Calibration method, device, electronic device, and storage medium for autonomous driving vehicle

Abstract

The present application discloses a calibration method, device, electronic device, and storage medium for an autonomous driving vehicle. The autonomous driving vehicle at least includes: an RTK positioning device and an image acquisition device, and realizes the calibration of the relative position of the RTK positioning device and the image acquisition device in the horizontal direction perpendicular to the vehicle body. Through the present application, the calculation result of the lane line is accurate, and the relative position calibration result of the RTK positioning device and the image acquisition device is obtained.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a calibration method, device, electronic device, and storage medium for an autonomous driving vehicle. Background Art

[0002] Autonomous driving vehicles use sensors for positioning perception. For example, RTK positioning equipment can provide millimeter-level precise positioning information, and image acquisition equipment can provide visual information.

[0003] Autonomous driving vehicles need to use RTK positioning equipment and image acquisition equipment to work together to obtain the specific location of observed objects.

[0004] The related technology uses direct measurement to obtain the position relationship. However, due to the fact that the placement angle of the RTK positioning equipment and the installation angle of the image acquisition equipment are not completely consistent, the error is large. Summary of the invention

[0005] The embodiments of the present application provide a calibration method, device, electronic device, and storage medium for an autonomous driving vehicle to reduce calibration errors.

[0006] The present application embodiment adopts the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a calibration method for an autonomous driving vehicle, wherein the autonomous driving vehicle comprises at least: an RTK positioning device and an image acquisition device, for calibrating the relative positions of the RTK positioning device and the image acquisition device, the method comprising: after the autonomous driving vehicle has made at least one round trip along the center lane line of a target road section, based on the external parameters of the image acquisition device obtained in advance, obtaining continuous RTK position trajectory point data of the autonomous driving vehicle's round trip travel respectively acquired by the RTK positioning device and the image acquisition device, and continuous image data of the autonomous driving vehicle's round trip travel, wherein there is a corresponding time and position relationship between the RTK position trajectory point data and the continuous image data; identifying each frame of the continuous image data ; determining the spatial coordinate position of a preset spatial point in the vehicle body coordinate system according to the pixel coordinate position of the lane line in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points; obtaining the spatial coordinate position of the preset spatial point in the world coordinate system according to the spatial coordinate position of the preset spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame of the image; obtaining the second position parameter value by solving the spatial coordinate position of the preset spatial point in the world coordinate system, wherein the second position parameter value is a pixel position matching result of the pixel point parameter value of the spatial coordinate position at a horizontal distance perpendicular to the vehicle body; obtaining the calibration result of the relative positions of the RTK positioning device and the image acquisition device according to the second position parameter value.

[0008] In a second aspect, an embodiment of the present application further provides a calibration device for an autonomous driving vehicle, wherein the autonomous driving vehicle comprises at least: an RTK positioning device and an image acquisition device, for calibrating the relative positions of the RTK positioning device and the image acquisition device, wherein the device comprises: an acquisition module, for obtaining continuous RTK position trajectory point data of a round trip of the autonomous driving vehicle and continuous image data of a round trip of the autonomous driving vehicle respectively acquired by the RTK positioning device and the image acquisition device after the autonomous driving vehicle has made at least one round trip along the center lane line of the target road section, based on the external parameters of the image acquisition device obtained in advance, wherein there is a corresponding time and position relationship between the RTK position trajectory point data and the continuous image data; an identification module, for identifying the vehicle in each frame of the continuous image data. a pixel coordinate position of a lane line; determining the spatial coordinate position of a preset spatial point in the vehicle body coordinate system according to the pixel coordinate position of the lane line in multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points; a second determination module, for obtaining the spatial coordinate position of the spatial point in the world coordinate system according to the spatial coordinate position of the preset spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame of the image; a conversion module, for solving the second position parameter value through the spatial coordinate position of the preset spatial point in the world coordinate system, wherein the second position parameter value is obtained after matching the pixel point parameter value of the spatial coordinate position in the pixel position in the horizontal direction of the vehicle body; a solving module, for obtaining the calibration result of the relative position of the RTK positioning device and the image acquisition device according to the second position parameter value.

[0009] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform any of the aforementioned methods.

[0010] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes any of the aforementioned methods.

[0011] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0012] By only using the RTK positioning device and the image acquisition device in the autonomous driving measurement, the relative position calibration result of the two is obtained while the calculation result of the lane line is accurate, so as to realize the calibration of the relative position of the RTK positioning device and the image acquisition device. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0014] Figure 1 Schematic diagram of the hardware structure of the calibration method for an autonomous driving vehicle in an embodiment of the present application;

[0015] Figure 2 This is a flow chart of a calibration method for an autonomous driving vehicle in an embodiment of the present application;

[0016] Figure 3 This is a schematic diagram of the structure of a calibration device for an autonomous driving vehicle in an embodiment of the present application;

[0017] Figure 4 This is a schematic diagram of shooting a target road section in a calibration method for an autonomous driving vehicle in an embodiment of the present application;

[0018] Figure 5 This is an initial schematic diagram of trajectory points of an RTK positioning device in a calibration method for an autonomous driving vehicle in an embodiment of the present application;

[0019] Figure 6 The optimization intention of the trajectory points of the RTK positioning device in the calibration method for the autonomous driving vehicle in the embodiment of the present application is shown;

[0020] Figure 7 This is an enlarged schematic diagram of the trajectory points of the RTK positioning device in the calibration method for the autonomous driving vehicle in the embodiment of the present application;

[0021] Figure 8 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0023] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0024] like Figure 1As shown, a hardware structure diagram of the calibration method for an autonomous driving vehicle in an embodiment of the present application is provided, including: lane line 400, autonomous driving vehicle 300, image acquisition device 200, RTK positioning device 100. The right side of the autonomous driving vehicle 300 pointing upwards represents the first acquisition, and the left side of the autonomous driving vehicle 300 pointing downwards represents the second acquisition, that is, the two represent a round trip acquisition process.

