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, wherein the autonomous driving vehicle at least includes: an RTK positioning device and an image acquisition device, and realizes the calibration of the relative positions of the RTK positioning device and the image acquisition device in the horizontal direction of the line connecting the front and rear wheels of 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 autonomous driving technology, and in particular to a calibration method, device, electronic device, and storage medium for autonomous driving vehicles. Background Art

[0002] Autonomous 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] In related technologies, when measuring the relative positions of RTK positioning equipment and image acquisition equipment, there are still large errors in the front and rear position directions of the autonomous driving vehicle. Summary of the Invention

[0005] The embodiments of the present application provide a calibration method, device, electronic device, and storage medium for autonomous driving vehicles to optimize the calibration process and improve the accuracy of the calibration results.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a calibration method for an autonomous vehicle, wherein the autonomous vehicle includes 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:

[0008] After the autonomous driving vehicle travels back and forth at least once along the non-solid 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;

[0009] Identifying the pixel coordinate position of the lane line in each frame of the continuous image data;

[0010] Determining the spatial coordinate position of a preset spatial point in the vehicle body coordinate system based on the pixel coordinate positions of the lane lines in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points;

[0011] Obtain the spatial coordinate position of the spatial point in the world coordinate system based on 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;

[0012] The second position parameter value is calculated based on 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 line connecting the front and rear wheels on the vehicle body;

[0013] 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.

[0014] In a second aspect, an embodiment of the present application further provides a calibration device for an autonomous vehicle, wherein the autonomous vehicle includes 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 device including:

[0015] an acquisition module configured to obtain, after the autonomous driving vehicle has made at least one round trip along the non-solid center lane line of the target road section, continuous RTK position trajectory point data and continuous image data of the round trip of the autonomous driving vehicle, respectively acquired by the RTK positioning device and the image acquisition device, based on pre-calibrated external parameters of the image acquisition device, wherein the RTK position trajectory point data and the continuous image data have a corresponding time and position relationship;

[0016] an identification module, configured to identify pixel coordinate positions of lane lines in each frame of the continuous image data;

[0017] a second determining module, configured to determine a spatial coordinate position of a preset spatial point in the vehicle body coordinate system based on the pixel coordinate positions of the lane lines in the plurality of frames of the image, wherein the preset spatial point includes a plurality of lane line points;

[0018] A conversion module is used to obtain the spatial coordinate position of the preset spatial point in the world coordinate system based on the spatial coordinate position of the spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame image;

[0019] a calculating module, configured to calculate a second position parameter value based on 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 values ​​at the spatial coordinate position with the pixel positions in the horizontal direction of the line connecting the front and rear wheels on the vehicle body;

[0020] The 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.

[0021] 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 execute any of the aforementioned methods.

[0022] 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 applications, the electronic device executes any of the aforementioned methods.

[0023] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0024] By using only RTK positioning equipment and image acquisition equipment in autonomous driving measurements, the relative position calibration results of the two are obtained while ensuring accurate lane line calculation results, reducing calibration errors relative to the front and rear directions of the vehicle body, and optimizing the calibration results of the relative positions of the RTK positioning equipment and the image acquisition equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] 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:

[0026] Figure 1 Schematic diagram of the hardware structure of the calibration method for an autonomous driving vehicle in an embodiment of the present application;

[0027] Figure 2 This is a flow chart of a calibration method for an autonomous driving vehicle in an embodiment of the present application;

[0028] 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;

[0029] Figure 4 This is a schematic diagram of shooting a target road section in the calibration method for an autonomous driving vehicle in an embodiment of the present application (the center lane line is a dotted line);

[0030] Figure 5 This is an initial schematic diagram (z direction) of the trajectory points of the RTK positioning device in the calibration method for the autonomous driving vehicle in an embodiment of the present application;

[0031] Figure 6This is an optimized plot of the RTK positioning device trajectory points in the calibration method for an autonomous vehicle in an embodiment of the present application (in the z direction);

[0032] Figure 7 This is an enlarged schematic diagram (z direction) of the trajectory points of the RTK positioning device in the calibration method for the autonomous driving vehicle in an embodiment of the present application;

[0033] Figure 8 This is a schematic structural diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0034] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0035] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0036] like Figure 1 FIG. 1 shows a schematic diagram of the hardware structure of a calibration method for an autonomous vehicle according to an embodiment of the present application, including lane markings 400, an autonomous vehicle 300, an image acquisition device 200, and an RTK positioning device 100. The right side of the autonomous vehicle 300 pointing upwards represents the first acquisition, and the left side of the autonomous vehicle 300 pointing downwards represents the second acquisition, i.e., the two represent a round-trip acquisition process.

