Vehicle calibration method and device, computer equipment and storage medium

Abstract

The embodiment of the invention relates to a vehicle calibration method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a plurality of target signals sent by a vehicle in a calibration room; vehicle coordinates of the vehicle in the calibration room are determined according to the multiple target signals; obtaining a calibration plate image shot by the vehicle in the punctuation room; determining a first calibration plate coordinate of a target calibration plate combination contained in the calibration plate image in the calibration room, and determining a second calibration plate coordinate of the target calibration plate combination in the calibration plate image; and calibrating a camera and a laser radar of the vehicle according to the vehicle coordinate, the first calibration board coordinate and the second calibration board coordinate. Therefore, the vehicle of any model and size can be positioned without parking the vehicle at a certain fixed position in the calibration process, the wide adaptability to different types of vehicles during calibration is improved, the influence of the vehicle position on the calibration device is reduced, and the calibration accuracy is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of calibration technology, and in particular, to a vehicle calibration method, apparatus, computer equipment, and storage medium. Background Art

[0002] At present, after the vehicle is assembled, the sensor will be calibrated individually or fused. The joint calibration station is mostly used for the calibration of multiple sensors such as cameras, radars, and lidars in autonomous driving and advanced assisted driving systems. It is crucial to ensure the accuracy and reliability of sensor data. For camera calibration, the first step is to complete the camera's intrinsic calibration to solve the distortion problem caused by the camera hardware, and then perform external calibration based on the real coordinates of the points in space and the pixel coordinates in the camera image for bidirectional mapping to eliminate installation errors and achieve unified adaptation of the intelligent driving system.

[0003] The core of laser radar calibration is to calibrate its external parameters to eliminate installation errors. In the current actual mass production stage, the existing calibration station needs to use multiple sensors. In addition to the high price and high operating cost of the multi-sensor joint calibration station and its supporting software and hardware, the mass production time cost is also too high. The existing calibration station can only calibrate one vehicle each time. Since the calibration process is a very time-consuming and delicate job, this will lead to a decrease in the unit time utilization rate of vehicles and equipment, thereby affecting production efficiency. In addition, the joint calibration of multiple sensors involves a complex operation process, which requires precise control and a large number of manual settings, and requires high skills of operators. There will be large parameter differences between sensors of the same category and different suppliers, which makes the calibration station unable to adapt to the platform engineering of the OEM and is not conducive to the switching of sensor selection. Fixed calibration stations may not be suitable for all types and configurations of vehicles, limiting the flexibility and breadth of their application. If the same calibration station is used for any vehicle in order to reduce costs, it is easy to cause inaccurate calibration. Therefore, how to improve the accuracy of the calibration of vehicle cameras and sensors has become a problem that needs to be solved urgently. Summary of the invention

[0004] In view of this, in order to solve the above technical problems or part of the technical problems, an embodiment of the present invention provides a vehicle calibration method, apparatus, computer equipment and storage medium.

[0005] In a first aspect, an embodiment of the present invention provides a vehicle calibration method, comprising:

[0006] Acquire a plurality of target signals emitted by a vehicle in a calibration room, wherein the target signals are emitted by a signal generator at a target position of the vehicle;

[0007] determining the vehicle coordinates of the vehicle in the calibration room according to the multiple target signals;

[0008] Acquire a calibration plate image taken by the vehicle in a calibration room, wherein a plurality of calibration plate combinations are arranged in the calibration room;

[0009] Determine a first calibration plate coordinate of a target calibration plate combination contained in the calibration plate image in the calibration room, and determine a second calibration plate coordinate of the target calibration plate combination in the calibration plate image;

[0010] The camera and lidar of the vehicle are calibrated according to the vehicle coordinates, the first calibration plate coordinates and the second calibration plate coordinates.

[0011] In a possible implementation manner, the acquiring multiple target signals emitted by vehicles in the calibration room includes:

[0012] When successful pairing with the vehicle is detected, a first instruction is sent to the vehicle to control the signal generator at multiple target positions of the vehicle to send the target signal through the first instruction, and the multiple target positions include: the center position of the right front wheel axle and the center position of the left rear wheel axle of the vehicle, or the center position of the left front wheel axle and the center position of the right rear wheel axle of the vehicle;

[0013] Controlling a plurality of signal receivers in the calibration room to receive the target signal emitted by each signal generator;

[0014] Receive the target signal forwarded by each signal receiver.

[0015] In a possible implementation manner, determining the vehicle coordinates of the vehicle in the calibration room according to the multiple target signals includes:

[0016] Acquire a first coordinate system corresponding to the calibration room, and acquire the signal receiver coordinates of each signal receiver in the first coordinate system;

[0017] Determining the distance between each of the signal receivers and each of the signal generators according to the arrival time difference of the target signal received by each of the signal receivers;

[0018] For each of the signal generators, determining the coordinates of the signal generator in the first coordinate system according to the corresponding multiple distances and multiple coordinates of the signal receivers as the coordinates of each of the target positions;

[0019] The vehicle coordinates of the center of the vehicle in the first coordinate system are determined according to the wheelbase, the wheel width of the vehicle and the coordinates of the target position.

[0020] In a possible implementation, determining the first calibration plate coordinates of the target calibration plate combination included in the calibration plate image in the calibration room includes:

[0021] Performing information identification on the main calibration plate contained in the calibration plate image;

[0022] Determine that the main calibration plate and the corresponding auxiliary calibration plate whose calibration plate information is identified are the target calibration plate combination;

[0023] Acquire the first corner point coordinates of the connecting corner points of each pixel block in the main calibration plate in the first coordinate system from the calibration plate information, acquire the second corner point coordinates of the main calibration plate in the first coordinate system, and acquire the third corner point coordinates of the hole of the auxiliary calibration plate in the first coordinate system;

[0024] The first corner point coordinates, the second corner point coordinates and the third corner point coordinates are used as the first calibration plate coordinates.

[0025] In a possible implementation, determining the second calibration plate coordinates of the target calibration plate combination in the calibration plate image includes:

[0026] Acquire all corner points contained in the target calibration plate combination;

[0027] The coordinates of each corner point in the calibration plate image are used as the second calibration plate coordinates.

[0028] In a possible implementation, the calibrating the camera and the laser radar of the vehicle according to the vehicle coordinates, the first calibration plate coordinates, and the second calibration plate coordinates includes:

[0029] Determine the camera coordinates of the camera of the vehicle in the first coordinate system according to the vehicle coordinates, and determine the laser radar coordinates of the laser radar of the vehicle in the first coordinate system;

[0030] Calibrate the intrinsic parameters and extrinsic parameters of the camera according to the first calibration plate coordinates, the second calibration plate coordinates and the camera coordinates;

[0031] Acquire a first position of the hole of the secondary calibration plate by using the laser radar;

[0032] Obtaining a second position of the hole in the image of the camera through the calibrated camera;

[0033] The parameters of the laser radar are calibrated according to the first position and the second position.

