A parameter calibration method, system, device and equipment

Abstract

The present application provides a parameter calibration method, system, device and equipment, the method comprising: sending a first instruction to a robot, the first instruction is used to instruct the robot to move a target vehicle to a calibration site, so that after receiving the first instruction, the robot moves the target vehicle to the center of the calibration site; receiving a first response returned by the robot, the first response indicating that the robot has moved the target vehicle to the center of the calibration site; after receiving the first response, sending a second instruction to the target vehicle, the second instruction is used to instruct the target vehicle to start parameter calibration, so that after receiving the second instruction, the target vehicle obtains the camera extrinsic parameters of the camera deployed on the target vehicle and stores the camera extrinsic parameters; receiving a second response returned by the target vehicle, the second response indicating that the target vehicle has completed parameter calibration. Through the technical solution of the present application, it is possible to realize automatic calibration of camera extrinsic parameters, accurately calibrate camera extrinsic parameters, and improve the imaging effect of panoramic images.

Description

Technical Field

[0001] The present application relates to the field of assisted driving, and in particular to a parameter calibration method, system, device and equipment. Background Art

[0002] With the continuous development of image technology, the vehicle panoramic system has also been widely used. The vehicle panoramic system includes multiple cameras installed on the vehicle, such as a camera located on the front side of the vehicle, a camera located on the rear side of the vehicle, a camera located on the left side of the vehicle, a camera located on the right side of the vehicle, etc. During the driving process of the vehicle, these cameras collect images in real time. Based on the multiple images collected by multiple cameras, the vehicle panoramic system can stitch multiple images into a panoramic image, that is, a 360-degree surround image. The vehicle panoramic system can provide the driver with the surrounding conditions of the vehicle based on the panoramic image and provide visual assistance for the driver's operation.

[0003] In order to enable the on-board panoramic system to generate panoramic images, the camera extrinsic parameters of the camera installed on the vehicle need to be calibrated before the vehicle leaves the factory. For example, in order to determine the relationship between the three-dimensional geometric position of a point on the surface of a spatial object and its corresponding point in the image, it is necessary to establish an imaging geometric model, and the parameters of the geometric model are the camera extrinsic parameters of the camera, and the process of solving the camera extrinsic parameters of the camera is called the calibration of the camera extrinsic parameters, which is a very critical link.

[0004] However, in the related art, there is no effective way to calibrate the camera extrinsic parameters of the camera, and the camera extrinsic parameters cannot be accurately calibrated, resulting in poor imaging effect of the panoramic image and poor user experience. Summary of the invention

[0005] The present application provides a parameter calibration method, which is applied to a scheduling device, and the method includes:

[0006] Sending a first instruction to the robot, wherein the first instruction is used to instruct the robot to move the target vehicle to a calibration site, so that after receiving the first instruction, the robot moves the target vehicle to a center position of the calibration site; receiving a first response returned by the robot, wherein the first response indicates that the robot has moved the target vehicle to a center position of the calibration site;

[0007] After receiving the first response, sending a second instruction to the target vehicle, the second instruction is used to instruct the target vehicle to start parameter calibration, so that after receiving the second instruction, the target vehicle obtains the camera extrinsic parameters of the camera deployed on the target vehicle and stores the camera extrinsic parameters; receiving a second response returned by the target vehicle, the second response indicating that the target vehicle has completed parameter calibration;

[0008] The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system of the camera, and the camera extrinsic parameters include rotation parameters and translation parameters.

[0009] Exemplarily, the acquiring of the camera extrinsic parameters of the camera deployed on the target vehicle includes: acquiring the camera extrinsic parameters of the camera deployed on the target vehicle through a parameter calibration controller, wherein the parameter calibration controller is located in a vehicle-mounted terminal of the target vehicle, or is independent of a vehicle-mounted terminal of the target vehicle;

[0010] Obtaining the camera extrinsic parameters of the camera deployed on the target vehicle through a parameter calibration controller includes:

[0011] Capturing a fisheye image of the calibration site by means of the camera, wherein the fisheye image includes a marking pattern of the calibration site, and selecting a plurality of key points from the marking pattern;

[0012] For each key point, determine the pixel coordinates of the key point in the fisheye image, and obtain the pre-configured physical coordinates of the key point in the world coordinate system;

[0013] Based on the pixel coordinates of the multiple key points in the fisheye image and the physical coordinates of the multiple key points in the world coordinate system, the camera extrinsic parameters of the camera are acquired.

[0014] Exemplarily, the marking pattern includes a checkerboard pattern, and the checkerboard pattern includes a plurality of regions;

[0015] The selecting a plurality of key points from the marking pattern comprises:

[0016] An area of ​​interest is selected from multiple areas of the checkerboard pattern, and a pixel point located at a specified position in the area of ​​interest is selected as a key point; wherein the specified position is the upper left corner position, the upper right corner position, the lower left corner position, the lower right corner position, or the center point position.

[0017] Exemplarily, after receiving the second response returned by the target vehicle, the method further includes:

[0018] Sending a third instruction to the robot, wherein the third instruction is used to instruct the robot to move the target vehicle outside the calibration site, so that after receiving the third instruction, the robot moves the target vehicle from the center position of the calibration site to a designated parking position outside the calibration site;

[0019] A third response returned by the robot is received, wherein the third response indicates that the robot has moved the target vehicle to a designated parking position outside the marked site.

[0020] Exemplarily, before sending the first instruction to the robot, the method further includes: establishing a first remote communication connection with the robot; sending the first instruction to the robot includes: sending the first instruction to the robot through the first remote communication connection; receiving the first response returned by the robot includes: receiving the first response returned by the robot through the first remote communication connection; wherein the first remote communication connection is specifically: a WIFI connection, or a 4G connection, or a 5G connection;

[0021] Before sending the second instruction to the target vehicle, the method also includes: establishing a second remote communication connection with the target vehicle; sending the second instruction to the target vehicle includes: sending the second instruction to the target vehicle through the second remote communication connection; receiving the second response returned by the target vehicle includes: receiving the second response returned by the target vehicle through the second remote communication connection; wherein the second remote communication connection is specifically a WIFI connection, or a 4G connection, or a 5G connection.

[0022] Exemplarily, the robot is specifically an AGV.

[0023] The present application provides a parameter calibration system, which comprises at least a dispatching device, a robot, and at least one target vehicle to be calibrated, wherein:

[0024] The scheduling device is used to send a first instruction to the robot, wherein the first instruction is used to instruct the robot to move the target vehicle to a calibration site;

[0025] The robot is configured to move the target vehicle to the center of the calibration site after receiving the first instruction, and return a first response to the dispatching device, wherein the first response indicates that the robot has moved the target vehicle to the center of the calibration site;

[0026] The scheduling device is used to send a second instruction to the target vehicle after receiving the first response, wherein the second instruction is used to instruct the target vehicle to start parameter calibration;

[0027] The target vehicle is used to obtain camera extrinsic parameters of a camera deployed on the target vehicle after receiving the second instruction, store the camera extrinsic parameters, and return a second response to the scheduling device, wherein the second response indicates that parameter calibration of the target vehicle has been completed;

[0028] The dispatching device is used to receive the second response returned by the target vehicle;

[0029] The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system of the camera, and the camera extrinsic parameters include rotation parameters and translation parameters.

[0030] Exemplarily, the scheduling device is used to send a third instruction to the robot after receiving the second response, and the third instruction is used to instruct the robot to move the target vehicle outside the calibration site; the robot is used to move the target vehicle from the center position of the calibration site to the designated parking position outside the calibration site after receiving the third instruction, and return a third response to the scheduling device, and the third response indicates that the robot has moved the target vehicle to the designated parking position outside the calibration site; the scheduling device is used to receive the third response returned by the robot.