[0037] 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), thereby calculating the relative position with the vehicle, and then making various decisions such as acceleration, parking, and steering. In addition, the data collection and generation of high-precision maps also require observing 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.

[0038] It is important to note that the center lane line must be a dotted line. Considering that the error results in the forward and backward directions are adjusted, if the dotted line is not used, the trajectory points will overlap, and the final calculation result will not be obtained.

[0039] Example 1

[0040] The first 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, such as Figure 2 As shown, the method includes:

[0041] Step S210, after the autonomous driving vehicle makes at least one round trip along the non-solid center lane line of the target road section, based on the pre-calibrated external parameters of the image acquisition device, obtain continuous RTK position trajectory point data of the autonomous driving vehicle's round trip and continuous image data of the autonomous driving vehicle's round trip, 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;

[0042] Step S220, identifying the pixel coordinate position of the lane line in each frame of the continuous image data;

[0043] Step S230, determining the spatial coordinate position of a preset spatial point in the vehicle body coordinate system based on the pixel coordinate positions of the lane lines in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points;

[0044] Step S240, obtaining the spatial coordinate position of the preset spatial point in the world coordinate system based on the spatial coordinate position of the preset spatial point in the vehicle body coordinate system, the RTK trajectory position corresponding to the frame image, and the vehicle orientation;

[0045] Step S250, calculating a second position parameter value based on 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 line connecting the front and rear wheels on the vehicle body;

[0046] 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.

[0047] Through the above steps, only the RTK positioning equipment and image acquisition equipment used in the autonomous driving measurement are used to obtain the relative position calibration results of the two while ensuring the accuracy of the lane line calculation results, thereby reducing the calibration error relative to the front and rear directions of the vehicle body, and optimizing the calibration results of the relative positions of the RTK positioning equipment and the image acquisition equipment.

[0048] In step S210, 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.

[0049] In one specific embodiment, the first position parameter value is the initial horizontal value of the line connecting the front and rear wheels on the vehicle body. It should be noted that the line connecting the front and rear wheels on the vehicle body is a virtual line connecting the front and rear wheels in horizontal space. Furthermore, the first position parameter value is the initial horizontal value of the line.

[0050] In the above step S210, the autonomous driving vehicle travels back and forth at least once along the non-solid center lane of the target road section, which means that the autonomous driving vehicle travels along the non-solid center lane of the target road section and travels back and forth after one trip, i.e., acquiring data twice. Figure 4 As shown in the figure, it is shown that the current vehicle is located on a certain target road section and is on the right side of the non-solid center lane line. It can be understood that if the solid center lane line is used during a round trip, it will make it impossible to distinguish the error distance between the front and rear positions of the vehicle body.

[0051] Then, based on the pre-calibrated external parameters of the image acquisition device, the continuous RTK position trajectory data for a round trip of the autonomous vehicle, as captured by the RTK positioning device, and the continuous image data for a round trip of the autonomous vehicle, as captured by the image acquisition device, are obtained. In other words, the continuous image data and corresponding trajectory data can be obtained by the RTK positioning device and the image acquisition device, respectively, during the autonomous vehicle's travel.

[0052] In one embodiment, the RTK position trajectory point data and the continuous image data have a corresponding time and position relationship. It should be noted that the corresponding time relationship refers to the same generation time of the two data, and the corresponding position relationship refers to the relative position relationship of the generation positions of the two data, which is the relative position of the two acquisition devices.

[0053] 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.

[0054] In the above step S220, the pixel coordinate position of the lane line in each frame image in the continuous image data is identified, for example, a lane line recognition model obtained by training a deep learning model can be used.

[0055] In a specific implementation, the lane line recognition model can be Lanenet, which is not specifically limited in the embodiments of the present application and can be selected according to actual detection and recognition needs.