[0025] The autonomous driving vehicle 300 needs to work together with the RTK positioning device 100 and the image acquisition device 200 to obtain the specific position of the observed object (pedestrian or vehicle), so as to calculate the relative position with the vehicle, and then make various judgments such as acceleration, parking, and steering. In addition, the data collection and generation of high-precision maps also require the observation of the position of external objects. If the calibration result of the position relationship between the RTK coordinate system and the image acquisition device coordinate system is inaccurate, the obtained position will be inaccurate.

[0026] Embodiment 1

[0027] Embodiment 1 of the present application provides a calibration method for an autonomous driving vehicle, wherein the autonomous driving vehicle comprises at least: an RTK positioning device and an image acquisition device, for calibrating the relative positions of the RTK positioning device and the image acquisition device, such as Figure 2 As shown, the method includes:

[0028] Step S210, after the autonomous driving vehicle has traveled back and forth at least once along the center lane line of the target road section, based on the pre-calibrated external parameters of the image acquisition device, continuous RTK position trajectory point data of the autonomous driving vehicle's round trip travel and continuous image data of the autonomous driving vehicle's round trip travel respectively collected by the RTK positioning device and the image acquisition device, wherein the RTK position trajectory point data and the continuous image data have a corresponding time and position relationship;

[0029] Step S220, identifying the pixel coordinate position of the lane line in each frame of the continuous image data;

[0030] Step S230, determining the spatial coordinate position of a preset spatial point in the vehicle body coordinate system according to the pixel coordinate position of the lane line in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points;

[0031] Step S240, obtaining the spatial coordinate position of the preset spatial point in the world coordinate system according to the spatial coordinate position of the preset spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame image;

[0032] Step S250, calculating the second position parameter value through the spatial coordinate position of the preset spatial point in the world coordinate system, wherein the second position parameter value is obtained after matching the pixel point parameter value of the spatial coordinate position with the pixel position in the horizontal direction of the vehicle body;

[0033] Step S260: Obtain a calibration result of the relative positions of the RTK positioning device and the image acquisition device according to the second position parameter value.

[0034] Through the above steps, only the RTK positioning device and image acquisition device used in the autonomous driving measurement are used to obtain the relative position calibration result of the two while making the calculation result of the lane line accurate, so as to realize the calibration of the relative position of the RTK positioning device and the image acquisition device.

[0035] Before executing the above step S220, it is first assumed that there is no position deviation between the RTK positioning device and the image acquisition device, and the position of the RTK positioning device and the pixel coordinate position of the current frame of the image acquisition device are calculated, and this is used as a reference standard.

[0036] In a specific implementation, it is also necessary to calibrate the external parameters of the image acquisition device. Based on the results of the external parameter calibration of the image acquisition device, the rotation transformation relationship between the image acquisition device coordinate system and the vehicle coordinate system and the installation height of the image acquisition device relative to the ground are obtained.

[0037] In the above step S220, a first position parameter value is determined based on the body coordinate system of the autonomous driving vehicle. The first position parameter value can be used as the relative initial position distance difference between the current RTK positioning device and the image acquisition device.

[0038] In a specific implementation, the first position parameter value is an initial value of a horizontal distance perpendicular to the vehicle body. The first position parameter value is perpendicular to the horizontal direction of the vehicle body and is configured with an initial value.

[0039] In the above step S230, the autonomous driving vehicle travels back and forth along the center lane line of the target road section at least once, which means that the autonomous driving vehicle travels along the center lane line of the target road section and returns after one trip, that is, data is obtained twice.

[0040] Then, based on the external parameters of the image acquisition device obtained based on the pre-calibration, the continuous RTK position trajectory point data of the self-driving vehicle's round trip collected by the RTK positioning device and the continuous image data of the self-driving vehicle's round trip collected by the image acquisition device are obtained. In other words, the continuous image data and the corresponding trajectory point data can be obtained by the RTK positioning device and the image acquisition device respectively during the driving process of the self-driving vehicle.

[0041] In a specific implementation, there is a corresponding time and position relationship between the RTK position trajectory point data and the continuous image data. It should be noted that the corresponding time and position relationship refers to a relative position relationship.

[0042] In a specific implementation, since the image acquisition device acquires continuous image data, the positioning information of the RTK positioning device does not need to consider its frequency.

[0043] In the above step S220, the pixel coordinate position of the lane line in each frame of the continuous image data is identified, for example, a lane line recognition model obtained by training a deep learning model can be used.

[0044] In a specific implementation, the lane line recognition model may adopt Lanenet, which is not specifically limited in the embodiments of the present application and may be selected according to actual detection and recognition needs.

[0045] In a specific implementation, the pixel coordinates of the lane line refer to the pixel coordinates of several points obtained through each point position coordinate set.

[0046] In the above step S230, the spatial coordinate position of the preset spatial point in the vehicle body coordinate system is determined according to the pixel coordinate position of the lane line in the multiple frames of the image. The preset spatial point is arbitrarily selected and the spatial coordinate position in the vehicle body coordinate system is obtained by coordinate conversion.

[0047] In a specific implementation, the preset spatial point includes a plurality of lane line points, and a plurality of lane lines constitute a lane line.

[0048] In the above step S240, the spatial coordinate position of the preset spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame image are obtained, which specifically includes the spatial coordinate position, RTK trajectory position and vehicle orientation, and the spatial coordinate position of the spatial point in the world coordinate system can be determined.