[0031] Exemplarily, when the robot moves the target vehicle to the center position of the calibration site, it is specifically used to: move to the calibration site based on a preconfigured driving route, and park the target vehicle at the center position of the calibration site based on robot positioning technology; wherein the center position of the calibration site has a special mark, and when the target vehicle is parked at the center position of the calibration site, the target position of the target vehicle coincides with the special mark at the center position of the calibration site.

[0032] Exemplarily, when the target vehicle obtains the camera extrinsic parameters of the camera deployed on the target vehicle, it is specifically used to: obtain the camera extrinsic parameters of the camera deployed on the target vehicle through a parameter calibration controller, and the parameter calibration controller is located in the vehicle-mounted terminal of the target vehicle, or is independent of the vehicle-mounted terminal of the target vehicle; specifically: collect a fisheye image of the calibration site through the camera, the fisheye image includes a marking pattern of the calibration site, and select multiple key points from the marking pattern;

[0033] For each key point, determine the pixel coordinates of the key point in the fisheye image, and obtain the pre-configured physical coordinates of the key point in the world coordinate system;

[0034] Based on the pixel coordinates of the multiple key points in the fisheye image and the physical coordinates of the multiple key points in the world coordinate system, the camera extrinsic parameters of the camera are acquired.

[0035] Exemplarily, the marking pattern includes a checkerboard pattern, and the checkerboard pattern includes a plurality of regions;

[0036] When selecting a plurality of key points from the marking pattern by the parameter calibration controller, it is specifically used for:

[0037] An area of ​​interest is selected from multiple areas of the checkerboard pattern, and a pixel point located at a specified position in the area of ​​interest is selected as a key point; wherein the specified position is the upper left corner position, the upper right corner position, the lower left corner position, the lower right corner position, or the center point position.

[0038] The present application provides a parameter calibration device, which is applied to a scheduling device, and the device includes:

[0039] A sending module, used for sending a first instruction to the robot, wherein the first instruction is used for instructing the robot to move the target vehicle to a calibration site, so that after receiving the first instruction, the robot moves the target vehicle to a central position of the calibration site;

[0040] A receiving module, configured to receive a first response returned by the robot, wherein the first response indicates that the robot has moved the target vehicle to a central position of the calibration site;

[0041] The sending module is further used to send a second instruction to the target vehicle after receiving the first response, wherein the second instruction is used to instruct the target vehicle to start parameter calibration, so that after the target vehicle receives the second instruction, the camera extrinsic parameters of the camera deployed on the target vehicle are obtained and the camera extrinsic parameters are stored;

[0042] The receiving module is further used to receive a second response returned by the target vehicle, wherein the second response indicates that parameter calibration of the target vehicle has been completed;

[0043] The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system of the camera, and the camera extrinsic parameters include rotation parameters and translation parameters.

[0044] The present application provides a scheduling device, comprising: a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions that can be executed by the processor;

[0045] The processor is used to execute machine executable instructions to implement the following steps:

[0046] Sending a first instruction to the robot, wherein the first instruction is used to instruct the robot to move the target vehicle to a calibration site, so that after receiving the first instruction, the robot moves the target vehicle to a center position of the calibration site; receiving a first response returned by the robot, wherein the first response indicates that the robot has moved the target vehicle to a center position of the calibration site;

[0047] After receiving the first response, sending a second instruction to the target vehicle, the second instruction is used to instruct the target vehicle to start parameter calibration, so that after receiving the second instruction, the target vehicle obtains the camera extrinsic parameters of the camera deployed on the target vehicle and stores the camera extrinsic parameters; receiving a second response returned by the target vehicle, the second response indicating that the target vehicle has completed parameter calibration;

[0048] The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system of the camera, and the camera extrinsic parameters include rotation parameters and translation parameters.

[0049] It can be seen from the above technical solutions that in the embodiment of the present application, by sending a first instruction to the robot so that the robot moves the target vehicle to the center of the calibration site, and sending a second instruction to the target vehicle so that the target vehicle obtains the camera extrinsic parameters of the camera and stores the camera extrinsic parameters, the automatic calibration of the camera extrinsic parameters is realized, the camera extrinsic parameters of the camera can be effectively calibrated, the camera extrinsic parameters can be accurately calibrated, the imaging effect of the panoramic image can be improved, and the user experience can be improved. The calibration process of the camera extrinsic parameters can be reduced, the calibration difficulty of the calibration parameters can be reduced, the manpower input in the mass production of vehicle calibration can be reduced, the construction cost and maintenance cost of the calibration site can be reduced, the entire calibration process can be made more automated, and the efficiency of the mass production of calibration can be effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments of the present application or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings of the embodiments of the present application.

[0051] Figure 1 is a schematic diagram of deploying multiple vehicle-mounted cameras in one embodiment of the present application;

[0052] Figure 2 is a schematic diagram of a calibration site in one embodiment of the present application;

[0053] Figure 3 It is a flow chart of a parameter calibration method in one embodiment of the present application;

[0054] Figure 4 It is a flow chart of a parameter calibration method in one embodiment of the present application;

[0055] Figure 5 It is a flow chart of a parameter calibration method in one embodiment of the present application;

[0056] Figure 6 is a schematic diagram of the structure of a parameter calibration device in one embodiment of the present application;

[0057] Figure 7 It is a hardware structure diagram of a scheduling device in one implementation of the present application. DETAILED DESCRIPTION

[0058] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, rather than limiting the present application. The singular forms of "a", "said" and "the" used in the present application and claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to any or all possible combinations of one or more associated listed items.

[0059] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in the embodiments of the present application, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, in addition, the word "if" used may be interpreted as "at..." or "when..." or "in response to determination".

[0060] See also Figure 1 As shown, the vehicle-mounted panoramic system includes multiple cameras (i.e., vehicle-mounted cameras) installed on the vehicle, such as a camera located on the front side of the vehicle, a camera located on the rear side of the vehicle, a camera located on the left side of the vehicle, a camera located on the right side of the vehicle, etc. These cameras can also be called surround view cameras. During the driving process of the vehicle, these cameras can capture images in real time. For example, the camera located on the front side of the vehicle captures images in front of the vehicle, the camera located on the rear side of the vehicle captures images behind the vehicle, the camera located on the left side of the vehicle captures images on the left side of the vehicle, and the camera located on the right side of the vehicle captures images on the right side of the vehicle. Based on the multiple images captured by the multiple cameras, the vehicle-mounted panoramic system can generate and display a panoramic view, thereby providing the driver with the situation around the vehicle and providing visual assistance for the driver's operation.

[0061] In order to enable the on-board panoramic system to generate panoramic images, the camera parameters of the camera installed on the vehicle need to be calibrated before the vehicle leaves the factory, and the camera parameters may include camera intrinsic parameters (i.e., internal parameters) and camera extrinsic parameters (i.e., external parameters). The camera intrinsic parameters are composed of parameters such as (cx, cy, fx, fy, s0, s1, s2, s3), (cx, cy) are the coordinates of the principal point, (fx, fy) are the focal length of the camera, (s0, s1, s2, s3) are the camera distortion coefficients, and the camera intrinsic parameters are parameters related to the characteristics of the camera itself. Regarding the calibration process of the camera intrinsic parameters, this embodiment does not limit it. The camera extrinsic parameters are composed of parameters such as (ω, δ, θ, Tx, Ty, Tz), (ω, δ, θ) are the rotation parameters of the three axes, (Tx, Ty, Tz) are the translation parameters of the three axes, and the camera extrinsic parameters are used to represent the conversion relationship between the world coordinate system and the camera coordinate system.

