

[0084] y(x)=y2-y1=(a2-a1)+(b2-b1)x+(c2-c1)x 2 +(d2-d1)x 3

[0085] Further simplify the expression of y as:

[0086] y(x)=a+bx+cx 2 +dx 3

[0087] In the formula, a=a2-a1, b=b2-b1, c=c2-c1, d=d2-d1. Take the sampling point x d , the y coordinate deviation of the to-be-measured lane line data and the true value lane line data at the sampling point x d is y(x d ), that is, x d is brought into y(x) to solve, y(x d )=a+bx d +cx d 2 +dx d 3 .

[0088] 2) use the cubic equation root formula to solve the real zero point of y, the cubic equation has at most three real zero points. Take the starting x of the lane line as x s , and the ending x as x e . If there are three real zero points in the interval [x s , x e ], in turn x z1 , x z2 , x z3 , then divide the interval into [x s , x z1 ), [x z1 , x z2 ), [x z2x z3 ), [x z3 x e Four subintervals; if there are two real zeros x in the interval. z1 x z2 Then the interval is divided into [x s x z1 ), [x z1 x z2 ), [x z2 x e Three subintervals; if there is a real zero x in the interval z1 Then the interval is divided into [x s x z1 ), [x z1 x e Two subintervals; if there are no real zeros in the interval, then the interval is divided into only [x...]. s x e A sub-interval, and so on.

[0089] 3) Sample points for x at fixed step sizes, denoted as x1, x2, x3, ..., x n Corresponding to y(x1), y(x2), ..., y(x n There are a total of n deviation values. The y(x) values ​​corresponding to sampling points x belonging to the same sub-interval have the same sign. Therefore, y values ​​belonging to the same sub-interval are grouped together for calculation.

[0090] 4) The fast calculation method is illustrated using sampling points distributed within a certain sub-interval as an example. Let x be the number of sampling points within the same sub-interval. i x i+1 x i+2 , ..., x j For y(x) i ), y(x i+1 ), ..., y(x) j To calculate the sum T using a simplified method, given a fixed sampling step size of s for x and a sampling number of l, T can be calculated using the following formula:

[0091]

[0092] f1=l(2x i +(l-1)s) / 2

[0093] f2=((x i +ls) 3 -x i 3 -3s 2 f1-ls 3 ) / (3s)

[0094] f3=((xi +ls) 4 -x i 4 -ls 4 -4s 3 f1-6s 2 f2) / (4s)

[0095] l=j-i+1

[0096] 5) According to the formula, the T value of different sub-intervals is calculated, and the sum of the absolute values of T is obtained, and finally the sum value is divided by the total number of sampling points n, that is, the matching error data defined in the application is obtained. According to the formula in 4), whether the sampling step value is large or small, the number of sampling points is more or less, the resource consumption of calculation is theoretically unchanged, but if y(x) of each sampling point is solved separately, and the matching error is calculated, the resource consumption of calculation is inversely proportional to the sampling step and proportional to the sampling number. Therefore, the application can quickly calculate the matching error of two lane line data, and save time.

[0097] Step five: loop calculation of lane_i and all true value lane line data matching error, record matching result.

[0098] Step six: take out the next lane line to be tested from the lane line to be tested, and repeat the above process to match the optimal true value lane line data for the current lane line.

[0099] Step seven: summarize the matching results of the lane line to be tested and the true value lane line, determine the minimum matching error data in the multiple groups of lane line data to be tested and the multiple groups of true value lane line data; according to the lane line data to be tested and the true value lane line data corresponding to the smallest matching error data, the optimal matching pair of the target lane line is obtained.

[0100] It should be noted that the application does not directly solve the numerical value of y(x), but according to the functional properties of the lane line, the x is grouped, and after the grouping is completed, the sum of each group of data is calculated by using a simple formula, which saves the time of calculating the matching error of each x point, thereby saving time.