[0049] In a specific implementation, the inclination obtained by the RTK positioning device includes three data: Roll, Pitch, and Yaw. Pitch is the pitch angle, Yaw is the yaw angle, and Roll is the roll angle.

[0050] In a specific implementation, the spatial coordinate position of the spatial point in the world coordinate system is determined, that is, the position coordinates of the spatial point in the real world.

[0051] In the above step S250, the second position parameter value is calculated by the spatial coordinate position of the preset spatial point in the world coordinate system, that is, the second position parameter value is obtained by inversely calculating the spatial coordinate position of the preset spatial point in the world coordinate system. The second position parameter value obtained here is the new relative distance difference between the RTK positioning device and the image acquisition device.

[0052] In a specific implementation manner, the second position parameter value is obtained by matching the pixel point parameter value of the spatial coordinate position in the world coordinate system with the pixel position in the horizontal direction of the vehicle body.

[0053] In a specific implementation, the pixel position matching in the horizontal direction of the vehicle body, i.e., the left and right positions of the vehicle body, by the pixel point parameter value of the spatial coordinate position in the horizontal direction of the vehicle body is to adjust the position at the left and right positions of the vehicle body.

[0054] Since the first position parameter is an initial value in the horizontal direction perpendicular to the vehicle body, the second position parameter value can represent a change value in the left-right direction of the vehicle body.

[0055] In the above step S260, the calibration result of the relative position of the RTK positioning device and the image acquisition device is obtained according to the second position parameter value. That is to say, the relative position of the RTK positioning device and the image acquisition device can be adjusted by the calculated relative position error value, which is used as the calibration result of the two.

[0056] In a specific implementation, the RTK positioning device and image acquisition device in each autonomous driving vehicle need to be calibrated.

[0057] In a specific implementation, the calibration result can be used as a calibration parameter for the autonomous driving vehicle thereafter.

[0058] In one embodiment of the present application, the calibration of the relative positions of the RTK positioning device and the image acquisition device further includes: determining a first position parameter value based on the body coordinate system of the autonomous driving vehicle, wherein the first position parameter value is an initial value of the horizontal distance perpendicular to the body; judging whether the distance information between the relative positions of the RTK positioning device and the image acquisition device deviates in the horizontal distance perpendicular to the body; if it is judged that the first distance information between the relative positions of the RTK positioning device and the image acquisition device has deviated in the horizontal distance perpendicular to the body, adjusting the relative position of the RTK positioning device and the image acquisition device using the second distance information; if it is judged that the distance information between the relative positions of the RTK positioning device and the image acquisition device has not deviated in the horizontal distance perpendicular to the body, continuing to use the first distance information as the distance of the relative position of the RTK positioning device and the image acquisition device, wherein the first distance information is obtained by measurement or determined according to the calibration result, and the second distance information is determined by the updated calibration result.

[0059] The first position parameter value may be used as the relative initial position distance difference between the current RTK positioning device and the camera.

[0060] In a specific implementation, the first position parameter value is an initial value of a distance perpendicular to the horizontal direction of the vehicle body. The first position parameter value is perpendicular to the horizontal direction of the vehicle body and is configured with an initial value.

[0061] In the embodiment of the present application, it is necessary to determine whether the distance information between the relative positions of the RTK positioning device and the image acquisition device deviates in the horizontal distance perpendicular to the vehicle body. It should be noted that the deviation here refers to the deviation in the relative position relationship, which can also be directly distinguished from the image, and can be obtained by calculation. In the case of a deviation, it means that the previously assumed positional relationship between the RTK positioning device and the image acquisition device or the calibration result has an error, so the second distance information is used to adjust the relative position of the RTK positioning device and the image acquisition device. The first distance information is the initial relative distance information. In the case of no deviation, it means that there is no error in the calibration result, so the first distance information will continue to be used as the distance of the relative position of the RTK positioning device and the image acquisition device.

[0062] Furthermore, the first distance information is obtained by measurement or determined according to a calibration result.

[0063] The second distance information is determined by the updated calibration result, that is, the new relative distance difference obtained by calibration.

[0064] In one embodiment of the present application, the determining of a first position parameter value based on the body coordinate system of the autonomous driving vehicle, wherein the first position parameter value is an initial value of the horizontal distance perpendicular to the body, comprises: assuming that the body coordinate system of the autonomous driving vehicle determines that the RTK positioning device and the image acquisition device are in the same position, determining the first position parameter value; obtaining a calibration result of the relative positions of the RTK positioning device and the image acquisition device based on the second position parameter value, comprising: after the autonomous driving vehicle travels back and forth at least once along the center lane line of the target road section, obtaining two acquisition results including a deviation value of the horizontal distance perpendicular to the body as the second position parameter value; obtaining the left or right relative position of the RTK positioning device and the image acquisition device in the horizontal distance perpendicular to the body as the calibration result based on the right side of the driving direction of the autonomous driving vehicle as the positive direction and the left side as the negative direction.

[0065] In the embodiment of the present application, it is assumed that the body coordinate system of the autonomous driving vehicle determines that the RTK positioning device and the image acquisition device are in the same position, and the first position parameter value is determined. Actual measurement may not be performed, and it is assumed that the RTK positioning device and the image acquisition device are in the same position, and the first position parameter value is zero, that is, there is no error.

[0066] Furthermore, after the autonomous driving vehicle travels back and forth along the center lane line of the target road section at least once, two collection results are obtained, including the distance deviation value in the horizontal direction perpendicular to the vehicle body as the second position parameter value. For the user, after the autonomous driving vehicle travels back and forth along the center lane line of the target road section at least once, the distance deviation value in the horizontal direction perpendicular to the vehicle body is obtained through background calculation as the second position parameter value.