[0062] In order to calibrate the camera extrinsic parameters, in the related art, the staff manually calibrates the camera extrinsic parameters of each camera on the vehicle before the vehicle leaves the factory. However, there are many vehicles to be calibrated, and the efficiency is very low when the staff manually calibrates the camera extrinsic parameters. There is no effective way to calibrate the camera extrinsic parameters, and the camera extrinsic parameters cannot be accurately calibrated, resulting in poor imaging effect of panoramic images and poor user experience.

[0063] In response to the above findings, in an embodiment of the present application, instructions are sent to the robot, which moves the target vehicle to the center of the calibration site, and instructions are sent to the target vehicle, which obtains the camera extrinsic parameters of the camera, thereby realizing automatic calibration of the camera extrinsic parameters. The camera extrinsic parameters of the camera can be effectively calibrated, and the camera extrinsic parameters can be accurately calibrated, thereby improving the imaging effect of the panoramic image and improving the user experience.

[0064] The technical solution of the embodiments of the present application is described below in conjunction with specific embodiments.

[0065] In the embodiment of the present application, a parameter calibration method is proposed, which is used to automatically calibrate the camera extrinsic parameters of the camera deployed on the vehicle before the vehicle leaves the factory. In order to realize the automatic calibration of the camera extrinsic parameters, it is necessary to build a calibration site, which may include at least one marking pattern, see Figure 2 , which is a schematic diagram of a calibration site, the calibration site includes four marking patterns, such as a marking pattern located on the upper left side of the vehicle, a marking pattern located on the lower left side of the vehicle, a marking pattern located on the upper right side of the vehicle, a marking pattern located on the lower right side of the vehicle, etc. Figure 2 Taking 4 marking patterns as an example, in actual applications, the number of marking patterns can be more or less. Figure 2 As shown, the marking pattern is a checkerboard pattern as an example. In practical applications, the marking pattern can also be other types of images, which is not limited. Figure 2 As shown, for each marking pattern (i.e., checkerboard pattern), the marking pattern may include multiple regions, i.e., each rectangle of the marking pattern is a region. Figure 2 In the example, a marking pattern including 5 areas is taken.

[0066] See also Figure 2 As shown, the position of the vehicle is taken as the center of the calibration site. Obviously, after the vehicle is placed at the center of the calibration site, the above four marking patterns are located around the vehicle, that is, when the image is captured by the camera deployed on the vehicle, the image can include the above four marking patterns.

[0067] In an embodiment of the present application, the parameter calibration system includes at least a scheduling device, a robot, and at least one target vehicle to be calibrated (for the convenience of distinction, each vehicle to be calibrated is referred to as a target vehicle, and one target vehicle is taken as an example in the following). In summary, the camera extrinsic parameters of the camera deployed on the target vehicle can be automatically calibrated through the cooperation between the scheduling device, the robot, and the target vehicle.

[0068] Exemplarily, the dispatching device can be a PC (Personal Computer), a terminal device, a mobile terminal, a laptop computer, etc. There is no limitation on the type of the dispatching device, as long as the dispatching device can control the robot and the dispatching device can control the target vehicle.

[0069] Exemplarily, the robot may be an AGV (Automatic Guided Vehicle), an industrial robot, a consumer robot, an entertainment robot, various drones, etc. There is no restriction on the type of robot as long as the robot can move the target vehicle.

[0070] Exemplarily, the target vehicle is a vehicle to be calibrated, which may be a vehicle that has not yet left the factory. The target vehicle supports an on-board panoramic system, and at least one camera (i.e., an on-board camera) is deployed on the target vehicle, such as a camera located on the front side of the target vehicle, a camera located on the rear side of the target vehicle, a camera located on the left side of the target vehicle, a camera located on the right side of the target vehicle, etc. These cameras are also called surround view cameras.

[0071] See also Figure 3 FIG. 1 is a flow chart of a parameter calibration method, which may include:

[0072] Step 301: The scheduling device sends a first instruction to the robot, where the first instruction is used to instruct the robot to move the target vehicle to a calibration site, such as moving the target vehicle to a center position of the calibration site.

[0073] Step 302: After receiving the first instruction, the robot moves the target vehicle to the center of the calibration site. After moving the target vehicle to the center of the calibration site, the robot returns a first response to the dispatching device, indicating that the robot has moved the target vehicle to the center of the calibration site.

[0074] Exemplarily, when it is necessary to calibrate the parameters of the camera deployed on the target vehicle, the scheduling device can send a first instruction to the robot, and the content of the first instruction is not limited. For example, the first instruction may include information about the target vehicle and an instruction type (hereinafter referred to as type T1), and type T1 means moving the target vehicle to the calibration site. After receiving the first instruction, the robot finds the target vehicle from all vehicles to be calibrated based on the information of the target vehicle included in the first instruction, and the target vehicle needs to be moved. Based on type T1 included in the first instruction, it is known that the target vehicle needs to be moved to the calibration site. In summary, the robot needs to move the target vehicle to the center of the calibration site.

[0075] Exemplarily, after the robot moves the target vehicle to the center of the calibration site, it can also return a first response to the dispatching device, and the content of the first response is not limited. For example, the first response may include information about the target vehicle and the instruction type (hereinafter referred to as type T2), and type T2 indicates that the target vehicle has been moved to the calibration site. After receiving the first response, the dispatching device learns that the target vehicle has been moved to the calibration site based on the information about the target vehicle and type T2 included in the first response.

[0076] In a possible implementation, before the dispatching device sends the first instruction to the robot, the dispatching device may also establish a first remote communication connection with the robot, and the first remote communication connection may be a WIFI (Wireless Fidelity) connection, or a 4G connection, or a 5G connection, etc. There is no restriction on the type of connection, as long as the dispatching device and the robot can communicate through the first remote communication connection. Based on this, the dispatching device sends the first instruction to the robot through the first remote communication connection, and the robot receives the first instruction through the first remote communication connection. Also, the robot sends a first response to the dispatching device through the first remote communication connection, and the dispatching device receives the first response through the first remote communication connection.

[0077] In a possible implementation, the robot moves the target vehicle to the center of the calibration site, which may include but is not limited to: the robot moves to the calibration site based on a preconfigured driving route, and parks the target vehicle at the center of the calibration site based on the robot positioning technology. Exemplarily, the center of the calibration site may have a special mark, and when the target vehicle is parked at the center of the calibration site, the target position of the target vehicle and the special mark at the center of the calibration site may overlap.

[0078] Step 303: After receiving the first response returned by the robot, the dispatching device may also send a second instruction to the target vehicle, where the second instruction is used to instruct the target vehicle to start parameter calibration.

[0079] Step 304, after receiving the second instruction, the target vehicle obtains the camera extrinsic parameters of the camera deployed on the target vehicle, stores the camera extrinsic parameters, and returns a second response to the scheduling device, where the second response indicates that the target vehicle has completed parameter calibration, that is, the camera extrinsic parameters of the camera have been successfully stored.

[0080] Exemplarily, after receiving the first response, the scheduling device can send a second instruction to the target vehicle, and the content of the second instruction is not limited, because the first response indicates that the robot has moved the target vehicle to the center of the calibration site, that is, the accurate work of the target vehicle has been completed, and the target vehicle can start the parameter calibration process. For example, the second instruction may include the instruction type (hereinafter referred to as type T3) and other content, and type T3 indicates the start of parameter calibration. After receiving the second instruction, the target vehicle learns that the parameter calibration needs to be started based on the type T3 included in the second instruction. Therefore, the target vehicle starts the parameter calibration, obtains the camera extrinsic parameters of the camera deployed on the target vehicle, and stores the camera extrinsic parameters.

