Lane line acquisition method and device, equipment and storage medium

Abstract

The invention discloses a lane line acquisition method and device, equipment and a storage medium. The lane line acquisition method comprises the following steps: acquiring foresight lane line information at a first historical moment; determining rear-view lane line information at the current moment based on the front-view lane line information at the first historical moment; and fitting to obtain a rearview lane line equation at the current moment based on the rearview lane line information at the current moment. By means of the mode, the computing power cost for obtaining the rear-view lane line can be reduced, and the continuity of the rear-view lane line and the front-view lane line is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a lane line acquisition method, device, equipment and storage medium. Background Art

[0002] Lane line detection is an essential function in intelligent driving. Vehicle trajectory planning, automatic control and some auxiliary driving functions (such as lane keeping, collision warning and adaptive cruise control, etc.) all require lane lines as data basis. Rear-view lane lines can assist in providing information such as the lane where the rear-facing vehicle is located and the movement trend (lane keeping or lane changing). Therefore, in order to improve the safety of vehicle intelligent driving, rear-view lane line detection is crucial.

[0003] In the related art, the method of obtaining the rearview lane line is similar to the method of obtaining the frontview lane line. Usually, the rearview image obtained by the rearview camera is processed based on the neural network model to obtain the rearview lane line information. However, this method requires large-scale data to train the neural network model, and the rearview lane line needs to go through cumbersome post-processing and other processes, which increases the computing power cost. In addition, since the calibration of the front view camera and the calibration of the rearview camera use different camera coordinate systems, the obtained rearview lane line has poor consistency with the front view lane line. Summary of the invention

[0004] The main technical problem solved by the present application is to provide a lane line acquisition method, device, equipment and computer-readable storage medium, which can reduce the computing power overhead of acquiring the rear-view lane line and improve the consistency between the rear-view lane line and the front-view lane line.

[0005] In order to solve the above technical problems, a technical solution adopted in the present application is: to provide a lane line acquisition method, the method comprising: acquiring the front-sight lane line information at a first historical moment; based on the front-sight lane line information at the first historical moment, determining the rear-sight lane line information at the current moment; based on the rear-sight lane line information at the current moment, fitting the rear-sight lane line equation at the current moment.

[0006] Optionally, the forward-sight lane line information at the first historical moment includes first position information of several first sampling points in a first vehicle coordinate system, wherein the several first sampling points are sampling points located on the forward-sight lane line at the first historical moment, and the first vehicle coordinate system is the vehicle coordinate system at the first historical moment; based on the forward-sight lane line information at the first historical moment, determining the rearward-sight lane line information at the current moment includes: transforming the first position information of each first sampling point into second position information in a second vehicle coordinate system, and the second vehicle coordinate system is the vehicle coordinate system at the current moment; selecting several second sampling points that meet the requirements from the several first sampling points; and using the second position information of the several second sampling points as the rearward-sight lane line information at the current moment.

[0007] Optionally, the first position information of each first sampling point is transformed into the second position information in the second vehicle coordinate system, including: obtaining the vehicle posture information at the first historical moment and the vehicle posture information at the current moment; determining the first transformation matrix based on the vehicle posture information at the first historical moment; and determining the second transformation matrix based on the vehicle posture information at the current moment; using the first transformation matrix to transform the first position information of each first sampling point into the third position information in the world coordinate system; using the second transformation matrix to transform the third position information of each first sampling point into the second position information in the second vehicle coordinate system.

[0008] Optionally, the vehicle posture information at the first historical moment includes the vehicle position information at the first historical moment and the vehicle posture information at the first historical moment; based on the vehicle posture information at the first historical moment, a first transformation matrix is ​​determined, including: based on the vehicle position information at the first historical moment, a first translation matrix is ​​determined; based on the vehicle posture information at the first historical moment, a first rotation matrix is ​​determined; based on the first translation matrix and the first rotation matrix, a first transformation matrix is ​​determined; and / or, the vehicle posture information at the current moment includes the vehicle position information at the current moment and the vehicle posture information at the current moment; based on the vehicle posture information at the current moment, a second transformation matrix is ​​determined, including: based on the vehicle position information at the current moment, a second translation matrix is ​​determined; based on the vehicle posture information at the current moment, a second rotation matrix is ​​determined; based on the second translation matrix and the second rotation matrix, a third transformation matrix is ​​determined; and the inverse matrix of the third transformation matrix is ​​used as the second transformation matrix.