[0067] It should be noted that the target road section must be a closed section or a test section, or other sections that meet the conditions. The center lane line refers to the center lane line of at least the lanes in different driving directions. The center lane line can be a solid line or a dotted line, which does not affect the result.

[0068] Finally, according to the right side of the driving direction of the autonomous driving vehicle as the positive direction and the left side as the negative direction, the left or right relative position of the RTK positioning device and the image acquisition device in the horizontal direction perpendicular to the vehicle body is obtained as a calibration result. Under the premise that the right side is the positive direction and the left side is the negative direction, the obtained positive or negative value can indicate the left and right directions. The left or right relative position of the RTK positioning device and the image acquisition device in the horizontal direction perpendicular to the vehicle body is obtained as a calibration result, that is, the relative position relationship in the X direction (horizontal left and right directions) is calibrated.

[0069] In one embodiment of the present application, the calibration result of the relative position of the RTK positioning device and the image acquisition device is obtained based on the second position parameter value, including: determining the deviation-free horizontal distance perpendicular to the vehicle body based on the second position parameter value and the relative position between the RTK positioning device and the image acquisition device, and using it as the calibration result.

[0070] In the embodiment of the present application, preferably, the deviation-free horizontal distance perpendicular to the vehicle body can be further determined based on the second position parameter value and the relative position between the RTK positioning device and the image acquisition device. This is the process of correcting (adjusting) the relative position distance between the two.

[0071] In one embodiment of the present application, the identifying the pixel coordinate position of the lane line in each frame of the continuous image data includes: pre-training a lane line detection model, wherein the lane line detection model is obtained by training multiple groups of training sets through deep machine learning, and each group of the training sets includes lane lines and corresponding labels; identifying the continuous image data through a deep learning model to obtain the pixel coordinate position of the lane line in each frame of the image.

[0072] In an embodiment of the present application, a deep machine learning method is used for the process of identifying lane lines.

[0073] A lane line detection model is pre-trained, wherein the lane line detection model is obtained by training multiple training sets in a deep machine learning manner, each training set includes lane lines and corresponding labels (label categories include but are not limited to real and virtual lane lines, single and double lane lines, non-lane lines, stop lines). The continuous image data is identified by the deep learning model to obtain the pixel coordinate position of the lane line in each frame of the image.

[0074] In one embodiment of the present application, the spatial coordinate position of the preset spatial point in the vehicle body coordinate system is determined according to the pixel coordinate position of the lane line in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points, including: according to the pixel coordinate position P of the lane line in the multiple frames of the image uv =K×CamRCar×P / d, determine the spatial coordinate positions of the several lane line points in the vehicle body coordinate system, where P is the spatial coordinate (x, y, z) of the spatial point in the vehicle coordinate system, CamRCar is the rotation transformation relationship between the image acquisition device coordinate system and the vehicle coordinate system, d is the depth value of the spatial point in the image acquisition device coordinate system, and K is the internal parameter matrix of the image acquisition device.

[0075] In the embodiment of the present application, the pixel coordinate position P of the lane line in the multiple frames of the image is uv =K×CamRCar×P / d, determine the spatial coordinate positions of the several lane line points in the vehicle body coordinate system.

[0076] P uv is the pixel coordinates of any spatial point on the photo

[0077] P uv =K×CamRCar×P / d

[0078] Among them, P is the spatial coordinate of a certain spatial point in the vehicle coordinate system (expressed as x, y, z); CamRCar is the rotation transformation relationship between the image acquisition device coordinate system and the vehicle coordinate system. Since the origin of the image acquisition device coordinate system coincides with the origin of the vehicle coordinate system, there is no translation transformation relationship between the two. Through external parameter calibration, the matrix and the installation height h of the image acquisition device can be obtained in advance; d is the depth value of the spatial point in the image acquisition device coordinate system; K is the intrinsic parameter matrix of the image acquisition device, which is a 3x3 matrix, including inherent parameters such as the focal length of the image acquisition device.

[0079] Assuming the road surface is a plane is equivalent to assuming that all points on the road surface have the same height value, h is known, that is, P(x, h, z), so in the above formula, if we want to find the spatial coordinates of a lane line point, there are only three unknown quantities x, z, and d. At the same time, Puv = K × CamRCar × P / d can be decomposed into three equations, and these three quantities can be solved.

[0080] In one embodiment of the present application, before determining the first position parameter value based on the body coordinate system of the autonomous driving vehicle, it also includes: defining the positive direction of each coordinate axis of the coordinate system of the autonomous driving vehicle as right (+x)-down (+y)-front (+z), and the negative direction as left (-x)-up (-y)-back (-z), where (±x) is the horizontal distance perpendicular to the body; based on the calculation result of the horizontal distance perpendicular to the body, calibrate the relative position relationship between the RTK positioning device and the image acquisition device in the x direction.

[0081] In the embodiment of the present application, by defining the positive direction of each coordinate axis of the vehicle coordinate system as right (+x)-down (+y)-front (+z), and the negative direction as left (-x)-up (-y)-back (-z), the relative position relationship in the x direction can be calibrated. Then, based on the calculation result of the horizontal distance perpendicular to the vehicle body, the relative position relationship between the RTK positioning device and the image acquisition device in the x direction is calibrated.

[0082] For example, if the right side of the driving direction is the positive direction (consistent with the positive direction of the x-axis), the calculation result is -0.13m, which means a deviation of 0.13m. This means that the origin of the image acquisition device coordinate system and the RTK coordinate system deviates by about -0.13m / 2=-0.065m in the x-direction, which means that the image acquisition device is 0.065m to the right of the RTK positioning device.