[0081] Exemplarily, after storing the camera external parameters of the camera, that is, completing the parameter calibration, the target vehicle can also return a second response to the dispatching device, and the content of the second response is not limited. For example, the second response may include the target vehicle information and instruction type (hereinafter referred to as type T4) and other content, and type T4 indicates that the target vehicle has completed the parameter calibration. After receiving the second response, the dispatching device learns that the target vehicle has completed the parameter calibration based on the target vehicle information and type T4 included in the second response.

[0082] In a possible implementation, before the dispatch device sends the second instruction to the target vehicle, the dispatch device may also establish a second remote communication connection with the target vehicle, and the second remote communication connection may be a WIFI connection, or a 4G connection, or a 5G connection, etc., and there is no restriction on the type of connection, as long as the dispatch device and the target vehicle can communicate through the second remote communication connection. On this basis, the dispatch device may send the second instruction to the target vehicle through the second remote communication connection, and the target vehicle may receive the second instruction through the second remote communication connection. Also, the target vehicle may send a second response to the dispatch device through the second remote communication connection, and the dispatch device may receive the second response through the second remote communication connection.

[0083] In a possible implementation, the target vehicle obtains the camera extrinsic parameters of the camera deployed on the target vehicle, which may include but is not limited to: obtaining the camera extrinsic parameters of the camera deployed on the target vehicle through a parameter calibration controller, the parameter calibration controller may be located in the vehicle-mounted terminal of the target vehicle (i.e., the vehicle-mounted system), or the parameter calibration controller may be independent of the vehicle-mounted terminal of the target vehicle, such as the parameter calibration controller may be a controller on the target vehicle independent of the vehicle-mounted terminal, or a controller on the scheduling device, without limitation. When obtaining the camera extrinsic parameters of the camera deployed on the target vehicle through the parameter calibration controller, the following steps may be adopted: for each camera deployed on the target vehicle (taking one camera as an example), the camera is used to collect an image of the calibration site (when the camera is a fisheye camera, the image is a fisheye image, and this article takes the fisheye camera and the fisheye image as examples, and of course it may also be other types of cameras), the fisheye image may include a marking pattern of the calibration site, the number of marking patterns is at least one, and multiple key points are selected from the marking pattern, for example, at least one key point is selected from each marking pattern, and the key points in all marking patterns are the multiple key points. For each key point, determine the pixel coordinates of the key point in the fisheye image, and obtain the pre-configured physical coordinates of the key point in the world coordinate system. Based on the pixel coordinates of multiple key points in the fisheye image and the physical coordinates of multiple key points in the world coordinate system, obtain the camera extrinsic parameters of the camera. The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system, and the camera extrinsic parameters include rotation parameters and translation parameters.

[0084] Exemplarily, the above-mentioned marking pattern can be a checkerboard pattern, and the checkerboard pattern can include multiple areas. On this basis, multiple key points are selected from the marking pattern, which can include but are not limited to: selecting an area of ​​interest from multiple areas of the checkerboard pattern, and selecting the pixel point located at a specified position in the area of ​​interest as the key point; the specified position can be the upper left corner position, the upper right corner position, the lower left corner position, the lower right corner position, or the center point position, and there is no limitation on this specified position.

[0085] See also Figure 2 As shown, for each checkerboard pattern, all regions (such as 5 regions) of the checkerboard pattern can be used as regions of interest, or some regions (such as 1 region, 2 regions, etc.) of the checkerboard pattern can be used as regions of interest. For each region of interest, a pixel point located at a specified position (which can be at least one of the upper left corner position, the upper right corner position, the lower left corner position, the lower right corner position, and the center point position) in the region of interest can be selected as a key point.

[0086] Step 305: The dispatching device receives a second response returned by the target vehicle.

[0087] Exemplarily, after receiving the second response, the dispatching device learns that the parameter calibration of the target vehicle has been completed because the second response indicates that the parameter calibration of the target vehicle has been completed.

[0088] In a possible implementation, after receiving the second response returned by the target vehicle, the dispatching device may further send a third instruction to the robot, and the third instruction may be used to instruct the robot to move the target vehicle outside the calibration site. After receiving the third instruction, the robot may move the target vehicle from the center of the calibration site to a designated parking position outside the calibration site, and return a third response to the dispatching device, and the third response may indicate that the robot has moved the target vehicle to the designated parking position outside the calibration site. Then, the dispatching device may receive the third response returned by the robot.

[0089] Exemplarily, after receiving the second response, the dispatching device learns that the target vehicle has completed parameter calibration and needs to move the target vehicle to a designated parking position outside the calibration site. Based on this, the dispatching device sends a third instruction to the robot, and the content of the third instruction is not limited. For example, the third instruction may include an instruction type (hereinafter referred to as type T5), and type T5 indicates that the target vehicle is moved to a designated parking position outside the calibration site. After receiving the third instruction, the robot learns that the target vehicle needs to be moved to a designated parking position outside the calibration site based on type T5 included in the third instruction. Therefore, the robot moves the target vehicle from the center of the calibration site to the designated parking position outside the calibration site.

[0090] After the robot moves the target vehicle to the designated parking position outside the calibration site, it can also return a third response to the dispatching device, and the content of the third response is not limited. For example, the third response includes the information of the target vehicle and the instruction type (subsequently recorded as type T6), and type T6 indicates that the target vehicle has been moved to the designated parking position outside the calibration site. After receiving the third response, the dispatching device learns that the target vehicle has moved to the designated parking position outside the calibration site based on the information of the target vehicle and type T6 included in the third response. At this point, the next target vehicle can be calibrated. The parameter calibration process of the next target vehicle is shown in steps 301-305, which will not be repeated here.

[0091] Before the scheduling device sends the third instruction to the robot, the scheduling device may also establish a third remote communication connection with the robot. The third remote communication connection may be a WIF connection, a 4G connection, a 5G connection, etc. There is no restriction on the type of connection, as long as the scheduling device and the robot can communicate through the third remote communication connection. Based on this, the scheduling device sends the third instruction to the robot through the third remote communication connection, and the robot receives the third instruction through the third remote communication connection. Also, the robot sends a third response to the scheduling device through the third remote communication connection, and the scheduling device receives the third response through the third remote communication connection.

[0092] Exemplarily, the robot moves the target vehicle from the center of the calibration site to a designated parking position outside the calibration site, which may include but is not limited to: the robot moves to the outside of the calibration site based on a pre-configured driving route, and parks the target vehicle at the designated parking position outside the calibration site based on the robot positioning technology. Exemplarily, there may be a parking area outside the calibration site, and the robot may park the target vehicle at any position in the parking area, and use any position in the parking area as the designated parking position.

[0093] In one example, the above execution order is just an example given for the convenience of description. In practical applications, the execution order between the steps can also be changed, and there is no limitation on this execution order. Moreover, in other embodiments, the steps of the corresponding method are not necessarily executed in the order shown and described in this specification, and the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; multiple steps described in this specification may also be combined into a single step for description in other embodiments.