[0009] Optionally, the vehicle posture information includes the roll angle, pitch angle and yaw angle of the vehicle.

[0010] Optionally, the second position information of the first sampling point includes the lateral coordinate and the longitudinal coordinate of the first sampling point in the second vehicle coordinate system; selecting a number of second sampling points that meet the requirements from the number of first sampling points includes: selecting a number of sampling points whose longitudinal coordinates are less than a preset value from the number of first sampling points as the number of second sampling points.

[0011] Optionally, obtaining the forward-view lane line information at the first historical moment includes: obtaining the vehicle speed at several target moments and the forward-view lane line equation at each target moment, the several target moments including the current moment and several second historical moments before the current moment; based on the vehicle speed at each target moment, determining the displacement of the vehicle from each second historical moment to the current moment; selecting a second historical moment with a displacement greater than a preset distance from each second historical moment as the first historical moment; sampling the forward-view lane line equation at the first historical moment to obtain the forward-view lane line information at the first historical moment.

[0012] In order to solve the above technical problems, another technical solution adopted in the present application is: to provide a lane line acquisition device, which includes: an acquisition module, used to obtain the front-sight lane line information at a first historical moment; a determination module, used to determine the rear-sight lane line information at the current moment based on the front-sight lane line information at the first historical moment; a fitting module, used to fit the rear-sight lane line equation at the current moment based on the rear-sight lane line information at the current moment.

[0013] Optionally, the forward-sight lane line information at the first historical moment includes first position information of several first sampling points in a first vehicle coordinate system, wherein the several first sampling points are sampling points located on the forward-sight lane line at the first historical moment, and the first vehicle coordinate system is the vehicle coordinate system at the first historical moment; the determination module is used to transform the first position information of each first sampling point into second position information in a second vehicle coordinate system, and the second vehicle coordinate system is the vehicle coordinate system at the current moment; select several second sampling points that meet the requirements from the several first sampling points; and use the second position information of the several second sampling points as the rear-sight lane line information at the current moment.

[0014] Optionally, the determination module is used to obtain the vehicle posture information at a first historical moment and the vehicle posture information at a current moment; determine a first transformation matrix based on the vehicle posture information at the first historical moment; and determine a second transformation matrix based on the vehicle posture information at the current moment; use the first transformation matrix to transform the first position information of each first sampling point into third position information located in the world coordinate system; use the second transformation matrix to transform the third position information of each first sampling point into second position information located in the second vehicle coordinate system.

[0015] Optionally, the vehicle posture information at the first historical moment includes the vehicle position information at the first historical moment and the vehicle posture information at the first historical moment; the determination module is used to determine the first translation matrix based on the vehicle position information at the first historical moment; determine the first rotation matrix based on the vehicle posture information at the first historical moment; determine the first transformation matrix based on the first translation matrix and the first rotation matrix; and / or, the vehicle posture information at the current moment includes the vehicle position information at the current moment and the vehicle posture information at the current moment; the determination module is used to determine the second translation matrix based on the vehicle position information at the current moment; determine the second rotation matrix based on the vehicle posture information at the current moment; determine the third transformation matrix based on the second translation matrix and the second rotation matrix; and use the inverse matrix of the third transformation matrix as the second transformation matrix.

[0016] Optionally, the vehicle posture information includes the roll angle, pitch angle and yaw angle of the vehicle.

[0017] Optionally, the second position information of the first sampling point includes the lateral coordinate and the longitudinal coordinate of the first sampling point in the second vehicle coordinate system; the determination module is used to select a number of sampling points whose longitudinal coordinates are less than a preset value from the first sampling points as the second sampling points.

[0018] Optionally, the acquisition module is used to obtain the vehicle speed at several target moments and the forward-looking lane line equation at each target moment, the several target moments including the current moment and several second historical moments before the current moment; based on the vehicle speed at each target moment, respectively determine the displacement of the vehicle from each second historical moment to the current moment; select a second historical moment from each second historical moment in which the displacement is greater than a preset distance as the first historical moment; sample the forward-looking lane line equation at the first historical moment to obtain the forward-looking lane line information at the first historical moment.

[0019] In order to solve the above technical problems, another technical solution adopted in the present application is: to provide an electronic device, including a memory and a processor coupled to each other, the memory storing program instructions; the processor is used to execute the program instructions stored in the memory to implement the above lane line acquisition method.

