Cooperative calibration device control method, cooperative calibration method and equipment, and engineering vehicle

Abstract

The invention provides a cooperative calibration device control method, a cooperative calibration method and device, and an engineering vehicle. The cooperative calibration device control method comprises the steps that the brightness of an LED array arranged in each two-dimensional code in four two-dimensional codes is adjusted through the environment illumination intensity collected by a photosensitive sensor in real time, and the four two-dimensional codes are arranged in the adjacent areas of the four corners of a rectangular calibration plate in a cooperative calibration device respectively; and adjusting at least one of the height and the pitch angle of an adjustable support bracket of the calibration plate so that the calibration plate can appear in the view of an image acquisition device, a laser radar and a millimeter wave radar on the unmanned engineering vehicle.

Description

Technical Field

[0001] This disclosure relates to the field of parameter calibration technology, and in particular to a control method for a collaborative calibration device, a collaborative calibration method and equipment, and an engineering vehicle. Background Technology

[0002] With the development of intelligent mining, unmanned engineering vehicles rely on multi-sensor (such as cameras, LiDAR, and millimeter-wave radar) fusion technology to achieve environmental perception. In this context, the accuracy of sensor extrinsic parameter calibration directly affects the safety and reliability of unmanned engineering vehicle operation, and its efficiency and robustness also directly impact the operational efficiency of the unmanned engineering vehicle. Currently, cameras and LiDAR are commonly used for extrinsic parameter calibration. Summary of the Invention

[0003] The inventors noted that in related technologies, cameras and lidar are usually used to calibrate the external parameters of cameras and lidar, but this cannot achieve integrated calibration for multi-modal devices (cameras, lidar, millimeter-wave radar).

[0004] Accordingly, this disclosure provides a collaborative calibration device control method and a collaborative calibration method, which can effectively realize the integrated calibration of cameras, lidar and millimeter-wave radar, and ensure the operational safety of unmanned engineering vehicles.

[0005] In a first aspect of this disclosure, a control method for a collaborative calibration device is provided, executed by a control device in the collaborative calibration device, comprising: adjusting the brightness of an LED array disposed within each of four QR codes by using ambient light intensity collected in real time by a photosensitive sensor, wherein the four QR codes are respectively disposed in the adjacent areas of the four corners of a rectangular calibration plate in the collaborative calibration device; and adjusting at least one of the height and pitch angle of an adjustable support bracket of the calibration plate so that the calibration plate can appear within the field of view of an image acquisition device, a lidar, and a millimeter-wave radar on an unmanned engineering vehicle.

[0006] In some embodiments, adjusting at least one of the height and pitch angle of the adjustable support bracket of the calibration plate includes: adjusting at least one of the height and pitch angle of the adjustable support bracket of the calibration plate according to the instruction information sent by the unmanned engineering vehicle, wherein the instruction information includes the type of the unmanned engineering vehicle and the distance information between the unmanned engineering vehicle and the collaborative calibration device.

[0007] In some embodiments, the brightness of the LED array inside each QR code is positively correlated with the ambient light intensity.

[0008] In a second aspect of this disclosure, a control device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute instructions stored in the memory to implement the cooperative calibration device control method as described in any of the above embodiments.

[0009] In a third aspect of this disclosure, a collaborative calibration device is provided, comprising: a control device as described in any of the above embodiments; a calibration plate, wherein the calibration plate is rectangular, the surface of the calibration plate is covered with a diffuse reflection coating, a QR code is provided in the adjacent area of ​​each corner of the calibration plate, the QR code is provided with an array of light-emitting diodes (LEDs), wherein the brightness of the LED array is adjusted according to the control of the control device; a plurality of photosensors for detecting ambient light intensity, wherein the plurality of photosensors are uniformly disposed on the calibration plate; a corner reflector disposed at the geometric center point on the back side of the calibration plate; and an adjustable support bracket for mounting the calibration plate, capable of adjusting at least one of the height and pitch angle of the calibration plate.

[0010] In some embodiments, the adjustable support bracket is configured to adjust at least one of the height and pitch angle of the calibration plate according to the control of the control device.

[0011] In a fourth aspect of this disclosure, a collaborative calibration method is provided, executed by a parameter configuration device in an unmanned engineering vehicle, comprising: reading initial values ​​of extrinsic parameters of an image acquisition device, a lidar, and a millimeter-wave radar; controlling the image acquisition device, the lidar, and the millimeter-wave radar to acquire time-synchronized first image data, a first lidar point cloud, and first millimeter-wave radar data; preprocessing the first image data, the first lidar point cloud, and the first millimeter-wave radar data respectively to obtain second image data, a second lidar point cloud, and second millimeter-wave radar data; extracting a first feature, a second feature, and a third feature of a collaborative calibration device from the second image data, the second lidar point cloud, and the second millimeter-wave radar data, wherein the collaborative calibration device is a collaborative calibration device as described in any of the above embodiments; and jointly optimizing the initial values ​​of extrinsic parameters of the image acquisition device, the lidar, and the millimeter-wave radar according to the first feature, the second feature, and the third feature of the collaborative calibration device to obtain extrinsic parameter calibration results of the image acquisition device, the lidar, and the millimeter-wave radar respectively.

[0012] In some embodiments, extracting the first feature from the second image data includes: establishing a world coordinate system with the geometric center point of the calibration plate in the collaborative calibration device as the origin; processing the second image data to identify four QR codes on the calibration plate; using the perspective n-point PnP algorithm to solve for the rotation matrix and translation vector of the image coordinate system relative to the world coordinate system based on the four QR codes; projecting the four corner points of the calibration plate from the world coordinate system to the image coordinate system based on the predetermined size information of the calibration plate, the rotation matrix, and the translation vector; extracting the two-dimensional coordinates of the four corner points in the image coordinate system; sorting the two-dimensional coordinates of the four corner points in a specified order, and using the obtained first sorting result as the first feature.