[0094] It can be seen from the above technical solutions that in the embodiment of the present application, by sending a first instruction to the robot so that the robot moves the target vehicle to the center of the calibration site, and sending a second instruction to the target vehicle so that the target vehicle obtains the camera extrinsic parameters of the camera and stores the camera extrinsic parameters, the automatic calibration of the camera extrinsic parameters is realized, the camera extrinsic parameters of the camera can be effectively calibrated, the camera extrinsic parameters can be accurately calibrated, the imaging effect of the panoramic image can be improved, and the user experience can be improved. The calibration process of the camera extrinsic parameters can be reduced, the calibration difficulty of the calibration parameters can be reduced, the manpower input in the mass production of vehicle calibration can be reduced, the construction cost and maintenance cost of the calibration site can be reduced, the entire calibration process can be made more automated, and the efficiency of the mass production of calibration can be effectively improved.

[0095] See also Figure 4 FIG. 2 is another flow chart of a parameter calibration method, which may include:

[0096] Step 401: The scheduling device sends a first instruction to the robot, where the first instruction is used to instruct the robot to move the target vehicle to a calibration site, such as moving the target vehicle to a center position of the calibration site.

[0097] Step 402: After receiving the first instruction, the robot moves the target vehicle to the center of the calibration site. For example, the robot may first move the target vehicle to the calibration site, and then the robot completes the centering process of the target vehicle, thereby moving the target vehicle to the center of the calibration site.

[0098] For example, the robot can be pre-configured with a driving route, which represents the route between the robot's current position and the calibration site. When the robot moves to the calibration site based on the driving route, the target vehicle can also be moved to the calibration site. After the target vehicle is moved to the calibration site, the vehicle centering can be completed by robot positioning technology, such as SLAM (Simultaneous Localization And Mapping) technology. Vehicle centering means: parking the target vehicle at a specified position so that the target vehicle is located at the center of the calibration site, see Figure 2 FIG. 1 is an example of parking the target vehicle at the center of the calibration site. In summary, the robot can park the target vehicle at the center of the calibration site based on the robot positioning technology.

[0099] For example, the center position of the calibration site may have a special mark. When the robot positioning technology is used to park the target vehicle at the center position of the calibration site, it is necessary to make the target position of the target vehicle coincide with the special mark at the center position of the calibration site, so that the target vehicle can be parked at the center position of the calibration site. There is no restriction on this parking process, as long as the target vehicle can be parked at the center position of the calibration site.

[0100] Exemplarily, the target vehicle is parked at the center of the calibration site, which means that the target position of the target vehicle coincides with a special mark at the center of the calibration site. The target position of the target vehicle may be any position of the target vehicle, such as the front position of the target vehicle, the rear position of the target vehicle, the center position of the target vehicle, etc., and there is no restriction on the target position of the target vehicle.

[0101] Step 403, after moving the target vehicle to the center of the calibration site, the robot returns a first response to the dispatching device, where the first response indicates that the robot has moved the target vehicle to the calibration site.

[0102] Step 404: After receiving the first response, the dispatching device learns that the target vehicle has been moved to the calibration site, and sends a second instruction to the target vehicle, where the second instruction is used to instruct the target vehicle to start parameter calibration.

[0103] Step 405: After receiving the second instruction, the target vehicle starts a parameter calibration process, that is, the target vehicle obtains the camera extrinsic parameters of the camera deployed on the target vehicle and stores the camera extrinsic parameters.

[0104] Exemplarily, after receiving the second instruction, the target vehicle first completes operations such as vehicle ignition and vehicle start, and then the parameter calibration process can be started. During the parameter calibration process, it is necessary to obtain the camera extrinsic parameters of the camera deployed on the target vehicle and store the camera extrinsic parameters. For example, the camera extrinsic parameters of the camera deployed on the target vehicle are obtained by a parameter calibration controller. The parameter calibration controller can be located in the vehicle system of the target vehicle or can be independent of the vehicle system deployed on the target vehicle. There is no restriction on the execution subject, as long as the camera extrinsic parameters of the camera deployed on the target vehicle can be obtained.

[0105] Since at least one camera can be deployed on the target vehicle, it is necessary to obtain the camera extrinsic parameters of each camera, and the camera extrinsic parameters of each camera are obtained in the same way. In the following, one camera is taken as an example.

[0106] In a possible implementation, the camera extrinsic parameters of the camera may be obtained by using the following steps:

[0107] Step 4051: collect a fisheye image of the calibration site through the camera, the fisheye image may include multiple marking patterns of the calibration site, and select multiple key points from the multiple marking patterns, such as selecting at least one key point from each marking pattern. Figure 2 As shown, the calibration site may include four marking patterns. When the fisheye image of the calibration site is collected by the camera, the fisheye image may include part or all of the four marking patterns, that is, the fisheye image includes the marking pattern within the field of view of the camera. For each marking pattern, the marking pattern may include multiple areas, and an area of ​​interest is selected from the multiple areas of the marking pattern, and the pixel point at a specified position in the area of ​​interest is selected as a key point.

[0108] Step 4052, for each key point in the fisheye image, determine the pixel coordinates of the key point in the fisheye image. For example, taking the upper left corner of the fisheye image as the coordinate origin, horizontal rightward as the X axis, and horizontal downward as the Y axis, then the pixel coordinates of the key point in the fisheye image can be determined.

[0109] Step 4053, for each key point in the fisheye image, obtain the pre-configured physical coordinates of the key point in the world coordinate system. For example, for the key points of all designated positions of the calibration site, the physical coordinates of these key points in the world coordinate system can be pre-configured. Based on this, for each key point in the fisheye image, the pre-configured physical coordinates of the key point in the world coordinate system can be directly obtained.

[0110] Step 4054, based on the pixel coordinates of the multiple key points in the fisheye image and the physical coordinates of the multiple key points in the world coordinate system, obtain the camera extrinsic parameters of the camera, the camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system, and the camera extrinsic parameters include rotation parameters and translation parameters.

[0111] For example, the conversion relationship between the world coordinate system and the camera coordinate system can be seen in formula (1):

[0112]

[0113] R represents the rotation parameter, which is composed of (ω, δ, θ). T represents the translation parameter, which is composed of (Tx, Ty, Tz). ω represents the rotation angle around the X axis of the camera coordinate system, δ represents the rotation angle around the Y axis of the camera coordinate system, θ represents the rotation angle around the Z axis of the camera coordinate system, Tx represents the translation in the X axis direction of the camera coordinate system, Ty represents the translation in the Y axis direction of the camera coordinate system, and Tz represents the translation in the Z axis direction of the camera coordinate system. w Represents the physical coordinates in the world coordinate system, P crepresents the pixel coordinates in the camera coordinate system, that is, the pixel coordinates in the fisheye image. In summary, based on the pixel coordinates of multiple key points in the fisheye image and the physical coordinates of multiple key points in the world coordinate system, the rotation parameter R and the translation parameter T can be solved by formula (1), thereby obtaining the camera extrinsic parameters of the camera.

[0114] In a possible implementation, the vehicle system deployed on the target vehicle may execute steps 4051 to 4054 to obtain the camera extrinsic parameters of the camera, or the controller deployed on the target vehicle and independent of the vehicle system may execute steps 4051 to 4054 to obtain the camera extrinsic parameters of the camera, or after the fisheye image of the calibration site is captured by the camera, the fisheye image may be sent to the scheduling device, and the scheduling device executes steps 4052 to 4054 to obtain the camera extrinsic parameters of the camera, and the camera extrinsic parameters of the camera are sent to the target vehicle. Of course, the above are just a few examples and are not limited to this.

[0115] Step 406, after obtaining the camera extrinsic parameters of the camera and storing the camera extrinsic parameters, the target vehicle returns a second response to the dispatching device, and the second response indicates that the target vehicle has completed parameter calibration and automatically shuts down.