[0020] In order to solve the above technical problems, another technical solution adopted in the present application is: providing a computer-readable storage medium, which is used to store program instructions, and the program instructions can be executed by a processor to implement the above lane line acquisition method.

[0021] The above scheme determines the rear-view lane line information at the current moment based on the front-view lane line information at the first historical moment, and obtains the rear-view lane line equation at the current moment based on the rear-view lane line information at the current moment. That is, the rear-view lane line equation at the current moment is obtained based on the historical front-view lane line information. In this way, there is no need to extract the rear-view lane line information from the rear-view image obtained by the rear-view camera, which can reduce the computing power overhead of obtaining the rear-view lane line and improve the coherence of the rear-view lane line and the front-view lane line. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flowchart of an embodiment of a lane line acquisition method provided by the present application;

[0023] Figure 2 is a flowchart of another embodiment of the lane line acquisition method provided by the present application;

[0024] Figure 3 It is a schematic diagram of vehicle posture change provided by this application;

[0025] Figure 4 It is a schematic diagram of the framework of an embodiment of a lane line acquisition device provided by the present application;

[0026] Figure 5 It is a schematic diagram of a framework of an embodiment of an electronic device provided by the present application;

[0027] Figure 6 It is a schematic diagram of a framework of an embodiment of a computer-readable storage medium provided by the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and effect of the present application clearer and more specific, the present application is further described in detail below with reference to the accompanying drawings and examples.

[0029] It should be noted that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone; the term "several" means at least one; the terms "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0030] See also Figure 1 , Figure 1 1 is a flow chart of an embodiment of a lane line acquisition method provided by the present application, which can be executed by a vehicle controller. It should be noted that if there are substantially the same results, the method of the present application is not limited to the method of the present application. Figure 1 The process sequence shown is limited. Figure 1 As shown, the method comprises the following steps:

[0031] S11: Obtaining the front lane line information at the first historical moment.

[0032] The first historical moment is a historical moment before the current moment. It should be noted that, in order to ensure the accuracy of the rearview lane line information subsequently obtained, the displacement of the vehicle changes from the first historical moment to the current moment, that is, the vehicle is in motion. Exemplarily, the displacement of the vehicle from the first historical moment to the current moment is greater than a preset distance, and the preset distance can be set according to actual needs.

[0033] The forward-looking lane line information at the first historical moment includes the first position information of several first sampling points in the first vehicle coordinate system. Among them, the several first sampling points are sampling points located on the forward-looking lane line at the first historical moment, the first vehicle coordinate system is the vehicle coordinate system at the first historical moment, and the first position information of the first sampling point includes the lateral coordinate and the longitudinal coordinate of the first sampling point in the first vehicle coordinate system. Specifically, the forward-looking lane line equation at the first historical moment can be obtained first, and then the forward-looking lane line equation at the first historical moment can be sampled to obtain the first position information of several first sampling points in the first vehicle coordinate system. The steps of obtaining the forward-looking lane line equation based on the forward-looking image can refer to the relevant known technology and will not be described in detail here.

[0034] S12: Determine the rear-view lane line information at the current moment based on the front-view lane line information at the first historical moment.

[0035] After acquiring the front-view lane line information at the first historical moment, the rear-view lane line information at the current moment is further determined based on the front-view lane line information at the first historical moment.

[0036] It can be understood that from the perspective of the vehicle, the front-view lane line at the first historical moment and the rear-view lane line at the current moment correspond to each other. Therefore, the front-view lane line information at the first historical moment can be obtained to infer the rear-view lane line information at the current moment.

[0037] S13: Based on the rear-view lane line information at the current moment, a rear-view lane line equation at the current moment is obtained by fitting.

[0038] For the relevant contents of fitting the lane line equation, reference may be made to the relevant known technologies and will not be described in detail here.

[0039] In addition, it should be noted that, assuming that the vehicle driving road includes several lanes, the several lanes may correspond to several lane lines (such as 3 lanes correspond to 4 lane lines), and the forward-sight lane line information corresponding to each lane line at the first historical moment can be obtained respectively, and based on the forward-sight lane line information corresponding to each lane line at the first historical moment, the rear-sight lane line equation corresponding to each lane line at the current moment can be inferred respectively.