[0083] Embodiment 2

[0084] In an embodiment of the present application, a calibration device for an autonomous driving vehicle is provided, wherein the autonomous driving vehicle comprises at least: an RTK positioning device and an image acquisition device, for realizing the calibration of the relative positions of the RTK positioning device and the image acquisition device, such as Figure 3 As shown, the device comprises:

[0085] The acquisition module 310 is used to obtain the continuous RTK position trajectory point data of the round trip of the autonomous driving vehicle and the continuous image data of the round trip of the autonomous driving vehicle respectively acquired by the RTK positioning device and the image acquisition device after the autonomous driving vehicle has made at least one round trip along the central lane line of the target road section, based on the external parameters of the image acquisition device obtained in advance, wherein the RTK position trajectory point data and the continuous image data have a corresponding time and position relationship.

[0086] An identification module 320, configured to identify the pixel coordinate position of the lane line in each frame of the continuous image data;

[0087] A second determination module 330 is used to determine the spatial coordinate position of a preset spatial point in the vehicle body coordinate system according to the pixel coordinate position of the lane line in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points;

[0088] A conversion module 340, configured to obtain the spatial coordinate position of the preset spatial point in the world coordinate system according to the spatial coordinate position of the preset spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame image;

[0089] A calculation module 350 is used to calculate the second position parameter value through the spatial coordinate position of the preset spatial point in the world coordinate system, wherein the second position parameter value is a pixel position matching result of the pixel point parameter value at the horizontal direction perpendicular to the vehicle body through the spatial coordinate position;

[0090] The calibration result module 360 ​​is used to obtain the calibration result of the relative position of the RTK positioning device and the image acquisition device according to the second position parameter value.

[0091] It also includes: a first determination module, used to determine a first position parameter value based on the body coordinate system of the autonomous driving vehicle, wherein the first position parameter value is an initial value of the horizontal distance perpendicular to the body.

[0092] In the acquisition module 310 in the embodiment of the present application, the autonomous driving vehicle travels back and forth along the center lane line of the target road section at least once, which means that the autonomous driving vehicle travels along the center lane line of the target road section and travels back and forth after one trip, that is, data is acquired twice.

[0093] Then, based on the external parameters of the image acquisition device obtained based on the pre-calibration, the continuous RTK position trajectory point data of the self-driving vehicle's round trip collected by the RTK positioning device and the continuous image data of the self-driving vehicle's round trip collected by the image acquisition device are obtained. In other words, the continuous image data and the corresponding trajectory point data can be obtained by the RTK positioning device and the image acquisition device respectively during the driving process of the self-driving vehicle.

[0094] In a specific implementation, there is a corresponding time and position relationship between the RTK position trajectory point data and the continuous image data. It should be noted that the corresponding time and position relationship refers to a relative position relationship.

[0095] In a specific implementation, since the image acquisition device acquires continuous image data, the positioning information of the RTK positioning device does not need to consider its frequency.

[0096] The recognition module 320 in the embodiment of the present application identifies the pixel coordinate position of the lane line in each frame of the continuous image data, for example, a lane line recognition model obtained by training a deep learning model may be used.

[0097] In a specific implementation, the lane line recognition model may be Lanenet, which is not specifically limited in the embodiments of the present application and may be selected according to actual detection and recognition needs.

[0098] In a specific implementation, the pixel coordinates of the lane line refer to the pixel coordinates of a plurality of points obtained through each point position coordinate set.

[0099] The second determination module 330 in the embodiment of the present application determines the spatial coordinate position of the preset spatial point in the vehicle body coordinate system according to the pixel coordinate position of the lane line in the multiple frames of the image. The preset spatial point is arbitrarily selected and the spatial coordinate position in the vehicle body coordinate system is obtained by coordinate conversion.

[0100] In a specific implementation, the preset spatial point includes a plurality of lane line points, and a plurality of lane lines first form a lane line.

[0101] In the conversion module 340 in the embodiment of the present application, the spatial coordinate position of the preset spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame image are obtained, which specifically includes the spatial coordinate position, RTK trajectory position and vehicle orientation, and the spatial coordinate position of the spatial point in the world coordinate system can be determined.

[0102] In a specific implementation, the inclination obtained by the RTK positioning device includes three data: Roll, Pitch, and Yaw. Pitch is the pitch angle, Yaw is the yaw angle, and Roll is the roll angle.

[0103] In a specific implementation, the spatial coordinate position of the spatial point in the world coordinate system is determined, that is, the position coordinates of the spatial point in the real world.

[0104] In the solving module 350 in the embodiment of the present application, the second position parameter value is solved by the spatial coordinate position of the preset spatial point in the world coordinate system, that is, the second position parameter value is obtained by inverse calculation through the spatial coordinate position of the preset spatial point in the world coordinate system. The second position parameter value obtained here is the new relative distance difference between the RTK positioning device and the image acquisition device.

[0105] In a specific implementation manner, the second position parameter value is obtained after matching the pixel point parameter value of the spatial coordinate position with the pixel position in the horizontal direction of the vehicle body.

[0106] In a specific implementation, the pixel position matching in the horizontal direction of the vehicle body, i.e., the left and right positions of the vehicle body, by the pixel point parameter value of the spatial coordinate position in the horizontal direction of the vehicle body is to adjust the position at the left and right positions of the vehicle body.

[0107] Since the first position parameter is an initial value in the horizontal direction perpendicular to the vehicle body, the second position parameter value can represent a change value in the left-right direction of the vehicle body.