[0116] Step 407: After receiving the second response, the dispatching device learns that the parameter calibration has been completed, and sends a third instruction to the robot, where the third instruction is used to instruct the robot to move the target vehicle outside the calibration site.

[0117] Step 408: After receiving the third instruction sent by the dispatching device, the robot may move the target vehicle from the center position of the calibration site to a designated parking position outside the calibration site.

[0118] Exemplarily, the robot may be pre-configured with a driving route, which represents the route between the robot's current position and a parking area outside the calibrated site. When the robot moves to the parking area outside the calibrated site based on the driving route, the target vehicle may also be moved to the parking area outside the calibrated site.

[0119] After moving the target vehicle to a parking area outside the calibration site, the robot can park the target vehicle at a designated parking location outside the calibration site based on robot positioning technology (such as SLAM technology), for example, parking the target vehicle at a designated parking location in the parking area, and there is no restriction on this parking process.

[0120] Step 409, after moving the target vehicle to the designated parking position, the robot returns a third response to the dispatching device, and the third response indicates that the target vehicle has been moved to the designated parking position outside the calibration site.

[0121] Exemplarily, after receiving the third response, the dispatching device learns that the target vehicle has been moved to a designated parking position outside the calibration site, and can perform a parameter calibration process for the next target vehicle.

[0122] Based on the same application concept as the above method, another parameter calibration method is proposed in the embodiment of the present application, which can be applied to the dispatching equipment, see Figure 5 As shown, the parameter calibration method may include:

[0123] Step 501, sending a first instruction to the robot, the first instruction is used to instruct the robot to move the target vehicle to the calibration site, so that after the robot receives the first instruction, it moves the target vehicle to the center position of the calibration site. Regarding the related processing of the robot, there is no limitation in this embodiment.

[0124] Step 502: receiving a first response returned by the robot, where the first response indicates that the robot has moved the target vehicle to the center of the calibration site, that is, the target vehicle can start the parameter calibration process.

[0125] Step 503, after receiving the first response, sending a second instruction to the target vehicle, the second instruction is used to instruct the target vehicle to start parameter calibration, so that after the target vehicle receives the second instruction, it obtains the camera extrinsic parameters of the camera deployed on the target vehicle and stores the camera extrinsic parameters.

[0126] Step 504, receiving a second response returned by the target vehicle, the second response indicating that the parameter calibration of the target vehicle has been completed, and thus the parameter calibration process of the target vehicle has been successfully completed.

[0127] In a possible implementation, after receiving the second response returned by the target vehicle, a third instruction may be sent to the robot, the third instruction being used to instruct the robot to move the target vehicle outside the calibration site, so that after receiving the third instruction, the robot moves the target vehicle from the center of the calibration site to a designated parking position outside the calibration site. Then, a third response returned by the robot is received, the third response indicating that the robot has moved the target vehicle to the designated parking position outside the calibration site.

[0128] In a possible implementation, before the scheduling device sends the first instruction to the robot, the scheduling device may establish a first remote communication connection with the robot. The scheduling device sends the first instruction to the robot, including: sending the first instruction to the robot through the first remote communication connection; the scheduling device receives the first response returned by the robot, including: receiving the first response returned by the robot through the first remote communication connection; wherein the first remote communication connection may specifically be: a WIFI connection, or a 4G connection, or a 5G connection.

[0129] In a possible implementation, before the dispatch device sends the second instruction to the target vehicle, the dispatch device may establish a second remote communication connection with the target vehicle. The dispatch device sends the second instruction to the target vehicle, including: sending the second instruction to the target vehicle through the second remote communication connection. The dispatch device receives the second response returned by the target vehicle, including: receiving the second response returned by the target vehicle through the second remote communication connection; wherein the second remote communication connection is specifically a WIFI connection, or a 4G connection, or a 5G connection.

[0130] Based on the same application concept as the above method, a parameter calibration system is also proposed in an embodiment of the present application, and the parameter calibration system may at least include a scheduling device, a robot, and at least one target vehicle to be calibrated, wherein: the scheduling device is used to send a first instruction to the robot, and the first instruction is used to instruct the robot to move the target vehicle to a calibration site; the robot is used to move the target vehicle to the center of the calibration site after receiving the first instruction, and return a first response to the scheduling device, and the first response indicates that the robot has moved the target vehicle to the center of the calibration site; the scheduling device is used to send a second instruction to the target vehicle after receiving the first response, and the second instruction is used to instruct the target vehicle to start parameter calibration; the target vehicle is used to obtain the camera extrinsic parameters of the camera deployed on the target vehicle after receiving the second instruction, store the camera extrinsic parameters, and return a second response to the scheduling device, and the second response indicates that the target vehicle has completed parameter calibration; the scheduling device is used to receive the second response returned by the target vehicle;

[0131] The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system of the camera, and the camera extrinsic parameters include rotation parameters and translation parameters.

[0132] Exemplarily, the scheduling device is used to send a third instruction to the robot after receiving the second response, and the third instruction is used to instruct the robot to move the target vehicle outside the calibration site; the robot is used to move the target vehicle from the center position of the calibration site to the designated parking position outside the calibration site after receiving the third instruction, and return a third response to the scheduling device, and the third response indicates that the robot has moved the target vehicle to the designated parking position outside the calibration site; the scheduling device is used to receive the third response returned by the robot.

[0133] Exemplarily, when the robot moves the target vehicle to the center position of the calibration site, it is specifically used to: move to the calibration site based on a preconfigured driving route, and park the target vehicle at the center position of the calibration site based on robot positioning technology; wherein the center position of the calibration site has a special mark, and when the target vehicle is parked at the center position of the calibration site, the target position of the target vehicle coincides with the special mark at the center position of the calibration site.

[0134] Exemplarily, when the target vehicle obtains the camera extrinsic parameters of the camera deployed on the target vehicle, it is specifically used to: obtain the camera extrinsic parameters of the camera deployed on the target vehicle through a parameter calibration controller, and the parameter calibration controller is located in the vehicle-mounted terminal of the target vehicle, or is independent of the vehicle-mounted terminal of the target vehicle; specifically: collect a fisheye image of the calibration site through the camera, the fisheye image includes a marking pattern of the calibration site, and select multiple key points from the marking pattern;

[0135] For each key point, determine the pixel coordinates of the key point in the fisheye image, and obtain the pre-configured physical coordinates of the key point in the world coordinate system;

[0136] Based on the pixel coordinates of the multiple key points in the fisheye image and the physical coordinates of the multiple key points in the world coordinate system, the camera extrinsic parameters of the camera are acquired.

[0137] Exemplarily, the marking pattern includes a checkerboard pattern, and the checkerboard pattern includes a plurality of regions;

[0138] When selecting a plurality of key points from the marking pattern by the parameter calibration controller, it is specifically used for:

[0139] An area of ​​interest is selected from multiple areas of the checkerboard pattern, and a pixel point located at a specified position in the area of ​​interest is selected as a key point; wherein the specified position is the upper left corner position, the upper right corner position, the lower left corner position, the lower right corner position, or the center point position.