[0013] In some embodiments, extracting the second feature from the second lidar point cloud includes: rotating the second lidar point cloud to a specified plane; fitting a minimum bounding box of the second lidar point cloud in the specified plane, and extracting four vertices from the minimum bounding box as four candidate corner points; converting the four candidate corner points to three-dimensional space to obtain the three-dimensional coordinates of the four corner points of the calibration board in the lidar coordinate system; sorting the three-dimensional coordinates of the four corner points in a specified order, and using the obtained second sorting result as the second feature.

[0014] In some embodiments, extracting the third feature from the second millimeter-wave radar data includes: performing Euclidean clustering and target tracking on the second millimeter-wave radar data to obtain a first set of tracked targets; selecting target points that meet predetermined conditions from the first set of tracked targets to generate a second set of tracked targets, wherein the deviation between the radar cross-section value of the target points that meet the predetermined conditions and the predetermined radar cross-section value of the corner reflector located at the geometric center point on the back of the calibration plate is less than a predetermined cross-section threshold; determining the three-dimensional coordinates of the geometric center point of the calibration plate in the lidar coordinate system based on the three-dimensional coordinates of the four corner points of the calibration plate in the lidar coordinate system; converting the three-dimensional coordinates of the geometric center point of the calibration plate in the lidar coordinate system to the millimeter-wave radar coordinate system; selecting the corresponding target point of the corner reflector from the second set of tracked targets, wherein the deviation between the three-dimensional coordinates of the corresponding target point and the three-dimensional coordinates of the geometric center point of the calibration plate in the millimeter-wave radar coordinate system is less than a predetermined distance threshold; and using the three-dimensional coordinates of the corresponding target point in the millimeter-wave radar coordinate system as the third feature.

[0015] In some embodiments, joint optimization of the initial extrinsic parameters of the image acquisition device, the lidar, and the millimeter-wave radar includes: based on the deviation between the first sorting result and the second sorting result, and the deviation between the three-dimensional coordinates of the corresponding target point in the millimeter-wave radar coordinate system and the three-dimensional coordinates of the geometric center point of the corner reflector in the millimeter-wave radar coordinate system stored in advance, using a nonlinear least squares algorithm to jointly optimize the initial extrinsic parameters of the image acquisition device, the lidar, and the millimeter-wave radar.

[0016] In some embodiments, preprocessing the first image data includes: when the ambient light intensity is greater than a specified light intensity threshold, preprocessing the first image data using a histogram equalization algorithm to obtain the second image data; and when the ambient light intensity is not greater than a specified light intensity threshold, preprocessing the first image data using at least one of an adaptive brightness compensation algorithm and a multi-scale contrast enhancement algorithm to obtain the second image data.

[0017] In some embodiments, preprocessing the first lidar point cloud includes: determining a region of interest based on the estimated position of the calibration board; extracting point clouds located within the region of interest from the first lidar point cloud as a first point cloud to be processed; performing point cloud downsampling on the first point cloud to be processed based on the line density of the lidar to obtain a second point cloud to be processed; extracting the plane where the calibration board is located using a plane segmentation algorithm based on the predetermined normal direction information of the calibration board; and deleting outlier point clouds from the second point cloud to be processed based on the plane to obtain the second lidar point cloud.

[0018] In some embodiments, preprocessing the first millimeter-wave radar data includes: determining a region of interest based on the estimated position of the calibration board; and extracting point clouds located in the region of interest from the first millimeter-wave radar data as the second millimeter-wave radar data.

[0019] In some embodiments, the extrinsic parameter calibration results are visualized to determine the reprojection error; if the reprojection error is greater than a predetermined error threshold, the acquisition of first image data, first lidar point cloud and first millimeter-wave radar data synchronized by the control of the image acquisition device, the lidar and the millimeter-wave radar is repeated.

[0020] In some embodiments, the distance between the unmanned engineering vehicle and the collaborative calibration device is determined based on the second lidar point cloud; instruction information is sent to the collaborative calibration device, wherein the instruction information includes the type of the unmanned engineering vehicle and distance information of the distance.

[0021] In some embodiments, the image acquisition device is configured with parameters using its intrinsic and extrinsic parameters; the lidar is configured with parameters using its extrinsic parameters; and the millimeter-wave radar is configured with parameters using its extrinsic parameters.

[0022] In a fifth aspect of this disclosure, a parameter configuration device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute instructions stored in the memory to implement the cooperative calibration method as described in any of the above embodiments.

[0023] In a sixth aspect of this disclosure, an unmanned engineering vehicle is provided, comprising: a parameter configuration device as described in any of the above embodiments; an image acquisition device configured to acquire image data; a lidar configured to acquire lidar point clouds; and a millimeter-wave radar configured to acquire millimeter-wave radar data.

[0024] In a seventh aspect of this disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method as described in any of the above embodiments.

[0025] In an eighth aspect of this disclosure, a computer program product is provided, including computer instructions, wherein the computer instructions, when executed by a processor, implement the method as described in any of the above embodiments.

[0026] Other features and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of the structure of a collaborative calibration device according to an embodiment of the present disclosure;

[0029] Figure 2 This is a schematic flowchart of a collaborative calibration device control method according to an embodiment of the present disclosure;

[0030] Figure 3 This is a schematic diagram of the structure of a control device according to an embodiment of the present disclosure;

[0031] Figure 4This is a flowchart illustrating a collaborative calibration method according to an embodiment of the present disclosure;

[0032] Figure 5 This is a flowchart illustrating a collaborative calibration method according to another embodiment of the present disclosure;

[0033] Figure 6 This is a schematic diagram of the structure of a parameter configuration device according to an embodiment of the present disclosure;

[0034] Figure 7 This is a schematic diagram of the structure of an unmanned engineering vehicle according to an embodiment of the present disclosure;

[0035] Figure 8 This is a schematic diagram of a collaborative calibration scenario according to an embodiment of the present disclosure. Detailed Implementation

[0036] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0037] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0038] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0039] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0040] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0041] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0042] Figure 1 This is a schematic diagram of the structure of a collaborative calibration device according to an embodiment of the present disclosure.

[0043] like Figure 1 As shown, the collaborative calibration device includes a calibration plate 1, an adjustable support bracket 2, and a control device 3.