[0040] In this embodiment, the rear-view lane line information at the current moment is determined based on the front-view lane line information at the first historical moment, and the rear-view lane line equation at the current moment is fitted based on the rear-view lane line information at the current moment. That is, the rear-view lane line equation at the current moment is obtained based on the historical front-view lane line information. In this way, there is no need to extract the rear-view lane line information from the rear-view image obtained by the rear-view camera, which can reduce the computing power overhead of obtaining the rear-view lane line and improve the coherence of the rear-view lane line and the front-view lane line.

[0041] See also Figure 2 , Figure 2 is a flow chart of another embodiment of the lane line acquisition method provided by the present application, which can be executed by a vehicle controller. It should be noted that if there is substantially the same result, the method of the present application is not limited to the lane line acquisition method of the present application. Figure 2 The process sequence shown is limited. Figure 2 As shown, the method comprises the following steps:

[0042] S21: Acquire forward-view lane line information at a first historical moment, where the forward-view lane line information at the first historical moment includes first position information of a plurality of first sampling points in a first vehicle coordinate system.

[0043] Among them, the several first sampling points are sampling points located on the front lane line at the first historical moment, the first vehicle coordinate system is the vehicle coordinate system at the first historical moment, and the first position information of the first sampling point includes the lateral coordinate and the longitudinal coordinate of the first sampling point in the first vehicle coordinate system.

[0044] In this embodiment, obtaining the front lane line information at the first historical moment includes the following steps:

[0045] Step 1: Obtain the vehicle speed at several target moments and the forward lane line equation at each target moment, wherein the several target moments include the current moment and several second historical moments before the current moment.

[0046] Among them, the several second historical moments are several historical moments before the current moment.

[0047] In one embodiment, during vehicle driving, the vehicle controller may acquire and store driving information of several target moments, where the driving information of each target moment includes a timestamp, a vehicle speed, and a forward-looking lane line equation corresponding to the target moment.

[0048] Furthermore, the driving information at each target time may also include the vehicle posture information corresponding to the target time in the world coordinate system. The vehicle posture information includes the vehicle position information and the vehicle attitude information. The vehicle position information includes the three-dimensional coordinates of the vehicle in the world coordinate system, and the vehicle attitude information includes the roll angle, pitch angle and yaw angle of the vehicle. Exemplarily, the vehicle position information can be obtained through a positioning unit installed on the vehicle, and the vehicle attitude information can be obtained through an IMU (Inertial Measurement Unit) installed on the vehicle.

[0049] The driving information at each target time can be expressed as:

[0050] {timestamp,speed,lanes,(x,y,z,roll,pitch,yaw)}

[0051] Among them, timestamp represents the timestamp corresponding to the target time, speed represents the vehicle speed at the target time, lanes represents all forward-looking lane line equations at the target time, x, y, and z represent the vehicle position information at the target time, and roll, pitch, and yaw represent the vehicle posture information at the target time.

[0052] Step 2: Based on the vehicle speed at each target moment, the displacement of the vehicle from each second historical moment to the current moment is determined respectively.

[0053] In one embodiment, the displacement of the vehicle from each second historical moment to the current moment can be calculated based on the timestamp and vehicle speed of each target moment. Alternatively, in other embodiments, other methods can be used to calculate the displacement of the vehicle from each second historical moment to the current moment, which is not specifically limited in this embodiment.

[0054] Step three, selecting a second historical moment whose displacement is greater than a preset distance from each second historical moment as the first historical moment.

[0055] Step 4: Sample the front lane line equation at the first historical moment to obtain the front lane line information at the first historical moment.

[0056] For example, the front lane line equation at the first historical moment is x0=f(y0), which can be specifically expressed by expression (1):

[0057]

[0058] Among them, C0, C1, C2 and C3 are equation fitting parameters.

[0059] The forward-view lane line equation at the first historical moment is sampled, such as sampling at a preset interval on the x-axis, to obtain first position information of a plurality of first sampling points in the first vehicle coordinate system, that is, to obtain the forward-view lane line information at the first historical moment.

[0060] In steps one to four, a second historical moment with a displacement greater than a preset distance is selected from a number of second historical moments as the first historical moment, and the front-sight lane line equation of the first historical moment is sampled as the lane line baseline to obtain the front-sight lane line information of the first historical moment. This can avoid the phenomenon that the rear-sight lane line information subsequently obtained is inaccurate due to the vehicle being stationary, and further improve the accuracy of the rear-sight lane line equation subsequently obtained.