[0140] Based on the same application concept as the above method, a parameter calibration device is proposed in the embodiment of the present application and applied to the dispatching equipment, see Figure 6 FIG. 1 is a schematic diagram of the structure of the device, wherein the device comprises:

[0141] The sending module 61 is used to send a first instruction to the robot, wherein the first instruction is used to instruct the robot to move the target vehicle to the calibration site, so that after receiving the first instruction, the robot moves the target vehicle to the center of the calibration site; the receiving module 62 is used to receive a first response returned by the robot, wherein the first response indicates that the robot has moved the target vehicle to the center of the calibration site; the sending module 61 is also used to send a second instruction to the target vehicle after receiving the first response, wherein the second instruction is used to instruct the target vehicle to start parameter calibration, so that after receiving the second instruction, the target vehicle obtains the camera extrinsic parameters of the camera deployed on the target vehicle and stores the camera extrinsic parameters; the receiving module 62 is also used to receive a second response returned by the target vehicle, wherein the second response indicates that the target vehicle has completed parameter calibration;

[0142] The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system of the camera, and the camera extrinsic parameters include rotation parameters and translation parameters.

[0143] Exemplarily, the sending module 61 is further used to send a third instruction to the robot after receiving the second response, wherein the third instruction is used to instruct the robot to move the target vehicle outside the calibration site, so that after the robot receives the third instruction, the robot moves the target vehicle from the center position of the calibration site to a designated parking position outside the calibration site;

[0144] The receiving module 62 is further configured to receive a third response returned by the robot, wherein the third response indicates that the robot has moved the target vehicle to a designated parking position outside the calibration site.

[0145] Based on the same application concept as the above method, a scheduling device is proposed in the embodiment of the present application, see Figure 7 As shown, the scheduling device may include: a processor 71 and a machine-readable storage medium 72, wherein the machine-readable storage medium 72 stores machine-executable instructions that can be executed by the processor 71; the processor 71 is used to execute the machine-executable instructions to implement the parameter calibration method disclosed in the above example of this application. For example, the processor 71 is used to execute the machine-executable instructions to implement the following steps:

[0146] Sending a first instruction to the robot, wherein the first instruction is used to instruct the robot to move the target vehicle to a calibration site, so that after receiving the first instruction, the robot moves the target vehicle to a center position of the calibration site; receiving a first response returned by the robot, wherein the first response indicates that the robot has moved the target vehicle to a center position of the calibration site;

[0147] After receiving the first response, sending a second instruction to the target vehicle, the second instruction is used to instruct the target vehicle to start parameter calibration, so that after receiving the second instruction, the target vehicle obtains the camera extrinsic parameters of the camera deployed on the target vehicle and stores the camera extrinsic parameters; receiving a second response returned by the target vehicle, the second response indicating that the target vehicle has completed parameter calibration;

[0148] The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system of the camera, and the camera extrinsic parameters include rotation parameters and translation parameters.

[0149] Based on the same application concept as the above method, an embodiment of the present application also provides a machine-readable storage medium, on which a number of computer instructions are stored. When the computer instructions are executed by a processor, the parameter calibration method disclosed in the above example of the present application can be implemented.

[0150] The above-mentioned machine-readable storage medium may be any electronic, magnetic, optical or other physical storage device, which may contain or store information, such as executable instructions, data, etc. For example, the machine-readable storage medium may be: RAM (Radom Access Memory), volatile memory, non-volatile memory, flash memory, storage drive (such as hard disk drive), solid state drive, any type of storage disk (such as CD, DVD, etc.), or similar storage medium, or a combination thereof.

[0151] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver, a game console, a tablet computer, a wearable device or a combination of any of these devices.

[0152] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0153] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the embodiments of the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0154] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0155] Moreover, these computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0157] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A parameter calibration method, characterized in that: Applied to a scheduling device, the method comprises: Sending a first instruction to the robot, wherein the first instruction includes information of a target vehicle and a first type, wherein the first type included in the first instruction is used to instruct the robot to move the target vehicle to a calibration site, so that after receiving the first instruction, the robot finds the target vehicle from all vehicles to be calibrated based on the information of the target vehicle included in the first instruction, and moves the target vehicle to a central position of the calibration site based on the first type included in the first instruction; receiving a first response returned by the robot, wherein the first response includes information of the target vehicle and a second type, wherein the second type included in the first response indicates that the robot has moved the target vehicle to a central position of the calibration site; After receiving the first response, based on the information of the target vehicle and the second type included in the first response, it is determined that the target vehicle has moved to the calibration site, and a second instruction is sent to the target vehicle, wherein the second instruction includes a third type, and the third type included in the second instruction is used to instruct the target vehicle to start parameter calibration, so that after receiving the second instruction, the target vehicle determines that the parameter calibration needs to be started based on the third type included in the second instruction, completes vehicle ignition and vehicle start, and then starts the parameter calibration process. During the parameter calibration process, the camera extrinsic parameters of the camera deployed on the target vehicle are obtained, and the camera extrinsic parameters are stored; receiving a second response returned by the target vehicle, wherein the second response includes information of the target vehicle and a fourth type, wherein the fourth type included in the second response indicates that parameter calibration of the target vehicle has been completed; wherein the target vehicle automatically turns off the engine after returning the second response; After receiving a second response returned by the target vehicle, based on the information of the target vehicle and the fourth type included in the second response, it is determined that the parameter calibration of the target vehicle has been completed, and a third instruction is sent to the robot, wherein the third instruction includes a fifth type, and the fifth type included in the third instruction is used to instruct the robot to move the target vehicle outside the calibration site, so that after receiving the third instruction, the robot learns that the target vehicle needs to be moved outside the calibration site based on the fifth type included in the third instruction, and moves the target vehicle from the center position of the calibration site to a designated parking position outside the calibration site; receiving a third response returned by the robot, wherein the third response includes information of the target vehicle and a sixth type, wherein the sixth type included in the third response indicates that the robot has moved the target vehicle to a designated parking position outside the calibration site; The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system of the camera, and the camera extrinsic parameters include rotation parameters and translation parameters.

2. The method according to claim 1, characterized in that: The acquiring of the camera extrinsic parameters of the camera deployed on the target vehicle comprises: acquiring the camera extrinsic parameters of the camera deployed on the target vehicle through a parameter calibration controller, wherein the parameter calibration controller is located in a vehicle-mounted terminal of the target vehicle, or is independent of a vehicle-mounted terminal of the target vehicle; Obtaining the camera extrinsic parameters of the camera deployed on the target vehicle through a parameter calibration controller includes: Capturing a fisheye image of the calibration site by means of the camera, wherein the fisheye image includes a marking pattern of the calibration site, and selecting a plurality of key points from the marking pattern; For each key point, determine the pixel coordinates of the key point in the fisheye image, and obtain the pre-configured physical coordinates of the key point in the world coordinate system; Based on the pixel coordinates of the multiple key points in the fisheye image and the physical coordinates of the multiple key points in the world coordinate system, the camera extrinsic parameters of the camera are acquired.

3. The method according to claim 2, characterized in that The marking pattern comprises a checkerboard pattern, the checkerboard pattern comprising a plurality of regions; The selecting a plurality of key points from the marking pattern comprises: An area of ​​interest is selected from multiple areas of the checkerboard pattern, and a pixel point located at a specified position in the area of ​​interest is selected as a key point; wherein the specified position is the upper left corner position, the upper right corner position, the lower left corner position, the lower right corner position, or the center point position.

4. The method according to any one of claims 1 to 3, characterized in that: Before sending the first instruction to the robot, the method further includes: establishing a first remote communication connection with the robot; sending the first instruction to the robot includes: sending the first instruction to the robot through the first remote communication connection; receiving the first response returned by the robot includes: receiving the first response returned by the robot through the first remote communication connection; wherein the first remote communication connection is specifically: a WIFI connection, or a 4G connection, or a 5G connection; Before sending the second instruction to the target vehicle, the method also includes: establishing a second remote communication connection with the target vehicle; sending the second instruction to the target vehicle includes: sending the second instruction to the target vehicle through the second remote communication connection; receiving the second response returned by the target vehicle includes: receiving the second response returned by the target vehicle through the second remote communication connection; wherein the second remote communication connection is specifically a WIFI connection, or a 4G connection, or a 5G connection.