[0044] The calibration plate 1 is rectangular, and its surface is covered with a diffuse reflection coating. A QR code 11 is provided in the adjacent area of ​​each corner of the calibration plate 1. An LED (Light Emitting Diode) array is provided in the QR code 11, and the brightness of the LED array is adjusted according to the control of the control device 3.

[0045] It should be noted that a diffuse reflection coating is applied to the surface of calibration board 1 to effectively suppress specular reflection and local bright interference under strong light, significantly improve the stability of visual features under extreme lighting conditions such as direct sunlight and backlight, and avoid the problem of QR code recognition failure caused by reflection of calibration board 1.

[0046] In some embodiments, the lateral and longitudinal distances between each QR code are equal, thus forming a feature layout with high geometric symmetry. This layout not only facilitates robust recognition by the image acquisition device under non-ideal observation conditions such as wide viewing angles, long distances, or partial occlusion, but also improves the accuracy and reliability of pose calculation through multi-point constraints.

[0047] Multiple photosensors 12 are evenly arranged on the calibration plate 1 to detect ambient light intensity, so that the control device 3 can control the brightness of the LED array in each QR code 11 according to the ambient light intensity. This ensures that the QR code can still actively emit light in nighttime, low-light, or completely dark environments, maintaining high contrast and clear visibility, thereby ensuring the continuity and stability of all-weather visual calibration.

[0048] A corner reflector 13 is installed at the geometric center point on the back of the calibration plate 1. Since the corner reflector 13 has strong and stable echo characteristics in the millimeter-wave radar band, it can serve as a precise positioning feature point for the millimeter-wave radar. The three-dimensional position of the geometric center point of the corner reflector 13 in the calibration plate coordinate system is precisely measured and pre-stored in the system. Together with four QR codes, it forms a unified, high-precision multimodal reference benchmark, enabling joint calibration of the image acquisition device, lidar, and millimeter-wave radar.

[0049] The adjustable support bracket 2 is used to mount the calibration plate 1 and can adjust at least one of the height and pitch angle of the calibration plate 1.

[0050] In some embodiments, the adjustable support bracket 2 is configured to adjust at least one of the height and pitch angle of the calibration plate 1 according to the control of the control device 3, so that the calibration plate 1 can appear in the field of view of the image acquisition device, lidar and millimeter-wave radar on the unmanned engineering vehicle, thereby effectively improving the field adaptability and engineering practicality of the collaborative calibration device.

[0051] Figure 2 This is a schematic flowchart illustrating a collaborative calibration device control method according to an embodiment of the present disclosure. In some embodiments, the following collaborative calibration device control method is executed by a control device in the collaborative calibration device, including steps 21-22.

[0052] In step 21, the brightness of the LED array inside each of the four QR codes is adjusted by using the ambient light intensity collected in real time by the photosensitive sensor. The four QR codes are respectively set in the adjacent areas of the four corners of the rectangular calibration plate in the collaborative calibration device.

[0053] In some embodiments, the brightness of the LED array inside each QR code is positively correlated with the ambient light intensity.

[0054] For example, if the ambient light intensity collected in real time by the photosensor is The brightness of the LED array As shown in formula (1).

[0055] (1)

[0056] In formula (1), the parameter The preset adjustment coefficient, parameter The preset bias value ensures that the QR code pattern has high contrast and clear visibility under different lighting conditions.

[0057] In step 22, at least one of the height and pitch angle of the adjustable support bracket of the calibration plate is adjusted so that the calibration plate can appear in the field of view of the image acquisition device, lidar and millimeter-wave radar on the unmanned engineering vehicle.

[0058] In some embodiments, at least one of the height and pitch angle of the adjustable support bracket of the calibration plate is adjusted according to the instruction information sent by the unmanned engineering vehicle, wherein the instruction information includes the type of the unmanned engineering vehicle and the distance information between the unmanned engineering vehicle and the collaborative calibration device. This effectively improves the field adaptability and engineering practicality of the collaborative calibration device.

[0059] For example, depending on the type of unmanned engineering vehicle And the distance between unmanned engineering vehicles and collaborative calibration devices. Adjustable support height and pitch angle As shown in formulas (2) and (3) respectively.

[0060] (2)

[0061] (3)

[0062] In formula (2), For the pre-calibrated height adjustment function, This is a pre-calibrated angle adjustment function. By using formulas (2) and (3), the optimal viewing angle and range of the image acquisition device, lidar, and millimeter-wave radar can be ensured.

[0063] In the collaborative calibration device control method provided in the above embodiments of this disclosure, the working state of the calibration board is automatically adjusted according to the external environment and the distance between the unmanned engineering vehicle and the collaborative calibration device, thereby effectively realizing the integrated calibration of the camera, lidar and millimeter-wave radar, and ensuring the operational safety of the unmanned engineering vehicle.

[0064] Figure 3 This is a schematic diagram of the structure of a control device according to an embodiment of the present disclosure.

[0065] like Figure 3 As shown, the control device 30 can be represented in the form of a general computing device. The control device 30 includes a memory 31, a processor 32, and a bus 33 connecting different system components.

[0066] The memory 31 may include, for example, system memory, non-volatile storage media, etc. System memory may store, for example, an operating system, application programs, a boot loader, and other programs. System memory may include volatile storage media, such as random access memory (RAM) and / or cache memory. Non-volatile storage media may store, for example, instructions for a corresponding embodiment of at least one co-calibration device control method being executed. Non-volatile storage media include, but are not limited to, disk storage, optical storage, flash memory, etc.

[0067] Processor 32 can be implemented using a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA) or other programmable logic devices, discrete hardware components such as discrete gates or transistors. Accordingly, each module, such as the acquisition module, calculation module, and adjustment module, can be implemented by executing instructions in the central processing unit (CPU) running memory to perform the corresponding steps, or by implementing dedicated circuitry to perform the corresponding steps.

[0068] For example, processor 32 is configured to execute instructions stored in memory 31, such as Figure 2 The method involved in any of the embodiments.

[0069] Bus 33 can use any of the various bus architectures. For example, bus architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MCA) bus, and the Peripheral Component Interconnect (PCI) bus.