[0056] In a specific embodiment, the pixel coordinates of the lane line refer to the pixel coordinates of several points obtained by each point position coordinate set.

[0057] In step S230, the spatial coordinate position of a preset spatial point in the vehicle body coordinate system is determined based on the pixel coordinate positions of the lane lines 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 through coordinate transformation.

[0058] In a specific embodiment, the preset spatial points include a plurality of lane line points, and a plurality of lane lines are first formed into a lane line.

[0059] 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.

[0060] In a specific embodiment, 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.

[0061] 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.

[0062] 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.

[0063] In a specific embodiment, the second position parameter value is obtained by matching the pixel point parameter values ​​of the spatial coordinate position with the pixel position in the horizontal direction of the line connecting the front and rear wheels on the vehicle body.

[0064] In a specific embodiment, the position adjustment is performed at the front and rear positions of the vehicle body by matching the pixel position of the pixel point parameter value of the spatial coordinate position in the horizontal direction of the vehicle body in the horizontal direction of the vehicle body.

[0065] Since the first position parameter is the horizontal initial value of the line connecting the front and rear wheels on the vehicle body, the second position parameter value can represent the change value in the front and rear directions of the vehicle body.

[0066] In the above step S260, the calibration result of the relative positions of the RTK positioning device and the image acquisition device is obtained based on the second position parameter value. That is to say, the relative positions of the RTK positioning device and the image acquisition device can be adjusted by calculating the relative position error value, which is used as the calibration result of the two.

[0067] In a specific embodiment, the RTK positioning device and image acquisition device in each autonomous driving vehicle need to be calibrated.

[0068] In a specific embodiment, the calibration result can be used as the calibration parameter of the autonomous driving vehicle in the future.

[0069] In one embodiment of the present application, after the autonomous driving vehicle travels back and forth at least once along the non-solid center lane line of the target road section, based on the external parameters of the image acquisition device obtained in advance, the continuous RTK position trajectory point data of the autonomous driving vehicle's round trip travel, which are 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, are obtained, wherein the RTK position trajectory point data and the continuous image data have a corresponding time and position relationship, including: the non-solid center lane line includes: a single-dashed center lane line and a double-dashed center lane line, and the RTK position trajectory point data and the continuous image data have a deviation distance position relationship at the same center lane line and the same point; after the autonomous driving vehicle travels back and forth at least once along the single-dashed center lane line or the double-dashed center lane line of the target road section, 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 are respectively collected.

[0070] The non-solid center lane line in the embodiments of the present application includes but is not limited to a single-dashed center lane line and a double-dashed center lane line.

[0071] Furthermore, since the RTK position trajectory point data and the continuous image data have a deviation distance position relationship at the same center lane line and the same point, after the autonomous driving vehicle travels back and forth at least once along the single-dashed center lane line or the double-dashed center lane line of the target road section, 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 are collected respectively.

[0072] It's understood that the center lane line is horizontal, and that common points also lie on the same horizontal plane. To determine the relative distance difference between the RTK positioning device and the image acquisition device in the forward and rearward directions of the vehicle, the difference between the two acquisition results must be calculated based on the dashed center lane line.

[0073] In one embodiment of the present application, a first position parameter value is determined based on a body coordinate system of the autonomous vehicle, wherein the first position parameter value is an initial value in the horizontal direction of a line connecting the front and rear wheels of the vehicle body; before determining the first position parameter value based on the body coordinate system of the autonomous vehicle, the method includes:

[0074] 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 (±z) is the horizontal direction of the line connecting the front and rear wheels on the vehicle body; based on the calculation result of the horizontal direction of the line connecting the front and rear wheels on the vehicle body, the relative position relationship between the RTK positioning device and the image acquisition device in the z direction is calibrated.

[0075] First, it is assumed that there is no position deviation between the RTK positioning device and the image acquisition device. The position of the RTK positioning device and the pixel coordinate position of the image acquisition device in the current frame are calculated, and this is used as a reference standard.

[0076] In a specific embodiment, 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 and the vehicle coordinate system and the installation height of the image acquisition device relative to the ground are obtained.