[0061] S22: transforming the first position information of each first sampling point into second position information in a second vehicle coordinate system.

[0062] The second vehicle coordinate system is the vehicle coordinate system at the current moment, and the second position information of the first sampling point includes the lateral coordinate and the longitudinal coordinate of the first sampling point in the second vehicle coordinate system.

[0063] It should be noted that the origin of the vehicle coordinate system is the center of mass of the vehicle or the midpoint of the rear axle of the vehicle, the x-axis (i.e., the longitudinal axis) is parallel to the ground and points to the front of the vehicle (or the front of the driver's field of vision), the y-axis (i.e., the horizontal axis) is perpendicular to the x-axis and points to the driver's left hand side, and the z-axis points to the top of the vehicle. The lane line information in this embodiment only considers the x-axis and y-axis, and does not consider the z-axis.

[0064] Figure 3 This is a schematic diagram of vehicle posture change provided by this application. Figure 3 As shown, since the vehicle coordinate system changes with the movement of the vehicle, that is, the first vehicle coordinate system at the first historical moment ( Figure 3 X0Y0Z0) and the second vehicle coordinate system at the current moment ( Figure 3 Therefore, it is necessary to first transform the first position information of each first sampling point in the first vehicle coordinate system into the second position information in the second vehicle coordinate system.

[0065] In this embodiment, transforming the first position information of each first sampling point into the second position information in the second vehicle coordinate system includes the following steps:

[0066] Step 1: Obtain the vehicle position information at the first historical moment and the vehicle position information at the current moment.

[0067] The vehicle position information at the first historical moment includes the vehicle position information at the first historical moment and the vehicle attitude information at the first historical moment. The vehicle position information at the first historical moment includes the three-dimensional coordinates of the vehicle corresponding to the first historical moment in the world coordinate system, and the vehicle attitude information at the first historical moment includes the roll angle, pitch angle and yaw angle of the vehicle corresponding to the first historical moment.

[0068] The vehicle position information at the current moment includes the vehicle position information at the current moment and the vehicle attitude information at the current moment. The vehicle position information at the current moment includes the three-dimensional coordinates of the vehicle corresponding to the current moment in the world coordinate system, and the vehicle attitude information at the current moment includes the roll angle, pitch angle and yaw angle of the vehicle corresponding to the current moment.

[0069] Step 2: Determine a first transformation matrix based on the vehicle posture information at the first historical moment.

[0070] In one embodiment, determining the first transformation matrix includes the following sub-steps:

[0071] Sub-step one: determining a first translation matrix based on the vehicle position information at a first historical moment.

[0072] Specifically, the first translation matrix can be expressed by expression (2):

[0073]

[0074] Wherein, T represents the first translation matrix, and x, y, and z represent the three-dimensional coordinates of the vehicle in the world coordinate system corresponding to the first historical moment.

[0075] Sub-step 2: determining a first rotation matrix based on the vehicle posture information at the first historical moment.

[0076] Specifically, the first rotation matrix can be expressed by expression (3):

[0077] R=R x *R y *R z (3)

[0078] Among them, R x , R y and R z Represents the rotation matrix around the x-axis, y-axis, and z-axis respectively. x , R y and R z It can be expressed by expressions (4), (5) and (6) respectively:

[0079]

[0080] Among them, roll, pitch and yaw represent the roll angle, pitch angle and yaw angle of the vehicle corresponding to the first historical moment respectively.

[0081] Sub-step three: determining a first transformation matrix based on the first translation matrix and the first rotation matrix.

[0082] Specifically, the first transformation matrix can be expressed by expression (7):

[0083]

[0084] Among them, P represents the first transformation matrix, T represents the first translation matrix, and R represents the first rotation matrix.

[0085] Step three, determine the second transformation matrix based on the vehicle posture information at the current moment.

[0086] In one embodiment, determining the second transformation matrix includes the following sub-steps:

[0087] Sub-step one: determining a second translation matrix based on the vehicle position information at the current moment.

[0088] Sub-step 2: determining a second rotation matrix based on the vehicle posture information at the current moment.

[0089] Sub-step three: determining a third transformation matrix based on the second translation matrix and the second rotation matrix.

[0090] The relevant contents of determining the second translation matrix, the second rotation matrix and the third transformation matrix may refer to the aforementioned contents of determining the first translation matrix, the first rotation matrix and the first transformation matrix, and will not be repeated here.