[0070] The interfaces 34, 35, and 36 of the control device 30, as well as the memory 31 and processor 32, can be connected via bus 33. Input / output interface 34 provides a connection interface for input / output devices such as monitors, mice, and keyboards. Network interface 35 provides a connection interface for various networked devices. Storage interface 36 provides a connection interface for external storage devices such as floppy disks, USB flash drives, and SD cards.

[0071] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations thereof, can be implemented by computer-readable program instructions.

[0072] These computer-readable program instructions are provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable device to produce a machine, such that execution of the instructions by the processor produces means for implementing the functions specified in one or more boxes of the flowchart and / or block diagram.

[0073] These computer-readable program instructions may also be stored in a computer-readable storage medium. These instructions cause a computer to work in a particular manner to produce an article of manufacture, including instructions that implement the functions specified in one or more boxes in a flowchart and / or block diagram.

[0074] This disclosure may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.

[0075] This disclosure also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement... Figure 2 The method involved in any of the embodiments.

[0076] This disclosure also provides a computer program product, including computer instructions, wherein the computer instructions, when executed by a processor, implement as follows: Figure 2 The method involved in any of the embodiments.

[0077] Figure 4 This is a flowchart illustrating a collaborative calibration method according to an embodiment of the present disclosure. In some embodiments, the following collaborative calibration method is performed by a parameter configuration device in an unmanned engineering vehicle, including steps 41-45.

[0078] In step 41, the initial values ​​of the external parameters of the image acquisition device, lidar, and millimeter-wave radar are read.

[0079] It should be noted that in order to configure the image acquisition device, it is also necessary to read the intrinsic parameter matrix of the image acquisition device. Including focal length , and principal point coordinates As shown in formula (4).

[0080] (4)

[0081] In step 42, the image acquisition device, lidar, and millimeter-wave radar are controlled to acquire time-synchronized first image data, first lidar point cloud, and first millimeter-wave radar data.

[0082] In step 43, the first image data, the first lidar point cloud, and the first millimeter-wave radar data are preprocessed to obtain the second image data, the second lidar point cloud, and the second millimeter-wave radar data.

[0083] In some embodiments, the step of preprocessing the first image data includes steps S11-S12.

[0084] S11. When the ambient light intensity is greater than the specified light intensity threshold, the first image data is preprocessed using a histogram equalization algorithm to obtain the second image data.

[0085] For example, images in bright light environments The contrast is enhanced by applying a histogram equalization algorithm, as shown in formula (5).

[0086] (5)

[0087] It's important to note that in strong light conditions, images are prone to overexposure and decreased contrast, leading to blurred or lost QR code details and affecting recognition stability. To address this, a histogram equalization algorithm is introduced during image preprocessing to enhance the images acquired by the image acquisition device. This algorithm, combined with the self-illuminating QR code and diffuse reflection coating, forms a dual guarantee of "hardware anti-interference + software enhancement," significantly improving the recognition success rate under strong light conditions.

[0088] S12. When the ambient light intensity is not greater than a specified light intensity threshold, the first image data is preprocessed using at least one of an adaptive brightness compensation algorithm and a multi-scale contrast enhancement algorithm to obtain the second image data.

[0089] For example, for low-light images Enhancement is achieved by combining adaptive brightness compensation with the Retinex algorithm, whereby... These are the parameters of the Retinex algorithm, as shown in formula (6).

[0090] (6)

[0091] It's important to note that in low-light scenes, images suffer from insufficient brightness, low signal-to-noise ratio, and blurred features. By combining adaptive brightness compensation with the Retinex (multi-scale contrast enhancement) algorithm, low-light images are enhanced to ensure that QR codes maintain high contrast and clear outlines even in extremely dark environments.

[0092] In some embodiments, the step of preprocessing the first lidar point cloud includes steps S21-S25.

[0093] S21. Determine the Region of Interest (ROI) based on the estimated position of the calibration board.

[0094] It should be noted that by identifying the region of interest, interference from irrelevant point clouds can be effectively reduced, thus improving processing speed.

[0095] S22. Extract the point cloud located in the region of interest from the first lidar point cloud, and use it as the first point cloud to be processed.

[0096] S23. Based on the beam density of the lidar, perform point cloud downsampling on the first point cloud to be processed to obtain the second point cloud to be processed.

[0097] Point cloud downsampling can further improve processing speed.

[0098] S24. Based on the predetermined normal direction information of the calibration board, the plane where the calibration board is located is extracted using a plane segmentation algorithm.

[0099] S25. Based on the plane, delete the outlier point clouds in the second point cloud to be processed to obtain the second lidar point cloud.

[0100] In some embodiments, statistical filtering methods are used to remove outlier point clouds, providing a good foundation for subsequent accurate extraction of corner information.

[0101] In some embodiments, the distance between the unmanned engineering vehicle and the collaborative calibration device is determined based on the second lidar point cloud, and instruction information is sent to the collaborative calibration device. The instruction information includes the type of the unmanned engineering vehicle and distance information, so as to control the collaborative calibration device to adjust the height and tilt angle of the calibration plate, thereby ensuring the optimal observation angle and range of the image acquisition device, lidar and millimeter-wave radar.

[0102] In some embodiments, the step of preprocessing the first millimeter-wave radar data includes steps S31-S32.

[0103] S31. Determine the region of interest based on the estimated position of the calibration plate.

[0104] It should be noted that by identifying the region of interest, interference from irrelevant point clouds can be effectively reduced, thus improving processing speed.

[0105] S32. Extract the point cloud located in the region of interest from the first millimeter-wave radar data and use it as the second millimeter-wave radar data.

[0106] In step 44, the first feature, second feature, and third feature of the collaborative calibration device are extracted from the second image data, the second lidar point cloud, and the second millimeter-wave radar data, respectively. The collaborative calibration device is as follows: Figure 1 The collaborative calibration device shown in any of the embodiments.

[0107] In some embodiments, the step of extracting the first feature from the second image data includes steps S41-S46.

[0108] S41. Establish a world coordinate system with the geometric center point of the calibration plate in the collaborative calibration device as the origin.