[0034] In a possible implementation, the method further includes:

[0035] Sending a data burning request to the vehicle;

[0036] When confirmation information returned by the vehicle in response to the data burning request is received, the calibrated data is sent to the vehicle for burning.

[0037] In a second aspect, an embodiment of the present invention provides a vehicle calibration device, including:

[0038] An acquisition module, used for acquiring a plurality of target signals emitted by a vehicle in a calibration room, wherein the target signals are emitted by a signal generator at a target position of the vehicle;

[0039] A determination module, configured to determine the vehicle coordinates of the vehicle in the calibration room according to the plurality of target signals;

[0040] The acquisition module is further used to acquire a calibration plate image taken by the vehicle in a calibration room, wherein a plurality of calibration plate combinations are arranged in the calibration room;

[0041] The determination module is further used to determine the first calibration plate coordinates of the target calibration plate combination contained in the calibration plate image in the calibration room, and to determine the second calibration plate coordinates of the target calibration plate combination in the calibration plate image;

[0042] A calibration module is used to calibrate the camera and lidar of the vehicle according to the vehicle coordinates, the first calibration plate coordinates and the second calibration plate coordinates.

[0043] In a third aspect, an embodiment of the present invention provides a computer device, comprising: a processor and a memory, wherein the processor is used to execute a vehicle calibration program stored in the memory to implement the vehicle calibration method described in any one of the first aspects above.

[0044] In a fourth aspect, an embodiment of the present invention provides a storage medium, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the vehicle calibration method described in any one of the first aspects above.

[0045] The vehicle calibration scheme provided by the embodiment of the present invention obtains multiple target signals emitted by the vehicle in the calibration room, and the target signals are emitted by the signal generator of the target position of the vehicle; the vehicle coordinates of the vehicle in the calibration room are determined according to the multiple target signals; the calibration plate image taken by the vehicle in the calibration room is obtained, and the calibration room is provided with multiple calibration plate combinations; the first calibration plate coordinates of the target calibration plate combination contained in the calibration plate image in the calibration room are determined, and the second calibration plate coordinates of the target calibration plate combination in the calibration plate image are determined; the camera and laser radar of the vehicle are calibrated according to the vehicle coordinates, the first calibration plate coordinates and the second calibration plate coordinates. Thus, the vehicle camera and laser radar can be calibrated according to the vehicle coordinates in the calibration room, the coordinates of the calibration plate in the calibration room and the coordinates in the calibration plate image taken by the vehicle. During the calibration process, the vehicle can be positioned for vehicles of any model and size without parking the vehicle in a fixed position, which improves the wide adaptability to different types of vehicles during calibration, reduces the influence of the vehicle position on the calibration device, and improves the calibration accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic flow chart of a vehicle calibration method provided for an embodiment of the invention;

[0047] Figure 2 A schematic flow chart of another vehicle calibration method provided by an embodiment of the invention;

[0048] Figure 3 A schematic diagram of the structure of a vehicle calibration device provided by an embodiment of the invention;

[0049] Figure 4 A schematic diagram of the structure of a computer device provided for an embodiment of the invention;

[0050] Figure 5 A schematic diagram of an application scenario of a vehicle calibration method provided by an embodiment of the present invention;

[0051] Figure 6 A schematic diagram of a calibration plate assembly provided by an embodiment of the present invention;

[0052] Figure 7 A schematic diagram of an application scenario of another vehicle calibration method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] To facilitate understanding of the embodiments of the present invention, specific embodiments will be further explained below in conjunction with the accompanying drawings. The embodiments do not constitute a limitation on the embodiments of the present invention.

[0055] Figure 1 A flow chart of a vehicle calibration method provided by an embodiment of the present invention is shown as follows: Figure 1 As shown, the method specifically includes:

[0056] S11. Acquire multiple target signals emitted by vehicles in the calibration room, where the target signals are emitted by a signal generator at a target position of the vehicle.

[0057] The vehicle calibration method provided in an embodiment of the present invention is applied to a computer device, which is a device with a central processing unit and a CPU\GPU processing capability, and may include but is not limited to a desktop computer, a tablet computer, a server, etc. The specific computer device can obtain the vehicle coordinates in the calibration room, the coordinates of the calibration plate in the calibration room, and the coordinates in the calibration plate image taken by the vehicle, and calibrate the vehicle camera and lidar according to the acquired coordinates.

[0058] In this embodiment, a calibration room is pre-set, and the calibration room is used to calibrate the vehicle's camera and lidar. The calibration room is a closed, stable rectangular house without strong winds and vibrations to ensure the stability and consistency of the sensor data in the calibration room. An area where multiple vehicles can be parked at the same time is set in the calibration room for simultaneous calibration of multiple vehicles. The calibration room uses uniform and stable light to avoid strong light or shadows affecting the sensor data. The road surface in the calibration room is flat to ensure that the later calibration is based on the horizon hypothesis to reduce the calibration error. The calibration environment is away from strong electromagnetic interference, and the calibration environment temperature is kept stable to avoid the impact of temperature changes on sensor performance and calibration results.

[0059] Furthermore, a UWB main signal receiving base station is installed at the center of the top of the calibration room. The main signal receiving base station is a computer device in the present invention, and a central integrated calibration processor can be selected. At the same time, signal receivers are set at four different positions in the calibration room to receive the target signal sent by the vehicle and forward the target signal to the main signal receiving base station, and realize signal receiving redundancy design. When each signal receiver receives the target signal sent by the signal generator of the vehicle, it sends the target signal to the main signal receiving base station, wherein the target signal is a UWB signal, and a UWB signal generator is installed at the preset target position of the vehicle for sending the UWB signal.

[0060] S12. Determine the vehicle coordinates of the vehicle in the calibration room according to the multiple target signals.

[0061] In this embodiment, the vehicle sends target signals to two target positions, which are usually set at the center positions of two diagonal wheels of the vehicle. Each signal receiver can receive target signals from the two positions. The distance between each target position and the four signal receivers can be determined through the target signals received by each signal receiver, thereby obtaining four distances corresponding to each target position.

[0062] Furthermore, a right-handed UWB coordinate system (Ouc, Xuc, Yuc, Zuc) is established in advance with any position of the ground in the calibration room, or the center point of the ground, thereby determining the coordinate positions of the four signal receivers in the coordinate system, and according to the coordinates of the four signal receivers and the distance between each signal receiver and the target position, the position where the four distances intersect in the calibration room can be determined as the target position, and the coordinates of the target position can be determined at the same time. Thus, the coordinates of the two target positions of the vehicle are obtained (for example, the coordinates of the center position of the left front wheel of the vehicle and the coordinates of the center position of the right rear wheel of the vehicle).

[0063] Connect the two target positions. Since the two target positions are the two wheel center points in the diagonal direction of the vehicle, the coordinates of the center position of the vehicle can be calculated based on the wheelbase and axle width of the vehicle itself and the coordinates of the two target positions as the vehicle coordinates.