[0108] In the calibration result module 360 ​​in the embodiment of the present application, a calibration result of the relative position of the RTK positioning device and the image acquisition device is obtained according to the second position parameter value. That is to say, the relative position of the RTK positioning device and the image acquisition device can be adjusted by the calculated relative position error value, which is used as the calibration result of the two.

[0109] In a specific implementation, the RTK positioning device and image acquisition device in each autonomous driving vehicle need to be calibrated.

[0110] In a specific implementation, the calibration result can be used as a calibration parameter for the autonomous driving vehicle thereafter.

[0111] It can be understood that the above-mentioned calibration device for autonomous driving vehicles can implement the various steps of the calibration method for autonomous driving vehicles provided in the aforementioned embodiment, and the relevant explanations about the calibration method are applicable to the calibration device for autonomous driving vehicles and will not be repeated here.

[0112] In order to better understand the above-mentioned calibration method process for autonomous driving vehicles, the above-mentioned technical solution is explained below in conjunction with a preferred embodiment, but is not used to limit the technical solution of the embodiment of the present invention.

[0113] The preferred embodiment of the present application can, by using only the RTK positioning device and the image acquisition device in the autonomous driving measurement, obtain the relative position calibration result of the two while making the calculation result of the lane line accurate, so as to realize the calibration of the relative position of the RTK positioning device and the image acquisition device.

[0114] In addition, the method in this application does not require a specific calibration site and special measuring equipment. It only needs to obtain the data collected by the image acquisition device and the RTK positioning device to complete the calibration, or it can select the road sections that meet the requirements from the driving data to complete the calibration, and the results are more accurate than the general direct measurement method.

[0115] The conventional method in the related art is to directly measure the position relationship between the RTK antenna and the RTK chip, and the position relationship between the RTK chip and the camera. However, due to the fact that the RTK chip placement angle and the camera installation angle are not completely consistent, there will be a relatively large measurement error, which may even be more than 20cm in the left and right directions.

[0116] Based on the above, if Figure 4 As shown, it is a schematic diagram of the target road section shooting in the calibration method for the autonomous driving vehicle in the embodiment of the present application. The center line of the lane can be a solid line or a dotted line, or a double solid line or a double dotted line, which is not specifically limited in the embodiments of the present application.

[0117] The method in this application can reduce the vertical error of the vehicle body, that is, the error in the X direction, and specifically includes the following steps:

[0118] S1, calibrate the external parameters of the image acquisition device to obtain the rotation transformation relationship between the image acquisition device and the vehicle coordinate system and the installation height of the image acquisition device relative to the ground.

[0119] S2, select a road segment, such as Figure 4 As shown, the center lane line is a single or double line (can be a solid line or a dashed line, but cannot be a dividing strip or guardrail), and there are different driving directions on both sides of the line (according to traffic regulations).

[0120] S3, collect data back and forth on this road section to obtain the RTK trajectory of the autonomous driving vehicle traveling on the road in different driving directions on both sides and the continuous image data taken.

[0121] S4, using a deep learning method to identify the pictures collected on the road section, and obtain the pixel coordinates of the lane lines corresponding to each picture. Preferably, a Lanenet network model is used.

[0122] S5, using the imaging formula of the image acquisition device, the coordinates of the lane line, and the external parameters of the image acquisition device to solve the actual coordinates of the lane line pixel coordinates.

[0123] Imaging formula of image acquisition device

[0124] P uv =K×CamRCar×P / d

[0125] Wherein, P is the spatial coordinate of a certain spatial point in the vehicle coordinate system (expressed by x, y, z);

[0126] CamRCar is the rotation transformation relationship between the image acquisition device coordinate system and the vehicle coordinate system. Since the origin of the image acquisition device coordinate system and the vehicle coordinate system coincides, there is no translation transformation relationship between the two. Through external parameter calibration, the matrix and the installation height h of the image acquisition device can be obtained in advance. d is the depth value of the spatial point in the image acquisition device coordinate system. K is the intrinsic parameter matrix of the image acquisition device, which is a 3x3 matrix, including the inherent parameters such as the focal length of the image acquisition device. P uv is the pixel coordinate of the spatial point on the photo.

[0127] Assuming the road surface is a plane is equivalent to assuming that all points on the road surface have the same height value, that is, P(xh,z). Therefore, in the above formula, if we want to find the spatial coordinates of a lane line point, there are only three unknown quantities: x, z, and d. At the same time, since formula 1 can be decomposed into three equations, these three quantities can be solved.

[0128] Based on the above, for the target image, the longitude and latitude positions of the lane line point are inferred through the position at the time of taking the image (current target frame) and the heading angle (which can be obtained from the data of the RTK positioning device).

[0129] S6, calculate the lane line points contained in multiple continuous images, and finally obtain the actual coordinate positions of all lane line points on the road section, such as Figure 5 shown.

[0130] Figure 5 In Figure 4 The road section shown in the figure is calculated using RTK and image acquisition equipment without position deviation (equivalent to assuming that the two are in the same position).

[0131] The star-shaped dots in the figure are the RTK track points of the vehicle. The black (dark) lane line is the calculation result of the right side driving from bottom to top, and the white (light) lane line is the calculation result of the left side driving from top to bottom. It can be seen that the calculation results of the same lane line in the two acquisitions have obvious deviations in the left and right (x) directions, and the deviation measured by the map is about 0.13m.

[0132] S7, the initial calculation assumes that the RTK and image acquisition equipment are in the same position, the calculation results are as follows Figure 5 It can be seen that the calculation results of the two acquisitions have a deviation of about 0.13m in the x direction, and the black calculation result is biased to the left of the driving direction, and the white calculation result is biased to the left of the driving direction (the two are definitely consistent).