[0091] Sub-step four: using the inverse matrix of the third transformation matrix as the second transformation matrix.

[0092] Specifically, the second transformation matrix can be expressed by expression (8):

[0093]

[0094] Among them, P ′ represents the second transformation matrix, represents the third transformation matrix, T ′ represents the second translation matrix, R ′ represents the second rotation matrix.

[0095] Step 4: Use the first transformation matrix to transform the first position information of each first sampling point into third position information in the world coordinate system.

[0096] Specifically, step 4 can be expressed by expression (9):

[0097]

[0098] Among them, x i and i represents the first position information of the i-th first sampling point, z i is 0, P represents the first transformation matrix, x wi ,y wi and z wi Represents the third position information of the i-th first sampling point.

[0099] Step five: transform the third position information of each first sampling point into second position information in a second vehicle coordinate system using a second transformation matrix.

[0100] Specifically, step five can be expressed by expression (10):

[0101]

[0102] Among them, x i ′ and i ′ represents the second position information of the i-th first sampling point, P ′ represents the second transformation matrix, x wi ,y wi and z wi Represents the third position information of the i-th first sampling point.

[0103] In step 1 to step 5, the first position information of each first sampling point is transformed into the second position information in the second vehicle coordinate system using the first transformation matrix and the second transformation matrix. Since the first transformation matrix and the second transformation matrix both take into account the roll angle, pitch angle and yaw angle of the vehicle, the second position information of several first sampling points obtained under flat, uphill, bumpy and tilted road conditions is relatively accurate, further improving the accuracy of the rearview lane line obtained subsequently.

[0104] S23: Selecting a plurality of second sampling points that meet the requirements from the plurality of first sampling points.

[0105] The second position information of the first sampling point includes the lateral coordinate and the longitudinal coordinate of the first sampling point in the second vehicle coordinate system. Specifically, based on the second position information of the first sampling points, a plurality of sampling points whose longitudinal coordinates are less than a preset value are selected from the first sampling points as the second sampling points. Exemplarily, the preset value is 0.

[0106] S24: Using the second position information of the plurality of second sampling points as the rearview lane line information at the current moment.

[0107] S25: Based on the rear-view lane line information at the current moment, a rear-view lane line equation at the current moment is obtained by fitting.

[0108] Furthermore, after obtaining the rear-view lane line equation at the current moment, the front-view lane line equation and the rear-view lane line equation at the current moment can be aligned, fused, etc. to obtain the lane line detection result at the current moment. Furthermore, the lane line detection result at the current moment is output for subsequent vehicle trajectory planning, vehicle automatic control, lane keeping, collision warning or adaptive cruise control, etc.

[0109] In this embodiment, the rearview lane line equation at the current moment is obtained based on the historical front view lane line information. There is no need to extract the rearview lane line information through the rearview image obtained by the rearview camera, which can reduce the computing power overhead of obtaining the rearview lane line and improve the consistency of the rearview lane line and the front view lane line. In addition, in this embodiment, in the process of obtaining the rearview lane line information at the current moment, the first position information of each first sampling point is transformed into the second position information in the second vehicle coordinate system using the first transformation matrix and the second transformation matrix. The first transformation matrix and the second transformation matrix both take into account the roll angle, pitch angle and yaw angle of the vehicle, and are applicable to a richer range of driving conditions. Moreover, the lane line acquisition method in this embodiment is not only applicable to vehicles equipped with both a front view camera and a rear view camera, but also to vehicles equipped only with a front view camera.

[0110] See also Figure 4 , Figure 4: is a schematic diagram of a framework of an embodiment of a lane line acquisition device provided by the present application. In this embodiment, the lane line acquisition device 40 includes an acquisition module 41, a determination module 42 and a fitting module 43. Among them, the acquisition module 41 is used to acquire the front-view lane line information at the first historical moment; the determination module 42 is used to determine the rear-view lane line information at the current moment based on the front-view lane line information at the first historical moment; the fitting module 43 is used to fit the rear-view lane line equation at the current moment based on the rear-view lane line information at the current moment.