[0064] S13, obtaining a calibration plate image taken by the vehicle in a calibration room, where a plurality of calibration plate combinations are arranged.

[0065] In this embodiment, a plurality of calibration plate combinations are pre-set in the calibration room. For the calibration plates corresponding to the vehicle's cameras (e.g., front-view camera, rear-view camera, side-view camera) and sensors (e.g., lidar), a chessboard calibration plate with semantic information is used as a main plate (a calibration plate shaped like a QR code, consisting of multiple black and white squares) and a calibration plate with circular holes is used as a sub-plate. The QR code in the main calibration plate can be identified by scanning. After identification, the coordinates, size, mark and other information of each point of the current main calibration plate in the coordinate system of the calibration room can be obtained, and the coordinates, size, mark and hole position coordinates of the corresponding sub-calibration plate can be identified.

[0066] The calibration plates are arranged in groups on the walls around the calibration room in a regular order. Each main calibration plate and the corresponding adjacent secondary calibration plate are combined as a calibration plate. The main calibration plate and the secondary calibration plate are of the same width and height. They are laid horizontally on the wall of the calibration room in a similar way to laying floor tiles, ensuring that the secondary calibration plate is on the right side of the main calibration plate. For the vehicle's surround view camera, since its main function is the ground, there is no need for the holes of the secondary calibration plate to assist in calibration. Calibration can be performed as long as the QR code of the main calibration plate needs to be recognized. Therefore, the ground calibration plate combination only needs to include the main calibration plate without the need to set up the corresponding secondary calibration plate.

[0067] Among them, since the main calibration plate is in the form of a QR code, according to the QR code protocol standard, each QR code has four positioning codes so that the camera can capture and identify the position of the QR code later. In the spatial coordinate system established at the origin of the coordinate system in the calibration room, each QR code has the spatial semantic position information of the center position (x, y, z) of the QR code, that is, by identifying the QR code, the coordinates of each point in the main calibration plate in the coordinate system of the calibration room can be obtained, and the ID number of the QR code and the hole position of its secondary calibration plate can be included. In the entire calibration space, each set of calibration plates has a unique identification number. For the calibration of the surround camera, only the main calibration plate is used, and the secondary calibration plate is not used. The laying method is to lay the calibration plate in proportion on the flat ground in the calibration room. Since the width or length of the calibration room ground may not be divisible by the width or length of the calibration plate, it is necessary to adjust the calibration plate area to complete the laying by geometrically enlarging and reducing it, so that the width of the calibration room ground can be divided by the adjusted width of the calibration plate, and the length of the calibration room ground can be divided by the adjusted length of the calibration plate. The QR code should be set in large and small sizes to expand the versatility of the system, and the physical materials of the black and white areas in the main calibration plate should use layers with different reflection intensities.

[0068] After the vehicle coordinates are determined, the vehicle is controlled to remain stationary at the current position, and the camera that needs to be calibrated is controlled to capture images, so as to obtain the calibration plate image captured by the vehicle in the calibration room, and receive the calibration plate image sent by the vehicle.

[0069] S14, determining first calibration plate coordinates of the target calibration plate combination contained in the calibration plate image in the calibration room, and determining second calibration plate coordinates of the target calibration plate combination in the calibration plate image.

[0070] In this embodiment, the QR code in the main calibration plate contained in the calibration plate image is scanned and identified. When the information contained in the main calibration plate can be identified, it is determined that the main calibration plate image is complete, and the main calibration plate and the corresponding sub-calibration plate are removed as the target calibration plate combination. The first calibration plate coordinates pre-set in the QR code can be obtained by scanning and identifying the QR code. The first calibration plate coordinates may include: the coordinates of each point in the main calibration plate in the coordinate system of the calibration room, the coordinates of the corresponding sub-calibration plate in the coordinate system of the calibration room, and the ID of the target calibration plate combination.

[0071] Furthermore, the second calibration plate coordinates of the target calibration plate combination in the camera coordinate system of the camera that captures the current calibration plate image are obtained. The second calibration plate coordinates may include: the coordinates of each point in the main calibration plate in the camera coordinate system, and the coordinates of the corresponding secondary calibration plate in the camera coordinate system.

[0072] S15. Calibrate the camera and lidar of the vehicle according to the vehicle coordinates, the first calibration plate coordinates, and the second calibration plate coordinates.

[0073] In this embodiment, different cameras of each vehicle will read QR codes with different IDs, identify points in each QR code in the camera image, and bidirectionally map the coordinates of the points in the QR code contained in the coordinates of the first calibration plate in the coordinate system of the calibration room and the coordinates of the points in the QR code contained in the coordinates of the second calibration plate in the image. The Zhang Zhengyou calibration method is used to calibrate the internal and external parameters of the camera. The optical axis of the camera should be parallel to the X-axis. The position of the camera and the laser radar in the coordinate system of the calibration room is determined by using the preset size of the vehicle body and the position of the camera and the laser radar in the vehicle. The coordinates (hole position) of the secondary calibration plate are read by identifying the QR code, and the hole is mapped to the The position is converted into the camera coordinate system and recorded as K1. The lidar calculates the hole position K2. Due to the determinism of the lidar and camera installation parameters in the design, the rigid transformation of space is used to obtain K1=F*K2. The transformation matrix is ​​recorded as F. From this, F is solved to obtain the pitch\roll\yaw (pitch angle\roll angle\heading angle) of the lidar and the installation height of the lidar. The lidar coordinate system is then rotated and translated to the calibrated forward-looking camera coordinates. The camera coordinate system and the image coordinate system can be further used to obtain the corresponding transformation relationship between the lidar data and the camera image pixels, thereby realizing the joint calibration of sensors such as vehicle cameras and lidars.

[0074] The vehicle calibration method provided by the embodiment of the present invention obtains multiple target signals emitted by the vehicle in the calibration room, and the target signals are emitted by the signal generator of the target position of the vehicle; the vehicle coordinates of the vehicle in the calibration room are determined according to the multiple target signals; the calibration plate image taken by the vehicle in the calibration room is obtained, and the calibration room is provided with multiple calibration plate combinations; the first calibration plate coordinates of the target calibration plate combination contained in the calibration plate image in the calibration room are determined, and the second calibration plate coordinates of the target calibration plate combination in the calibration plate image are determined; the camera and laser radar of the vehicle are calibrated according to the vehicle coordinates, the first calibration plate coordinates and the second calibration plate coordinates. Thus, the vehicle camera and laser radar can be calibrated according to the vehicle coordinates in the calibration room, the coordinates of the calibration plate in the calibration room and the coordinates in the calibration plate image taken by the vehicle. During the calibration process, the vehicle can be positioned for vehicles of any model and size without parking the vehicle in a fixed position, which improves the wide adaptability to different types of vehicles during calibration, reduces the influence of the vehicle position on the calibration device, and improves the calibration accuracy.