[0077] In the embodiment of the present application, the positive direction of each coordinate axis of the vehicle coordinate system is defined as right (+x) - bottom (+y) - front (+z), and the negative direction is defined as left (-x) - top (-y) - back (-z). (±x) is perpendicular to the horizontal direction of the vehicle body, that is, the relative position relationship in the z direction can be calibrated through this application. Then, based on the calculation results perpendicular to the horizontal direction of the vehicle body, the relative position relationship in the z direction of the RTK positioning device and the image acquisition device is calibrated. In other words, in the embodiment of the present application, the individual calibration results in the z direction are mainly considered, and the difference in the left and right directions of the vehicle is not considered at this time.

[0078] In one embodiment of the present application, the spatial coordinate position of the preset spatial point in the vehicle body coordinate system is determined based on the pixel coordinate position of the lane line in the multiple frames of the image, wherein the preset spatial point includes several lane line points, including: based on 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 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 intrinsic parameter matrix of the image acquisition device.

[0079] 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 lane line points in the vehicle body coordinate system.

[0080] P uv The pixel coordinates of any spatial point on the photo

[0081] P uv =K×CamRCar×P / d

[0082] 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.

[0083] Assuming the road surface is flat 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). 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, P uv =K×CamRCar×P / d can be decomposed into three equations, and these three quantities can be solved.

[0084] 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 in the horizontal direction of a line connecting the front and rear wheels on the body, includes: 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, including: 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 in the horizontal direction of the line connecting the front and rear wheels on the 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, obtaining the front or rear relative position of the RTK positioning device and the image acquisition device in the horizontal direction of the line connecting the front and rear wheels on the body as the calibration result.

[0085] In the embodiments of the present application, the first position parameter value is determined assuming that the RTK positioning device and the image acquisition device are co-located, as determined by the autonomous vehicle's body coordinate system. Actual measurement is not required; it can be assumed that the RTK positioning device and the image acquisition device are co-located, resulting in a zero first position parameter value, i.e., no error.

[0086] Furthermore, after the autonomous driving vehicle travels back and forth along the non-solid center lane line of the target road section at least once, two collection results are obtained, including a deviation value in the horizontal direction of the line connecting the front and rear wheels on 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 deviation value in the horizontal direction of the line connecting the front and rear wheels on the vehicle body is obtained through background calculation as the second position parameter value.

[0087] It is important to note that the target road section may need to be a closed section, a test section, or other sections that meet the requirements. The center lane line refers to at least the center lane line of lanes in different driving directions. The center lane line needs to be collected on the dashed section.

[0088] Finally, based on the forward direction of the autonomous vehicle's travel being positive and the rearward direction being negative, the forward or rearward relative position of the RTK positioning device and the image acquisition device in the horizontal direction of the line connecting the front and rear wheels on the vehicle body is obtained and used as the calibration result. Under the premise that the forward direction is positive and the rear direction is negative, the obtained positive or negative value can indicate the forward or backward direction. The forward or rearward relative position of the RTK positioning device and the image acquisition device in the horizontal direction of the line connecting the front and rear wheels on the vehicle body is obtained and used as the calibration result, i.e., the relative position relationship in the z direction (horizontal forward and backward direction) is calibrated.

[0089] In one embodiment of the present application, the calibration result of the relative positions of the RTK positioning device and the image acquisition device is obtained based on the second position parameter value, and then it also includes: the autonomous driving vehicle determines the position of external objects based on the joint work of the RTK positioning device and the image acquisition device, which is used to realize data collection and generation in a preset high-precision map.

[0090] Based on the autonomous driving vehicle, the RTK positioning device and the image acquisition device work together to determine the position of external objects, and realize data collection and generation in a preset high-precision map, including but not limited to: optimized generation of lane lines.

[0091] 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 whether the distance information between the relative positions of the RTK positioning device and the image acquisition device deviates in the horizontal direction perpendicular to the line connecting the front and rear wheels on 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 in the horizontal direction of the line connecting the front and rear wheels on the vehicle body, the second distance information is used to adjust the relative position of the RTK positioning device and the image acquisition device; 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 in the horizontal direction of the line connecting the front and rear wheels on the vehicle body, the first distance information continues to be used as the distance of the relative positions 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.

[0092] 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 direction 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 specifically 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 the calibration result has no error, 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.

[0093] Furthermore, the first distance information is obtained through measurement or determined according to a calibration result.