[0109] For example, the x-axis is defined to the right, the y-axis to the up, and the z-axis is perpendicular to the surface of the calibration plate and points outward.

[0110] S42. Process the second image data to identify the four QR codes on the calibration board.

[0111] S43. Based on the four QR codes, use the PnP (Perspective-n-Point) algorithm to solve for the rotation matrix and translation vector of the image coordinate system relative to the world coordinate system.

[0112] It should be noted that the PnP algorithm is the core method for solving camera pose in computer vision. Its core idea is to estimate the position R and pose t of the camera relative to the world coordinate system by using known 3D spatial points and their 2D projection points in the image, as shown in formula (7).

[0113] (7)

[0114] In formula (7), The coordinates of the QR code in the world coordinate system. The coordinates of the QR code in the image coordinate system. These are preset parameters.

[0115] S44. Based on the predetermined size information, rotation matrix, and translation vector of the calibration plate, project the four corner points of the calibration plate from the world coordinate system to the image coordinate system.

[0116] S45. Extract the two-dimensional coordinates of the four corner points in the image coordinate system.

[0117] S46. Sort the two-dimensional coordinates of the four corner points in the specified order, and take the first sorting result as the first feature.

[0118] For example, starting from the top left corner, arrange the two-dimensional coordinates of the first corner point, the second corner point, the third corner point and the fourth corner point in a clockwise direction, as shown in formula (8).

[0119] (8)

[0120] In some embodiments, the step of extracting the second feature from the second lidar point cloud includes S51-S54.

[0121] S51. Rotate the second lidar point cloud to the designated plane.

[0122] For example, the point cloud of the second lidar is rotated to the z=0 plane by combining the normal information of the calibration board, as shown in formula (9).

[0123] (9)

[0124] In formula (9), The lidar point cloud before rotation, The point cloud of the LiDAR after rotation. These are rotation parameters.

[0125] S52. Fit the minimum bounding box of the second lidar point cloud in the specified plane, and extract the four vertices in the minimum bounding box as four candidate corner points.

[0126] For example, in the xy plane, based on the known prior size information of the calibration board, the minimum bounding box of the point cloud data is fitted, and the four vertices of the bounding box are extracted as candidate corner points.

[0127] For example, the minimum bounding box is fitted as shown in Equation (10), and the four vertices in the minimum bounding box are extracted using Equation (11).

[0128] (10)

[0129] (11)

[0130] S53. Transform the four candidate corner points into three-dimensional space to obtain the three-dimensional coordinates of the four corner points of the calibration board in the lidar coordinate system.

[0131] S54. Sort the three-dimensional coordinates of the four corner points in the specified order, and use the second sorting result as the second feature.

[0132] For example, starting from the top left corner, arrange the two-dimensional coordinates of the first corner point, the second corner point, the third corner point and the fourth corner point in a clockwise direction, as shown in formula (12).

[0133] (12)

[0134] In some embodiments, the step of extracting the third feature from the second millimeter-wave radar data includes steps S61-S66.

[0135] S61. Perform Euclidean clustering and target tracking on the second millimeter-wave radar data to obtain the first set of tracked targets.

[0136] S62. Select target points that meet predetermined conditions from the first set of tracking targets to generate a second set of tracking targets, wherein the deviation between the radar cross section (RCS) value of the target points that meet the predetermined conditions and the predetermined RCS value of the corner reflector located at the geometric center point on the back of the calibration plate is less than the predetermined RCS threshold.

[0137] For example, the typical radar cross-section of a corner reflector located at the geometric center point on the back of the calibration plate is [value missing]. And the predetermined scattering cross-sectional area threshold is If the radar cross-section of the i-th target point is If the conditions shown in formula (13) are met, the target point is retained.

[0138] (13)

[0139] S63. Based on the three-dimensional coordinates of the four corner points of the calibration plate in the lidar coordinate system, determine the three-dimensional coordinates of the geometric center point of the calibration plate in the lidar coordinate system.

[0140] S64. Transform the three-dimensional coordinates of the geometric center point of the calibration plate in the lidar coordinate system to the millimeter-wave radar coordinate system.

[0141] S65. Select the target point corresponding to the corner reflector in the second set of tracking targets, wherein the deviation between the three-dimensional coordinates of the corresponding target point and the three-dimensional coordinates of the geometric center point of the calibration plate in the millimeter-wave radar coordinate system is less than a predetermined distance threshold.

[0142] S66. The three-dimensional coordinates of the corresponding target point in the millimeter-wave radar coordinate system are used as the third feature.

[0143] In step 45, based on the first, second, and third features of the collaborative calibration device, the initial values ​​of the extrinsic parameters of the image acquisition device, the lidar, and the millimeter-wave radar are jointly optimized to obtain the extrinsic parameter calibration results of the image acquisition device, the lidar, and the millimeter-wave radar, respectively.

[0144] In some embodiments, based on the deviation between the first sorting result and the second sorting result, and the deviation between the three-dimensional coordinates of the corresponding target point in the millimeter-wave radar coordinate system and the three-dimensional coordinates of the pre-stored geometric center point of the corner reflector in the millimeter-wave radar coordinate system, the initial values ​​of the extrinsic parameters of the image acquisition device, the lidar, and the millimeter-wave radar are jointly optimized using a nonlinear least squares algorithm.

[0145] For example, the Levenberg-Marquardt algorithm can be used for extrinsic parameter optimization.

[0146] It's important to note that the Levenberg-Marquardt algorithm is a parameter estimation method for solving nonlinear least squares problems. It optimizes parameters by combining the steepest descent method and the Gauss-Newton method. This method uses the steepest descent method in the early stages of iteration when the value is far from the optimum, and switches to the Gauss-Newton method as the value approaches the optimum in the later stages.

[0147] In some embodiments, after obtaining the extrinsic parameter calibration results, the extrinsic parameter calibration results are further visualized to determine the reprojection error. If the reprojection error is greater than a predetermined error threshold, the acquisition of time-synchronized first image data, first lidar point cloud, and first millimeter-wave radar data by the control image acquisition device, lidar, and millimeter-wave radar is repeated until the reprojection error is no greater than the predetermined error threshold.