[0111] Optionally, the front-view lane line information at the first historical moment includes first position information of a plurality of first sampling points in a first vehicle coordinate system, the plurality of first sampling points are sampling points located on the front-view lane line at the first historical moment, and the first vehicle coordinate system is the vehicle coordinate system at the first historical moment. The determination module 42 is used to transform the first position information of each first sampling point into second position information in a second vehicle coordinate system, and the second vehicle coordinate system is the vehicle coordinate system at the current moment; select a plurality of second sampling points that meet the requirements from the plurality of first sampling points; and use the second position information of the plurality of second sampling points as the rear-view lane line information at the current moment.

[0112] Optionally, the determination module 42 is used to obtain the vehicle posture information at a first historical moment and the vehicle posture information at a current moment; determine a first transformation matrix based on the vehicle posture information at the first historical moment; and determine a second transformation matrix based on the vehicle posture information at the current moment; use the first transformation matrix to transform the first position information of each first sampling point into third position information located in the world coordinate system; use the second transformation matrix to transform the third position information of each first sampling point into second position information located in the second vehicle coordinate system.

[0113] Optionally, the vehicle position information at the first historical moment includes the vehicle position information at the first historical moment and the vehicle posture information at the first historical moment. The determination module 42 is used to determine the first translation matrix based on the vehicle position information at the first historical moment; determine the first rotation matrix based on the vehicle posture information at the first historical moment; and determine the first transformation matrix based on the first translation matrix and the first rotation matrix.

[0114] The vehicle posture information at the current moment includes the vehicle position information at the current moment and the vehicle posture information at the current moment. The determination module 42 is used to determine the second translation matrix based on the vehicle position information at the current moment; determine the second rotation matrix based on the vehicle posture information at the current moment; determine the third transformation matrix based on the second translation matrix and the second rotation matrix; and use the inverse matrix of the third transformation matrix as the second transformation matrix.

[0115] Optionally, the vehicle posture information includes the roll angle, pitch angle and yaw angle of the vehicle.

[0116] Optionally, the second position information of the first sampling point includes the lateral coordinate and the longitudinal coordinate of the first sampling point in the second vehicle coordinate system. The determination module 42 is used to select a plurality of sampling points whose longitudinal coordinates are less than a preset value from the plurality of first sampling points as a plurality of second sampling points.

[0117] Optionally, the acquisition module 41 is used to obtain the vehicle speed at several target moments and the forward-looking lane line equation at each target moment, the several target moments including the current moment and several second historical moments before the current moment; based on the vehicle speed at each target moment, respectively determine the displacement of the vehicle from each second historical moment to the current moment; select a second historical moment from each second historical moment in which the displacement is greater than a preset distance as the first historical moment; sample the forward-looking lane line equation at the first historical moment to obtain the forward-looking lane line information at the first historical moment.

[0118] It should be noted that the device of this embodiment can execute the steps in the above method. For detailed description of the relevant content, please refer to the above method part, which will not be repeated here.

[0119] See also Figure 5 , Figure 5 1 is a schematic diagram of a framework of an electronic device according to an embodiment of the present application. In this embodiment, the electronic device 50 includes a memory 51 and a processor 52 .

[0120] The processor 52 may also be referred to as a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip having signal processing capabilities. The processor 52 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor 52 may also be any conventional processor 52, etc.

[0121] The memory 51 in the electronic device 50 is used to store program instructions required for the processor 52 to run.

[0122] The processor 52 is used to execute program instructions to implement the lane line acquisition method in the present application.

[0123] See also Figure 6 , Figure 6It is a schematic diagram of the framework of an embodiment of a computer-readable storage medium provided by the present application. The computer-readable storage medium 60 of the embodiment of the present application stores program instructions 61, and when the program instructions 61 are executed, the lane line acquisition method provided by the present application is implemented. Among them, the program instructions 61 can form a program file and be stored in the above-mentioned computer-readable storage medium 60 in the form of a software product, so that a computer device (which can be a personal computer, a server, or a network device, etc.) executes all or part of the steps of each implementation method of the present application. The aforementioned computer-readable storage medium 60 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0124] The above scheme determines the rear-view lane line information at the current moment based on the front-view lane line information at the first historical moment, and obtains the rear-view lane line equation at the current moment based on the rear-view lane line information at the current moment. That is, the rear-view lane line equation at the current moment is obtained based on the historical front-view lane line information. In this way, there is no need to extract the rear-view lane line information from the rear-view image obtained by the rear-view camera, which can reduce the computing power overhead of obtaining the rear-view lane line and improve the coherence of the rear-view lane line and the front-view lane line.