[0101] Figure 9 is a block diagram of a matching device shown in an exemplary embodiment of the application. The device can also be applied to other exemplary implementation environments and specifically configured in other devices, and the embodiment does not limit the implementation environment to which the device is applied.

[0102] As Figure 9 shown, the exemplary matching device comprises:

[0103] The data acquisition module 1101 is configured to obtain a lane line data set to be tested and a true value lane line data set of a target lane line at the same time.

[0104] The matching module 1102 is configured to respectively match each piece of to-be-tested lane line data in the to-be-tested lane line data set with each piece of ground truth lane line data in the ground truth lane line data set, to obtain a matching error data respectively, to select a minimum matching error data from the matching error data, and to determine, based on a pair of to-be-tested lane line data and ground truth lane line data mapped by the minimum matching error data, that the corresponding ground truth lane line and to-be-tested lane line are an optimal matching pair of the target lane line.

[0105] It should be noted that the matching apparatus provided by the above examples and the matching method provided by the above examples belong to the same concept, and the specific manner of each module has been described in detail in the method embodiments, which will not be described here. The matching apparatus provided by the above embodiments can be used in actual applications, and the above functions can be completed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0106] Embodiments of the present application also provide an electronic device, comprising: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, the electronic device implements the steps of the matching method provided in each of the above embodiments.

[0107] Figure 10 The structure of the computer system of the electronic device suitable for implementing the embodiments of the present application is shown. It should be noted that, Figure 10 The computer system 1200 of the electronic device shown is only an example, and should not limit the functions and use range of the embodiments of the present application.

[0108] As Figure 10 shown, the computer system 1200 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1202 or programs loaded from a storage portion 1208 into a random access memory (RAM) 1203, such as performing the methods described in the above embodiments. In the RAM 1203, various programs and data required for system operation are also stored. The CPU 1201, the ROM 1202, and the RAM 1203 are connected to each other through a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0109] The following components are connected to the I / O interface 1205: an input part 1206 including a keyboard, a mouse, etc.; an output part 1207 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc., and a speaker, etc.; a storage part 1208 including a hard disk, etc.; and a communication part 1209 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication part 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to the I / O interface 1205 as necessary. A removable media 1211 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 1210 as necessary, so that a computer program read therefrom is installed in the storage part 1208 as necessary.

[0110] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present application. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing a computer program for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication part 1209, and / or installed from the removable media 1211. When the computer program is executed by the central processing unit (CPU) 1201, various functions defined in the system of the present application are executed.

[0111] It should be noted that the computer-readable medium in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may, for example, be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, the computer-readable signal medium can include a data signal propagated in a baseband or as a carrier wave in a propagated data signal, in which the computer-readable computer program is carried. Such a propagated data signal can take on many forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit the program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted in any suitable medium, including but not limited to wireless, wired, or the like, or any suitable combination thereof.

[0112] The flowcharts and block diagrams in the drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Each block in the flowcharts or block diagrams can represent a module, a program segment, or a portion of code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in a different order than that shown in the figures. For example, two blocks noted in succession can actually be executed substantially concurrently, or they can sometimes be executed in reverse order, depending on the functionality involved. It should also be noted that each block in the flowcharts or block diagrams, and combinations of blocks in the flowcharts or block diagrams, can be implemented by special-purpose hardware-based systems, which perform the specified functions or operations, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0113] The units described in the embodiments of the present application can be implemented in the form of software, or can be implemented in the form of hardware, and the described units can also be arranged in a processor. In some cases, the names of the units do not constitute a limitation on the units themselves.

[0114] Another aspect of the present application also provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the matching method as described above. The computer readable storage medium can be included in the electronic device described in the above embodiments, or can exist separately without being assembled into the electronic device.

[0115] Another aspect of the present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to perform the matching method provided in the above embodiments.