[0094] The second distance information is determined by the updated calibration result, that is, the new relative distance difference obtained by calibration.

[0095] Example 2

[0096] 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 calibrating the relative positions of the RTK positioning device and the image acquisition device, such as Figure 3 As shown, the device includes:

[0097] An acquisition module 310 is configured to obtain, after the autonomous driving vehicle has made at least one round trip along the non-solid center lane line of a target road segment, continuous RTK position trajectory point data and continuous image data of the round trip, respectively acquired by the RTK positioning device and the image acquisition device, based on pre-calibrated external parameters of the image acquisition device, wherein the RTK position trajectory point data and the continuous image data have a corresponding time and position relationship.

[0098] an identification module 320 for identifying the pixel coordinate position of a lane line in each frame of the continuous image data;

[0099] A second determining module 330 is configured to determine a spatial coordinate position of a preset spatial point in the vehicle body coordinate system based on the pixel coordinate positions of the lane lines in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points;

[0100] A conversion module 340 is configured to obtain the spatial coordinate position of the preset spatial point in the world coordinate system based on the spatial coordinate position of the spatial point in the vehicle body coordinate system and the RTK trajectory position and vehicle orientation corresponding to the frame image;

[0101] a calculating module 350 configured to calculate a second position parameter value based on 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 at the spatial coordinate position with the pixel position in the horizontal direction of the line connecting the front and rear wheels on the vehicle body;

[0102] The calibration result module 360 ​​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.

[0103] It also includes: a first determination module, which determines 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 in the horizontal direction of a line connecting the front and rear wheels on the body.

[0104] In the first determination module of the embodiment of the present application, 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.

[0105] In one specific embodiment, the first position parameter value is the initial horizontal value of the line connecting the front and rear wheels on the vehicle body. It should be noted that the line connecting the front and rear wheels on the vehicle body is a virtual line connecting the front and rear wheels in horizontal space. Furthermore, the first position parameter value is the initial horizontal value of the line.

[0106] In the acquisition module 310 of the embodiment of the present application, the autonomous driving vehicle travels back and forth at least once along the non-solid center lane of the target road section, which means that the autonomous driving vehicle travels along the non-solid center lane of the target road section and travels back and forth after one trip, i.e., acquiring data twice. Figure 4 As shown in the figure, it is shown that the current vehicle is located on a certain target road section and is on the right side of the non-solid center lane line. It can be understood that if the solid center lane line is used during a round trip, it will make it impossible to distinguish the error distance between the front and rear positions of the vehicle body.

[0107] Then, based on the pre-calibrated external parameters of the image acquisition device, the continuous RTK position trajectory data for a round trip of the autonomous vehicle, as captured by the RTK positioning device, and the continuous image data for a round trip of the autonomous vehicle, as captured by the image acquisition device, are obtained. In other words, the continuous image data and corresponding trajectory data can be obtained by the RTK positioning device and the image acquisition device, respectively, during the autonomous vehicle's travel.

[0108] In one embodiment, the RTK position trajectory point data and the continuous image data have a corresponding time and position relationship. It should be noted that the corresponding time relationship refers to the same generation time of the two data, and the corresponding position relationship refers to the relative position relationship of the generation positions of the two data, which is the relative position of the two acquisition devices.

[0109] 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.

[0110] The recognition module 320 in the embodiment of the present application identifies the pixel coordinate position of the lane line in each frame image in the continuous image data, for example, a lane line recognition model obtained by training a deep learning model can be used.

[0111] In a specific implementation, the lane line recognition model can be Lanenet, which is not specifically limited in the embodiments of the present application and can be selected according to actual detection and recognition needs.

[0112] In a specific embodiment, the pixel coordinates of the lane line refer to the pixel coordinates of several points obtained by each point position coordinate set.

[0113] In the second determination module 330 of the present embodiment, the spatial coordinate position of a preset spatial point in the vehicle body coordinate system is determined based on the pixel coordinate positions of the lane lines in the multiple frames of the image. The preset spatial point is arbitrarily selected and its spatial coordinate position in the vehicle body coordinate system is obtained through coordinate transformation.

[0114] In a specific embodiment, the preset spatial points include a plurality of lane line points, and a plurality of lane lines are first formed into a lane line.