[0075] Figure 2 A flow chart of another vehicle calibration method provided by an embodiment of the present invention is shown as follows: Figure 2 As shown, the method specifically includes:

[0076] S21. When successful pairing with the vehicle is detected, a first instruction is sent to the vehicle to control the signal generators at multiple target positions of the vehicle to send target signals through the first instruction; control multiple signal receivers in the calibration room to receive the target signal sent by each signal generator; and receive the target signal forwarded by each signal receiver.

[0077] In this embodiment, the vehicle opens the data path and completes pairing with the calibration room before entering the calibration room. After TCP / IP completes the three-way security handshake, real-time data is sent. The vehicle-side controller, as a forwarding node, does not perform calibration calculations, and subsequently sends data to the main signal receiving base station (integrated central computing module) in the calibration room for accelerated calculation. Each vehicle will be matched with the main signal receiving base station with a unique matching code. If multiple vehicles enter the calibration room for synchronous calibration at the same time, the integrated system will be enabled to automatically allocate computing cores for distributed computing.

[0078] When it is detected that the main signal receiving base station is successfully paired with the vehicle, a first instruction is sent to the vehicle, and the first instruction is used to control the signal generator on the vehicle to send a UWB signal as a target signal. The UWB signal generator is pre-set at two target positions of the vehicle, and the two target positions may include: the center position of the right front wheel axle and the center position of the left rear wheel axle of the vehicle, or the center position of the left front wheel axle and the center position of the right rear wheel axle of the vehicle.

[0079] Each signal receiver can receive the target signal sent by the signal generators at the two target locations and forward the target signal to the main signal receiving base station.

[0080] S22, obtaining a first coordinate system corresponding to the calibration room, and obtaining the signal receiver coordinates of each signal receiver in the first coordinate system; determining the distance between each signal receiver and each signal generator according to the arrival time difference of the target signal received by each signal receiver.

[0081] In this embodiment, if Figure 5 FIG. 1 is a schematic diagram of an application scenario of a vehicle calibration method provided by an embodiment of the present invention. Figure 5 It is a rectangular calibration room. The cube on the top of the calibration room is the pre-set main signal receiving base station. There are multiple signal receivers on the walls of different planes and positions in the calibration room, namely: receivers A, B, C and D, which are used to receive the signal bands emitted by the UWB generator on the vehicle. The black mark on the ground can represent the UWB signal generator. The position of the signal generator in the calibration room can be determined by receiving UWB signals through signal receivers in four different directions. The right-handed UWB coordinate system (Ouc, Xuc, Yuc, Zuc) is established with the ground center point at the bottom of the calibration room as the first coordinate system, thereby determining the signal receiver coordinates of the four signal receivers in the first coordinate system.

[0082] Lay out multiple calibration board combinations in the calibration room, such as Figure 6 FIG. 1 is a schematic diagram of a calibration plate assembly provided by an embodiment of the present invention. Figure 6 It includes the main calibration plate on the left and the secondary calibration plate on the right. The main calibration plate is a chessboard calibration plate, which contains a QR code composed of multiple black and white grids. Each QR code has the spatial semantic position information of the center position (x, y, z) of the QR code in the first coordinate system, and contains the unique ID number of the QR code. The position of each intersection point of the black grid and the white grid in the main calibration plate can be determined in the entire calibration plate, and then the position of each intersection point in the first coordinate system can be obtained. The spatial position of the calibration plate in the first coordinate system can be obtained by scanning the QR code (the inherent advantage of the QR code is that it has 3 positioning points for identification). The calibration speed and accuracy are accelerated by pre-storing the coordinates of the points in the main calibration plate in the QR code information. There is a hole in the middle of the secondary calibration plate, and the QR code information of the main calibration plate also pre-stores the position coordinates of the different corner points of the corresponding secondary calibration plate in the first coordinate system and the position coordinates of the holes. The laying method of the calibration plate combination is similar to Figure 1 The laying method of the plurality of calibration plate combinations set in the calibration room in step S13 is consistent, and the specific method can be referred to Figure 1 For the sake of brevity, the relevant content will not be repeated here.

[0083] Furthermore, based on the propagation characteristics of the UWB signal, the distance between each signal receiver and the signal generator at each target location can be determined according to the arrival time difference of the target signal received by each signal receiver.

[0084] S23. For each signal generator, determine the coordinates of the signal generator in the first coordinate system according to the corresponding multiple distances and multiple signal receiver coordinates as the coordinates of each target position; determine the vehicle coordinates of the center of the vehicle in the first coordinate system according to the wheelbase, wheelwidth and coordinates of the target position of the vehicle.

[0085] In this embodiment, if Figure 7 The figure shows a schematic diagram of an application scenario of another vehicle calibration method provided by an embodiment of the present invention, in which the signal generator is set at the target position of the center of the right front wheel axle and the target position of the center of the left rear wheel axle of the vehicle. According to the distance between each signal generator and each signal receiver, and the coordinates of multiple signal receivers, the coordinates [Xu1, Yu1, Zu1] and [Xu2, Yu2, Zu2] of a single signal generator in the first coordinate system are calculated using the TDOA positioning algorithm, that is, the coordinates of each target position. Since the vehicle calibration uses signal generators in two different positions, and there are distinctions between the front, rear, left and right labels of the vehicle wheels, the coordinates of the four-wheel positions are completed in combination with the preset vehicle wheelbase and axle width, and then the vehicle coordinates of the center position of the vehicle in the first coordinate system can be calculated.

[0086] S24, identifying information of the main calibration plate contained in the calibration plate image; determining the main calibration plate with the identified calibration plate information and the corresponding secondary calibration plate as the target calibration plate combination; obtaining the first corner point coordinates of the connecting corner points of each pixel block in the main calibration plate in the first coordinate system from the calibration plate information, obtaining the second corner point coordinates of the main calibration plate in the first coordinate system, and obtaining the third corner point coordinates of the hole of the secondary calibration plate in the first coordinate system; using the first corner point coordinates, the second corner point coordinates and the third corner point coordinates as the first calibration plate coordinates.

[0087] In this embodiment, the calibration plate image in the calibration room is obtained through the camera of the vehicle to be calibrated. The calibration plate image is first preprocessed, which may include but is not limited to: grayscale conversion, filtering and denoising, etc., to improve the detection rate of the QR code in the main calibration plate, and then an edge detection algorithm (for example, Canny edge detector) is used to perform image edge filtering. Then, the findContours (find corner point function) function in opencv (cross-platform computer vision library) is used to identify the QR code border from the edge image. When the QR code information can be identified, it is determined that the main calibration plate is complete in the image, and the identified main calibration plate and the corresponding secondary calibration plate are determined to be the target calibration plate combination.

[0088] Since each calibration plate combination has a unique mask (two-dimensional code graphic) and a unique ID, and each point in the calibration plate has a unique coordinate in the first coordinate system, the two-dimensional code is positioned by the square positioning mark unique to the two-dimensional code, and the first corner point coordinates of the connecting corners of the black pixel block and the white pixel block in each two-dimensional code are obtained in the first coordinate system. The second corner point coordinates of the four preset corner points in the two-dimensional code of the main calibration plate (indicating the position of the main calibration plate) in the first coordinate system are obtained, and the third corner point coordinates of the holes of the auxiliary calibration plate in the first coordinate system (indicating the unique coordinates of the hole position) are obtained; the first corner point coordinates, the second corner point coordinates, and the third corner point coordinates are used as the coordinates of the first calibration plate.