[0148] In some embodiments, after obtaining ideal extrinsic parameter calibration results, the image acquisition device is configured with parameters using both its intrinsic and extrinsic parameters. The lidar is configured with parameters using its extrinsic parameter calibration results. The millimeter-wave radar is configured with parameters using its extrinsic parameter calibration results. This ensures that the image acquisition device, lidar, and millimeter-wave radar can function properly.

[0149] Figure 5 This is a flowchart illustrating a collaborative calibration method according to another embodiment of the present disclosure. In some embodiments, the following collaborative calibration method is performed by a parameter configuration device in an unmanned engineering vehicle, including steps 51-512.

[0150] In step 51, relevant parameters are read, including the intrinsic parameters of the image acquisition device and the initial values ​​of the extrinsic parameters of the image acquisition device, lidar, and millimeter-wave radar.

[0151] In step 52, time-synchronized multimodal data is acquired, namely, the image acquisition device, lidar and millimeter-wave radar acquire time-synchronized first image data, first lidar point cloud and first millimeter-wave radar data.

[0152] In step 53, the first image data is preprocessed to obtain the second image data.

[0153] In some embodiments, the step of preprocessing the first image data includes steps S11-S12.

[0154] In step 54, the first feature is extracted from the second image data.

[0155] For example, the two-dimensional coordinates of the four corner points of the calibration board in the image coordinate system are extracted from the second image data, and the two-dimensional coordinates of the four corner points are sorted in a specified order to obtain the first sorting result, which is used as the first feature.

[0156] For example, the first sorting result is obtained by following steps S41-S46.

[0157] In step 55, the first lidar point cloud is preprocessed to obtain the second lidar point cloud.

[0158] In some embodiments, the step of preprocessing the first lidar point cloud includes steps S21-S25.

[0159] In step 56, the second feature is extracted from the second lidar point cloud.

[0160] For example, the three-dimensional coordinates of the four corner points of the calibration board in the lidar coordinate system are obtained from the second lidar point cloud, and the three-dimensional coordinates of the four corner points are sorted in a specified order to obtain a second sorting result, which is used as the second feature.

[0161] For example, the second sorting result is obtained by following steps S51-S54.

[0162] In step 57, the first millimeter-wave radar data is preprocessed to obtain the second millimeter-wave radar data.

[0163] In some embodiments, the step of preprocessing the first millimeter-wave radar data includes steps S31-S32.

[0164] In step 58, the third feature is extracted from the second millimeter-wave radar data.

[0165] For example, the corresponding target point of the corner reflector is extracted from the second millimeter-wave radar data, and the three-dimensional coordinates of the corresponding target point in the millimeter-wave radar coordinate system are determined as the third feature.

[0166] For example, the three-dimensional coordinates of the corresponding target point in the millimeter-wave radar coordinate system are obtained by following steps S61-S66.

[0167] In step 59, extrinsic parameter optimization is performed.

[0168] For example, based on the deviation between the first and second sorting results, and the deviation between the three-dimensional coordinates of the corresponding target point in the millimeter-wave radar coordinate system and the three-dimensional coordinates of the pre-stored geometric center point of the corner reflector in the millimeter-wave radar coordinate system, the initial values ​​of the extrinsic parameters of the image acquisition device, lidar, and millimeter-wave radar are jointly optimized using a nonlinear least squares algorithm.

[0169] In step 510, the extrinsic parameter calibration results are visualized to determine the reprojection error.

[0170] In step 511, it is determined whether the reprojection error is greater than a predetermined error threshold.

[0171] If the reprojection error is greater than the predetermined error threshold, then repeat step 52. Otherwise, proceed to step 512.

[0172] In step 512, parameter configuration is performed. After obtaining ideal extrinsic parameter calibration results, the image acquisition device's parameters are configured using both its intrinsic and extrinsic parameter calibration results. The lidar's parameters are configured using its extrinsic parameter calibration results. Finally, the millimeter-wave radar's parameters are configured using its extrinsic parameter calibration results. This ensures the image acquisition device, lidar, and millimeter-wave radar can function properly.

[0173] Figure 6 This is a schematic diagram of the structure of a parameter configuration device according to an embodiment of this disclosure. Figure 6 As shown, the parameter configuration device 60 includes a memory 61, a processor 62, a bus 63, an input / output interface 64, a network interface 65, and a storage interface 66.

[0174] Figure 6 and Figure 3 The difference is that, in Figure 6 In the illustrated embodiment, processor 62 is configured to execute instructions stored in memory 61 as follows: Figure 4 or Figure 5 The method involved in any of the embodiments.

[0175] This disclosure also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement... Figure 4 or Figure 5 The method involved in any of the embodiments.

[0176] This disclosure also provides a computer program product, including computer instructions, wherein the computer instructions, when executed by a processor, implement as follows: Figure 4 or Figure 5 The method involved in any of the embodiments.

[0177] Figure 7 This is a schematic diagram of the structure of an unmanned engineering vehicle according to an embodiment of the present disclosure.

[0178] like Figure 7 As shown, the unmanned engineering vehicle 70 includes a parameter configuration device 71, an image acquisition device 72, a lidar 73, and a millimeter-wave radar 74. The parameter configuration device 71 is... Figure 6 The parameter configuration device involved in any of the embodiments.

[0179] Image acquisition device 72 is configured to acquire image data, lidar 73 is configured to acquire lidar point clouds, and millimeter-wave radar 74 is configured to acquire millimeter-wave radar data. Parameter configuration device 71 obtains parameter calibration results based on the image data, lidar point clouds, and millimeter-wave radar data acquired by image acquisition device 72, lidar 73, and millimeter-wave radar 74 respectively, and configures the parameters of image acquisition device 72, lidar 73, and millimeter-wave radar 74 accordingly.

[0180] Figure 8 This is a schematic diagram of a collaborative calibration scenario according to an embodiment of the present disclosure.

[0181] like Figure 8 As shown, three cooperative calibration devices 81, 82, and 83 are installed on the roadside in front of the unmanned engineering vehicle 80. The unmanned engineering vehicle 80 is... Figure 7 In any of the embodiments involving unmanned engineering vehicles, the collaborative calibration devices 81, 82, and 83 are Figure 1 The cooperative calibration device involved in any of the embodiments.