[0115] In the conversion module 340 of 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.

[0116] In a specific embodiment, 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.

[0117] 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.

[0118] In the solution module 350 of 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 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.

[0119] In a specific embodiment, the second position parameter value is obtained by matching the pixel point parameter values ​​of the spatial coordinate position with the pixel position in the horizontal direction of the line connecting the front and rear wheels on the vehicle body.

[0120] In a specific embodiment, the position adjustment is performed at the front and rear positions of the vehicle body by matching the pixel position of the pixel point parameter value of the spatial coordinate position in the horizontal direction of the vehicle body in the horizontal direction of the vehicle body.

[0121] Since the first position parameter is the horizontal initial value of the line connecting the front and rear wheels on the vehicle body, the second position parameter value can represent the change value in the front and rear directions of the vehicle body.

[0122] In the calibration result module 360 ​​of the 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. That is to say, the relative position error value obtained by calculation can be used to adjust the relative position of the RTK positioning device and the image acquisition device, which is used as the calibration result of the two.

[0123] In a specific embodiment, the RTK positioning device and image acquisition device in each autonomous driving vehicle need to be calibrated.

[0124] In a specific embodiment, the calibration result can be used as the calibration parameter of the autonomous driving vehicle in the future.

[0125] 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 embodiments. The relevant explanations on the calibration method for autonomous driving vehicles are applicable to the calibration device for autonomous driving vehicles and will not be repeated here.

[0126] 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 the preferred embodiment, but is not used to limit the technical solution of the embodiment of the present invention.

[0127] The preferred embodiment of the present application can, by using only the RTK positioning device and image acquisition device used in the autonomous driving measurement, obtain the relative position calibration result of the two while making the lane line calculation result accurate, so as to realize the calibration of the relative positions of the RTK positioning device and the image acquisition device.

[0128] In addition, the method in this application does not require a specific calibration site or special measuring equipment. It only needs to obtain data collected by the image acquisition device and the RTK positioning device to complete the calibration, or it can also complete the calibration by selecting a road section that meets the requirements from the driving data, and the result is more accurate than the general direct measurement method.

[0129] Conventional methods directly measure the positional relationship between the RTK antenna and the RTK chip, and between the RTK chip and the camera. However, due to variations in the RTK chip placement angle and camera installation angle, measurement errors can be significant, sometimes exceeding 20cm in the left and right directions.

[0130] Based on the above, if Figure 4 As shown, it is a schematic diagram of shooting the target road section in the calibration method for the autonomous driving vehicle in an embodiment of the present application. It should be noted that the center lane line needs to be selected as a dotted line.

[0131] The method in this application can reduce the horizontal error of the vehicle body, that is, the error in the Z direction, and specifically includes the following steps:

[0132] 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.

[0133] S2, select a target road segment, such as Figure 4 As shown, it should be noted that the center lane line in the figure is a single or double dashed line (there can be no isolation belt or guardrail), and the two sides of the line are different driving directions.

[0134] S3, collects data back and forth on this road section to obtain the RTK trajectory of the autonomous driving vehicle driving on both sides of the road and the continuous image data taken.

[0135] S4: Using deep learning to identify the images captured of the road section, obtain the pixel coordinates of the lane lines corresponding to each image. Preferably, a Lanenet network model is used.

[0136] 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 local coordinates of the lane line pixel coordinates.

[0137] Imaging formula of image acquisition equipment

[0138] P uv =K×CamRCar×P / d

[0139] Where P is the spatial coordinate of a certain spatial point in the vehicle coordinate system (expressed by x, y, z);

[0140] CamRCar is the rotational transformation relationship between the image acquisition device coordinate system and the vehicle coordinate system. Since the origins of the image acquisition device coordinate system and the vehicle coordinate system coincide, there is no translational transformation relationship between the two. Through external parameter calibration, this 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 that includes inherent parameters such as the focal length of the image acquisition device. uv is the pixel coordinate of the spatial point in the photo. Assuming the road surface is flat, this is equivalent to assuming that all points on the road have the same height, namely P(xh,z). Therefore, in the above equation, to find the spatial coordinates of a lane point, there are only three unknown quantities: x, z, and d. Furthermore, since Equation 1 can be decomposed into three equations, these three quantities can be solved.