[0089] Specifically, when recognizing a QR code, warpPerspective ("affine transformation") in opencv can be used to perform an affine transformation on the QR code using the four preset corner points in the QR code, so that the QR code can be projected onto a plane with the front side facing up, thereby improving the QR code recognition rate. Then, the Zbar QR code decoder is used to decode the QR code and read out the QR code information stored in the QR code, such as the ID of each QR code, the coordinates of the four corner points of each black pixel in the QR code in the main calibration plate [[X_id_n_i, Y_id_n_i, Z_id_n_i]], where XYZ are the three axes in the spatial coordinate system, id is the unique number of each calibration plate, n represents the number of black pixel blocks in the calibration plate, i is the number of corner points where black pixel blocks and white pixel blocks meet in the calibration plate, and if a secondary calibration plate is included, the QR code information also includes the coordinates of the preset four corner points of the holes of the secondary calibration plate for laser radar calibration.

[0090] S25, obtaining all corner points included in the target calibration plate combination; and taking the coordinates of each corner point in the calibration plate image as the second calibration plate coordinates.

[0091] In this embodiment, all corner points included in the target calibration plate combination are determined from the calibration plate image, and the coordinates of each corner point in the preset coordinate system in the calibration plate image are used as the second calibration plate coordinates.

[0092] S26. Determine the camera coordinates of the vehicle's camera in the first coordinate system according to the vehicle coordinates, and determine the laser radar coordinates of the vehicle's laser radar in the first coordinate system; calibrate the intrinsic parameters and extrinsic parameters of the camera according to the first calibration plate coordinates, the second calibration plate coordinates and the camera coordinates.

[0093] In this embodiment, the camera coordinates are obtained to determine the position coordinates of the camera in the first coordinate system, and the laser radar coordinates are obtained to determine the position coordinates of the laser radar in the first coordinate system. The intrinsic parameters of the camera are the distortion parameters of the camera, which may include: K1, K2, P1, P2, etc., and the extrinsic parameters include: pitch, roll, yaw, x, y, z, etc.

[0094] The vehicle coordinates (Xv, Yv, Zv) of the vehicle in the first coordinate system of the calibration room are obtained, that is, the world coordinates corresponding to the vehicle are obtained. QR code positioning and image affine are used to make each QR code flat. The QR code is identified to obtain the center position (X_code_i, Y_code_i, Z_code_i) and the intersection of each black pixel block and white pixel block in the QR code in the first coordinate system of the calibration room. The coordinates of the first calibration plate: [[X_code_i_1, Y_code_i_1, Z_code_i_1], ..., [X_code_i_n, Y_code_i_n, Z_code_i_n]], denoted as Pts_i, where i is the QR code ID, XYZ are the three axes in the spatial coordinate system, and n represents the number of black pixel blocks in the calibration plate.

[0095] The QR code corner point algorithm is used to identify the corner points of the QR code in each captured calibration plate image, and the position of each QR code in the image and the position coordinates of each corner point in the image are calculated, that is, the coordinates of the second calibration plate are: UV_camera_t_code_i=[[u1,v1],[u2,v2】…[u1,v1]].

[0096] Furthermore, using the uniqueness of the QR code ID recognized by the camera, Pts_i is matched with UV_camera_t_code_i, where the former is the point coordinate in three-dimensional space (the first calibration plate coordinate) and the latter is the point coordinate on the plane captured by the camera (the second calibration plate coordinate). Through the known internal parameters of the camera including focal length, principal point coordinates, distortion coefficient, and then using the preset spatial coordinate system->camera coordinate system->image coordinate system conversion relationship, the camera external parameter Pose_t_gt = [Xcam_t_gt, Ycam_t_gt, Zcam_t_gt, Pitch_cam_t_gt, Roll_cam_t_gt, Yaw_cam_t_gt] is obtained, where t is the camera ID, and gt represents the actual installation. Here, the external parameters are calculated using the points in the QR code for average calculation. As long as the calculation is involved When the point is greater than the set threshold, large occasional errors can be averaged. During the design, Pose_t_d [Xcam_t_d, Ycam_t_d, Zcam_t_d, Pitch_cam_t_d, Roll_cam_t_d, Yaw_cam_t_d] has a design value representing the ideal position under error-free installation. In this way, a Pose_t_gt and Pose_t_d can be calculated, and there is a parallel rotation matrix E_fineturn. Therefore, the intrinsic and extrinsic parameters of the camera can be calibrated according to the high parallel rotation matrix.

[0097] S27, obtaining a first position of the hole of the secondary calibration plate through a laser radar; obtaining a second position of the hole in the camera image through a calibrated camera; and calibrating the parameters of the laser radar according to the first position and the second position.

[0098] In this embodiment, first, 1. laser scanning is performed using the different reflectivities of the black pixel blocks and white pixel blocks of the QR code in the main calibration plate, and Poisson reconstruction is used to densify the point cloud. Similarly, the QR code obtained after densification is 2D binary visualized.

[0099] 2. Use the visualized QR code scanned by the laser to perform QR code recognition (the same as the QR code recognition process of the camera) to obtain the coordinates of the center position of the circular hole of the secondary calibration plate and the coordinates of the center position of the QR code.

[0100] 3. The QR code of the main calibration plate and the corresponding holes of the secondary calibration plate can be determined in the point cloud data.

[0101] 4. In the point cloud space, calculate the upper, lower, left and right endpoints according to the point cloud data of each hole, and record them as P_left, P_right, P_top, and P_bottom respectively. Without considering the depth information, the intersection of the line segment composed of P_left and P_right and the line segments of P_top and P_bottom is recorded as P_block_center, which is the midpoint of the circular hole of the secondary calibration plate.

[0102] 5. If the points in the space and the points in the point cloud space can be matched one by one (the same as the camera), the external parameters of the lidar [X_lidra_gt, Y_lidra_gt, Z_lidra_gt, Pitch_lidra_gt, Roll_lidra_gt, Yaw_lidra_gt] can be calculated, and the installation error can be corrected according to the lidar set position [X_lidra_d, Y_lidra_d, Z_lidra_d, Pitch_lidra_d, Roll_lidra_d, Yaw_lidra_d] to obtain the rotation transformation matrix E_lidar_fineturn between the two positions.

[0103] Furthermore, the camera and the lidar are jointly calibrated: 1. The coordinates of the camera and the lidar in the first coordinate system are obtained by calculating the transformation matrices E_fineturn and E_lidar_fineturn of the two actual installation positions and the ideal positions.