[0182] It should be noted that, for the sake of simplicity, three collaborative calibration devices are set up on the roadside, but other numbers of collaborative calibration devices can be set up as needed.

[0183] As the unmanned engineering vehicle 80 moves along the direction of the arrow, a set of data is collected at predetermined intervals (e.g., 2 meters) to gather 3-5 sets of data. The collected data is then used for collaborative calibration to obtain parameter calibration results.

[0184] By implementing the above embodiments of this disclosure, the following beneficial effects can be obtained.

[0185] (1) The multimodal calibration board proposed in this disclosure constructs an active light emission control mechanism of "hardware anti-interference + software self-adaptation" by covering the surface of the calibration board with a high-performance diffuse reflection coating and combining the programmable LED array integrated inside the QR code with the photosensitive chips distributed around it. This significantly improves the success rate of QR code recognition under complex lighting conditions such as direct sunlight and night, and ensures the continuity and robustness of visual calibration under all-weather conditions.

[0186] (2) The multimodal calibration board proposed in this disclosure integrates four QR codes with a highly symmetrical layout and a corner reflector at the center of the back, forming a unified and high-precision spatial reference benchmark. It realizes the integrated calibration of three types of heterogeneous sensors with high robustness and high precision.

[0187] (3) The adjustable support bracket with height lifting and pitch angle adjustment functions proposed in this disclosure can ensure that the calibration plate is always within the best observation field of view of multiple sensors according to different unmanned mining truck models, which greatly improves the deployment flexibility and operation convenience of the calibration system in complex mining environments.

[0188] (4) The lidar point cloud feature extraction method proposed in this disclosure has good adaptability to both high-beam and low-beam lidar, and can stably extract calibration board corner points under different point cloud density conditions, thus expanding the application scope of this invention on different sensor configuration platforms.

[0189] (5) The layout and data acquisition method of the multi-calibration board proposed in this disclosure reduces manual intervention and improves calibration efficiency.

[0190] (6) The calibration system proposed in this disclosure integrates complete modules such as data acquisition, preprocessing, feature extraction, external parameter optimization, result verification and human-computer interaction, forming a closed-loop calibration process, which improves the intelligence level and reliability of the system.

[0191] In some embodiments, the functional units described above may be implemented as general-purpose processors, programmable logic controllers (PLCs), digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or any suitable combination thereof for performing the functions described herein.

[0192] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0193] The description in this disclosure is provided for illustrative and descriptive purposes only and is not intended to be exhaustive or to limit the disclosure to its forms. Many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to better illustrate the principles and practical application of this disclosure and to enable those skilled in the art to understand this disclosure and to design various embodiments with various modifications suitable for a particular purpose.

Claims

1. A control method for a collaborative calibration device, executed by a control device in the collaborative calibration device, comprising: The brightness of the LED array inside each of the four QR codes is adjusted by using the ambient light intensity collected in real time by a photosensitive sensor. The four QR codes are respectively located in the adjacent areas of the four corners of the rectangular calibration plate in the collaborative calibration device. Adjust at least one of the height and pitch angle of the adjustable support bracket of the calibration plate so that the calibration plate can appear in the field of view of the image acquisition device, lidar and millimeter-wave radar on the unmanned engineering vehicle.

2. The collaborative calibration device control method according to claim 1, wherein, Adjusting at least one of the height and pitch angle of the adjustable support bracket of the calibration plate includes: Based on the instruction information sent by the unmanned engineering vehicle, adjust at least one of the height and pitch angle of the adjustable support bracket of the calibration plate, wherein the instruction information includes the type of the unmanned engineering vehicle and the distance information between the unmanned engineering vehicle and the collaborative calibration device.

3. The control method for the collaborative calibration device according to claim 1 or 2, wherein, The brightness of the LED array inside each QR code is positively correlated with the ambient light intensity.

4. A control device, comprising: Memory; A processor, coupled to a memory, is configured to implement the cooperative calibration device control method as described in any one of claims 1-3, based on the execution of instructions stored in the memory.

5. A collaborative calibration device, comprising: The control device as described in claim 4; A calibration board, wherein the calibration board is rectangular, the surface of the calibration board is covered with a diffuse reflection coating, and a QR code is provided in the adjacent area of ​​each corner of the calibration board, wherein an array of light-emitting diodes (LEDs) is provided in the QR code, and the brightness of the LED array is adjusted according to the control of the control device; Multiple photosensitive sensors are used to detect ambient light intensity, wherein the multiple photosensitive sensors are evenly arranged on the calibration plate; A corner reflector is located at the geometric center point on the back of the calibration plate; An adjustable support bracket for mounting the calibration plate, capable of adjusting at least one of the height and pitch angle of the calibration plate.

6. The collaborative calibration device according to claim 5, wherein, The adjustable support bracket is configured to adjust at least one of the height and pitch angle of the calibration plate according to the control of the control device.

7. A collaborative calibration method, executed by a parameter configuration device in an unmanned engineering vehicle, comprising: Read the initial values ​​of the external parameters of the image acquisition device, lidar, and millimeter-wave radar; The image acquisition device, the lidar, and the millimeter-wave radar are controlled to acquire time-synchronized first image data, first lidar point cloud, and first millimeter-wave radar data; The first image data, the first lidar point cloud, and the first millimeter-wave radar data are preprocessed respectively to obtain the second image data, the second lidar point cloud, and the second millimeter-wave radar data. The first feature, the second feature, and the third feature of the collaborative calibration device are extracted from the second image data, the second lidar point cloud, and the second millimeter-wave radar data, respectively, wherein the collaborative calibration device is the collaborative calibration device as described in claim 5 or 6. Based on the first, second, and third features of the collaborative calibration device, the initial values ​​of the extrinsic parameters of the image acquisition device, the lidar, and the millimeter-wave radar are jointly optimized to obtain the extrinsic parameter calibration results of the image acquisition device, the lidar, and the millimeter-wave radar, respectively.