[0141] Based on the above, for the target image, the latitude and longitude positions of the lane line point are inferred by the position at the time the image is taken (the current target frame) and the heading angle (these can be obtained from the data of the RTK positioning device).

[0142] S6, calculate the lane line points contained in multiple consecutive images, and finally obtain the actual coordinate positions of all lane line points on the road section, such as Figure 5 shown.

[0143] S7, assuming that the RTK device and the image acquisition device coincide in the z direction of the vehicle, calculate the lane line result of the road section, such as Figure 5 .

[0144] Figure 6 for Figure 1 The road section shown is calculated using RTK and image acquisition equipment without z-direction position deviation. Figure 6The large dots in the middle are RTK track points of the vehicle. The black (dark) lane lines are calculated from bottom-up on the right side, and the white (light) lane lines are calculated from top-down on the left side. It can be seen that the calculated results for the same lane line in the two acquisitions have a significant deviation in the direction of travel (z). After using the map to measure, the deviation is approximately 3.64m.

[0145] Figure 7 for Figure 6 The measurement results of the deviation distance at the same point on the same lane line are basically completely consistent. It can be seen that the calculation results of the two acquisitions have a deviation of about 3.64m in the z direction (the direction of vehicle travel), and the black calculation result deviates from the direction of travel, and the white calculation result also deviates from the direction of travel (the two are definitely consistent).

[0146] Taking the forward direction of travel as the positive direction (consistent with the positive direction of the z-axis), the deviation is -3.64m. This means that the origin of the image acquisition device coordinate system and the RTK coordinate system deviates by approximately -3.64m / 2 = -1.82m in the z-direction, meaning that the image acquisition device is in front of the RTK device.

[0147] S8, bringing the above deviation into the relative position of the RTK and image acquisition equipment, calculating the result without deviation in the z direction, and the calibration is completed.

[0148] 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, an internal bus, a network interface, and memory. The memory may include internal memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for its services.

[0149] The processor, network interface, and memory can be interconnected via 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 8Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0150] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0151] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming a calibration device for the autonomous vehicle at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0152] The autonomous driving vehicle includes at least an RTK positioning device and an image acquisition device, and is used to calibrate the relative positions of the RTK positioning device and the image acquisition device. The method includes:

[0153] After the autonomous driving vehicle travels back and forth at least once along the non-solid 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;

[0154] Identifying the pixel coordinate position of the lane line in each frame of the continuous image data;

[0155] Determining the spatial coordinate position of a preset spatial point in the vehicle body coordinate system based on the pixel coordinate positions of the lane lines in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points;

[0156] Obtain the spatial coordinate position of the spatial point in the world coordinate system based on 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;

[0157] The second position parameter value is calculated based on 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 line connecting the front and rear wheels on the vehicle body;

[0158] 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.

[0159] The above application Figure 2 The method disclosed in the illustrated embodiment for use in a calibration device for an autonomous vehicle can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor or by software instructions. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can 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 gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of this application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0160] The electronic device may also perform Figure 2 A method for executing a calibration device for an autonomous vehicle in Figure 2 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0161] The embodiment of 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, can enable the electronic device to execute Figure 2 The method performed by the calibration device for an autonomous vehicle in the illustrated embodiment is specifically used to perform:

[0162] The autonomous driving vehicle includes at least an RTK positioning device and an image acquisition device, and is used to calibrate the relative positions of the RTK positioning device and the image acquisition device. The method includes:

[0163] After the autonomous driving vehicle travels back and forth at least once along the non-solid 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;

[0164] Identifying the pixel coordinate position of the lane line in each frame of the continuous image data;

[0165] Determining the spatial coordinate position of a preset spatial point in the vehicle body coordinate system based on the pixel coordinate positions of the lane lines in the multiple frames of the image, wherein the preset spatial point includes a plurality of lane line points;

[0166] Obtain the spatial coordinate position of the spatial point in the world coordinate system based on 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;

[0167] The second position parameter value is calculated based on 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 line connecting the front and rear wheels on the vehicle body;

[0168] 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.

[0169] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0170] 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 flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 flowcharts and / or block diagrams. 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.

[0171] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0172] 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 the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0173] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0174] 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. Memory is an example of a computer-readable medium.