[0104] 2. Fine-tune the camera and lidar data through the transformation matrices E_fineturn and E_lidar_fineturn respectively. The data are recorded as feature_camera_finetune and feature_lidar_finetune respectively.

[0105] 3. Knowing the positions of the two sensors in the coordinate system, we can obtain the matrix E_trans for converting the camera coordinate system to the lidar coordinate system, feature_camera_trans = E_trans*feature_camera_finetune, where feature_camera_trans is the data after the camera data is converted to the lidar coordinate system, thereby achieving spatial synchronization and calibration of the camera and lidar.

[0106] S28, sending a data burning request to the vehicle; when receiving confirmation information returned by the vehicle in response to the data burning request, sending the calibrated data to the vehicle for burning.

[0107] In this embodiment, after the calibration of the main signal receiving base station is completed, a data burning request will be sent to the vehicle end. After waiting for the corresponding confirmation information from the vehicle end, the calibration calculation results will be burned in a file format. After the vehicle end completes the calibration request, the vehicle automatically disconnects from the calibration room, and the main signal receiving base station automatically uploads the calibration results to the cloud for later optimization of the calibration method.

[0108] The vehicle calibration method provided in this embodiment can determine the vehicle coordinates in the calibration room by receiving the target signal sent by the vehicle, and calibrate the vehicle camera and laser radar by the vehicle coordinates and the coordinates of the calibration plate combined at the top of the table taken by the vehicle, as well as the coordinates in the calibration plate image. It can provide multiple vehicles for calibration at the same time, and does not require the position of the vehicle. It can calculate the vehicle posture in real time and establish the connection between the camera coordinate system and the space coordinate system, which provides greater freedom for the calibration operator and greatly improves the mass production efficiency. At the same time, the central integrated calibration calculation core is used in the calibration room for calibration calculation, which does not require the use of vehicle-side computing power, and the vehicle calibration data can be backed up for later rollback query and later optimization. Using UWB for positioning judgment avoids the use of traditional four-wheel positioning devices and reduces hardware costs. The accuracy of vehicle coordinate determination is improved, thereby improving calibration accuracy. At the same time, it supports calibration engineers to reconstruct vehicle parameter information without changing the calibration hardware, which greatly improves the platform generalization ability and can be applied to calibration of different models.

[0109] Figure 3 A schematic diagram of a vehicle calibration device provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown, the device specifically includes:

[0110] An acquisition module 31 is used to acquire a plurality of target signals emitted by a vehicle in a calibration room, wherein the target signals are emitted by a signal generator at a target position of the vehicle;

[0111] A determination module 32, configured to determine the vehicle coordinates of the vehicle in the calibration room according to the plurality of target signals;

[0112] The acquisition module is further used to acquire a calibration plate image taken by the vehicle in a calibration room, wherein a plurality of calibration plate combinations are arranged in the calibration room;

[0113] The determination module is further used to determine the first calibration plate coordinates of the target calibration plate combination contained in the calibration plate image in the calibration room, and to determine the second calibration plate coordinates of the target calibration plate combination in the calibration plate image;

[0114] The calibration module 33 is used to calibrate the camera and the laser radar of the vehicle according to the vehicle coordinates, the first calibration plate coordinates and the second calibration plate coordinates.

[0115] In a possible implementation manner, the acquisition module is specifically configured to, when detecting successful pairing with the vehicle, send a first instruction to the vehicle, so as to control the signal generator at multiple target positions of the vehicle to send the target signal through the first instruction, wherein the multiple target positions include: the center position of the right front wheel axle and the center position of the left rear wheel axle of the vehicle, or the center position of the left front wheel axle and the center position of the right rear wheel axle of the vehicle;

[0116] Controlling a plurality of signal receivers in the calibration room to receive the target signal emitted by each signal generator;

[0117] Receive the target signal forwarded by each signal receiver.

[0118] In a possible implementation manner, the determination module is specifically configured to obtain a first coordinate system corresponding to the calibration room, and obtain a signal receiver coordinate of each signal receiver in the first coordinate system;

[0119] Determining the distance between each of the signal receivers and each of the signal generators according to the arrival time difference of the target signal received by each of the signal receivers;

[0120] For each of the signal generators, determining the coordinates of the signal generator in the first coordinate system according to the corresponding multiple distances and multiple coordinates of the signal receivers as the coordinates of each of the target positions;

[0121] The vehicle coordinates of the center of the vehicle in the first coordinate system are determined according to the wheelbase, the wheel width of the vehicle and the coordinates of the target position.

[0122] In a possible implementation manner, the determination module is specifically configured to identify information of the main calibration plate contained in the calibration plate image;

[0123] Determine that the main calibration plate and the corresponding auxiliary calibration plate whose calibration plate information is identified are the target calibration plate combination;

[0124] Acquire the first corner point coordinates of the connecting corner points of each pixel block in the main calibration plate in the first coordinate system from the calibration plate information, acquire the second corner point coordinates of the main calibration plate in the first coordinate system, and acquire the third corner point coordinates of the hole of the auxiliary calibration plate in the first coordinate system;

[0125] The first corner point coordinates, the second corner point coordinates and the third corner point coordinates are used as the first calibration plate coordinates.

[0126] In a possible implementation manner, the determination module is specifically configured to obtain all corner points included in the target calibration plate combination;

[0127] The coordinates of each corner point in the calibration plate image are used as the second calibration plate coordinates.

[0128] In a possible implementation, the calibration module is specifically used to determine the camera coordinates of the camera of the vehicle in the first coordinate system according to the vehicle coordinates, and to determine the laser radar coordinates of the laser radar of the vehicle in the first coordinate system;

[0129] Calibrate the intrinsic parameters and extrinsic parameters of the camera according to the first calibration plate coordinates, the second calibration plate coordinates and the camera coordinates;

[0130] Acquire a first position of the hole of the secondary calibration plate by using the laser radar;

[0131] Obtaining a second position of the hole in the image of the camera through the calibrated camera;

[0132] The parameters of the laser radar are calibrated according to the first position and the second position.

[0133] In a possible implementation, the sending module 34 is used to send a data burning request to the vehicle;

[0134] When confirmation information returned by the vehicle in response to the data burning request is received, the calibrated data is sent to the vehicle for burning.

[0135] The vehicle calibration device provided in this embodiment can be as follows Figure 4 The device shown in FIG. 1 may perform the following steps: Figure 1-2 All steps of the vehicle calibration method in Figure 1-2 The technical effect of the vehicle calibration method shown is shown in the figure. Figure 1-2 For the sake of brevity, the relevant description is not repeated here.

[0136] Figure 4 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention, Figure 4 The computer device 400 shown includes: at least one processor 401, a memory 402, at least one network interface 404 and other user interfaces 403. The various components in the computer device 400 are coupled together via a bus system 405. It is understood that the bus system 405 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 405 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 405 is not shown in FIG. Figure 4Various buses are labeled as bus system 405 .

[0137] The user interface 403 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, a touch pad, or a touch screen).