8. The collaborative calibration method according to claim 7, wherein, Extracting the first feature from the second image data includes: Establish a world coordinate system with the geometric center point of the calibration plate in the collaborative calibration device as the origin; The second image data is processed to identify the four QR codes on the calibration board; Based on the four QR codes, the rotation matrix and translation vector of the image coordinate system relative to the world coordinate system are solved using the perspective n-point PnP algorithm. Based on the predetermined size information of the calibration plate, the rotation matrix, and the translation vector, the four corner points of the calibration plate are projected from the world coordinate system to the image coordinate system; Extract the two-dimensional coordinates of the four corner points in the image coordinate system; The two-dimensional coordinates of the four corner points are sorted in a specified order, and the first sorting result is used as the first feature.

9. The collaborative calibration method according to claim 8, wherein, Extracting the second feature from the second lidar point cloud includes: Rotate the second lidar point cloud to the designated plane; Fit the minimum bounding box of the second lidar point cloud within the specified plane, and extract the four vertices of the minimum bounding box as four candidate corner points; The four candidate corner points are transformed into three-dimensional space to obtain the three-dimensional coordinates of the four corner points of the calibration board in the lidar coordinate system. The three-dimensional coordinates of the four corner points are sorted in a specified order, and the resulting second sorting result is used as the second feature.

10. The collaborative calibration method according to claim 9, wherein, Extracting the third feature from the second millimeter-wave radar data includes: Euclidean clustering and target tracking are performed on the second millimeter-wave radar data to obtain the first set of tracked targets; In the first set of tracking targets, target points that meet predetermined conditions are selected to generate a second set of tracking targets, wherein the deviation between the radar cross-section value of the target point that meets the predetermined conditions and the predetermined radar cross-section value of the corner reflector located at the geometric center point on the back of the calibration plate is less than a predetermined radar cross-section threshold. Based on the three-dimensional coordinates of the four corner points of the calibration plate in the lidar coordinate system, determine the three-dimensional coordinates of the geometric center point of the calibration plate in the lidar coordinate system. The three-dimensional coordinates of the geometric center point of the calibration plate in the lidar coordinate system are transformed to the millimeter-wave radar coordinate system. In the second set of tracking targets, the corresponding target point of the corner reflector is selected, wherein the deviation between the three-dimensional coordinates of the corresponding target point and the three-dimensional coordinates of the geometric center point of the calibration plate in the millimeter-wave radar coordinate system is less than a predetermined distance threshold. The three-dimensional coordinates of the corresponding target point in the millimeter-wave radar coordinate system are used as the third feature.

11. The collaborative calibration method according to claim 10, wherein, Joint optimization of the initial values ​​of the extrinsic parameters of the image acquisition device, the lidar, and the millimeter-wave radar includes: Based on the deviation between the first sorting result and the second sorting result, and the deviation between the three-dimensional coordinates of the corresponding target point in the millimeter-wave radar coordinate system and the three-dimensional coordinates of the geometric center point of the corner reflector in the millimeter-wave radar coordinate system (pre-stored), the initial values ​​of the extrinsic parameters of the image acquisition device, the lidar, and the millimeter-wave radar are jointly optimized using a nonlinear least squares algorithm.

12. The collaborative calibration method according to claim 7, wherein, Preprocessing the first image data includes: When the ambient light intensity is greater than a specified light intensity threshold, the first image data is preprocessed using a histogram equalization algorithm to obtain the second image data. When the ambient light intensity is not greater than a specified light intensity threshold, at least one of an adaptive brightness compensation algorithm and a multi-scale contrast enhancement algorithm is used to preprocess the first image data to obtain the second image data.

13. The collaborative calibration method according to claim 7, wherein, Preprocessing of the first lidar point cloud includes: Based on the estimated position of the calibration plate, determine the region of interest; Extract the point cloud located in the region of interest from the first lidar point cloud, and use it as the first point cloud to be processed; Based on the beam density of the lidar, the first point cloud to be processed is downsampled to obtain the second point cloud to be processed; Based on the predetermined normal direction information of the calibration board, a plane segmentation algorithm is used to extract the plane in which the calibration board is located; Based on the plane, outlier point clouds in the second point cloud to be processed are deleted to obtain the second lidar point cloud.

14. The collaborative calibration method according to claim 7, wherein, Preprocessing of the first millimeter-wave radar data includes: Based on the estimated position of the calibration plate, determine the region of interest; The point cloud located in the region of interest from the first millimeter-wave radar data is extracted and used as the second millimeter-wave radar data.

15. The collaborative calibration method according to claim 7, further comprising: The extrinsic parameter calibration results are visualized to determine the reprojection error; If the reprojection error is greater than a predetermined error threshold, the acquisition of first image data, first lidar point cloud and first millimeter-wave radar data by controlling the image acquisition device, the lidar and the millimeter-wave radar to be synchronized is repeated.

16. The collaborative calibration method according to claim 7, further comprising: The distance between the unmanned engineering vehicle and the collaborative calibration device is determined based on the second lidar point cloud. Send instruction information to the collaborative calibration device, wherein the instruction information includes the type of the unmanned engineering vehicle and the distance information of the distance.

17. The collaborative calibration method according to any one of claims 7-16, further comprising: The parameters of the image acquisition device are configured using the calibration results of the intrinsic and extrinsic parameters of the image acquisition device. The parameters of the lidar are configured using the external parameter calibration results of the lidar. The parameters of the millimeter-wave radar are configured using the external parameter calibration results of the millimeter-wave radar.

18. A parameter configuration device, comprising: Memory; A processor, coupled to a memory, is configured to implement the co-calibration method as described in any one of claims 7-17 based on memory-stored instruction execution.

19. An unmanned engineering vehicle, comprising: The parameter configuration device as described in claim 18; An image acquisition device is configured to acquire image data; The lidar is configured to collect lidar point clouds; Millimeter-wave radar, configured to acquire millimeter-wave radar data.

20. A computer-readable storage medium, wherein, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method as described in any one of claims 1-3 and 7-17.

21. A computer program product comprising computer instructions, wherein the computer instructions, when executed by a processor, implement the method as described in any one of claims 1-3, 7-17.

Images