[0125] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0126] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0127] In the several embodiments provided in the present application, it should be understood that the disclosed methods, devices and systems can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0129] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0130] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0131] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A lane line acquisition method, characterized in that: The method comprises: Get the front lane line information at the first historical moment; Determining rear-view lane line information at a current moment based on the front-view lane line information at the first historical moment; Based on the rear-view lane line information at the current moment, the rear-view lane line equation at the current moment is obtained by fitting.

2. The method according to claim 1, characterized in that The front-view lane line information at the first historical moment includes first position information of a plurality of first sampling points in a first vehicle coordinate system, the plurality of first sampling points being sampling points located on the front-view lane line at the first historical moment, and the first vehicle coordinate system being a vehicle coordinate system at the first historical moment; The determining the rear-view lane line information at the current moment based on the front-view lane line information at the first historical moment includes: transforming the first position information of each of the first sampling points into second position information in a second vehicle coordinate system, where the second vehicle coordinate system is the vehicle coordinate system at the current moment; Selecting a plurality of second sampling points that meet the requirements from the plurality of first sampling points; The second position information of the plurality of second sampling points is used as the rearview lane line information at the current moment.

3. The method according to claim 2, characterized in that The step of transforming the first position information of each of the first sampling points into second position information in a second vehicle coordinate system includes: Acquire the vehicle position information at the first historical moment and the vehicle position information at the current moment; Determining a first transformation matrix based on the vehicle posture information at the first historical moment; and determining a second transformation matrix based on the vehicle posture information at the current moment; Using the first transformation matrix, transform the first position information of each of the first sampling points into third position information in a world coordinate system; The third position information of each of the first sampling points is transformed into the second position information in the second vehicle coordinate system by using the second transformation matrix.

4. The method according to claim 3, characterized in that The vehicle posture information at the first historical moment includes the vehicle position information at the first historical moment and the vehicle posture information at the first historical moment; and determining the first transformation matrix based on the vehicle posture information at the first historical moment includes: Determining a first translation matrix based on the vehicle position information at the first historical moment; Determining a first rotation matrix based on the vehicle posture information at the first historical moment; Determine the first transformation matrix based on the first translation matrix and the first rotation matrix; and / or, The vehicle posture information at the current moment includes the vehicle position information at the current moment and the vehicle posture information at the current moment; and determining the second transformation matrix based on the vehicle posture information at the current moment includes: Determining a second translation matrix based on the vehicle position information at the current moment; Determining a second rotation matrix based on the vehicle posture information at the current moment; Determine a third transformation matrix based on the second translation matrix and the second rotation matrix; The inverse matrix of the third transformation matrix is ​​used as the second transformation matrix.

5. The method according to claim 4, characterized in that The vehicle posture information includes the roll angle, pitch angle and yaw angle of the vehicle.

6. The method according to claim 2, characterized in that The second position information of the first sampling point includes a lateral coordinate and a longitudinal coordinate of the first sampling point in the second vehicle coordinate system; The step of selecting a plurality of second sampling points that meet the requirements from the plurality of first sampling points comprises: A plurality of sampling points whose longitudinal coordinates are less than a preset value are selected from the plurality of first sampling points as the plurality of second sampling points.

7. The method according to claim 1, characterized in that The obtaining of the front lane line information at the first historical moment includes: Obtaining the vehicle speed at a plurality of target moments and the forward-looking lane line equation at each of the target moments, the plurality of target moments including the current moment and a plurality of second historical moments before the current moment; Based on the vehicle speed at each of the target moments, respectively determine the displacement of the vehicle from each of the second historical moments to the current moment; Selecting from the second historical moments one of the second historical moments in which the displacement is greater than a preset distance as the first historical moment; The front lane line equation at the first historical moment is sampled to obtain the front lane line information at the first historical moment.

8. A lane line acquisition device, characterized in that: The device comprises: An acquisition module, used to acquire the front lane line information at the first historical moment; A determination module, configured to determine rear-view lane line information at a current moment based on the front-view lane line information at the first historical moment; The fitting module is used to fit the rear-view lane line equation at the current moment based on the rear-view lane line information at the current moment.

9. An electronic device, characterized in that: comprising a memory and a processor coupled to each other, The memory stores program instructions; The processor is used to execute the program instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program instructions, and the program instructions can be executed by a processor to implement the method according to any one of claims 1 to 7.

Images