[0138] It can be understood that the memory 402 in the embodiment of the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DRRAM). The memory 402 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0139] In some implementations, the memory 402 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 4021 and application programs 4022 .

[0140] The operating system 4021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 4022 includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. The program for implementing the method of the embodiment of the present invention can be included in the application 4022.

[0141] In the embodiment of the present invention, by calling the program or instruction stored in the memory 402, specifically, the program or instruction stored in the application 4022, the processor 401 is used to execute the method steps provided by each method embodiment, for example, including:

[0142] Acquire a plurality of target signals emitted by a vehicle in a calibration room, wherein the target signals are emitted by a signal generator at a target position of the vehicle;

[0143] determining the vehicle coordinates of the vehicle in the calibration room according to the multiple target signals;

[0144] Acquire a calibration plate image taken by the vehicle in a calibration room, wherein a plurality of calibration plate combinations are arranged in the calibration room;

[0145] Determine a first calibration plate coordinate of a target calibration plate combination contained in the calibration plate image in the calibration room, and determine a second calibration plate coordinate of the target calibration plate combination in the calibration plate image;

[0146] The camera and lidar of the vehicle are calibrated according to the vehicle coordinates, the first calibration plate coordinates and the second calibration plate coordinates.

[0147] In a possible implementation, when successful pairing with the vehicle is detected, a first instruction is sent to the vehicle, so as to control the signal generator at multiple target positions of the vehicle to send the target signal through the first instruction, and the multiple target positions include: the center position of the right front wheel axle and the center position of the left rear wheel axle of the vehicle, or the center position of the left front wheel axle and the center position of the right rear wheel axle of the vehicle;

[0148] Controlling a plurality of signal receivers in the calibration room to receive the target signal emitted by each signal generator;

[0149] Receive the target signal forwarded by each signal receiver.

[0150] In a possible implementation, a first coordinate system corresponding to the calibration room is obtained, and a signal receiver coordinate of each signal receiver in the first coordinate system is obtained;

[0151] Determining the distance between each of the signal receivers and each of the signal generators according to the arrival time difference of the target signal received by each of the signal receivers;

[0152] For each of the signal generators, determining the coordinates of the signal generator in the first coordinate system according to the corresponding multiple distances and multiple coordinates of the signal receivers as the coordinates of each of the target positions;

[0153] The vehicle coordinates of the center of the vehicle in the first coordinate system are determined according to the wheelbase, the wheel width of the vehicle and the coordinates of the target position.

[0154] In a possible implementation, information recognition is performed on a main calibration plate included in the calibration plate image;

[0155] Determine that the main calibration plate and the corresponding auxiliary calibration plate whose calibration plate information is identified are the target calibration plate combination;

[0156] Acquire the first corner point coordinates of the connecting corner points of each pixel block in the main calibration plate in the first coordinate system from the calibration plate information, acquire the second corner point coordinates of the main calibration plate in the first coordinate system, and acquire the third corner point coordinates of the hole of the auxiliary calibration plate in the first coordinate system;

[0157] The first corner point coordinates, the second corner point coordinates and the third corner point coordinates are used as the first calibration plate coordinates.

[0158] In a possible implementation, all corner points included in the target calibration plate combination are obtained;

[0159] The coordinates of each corner point in the calibration plate image are used as the second calibration plate coordinates.

[0160] In a possible implementation, the camera coordinates of the camera of the vehicle in the first coordinate system are determined according to the vehicle coordinates, and the laser radar coordinates of the laser radar of the vehicle in the first coordinate system are determined;

[0161] Calibrate the intrinsic parameters and extrinsic parameters of the camera according to the first calibration plate coordinates, the second calibration plate coordinates and the camera coordinates;

[0162] Acquire a first position of the hole of the secondary calibration plate by using the laser radar;

[0163] Obtaining a second position of the hole in the image of the camera through the calibrated camera;

[0164] The parameters of the laser radar are calibrated according to the first position and the second position.

[0165] In a possible implementation, sending a data burning request to the vehicle;

[0166] When confirmation information returned by the vehicle in response to the data burning request is received, the calibrated data is sent to the vehicle for burning.

[0167] The method disclosed in the above embodiment of the present invention can be applied to the processor 401, or implemented by the processor 401. The processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 401 or the instruction in the form of software. The above processor 401 can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (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 invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor to execute, or the hardware and software units in the decoding processor can be executed. The software unit can be located in a mature storage medium in the field 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 402, and the processor 401 reads the information in the memory 402 and completes the steps of the above method in combination with its hardware.

[0168] It is understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPDevice, DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in the present application, or a combination thereof.

[0169] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0170] The computer device provided in this embodiment may be Figure 4 The computer device shown in , can execute Figure 1-2 All steps of the vehicle calibration method in Figure 1-2 The technical effect of the vehicle calibration method shown is shown in the figure. Figure 1-2 For the sake of brevity, the relevant description is not repeated here.

[0171] The embodiment of the present invention also provides a storage medium (computer-readable storage medium). The storage medium here stores one or more programs. The storage medium may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk or a solid-state drive; the memory may also include a combination of the above-mentioned types of memory.

[0172] When one or more programs in the storage medium can be executed by one or more processors, the vehicle calibration method executed on the device side can be implemented.

[0173] The processor is used to execute the vehicle calibration program stored in the memory to implement the following steps of the vehicle calibration method executed on the device side:

[0174] Acquire a plurality of target signals emitted by a vehicle in a calibration room, wherein the target signals are emitted by a signal generator at a target position of the vehicle;

[0175] determining the vehicle coordinates of the vehicle in the calibration room according to the multiple target signals;

[0176] Acquire a calibration plate image taken by the vehicle in a calibration room, wherein a plurality of calibration plate combinations are arranged in the calibration room;

[0177] Determine a first calibration plate coordinate of a target calibration plate combination contained in the calibration plate image in the calibration room, and determine a second calibration plate coordinate of the target calibration plate combination in the calibration plate image;

[0178] The camera and lidar of the vehicle are calibrated according to the vehicle coordinates, the first calibration plate coordinates and the second calibration plate coordinates.

[0179] In a possible implementation, when successful pairing with the vehicle is detected, a first instruction is sent to the vehicle, so as to control the signal generator at multiple target positions of the vehicle to send the target signal through the first instruction, and the multiple target positions include: the center position of the right front wheel axle and the center position of the left rear wheel axle of the vehicle, or the center position of the left front wheel axle and the center position of the right rear wheel axle of the vehicle;

[0180] Controlling a plurality of signal receivers in the calibration room to receive the target signal emitted by each signal generator;

[0181] Receive the target signal forwarded by each signal receiver.

[0182] In a possible implementation, a first coordinate system corresponding to the calibration room is obtained, and a signal receiver coordinate of each signal receiver in the first coordinate system is obtained;

[0183] Determining the distance between each of the signal receivers and each of the signal generators according to the arrival time difference of the target signal received by each of the signal receivers;

[0184] For each of the signal generators, determining the coordinates of the signal generator in the first coordinate system according to the corresponding multiple distances and multiple coordinates of the signal receivers as the coordinates of each of the target positions;

[0185] The vehicle coordinates of the center of the vehicle in the first coordinate system are determined according to the wheelbase, the wheel width of the vehicle and the coordinates of the target position.