[0116] The above embodiments only exemplarily illustrate the principles and effects of the present application, and are not used to limit the present application. Any person skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those skilled in the art without departing from the spirit and technical ideas disclosed by the present application should be covered by the claims of the present application.

Claims

1. A method of matching lane lines, characterized by, The method comprises the following steps: Obtain a plurality of sets of to-be-tested lane line data and a plurality of sets of true value lane line data of a target lane line at the same time; Match the to-be-tested lane line data and the true value lane line data to obtain matching error data, so as to determine the minimum matching error data in the plurality of sets of to-be-tested lane line data and the plurality of sets of true value lane line data; Obtain the optimal matching pair of the target lane line according to the to-be-tested lane line data and the true value lane line data corresponding to the minimum matching error data; The matching calculation of the to-be-tested lane line data and the true value lane line data comprises the following steps: Fit a curve in an image coordinate system based on the two-dimensional coordinate information of each point contained in the to-be-tested lane line data and the true value lane line data, to obtain a fitting curve of the to-be-tested lane line and a fitting curve of the true value lane line respectively, Match the fitting curve of the to-be-tested lane line and the fitting curve of the true value lane line to obtain the matching error data; The matching calculation of the fitting curve of the to-be-tested lane line and the fitting curve of the true value lane line to obtain the matching error data comprises the following steps: Take n sampling points in the x direction of the image coordinate system, and match the absolute error data of the to-be-tested lane line data and the true value lane line data in the y direction of the image coordinate system corresponding to each sampling point, Calculate the average value of the absolute error data as the matching error data; The taking of n sampling points in the x direction of the image coordinate system comprises the following steps: According to the real zero point segmentation method, the segment between the starting point and the ending point in the x direction of the image coordinate system is divided into at least one subinterval; Collect the sampling points in the x direction of the image coordinate system at a fixed step, and divide the sampling points belonging to the same subinterval into the same group; The calculation of the average value of the absolute error data comprises the following steps: Obtain the error data of the to-be-tested lane line data and the true value lane line data in the y direction of the image coordinate system corresponding to each sampling point in the same subinterval, and sum the error data to obtain the sum of the subinterval error data; Take the absolute value of each subinterval error data sum, and divide the sum by the total number of sampling points in each subinterval to obtain the average value of the absolute error data; The cubic equation of the current to-be-tested lane line data: y1(x) = a1 + b1x + c1x2+ d1x3 2 + e1x4 3 ; The cubic equation of the current true value lane line data: y2(x) = a2+ b2x + c2x2 2 + d2x 3 ; Calculate the matching error data y(x) of the current to-be-tested lane line data and the current true value lane line data, y(x) = a + bx + cx 2 +dx 3 ; a=a2-a1, b=b2-b1, c=c2-c1, d=d2-d1; Let x be the sampling point in one sub-interval i , x i+1 , x i+2 , …, x j , y(x i ), y(x i+1 ), …, y(x j ), sum value T, f1 = l(2x i + (1-1)s) / 2 f2 = ((x i + ls) 3 - x i 3 - 3s 2 f1 - ls 3 ) / (3s) f3 = ((x i + ls) 4 - x i 4 - ls 4 - 4s 3 f1 - 6s 2 f2) / (4s) l=j-i+1 Wherein, the fixed sampling step of x is s, the number of sampling points is l, the T value of each subinterval is calculated, the absolute value of each T value is taken, and the sum is divided by the total number of sampling points n, that is, the matching error data is obtained.

2. The lane line matching method according to claim 1, characterized by, The method comprises the following steps: Obtain all target lane line images of a target lane line at the same time through two groups of sensors, The lane line data set obtained after image processing of all the target lane line images obtained by the first group of sensors is taken as the to-be-tested lane line data set, The lane line data set obtained after image processing of all the target lane line images obtained by the second group of sensors is taken as the true value lane line data set.

3. The lane line matching method according to claim 2, characterized by, The first group of sensors are to-be-evaluated sensors; and the second group of sensors are reference sensors and are used to provide evaluation reference data for the to-be-evaluated sensors.