[0133] If the right side of the driving direction is the positive direction (consistent with the positive direction of the x-axis), then the deviation is -0.13m. In other words, the origin of the image acquisition device coordinate system and the RTK positioning device coordinate system deviates by about -0.13m / 2=-0.065m in the x-direction, that is, the image acquisition device is 0.065m to the right of the RTK.

[0134] S8, bring the above deviation into the relative position of RTK and image acquisition equipment, calculate and obtain the result without deviation in the x direction, and the calibration is completed, such as Figure 6 shown. Figure 7 for Figure 6 Substitute the calibrated -0.65m into the calculation result of the new lane line, and the two basically overlap in the X direction (the direction perpendicular to the direction of the vehicle body (the direction of vehicle travel)) Figure 7 for local magnification).

[0135] Figure 8 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 8 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0136] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0137] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0138] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a calibration device for the autonomous driving vehicle at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0139] The autonomous driving vehicle at least comprises: an RTK positioning device and an image acquisition device, which are used to calibrate the relative positions of the RTK positioning device and the image acquisition device. The method comprises: after the autonomous driving vehicle travels back and forth at least once along the central lane line of the target road section, based on the external parameters of the image acquisition device obtained by pre-calibration, obtaining the continuous RTK position trajectory point data of the autonomous driving vehicle's round trip travel respectively collected by the RTK positioning device and the image acquisition device and the continuous image data of the autonomous driving vehicle's round trip travel, wherein there is a corresponding time and position relationship between the RTK position trajectory point data and the continuous image data; identifying the pixel coordinate position of the lane line in each frame of the continuous image data;

[0140] Determine the spatial coordinate position of a preset spatial point in the vehicle body coordinate system according to the pixel coordinate position of the lane line in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points;

[0141] According to the spatial coordinate position of the preset spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame image, the spatial coordinate position of the spatial point in the world coordinate system is obtained;

[0142] The second position parameter value is obtained by solving the spatial coordinate position of the preset spatial point in the world coordinate system, wherein the second position parameter value is obtained by matching the pixel point parameter value of the spatial coordinate position with the pixel position in the horizontal direction of the vehicle body;

[0143] According to the second position parameter value, a calibration result of the relative positions of the RTK positioning device and the image acquisition device is obtained.

[0144] The above application Figure 2The method for executing the calibration device for an autonomous driving vehicle disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0145] The electronic device may also perform Figure 2 A method for executing a calibration device for an autonomous driving vehicle in Figure 2 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0146] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 2The method executed by the calibration device for the autonomous driving vehicle in the illustrated embodiment is specifically used to execute: the autonomous driving vehicle at least includes: an RTK positioning device and an image acquisition device, and is used to realize the calibration of the relative positions of the RTK positioning device and the image acquisition device. The method includes: after the autonomous driving vehicle travels back and forth at least once along the central lane line of the target road section, based on the external parameters of the image acquisition device obtained by pre-calibration, obtaining the continuous RTK position trajectory point data of the autonomous driving vehicle traveling back and forth once respectively collected by the RTK positioning device and the image acquisition device, and the continuous image data of the autonomous driving vehicle traveling back and forth once, wherein there is a corresponding time and position relationship between the RTK position trajectory point data and the continuous image data;

[0147] Identify the pixel coordinate position of the lane line in each frame of the continuous image data;

[0148] Determine the spatial coordinate position of a preset spatial point in the vehicle body coordinate system according to the pixel coordinate position of the lane line in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points;

[0149] According to the spatial coordinate position of the preset spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame image, the spatial coordinate position of the spatial point in the world coordinate system is obtained;

[0150] The second position parameter value is calculated by the spatial coordinate position of the preset spatial point in the world coordinate system, wherein the second position parameter value is obtained after matching the pixel position of the pixel point parameter value of the spatial coordinate position in the horizontal direction of the vehicle body; based on the second position parameter value, the calibration result of the relative position of the RTK positioning device and the image acquisition device is obtained.

[0151] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0152] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0153] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0154] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0155] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0156] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0157] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0158] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0159] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0160] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A calibration method for an autonomous driving vehicle, wherein: The autonomous driving vehicle at least includes: an RTK positioning device and an image acquisition device, which are used to calibrate the relative positions of the RTK positioning device and the image acquisition device. The method includes: After the autonomous driving vehicle travels back and forth at least once along the central lane line of the target road section, based on the pre-calibrated external parameters of the image acquisition device, the continuous RTK position trajectory point data of the autonomous driving vehicle's round trip travel and the continuous image data of the autonomous driving vehicle's round trip travel respectively collected by the RTK positioning device and the image acquisition device are obtained, wherein the RTK position trajectory point data and the continuous image data have a corresponding time and position relationship; Identify the pixel coordinate position of the lane line in each frame of the continuous image data; Determine the spatial coordinate position of a preset spatial point in a vehicle body coordinate system according to the pixel coordinate position of the lane line in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points; According to the spatial coordinate position of the preset spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame image, the spatial coordinate position of the spatial point in the world coordinate system is obtained; A second position parameter value is obtained by solving the spatial coordinate position of the preset spatial point in the world coordinate system, wherein the second position parameter value is a pixel position matching result of the pixel point parameter value at the horizontal direction perpendicular to the vehicle body through the spatial coordinate position; According to the second position parameter value, a calibration result of the relative position of the RTK positioning device and the image acquisition device is obtained, which includes: After the autonomous driving vehicle travels back and forth at least once along the central lane line of the target road section, a distance deviation value of the two acquisition results in the horizontal direction perpendicular to the vehicle body is obtained as the second position parameter value; According to the right side of the driving direction of the autonomous driving vehicle being the positive direction and the left side being the negative direction, the left or right relative position of the RTK positioning device and the image acquisition device in the horizontal direction perpendicular to the vehicle body is obtained and used as the calibration result.