[0186] In a possible implementation, information recognition is performed on a main calibration plate included in the calibration plate image;

[0187] Determine that the main calibration plate and the corresponding auxiliary calibration plate whose calibration plate information is identified are the target calibration plate combination;

[0188] Acquire the first corner point coordinates of the connecting corner points of each pixel block in the main calibration plate in the first coordinate system from the calibration plate information, acquire the second corner point coordinates of the main calibration plate in the first coordinate system, and acquire the third corner point coordinates of the hole of the auxiliary calibration plate in the first coordinate system;

[0189] The first corner point coordinates, the second corner point coordinates and the third corner point coordinates are used as the first calibration plate coordinates.

[0190] In a possible implementation, all corner points included in the target calibration plate combination are obtained;

[0191] The coordinates of each corner point in the calibration plate image are used as the second calibration plate coordinates.

[0192] In a possible implementation, the camera coordinates of the camera of the vehicle in the first coordinate system are determined according to the vehicle coordinates, and the laser radar coordinates of the laser radar of the vehicle in the first coordinate system are determined;

[0193] Calibrate the intrinsic parameters and extrinsic parameters of the camera according to the first calibration plate coordinates, the second calibration plate coordinates and the camera coordinates;

[0194] Acquire a first position of the hole of the secondary calibration plate by using the laser radar;

[0195] Obtaining a second position of the hole in the image of the camera through the calibrated camera;

[0196] The parameters of the laser radar are calibrated according to the first position and the second position.

[0197] In a possible implementation, sending a data burning request to the vehicle;

[0198] When confirmation information returned by the vehicle in response to the data burning request is received, the calibrated data is sent to the vehicle for burning.

[0199] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0200] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0201] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A vehicle calibration method, characterized in that: include: Acquire a plurality of target signals emitted by a vehicle in a calibration room, wherein the target signals are emitted by a signal generator at a target position of the vehicle; determining the vehicle coordinates of the vehicle in the calibration room according to the multiple target signals; Acquire a calibration plate image taken by the vehicle in a calibration room, wherein a plurality of calibration plate combinations are arranged in the calibration room; Determine a first calibration plate coordinate of a target calibration plate combination contained in the calibration plate image in the calibration room, and determine a second calibration plate coordinate of the target calibration plate combination in the calibration plate image; The camera and lidar of the vehicle are calibrated according to the vehicle coordinates, the first calibration plate coordinates and the second calibration plate coordinates.

2. The method according to claim 1, characterized in that The step of obtaining a plurality of target signals emitted by vehicles in the calibration room includes: When successful pairing with the vehicle is detected, a first instruction is sent to the vehicle to control the signal generator at multiple target positions of the vehicle to send the target signal through the first instruction, and the multiple target positions include: the center position of the right front wheel axle and the center position of the left rear wheel axle of the vehicle, or the center position of the left front wheel axle and the center position of the right rear wheel axle of the vehicle; Controlling a plurality of signal receivers in the calibration room to receive the target signal emitted by each signal generator; Receive the target signal forwarded by each signal receiver.

3. The method according to claim 2, characterized in that The determining the vehicle coordinates of the vehicle in the calibration room according to the multiple target signals includes: Acquire a first coordinate system corresponding to the calibration room, and acquire the signal receiver coordinates of each signal receiver in the first coordinate system; Determining the distance between each of the signal receivers and each of the signal generators according to the arrival time difference of the target signal received by each of the signal receivers; For each of the signal generators, determining the coordinates of the signal generator in the first coordinate system according to the corresponding multiple distances and multiple coordinates of the signal receivers as the coordinates of each of the target positions; The vehicle coordinates of the center of the vehicle in the first coordinate system are determined according to the wheelbase, the wheel width of the vehicle and the coordinates of the target position.

4. The method according to claim 3, characterized in that The determining of the first calibration plate coordinates of the target calibration plate combination contained in the calibration plate image in the calibration room includes: Performing information identification on the main calibration plate contained in the calibration plate image; Determine that the main calibration plate and the corresponding auxiliary calibration plate whose calibration plate information is identified are the target calibration plate combination; Acquire the first corner point coordinates of the connecting corner points of each pixel block in the main calibration plate in the first coordinate system from the calibration plate information, acquire the second corner point coordinates of the main calibration plate in the first coordinate system, and acquire the third corner point coordinates of the hole of the auxiliary calibration plate in the first coordinate system; The first corner point coordinates, the second corner point coordinates and the third corner point coordinates are used as the first calibration plate coordinates.

5. The method according to claim 4, characterized in that The determining of the second calibration plate coordinates of the target calibration plate combination in the calibration plate image includes: Acquire all corner points contained in the target calibration plate combination; The coordinates of each corner point in the calibration plate image are used as the second calibration plate coordinates.

6. The method according to claim 4, characterized in that The calibrating the camera and the laser radar of the vehicle according to the vehicle coordinates, the first calibration plate coordinates and the second calibration plate coordinates includes: Determine the camera coordinates of the camera of the vehicle in the first coordinate system according to the vehicle coordinates, and determine the laser radar coordinates of the laser radar of the vehicle in the first coordinate system; Calibrate the intrinsic parameters and extrinsic parameters of the camera according to the first calibration plate coordinates, the second calibration plate coordinates and the camera coordinates; Acquire a first position of the hole of the secondary calibration plate by using the laser radar; Obtaining a second position of the hole in the image of the camera through the calibrated camera; The parameters of the laser radar are calibrated according to the first position and the second position.

7. The method according to claim 1, characterized in that The method further comprises: Sending a data burning request to the vehicle; When confirmation information returned by the vehicle in response to the data burning request is received, the calibrated data is sent to the vehicle for burning.

8. A vehicle calibration device, characterized in that: include: An acquisition module, used for acquiring a plurality of target signals emitted by a vehicle in a calibration room, wherein the target signals are emitted by a signal generator at a target position of the vehicle; A determination module, configured to determine the vehicle coordinates of the vehicle in the calibration room according to the plurality of target signals; The acquisition module is further used to acquire a calibration plate image taken by the vehicle in a calibration room, wherein a plurality of calibration plate combinations are arranged in the calibration room; The determination module is further used to determine the first calibration plate coordinates of the target calibration plate combination contained in the calibration plate image in the calibration room, and to determine the second calibration plate coordinates of the target calibration plate combination in the calibration plate image; A calibration module is used to calibrate the camera and lidar of the vehicle according to the vehicle coordinates, the first calibration plate coordinates and the second calibration plate coordinates.

9. A computer device, characterized in that: include: A processor and a memory, wherein the processor is used to execute a vehicle calibration program stored in the memory to implement the vehicle calibration method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the vehicle calibration method according to any one of claims 1 to 7.

Images