[0175] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The 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 disc read-only memory (CD-ROM), digital versatile disc (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 transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0176] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0177] 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 take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0178] The foregoing is merely 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 modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within 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 non-solid center 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 in the horizontal direction of the line connecting the front and rear wheels on the vehicle body through the pixel point parameter value of the spatial coordinate position; 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; After the autonomous driving vehicle travels back and forth at least once along the non-solid center 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 traveling back and forth once and the continuous image data of the autonomous driving vehicle traveling back and forth once 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, including: The non-solid center lane line includes: a single dashed center lane line and a double dashed center lane line, and the RTK position trajectory point data and the continuous image data have a deviation distance position relationship at the same center lane line and the same point; After the autonomous driving vehicle travels back and forth at least once along the single dashed center lane line or the double dashed center lane line of the target road section, continuous RTK position trajectory point data of the autonomous driving vehicle traveling back and forth once and continuous image data of the autonomous driving vehicle traveling back and forth once are respectively collected; The method further includes: determining 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 in a horizontal direction of a line connecting front and rear wheels on the body; Before determining the first position parameter value based on the body coordinate system of the autonomous driving vehicle, the method 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)-rear (-z), where (±z) is the horizontal direction of the line connecting the front and rear wheels on the vehicle body; According to the calculation result of the horizontal direction of the line connecting the front and rear wheels on the vehicle body, the relative position relationship between the RTK positioning device and the image acquisition device in the z direction is calibrated.

2. 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.

3. The method of claim 1, 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 in the horizontal direction of a line connecting the front and rear wheels on the body, includes: 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, determine a first position parameter value; 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: 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 a deviation value in the horizontal direction of a line connecting the front and rear wheels on 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 front or rear relative position of the RTK positioning device and the image acquisition device in the horizontal direction of the line connecting the front and rear wheels on the vehicle body is obtained and used as the calibration result.

4. The method of claim 1, wherein: The method further comprises 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, and then further comprising: The autonomous driving vehicle determines the position of external objects based on the joint work of the RTK positioning device and the image acquisition device, which is used to realize data collection and generation in a preset high-precision map.

5. 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 whether the distance information between the relative positions of the RTK positioning device and the image acquisition device deviates in the horizontal direction perpendicular to the line connecting the front and rear wheels on 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 in the horizontal direction of the line connecting the front and rear wheels on the vehicle body, the relative positions of the RTK positioning device and the image acquisition device are 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 in the horizontal direction of the line connecting the front and rear wheels on 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.

6. A calibration device 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 device includes: An acquisition module, configured to obtain, based on the pre-calibrated external parameters of the image acquisition device, continuous RTK position trajectory point data of the round trip of the autonomous driving vehicle and 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 non-solid center 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 calculation module, used for calculating 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 obtained after matching the pixel point parameter value of the spatial coordinate position with the pixel position in the horizontal direction of the line connecting the front and rear wheels on the vehicle body; A calibration result module, used for obtaining a calibration result of the relative position of the RTK positioning device and the image acquisition device according to the second position parameter value; After the autonomous driving vehicle travels back and forth at least once along the non-solid center 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 traveling back and forth once and the continuous image data of the autonomous driving vehicle traveling back and forth once 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, including: The non-solid center lane line includes: a single dashed center lane line and a double dashed center lane line, and the RTK position trajectory point data and the continuous image data have a deviation distance position relationship at the same center lane line and the same point; After the autonomous driving vehicle travels back and forth at least once along the single dashed center lane line or the double dashed center lane line of the target road section, continuous RTK position trajectory point data of the autonomous driving vehicle traveling back and forth once and continuous image data of the autonomous driving vehicle traveling back and forth once are respectively collected; The method further includes: determining 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 in a horizontal direction of a line connecting front and rear wheels on the body; Before determining the first position parameter value based on the body coordinate system of the autonomous driving vehicle, the method 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)-rear (-z), where (±z) is the horizontal direction of the line connecting the front and rear wheels on the vehicle body; According to the calculation result of the horizontal direction of the line connecting the front and rear wheels on the vehicle body, the relative position relationship between the RTK positioning device and the image acquisition device in the z direction is calibrated.

7. 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 5.

8. 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 5.

Images