4. A lane line matching apparatus characterized by comprising: Comprise: The data acquisition module is used for acquiring a to-be-measured lane line data set and a true value lane line data set of the target lane line at the same time, The matching module is used for matching each to-be-measured lane line data in the to-be-measured lane line data set with each true value lane line data in the true value lane line data set respectively, obtaining matching error data respectively, selecting the smallest matching error data from each matching error data, and determining that a corresponding true value lane line and to-be-measured lane line are an optimal matching pair of the target lane line based on a pair of to-be-measured lane line data and true value lane line data mapped by the smallest matching error data; Wherein, the matching calculation of the to-be-measured lane line data and the true value lane line data to obtain the matching error data comprises: Based on the two-dimensional coordinate information of each point contained in the to-be-measured lane line data and the true value lane line data, curve fitting is performed in the image coordinate system to obtain a fitting curve of the to-be-measured lane line and a fitting curve of the true value lane line respectively, The matching calculation is performed according to the fitting curve of the to-be-measured lane line and the fitting curve of the true value lane line to obtain the matching error data; The matching calculation according to the fitting curve of the to-be-measured lane line and the fitting curve of the true value lane line to obtain the matching error data comprises: n sampling points are taken in the x direction of the image coordinate system, and the absolute error data of the to-be-measured lane line data and the true value lane line data in the y direction of the image coordinate system corresponding to each sampling point is matched and calculated, The average value of the absolute error data is calculated and taken as the matching error data; The n sampling points taken in the x direction of the image coordinate system comprise: According to the real zero point segmentation method, the segment between the starting point and the ending point in the x direction of the image coordinate system is divided into at least one subinterval; The sampling points in the x direction of the image coordinate system are collected according to a fixed step length, and the sampling points belonging to the same subinterval are divided into the same group; The calculation of the average value of the absolute error data comprises: The error data of the to-be-measured lane line data and the true value lane line data in the y direction of the image coordinate system corresponding to each sampling point in the same subinterval is obtained, and the error data is summed to obtain the sum of the subinterval error data; The average value of the absolute error data is obtained by taking the absolute value of each subinterval error data sum and dividing by the total number of sampling points in each subinterval; The cubic equation of the current to-be-measured lane line data: y1(x) = a1 + b1x + c1x2+ d1x3 2 y2(x) = a2 + b2x + c2x2+ d2x3 3 ; The cubic equation of the current true value lane line data: y2(x) = a2+ b2x + c2x2+ d2x3 2 + e2x4 3 ; Calculate the matching error data y(x) of the current to-be-tested lane line data and the current true value lane line data, y(x) = a + bx + cx 2 +dx 3 ; a=a2-a1, b=b2-b1, c=c2-c1, d=d2-d1; Let x be the sampling point in one sub-interval i , x i+1 , x i+2 , …, x j , y(x i ), y(x i+1 ), …, y(x j ) are summed up to get the value T f1 = l(2x i +(l-1)s) / 2 f2 = ((x i + ls) 3 - x i 3 - 3s 2 f1 - ls 3 ) / (3s) f3 = ((x i + ls) 4 - x i 4 - ls 4 - 4s 3 f1 - 6s 2 f2) / (4s) l=j-i+1 Wherein, the fixed sampling step length of x is s, the number of sampling points is l, the T value of each subinterval is calculated, the absolute value of each T value is taken and summed, and then divided by the total number of sampling points n, that is, the matching error data is obtained.

5. An electronic device, comprising: Comprise: One or more processors; a storage device for storing one or more programs, which when executed by the one or more processors, cause the electronic device to implement the steps of the lane line matching method of any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, a computer readable medium having stored thereon computer readable instructions, which when executed by a processor of a computer, cause the computer to perform the steps of the lane line matching method of any one of claims 1 to 3.

Images