2. The method of claim 1, wherein: The method of realizing the calibration of the relative positions of the RTK positioning device and the image acquisition device further includes: Determine a first position parameter value based on a body coordinate system of the autonomous driving vehicle, wherein the first position parameter value is an initial value of a horizontal distance perpendicular to the body; Determine whether the distance information between the relative positions of the RTK positioning device and the image acquisition device deviates from the initial value of the horizontal distance perpendicular to the vehicle body; If it is determined that the first distance information between the relative positions of the RTK positioning device and the image acquisition device has deviated from the initial value of the distance in the horizontal direction perpendicular to the vehicle body, the relative position of the RTK positioning device and the image acquisition device is adjusted using the second distance information; If it is determined that the distance information between the relative positions of the RTK positioning device and the image acquisition device has not deviated from the initial value of the distance in the horizontal direction perpendicular to the vehicle body, the first distance information continues to be used as the distance between the relative positions of the RTK positioning device and the image acquisition device, wherein the first distance information is obtained by measurement or determined based on a calibration result, and the second distance information is determined by an updated calibration result.

3. The method of claim 2, wherein: The determining of a first position parameter value based on the body coordinate system of the autonomous driving vehicle, wherein the first position parameter value is an initial value of a horizontal distance perpendicular to the body, comprises: Assuming that the body coordinate system of the autonomous driving vehicle determines that the RTK positioning device and the image acquisition device are in the same position, a first position parameter value is determined.

4. The method of claim 2, wherein: The step of obtaining a calibration result of the relative positions of the RTK positioning device and the image acquisition device according to the second position parameter value includes: According to the second position parameter value and the relative position between the RTK positioning device and the image acquisition device, it is determined that the horizontal distance perpendicular to the vehicle body has no deviation, and this is used as the calibration result.

5. The method of claim 1, wherein: The identifying the pixel coordinate position of the lane line in each frame of the continuous image data includes: Pre-training a lane detection model, wherein the lane detection model is obtained by training multiple training sets in a deep machine learning manner, each training set including lane lines and corresponding labels; The continuous image data is recognized by a deep learning model to obtain the pixel coordinate position of the lane line in each frame of the image.

6. The method of claim 1, wherein: The determining of the spatial coordinate position of a preset spatial point in the vehicle body coordinate system according to the pixel coordinate position of the lane line in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points, including: According to the pixel coordinate position P of the lane line in the multiple frames of the image uv =K×CamRCar×P / d, determine the spatial coordinate positions of the several lane line points in the vehicle body coordinate system, where P is the spatial coordinate (x, y, z) of the spatial point in the vehicle coordinate system, CamRCar is the rotation transformation relationship between the image acquisition device coordinate system and the vehicle coordinate system, d is the depth value of the spatial point in the image acquisition device coordinate system, and K is the internal parameter matrix of the image acquisition device.

7. The method of claim 2, wherein: Before determining the first position parameter value based on the body coordinate system of the autonomous driving vehicle, the method further includes: The positive direction of each coordinate axis of the coordinate system of the autonomous driving vehicle is defined as right (+x)-down (+y)-front (+z), and the negative direction is defined as left (-x)-up (-y)-back (-z), where (±x) is the horizontal distance perpendicular to the vehicle body; The relative position relationship between the RTK positioning device and the image acquisition device in the x direction is calibrated according to the calculation result of the horizontal distance perpendicular to the vehicle body.

8. A calibration device for an autonomous driving vehicle, the autonomous driving vehicle comprising at least: An RTK positioning device and an image acquisition device are used to calibrate the relative positions of the RTK positioning device and the image acquisition device. The device comprises: an acquisition module, configured to obtain, based on the pre-calibrated external parameters of the image acquisition device, the continuous RTK position trajectory point data of the round trip of the autonomous driving vehicle and the continuous image data of the round trip of the autonomous driving vehicle respectively acquired by the RTK positioning device and the image acquisition device after the autonomous driving vehicle has made at least one round trip along the central lane line of the target road section, wherein the RTK position trajectory point data and the continuous image data have a corresponding time and position relationship; An identification module, used to identify the pixel coordinate position of the lane line in each frame of the continuous image data; A second determination module is used to determine the spatial coordinate position of a preset spatial point in the vehicle body coordinate system according to the pixel coordinate position of the lane line in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points; A conversion module, used to obtain the spatial coordinate position of the preset spatial point in the world coordinate system according to the spatial coordinate position of the preset spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame image; A solving module, configured to solve a second position parameter value through the spatial coordinate position of the preset spatial point in the world coordinate system, wherein the second position parameter value is a pixel position matching result of the pixel point parameter value at the spatial coordinate position in a horizontal direction perpendicular to the vehicle body; A calibration result module is used to obtain a calibration result of the relative positions of the RTK positioning device and the image acquisition device according to the second position parameter value, which includes: after the autonomous driving vehicle travels back and forth along the central lane line of the target road section at least once, obtaining a distance deviation value of two acquisition results in the horizontal direction perpendicular to the vehicle body as the second position parameter value; According to the right side of the driving direction of the autonomous driving vehicle being the positive direction and the left side being the negative direction, the left or right relative position of the RTK positioning device and the image acquisition device in the horizontal direction perpendicular to the vehicle body is obtained and used as the calibration result.

9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute any one of the methods of claims 1 to 7.

Images