5. A parameter calibration system, characterized in that: The parameter calibration system at least includes a dispatching device, a robot, and at least one target vehicle to be calibrated, wherein: The scheduling device is used to send a first instruction to the robot, wherein the first instruction includes information of a target vehicle and a first type, and the first type included in the first instruction is used to instruct the robot to move the target vehicle to a calibration site; The robot is configured to, after receiving the first instruction, find a target vehicle from all vehicles to be calibrated based on the information of the target vehicle included in the first instruction, move the target vehicle to a central position of the calibration site based on a first type included in the first instruction, and return a first response to the dispatching device, wherein the first response includes the information of the target vehicle and a second type, and the second type included in the first response indicates that the robot has moved the target vehicle to the central position of the calibration site; The scheduling device is used to determine, after receiving the first response, based on the information of the target vehicle and the second type included in the first response, that the target vehicle has moved to the calibration site, and send a second instruction to the target vehicle, wherein the second instruction includes a third type, and the third type included in the second instruction is used to instruct the target vehicle to start parameter calibration; The target vehicle is used to determine that parameter calibration needs to be started based on the third type included in the second instruction after receiving the second instruction, and complete vehicle ignition and vehicle start-up, and then start the parameter calibration process. During the parameter calibration process, the camera external parameters of the camera deployed on the target vehicle are obtained, the camera external parameters are stored, and a second response is returned to the scheduling device, and the engine is automatically turned off, wherein the second response includes information of the target vehicle and a fourth type, and the fourth type included in the second response indicates that the parameter calibration of the target vehicle has been completed; The dispatching device is configured to receive the second response returned by the target vehicle; determine, based on the information of the target vehicle and the fourth type included in the second response, that the parameter calibration of the target vehicle has been completed, and send a third instruction to the robot, wherein the third instruction includes a fifth type, and the fifth type included in the third instruction is used to instruct the robot to move the target vehicle outside the calibration site; The robot is configured to, after receiving the third instruction, learn that the target vehicle needs to be moved outside the calibration site based on the fifth type included in the third instruction, and move the target vehicle from the center position of the calibration site to a designated parking position outside the calibration site; The dispatching device is used to receive a third response returned by the robot, wherein the third response includes information of the target vehicle and a sixth type, and the sixth type included in the third response indicates that the robot has moved the target vehicle to a designated parking position outside the calibration site; The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system of the camera, and the camera extrinsic parameters include rotation parameters and translation parameters.

6. The system according to claim 5, characterized in that When the robot moves the target vehicle to the center of the calibration site, it is specifically used to: Move to the calibration site based on a preconfigured driving route, and park the target vehicle at the center of the calibration site based on robot positioning technology; wherein the center of the calibration site has a special mark, and when the target vehicle is parked at the center of the calibration site, the target position of the target vehicle coincides with the special mark at the center of the calibration site.

7. The system according to claim 5 or 6, characterized in that: When the target vehicle obtains the camera extrinsic parameters of the camera deployed on the target vehicle, it is specifically used to: obtain the camera extrinsic parameters of the camera deployed on the target vehicle through a parameter calibration controller, and the parameter calibration controller is located in the vehicle terminal of the target vehicle, or is independent of the vehicle terminal of the target vehicle; specifically: Capturing a fisheye image of the calibration site by means of the camera, wherein the fisheye image includes a marking pattern of the calibration site, and selecting a plurality of key points from the marking pattern; For each key point, determine the pixel coordinates of the key point in the fisheye image, and obtain the pre-configured physical coordinates of the key point in the world coordinate system; Based on the pixel coordinates of the multiple key points in the fisheye image and the physical coordinates of the multiple key points in the world coordinate system, the camera extrinsic parameters of the camera are acquired.

8. The system according to claim 7, characterized in that The marking pattern comprises a checkerboard pattern, the checkerboard pattern comprising a plurality of regions; When selecting a plurality of key points from the marking pattern by the parameter calibration controller, it is specifically used for: An area of ​​interest is selected from multiple areas of the checkerboard pattern, and a pixel point located at a specified position in the area of ​​interest is selected as a key point; wherein the specified position is the upper left corner position, the upper right corner position, the lower left corner position, the lower right corner position, or the center point position.

9. A parameter calibration device, characterized in that: Applied to a dispatching device, the device comprises: a sending module, configured to send a first instruction to the robot, wherein the first instruction includes information of a target vehicle and a first type, wherein the first type included in the first instruction is used to instruct the robot to move the target vehicle to a calibration site, so that after receiving the first instruction, the robot finds the target vehicle from all vehicles to be calibrated based on the information of the target vehicle included in the first instruction, and moves the target vehicle to a central position of the calibration site based on the first type included in the first instruction; A receiving module, configured to receive a first response returned by the robot, wherein the first response includes information of a target vehicle and a second type, wherein the second type included in the first response indicates that the robot has moved the target vehicle to a central position of the calibration site; The sending module is further used to, after receiving the first response, determine that the target vehicle has moved to the calibration site based on the information of the target vehicle and the second type included in the first response, and send a second instruction to the target vehicle, wherein the second instruction includes a third type, and the third type included in the second instruction is used to instruct the target vehicle to start parameter calibration, so that after receiving the second instruction, the target vehicle determines that the parameter calibration needs to be started based on the second instruction including the third type, completes vehicle ignition and vehicle start, and then starts the parameter calibration process, and in the parameter calibration process, obtains the camera extrinsic parameters of the camera deployed on the target vehicle, and stores the camera extrinsic parameters; The receiving module is further used to receive a second response returned by the target vehicle, the second response includes information of the target vehicle and a fourth type, the fourth type included in the second response indicates that parameter calibration of the target vehicle has been completed; wherein the target vehicle automatically turns off after returning the second response; The sending module is further used for, after receiving a second response returned by the target vehicle, determining that the target vehicle has completed parameter calibration based on the information of the target vehicle and the fourth type included in the second response, and sending a third instruction to the robot, wherein the third instruction includes a fifth type, and the fifth type included in the third instruction is used to instruct the robot to move the target vehicle outside the calibration site, so that after receiving the third instruction, the robot learns that the target vehicle needs to be moved outside the calibration site based on the fifth type included in the third instruction, and moves the target vehicle from the center position of the calibration site to a designated parking position outside the calibration site; The receiving module is further used to receive a third response returned by the robot, wherein the third response includes information of the target vehicle and a sixth type, and the sixth type included in the third response indicates that the robot has moved the target vehicle to a designated parking position outside the calibration site; The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system of the camera, and the camera extrinsic parameters include rotation parameters and translation parameters.

10. A scheduling device, characterized in that: include: a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor; The processor is used to execute machine executable instructions to implement the following steps: Sending a first instruction to the robot, wherein the first instruction includes information of a target vehicle and a first type, wherein the first type included in the first instruction is used to instruct the robot to move the target vehicle to a calibration site, so that after receiving the first instruction, the robot finds the target vehicle from all vehicles to be calibrated based on the information of the target vehicle included in the first instruction, and moves the target vehicle to a central position of the calibration site based on the first type included in the first instruction; receiving a first response returned by the robot, wherein the first response includes information of the target vehicle and a second type, wherein the second type included in the first response indicates that the robot has moved the target vehicle to a central position of the calibration site; After receiving the first response, based on the information of the target vehicle and the second type included in the first response, it is determined that the target vehicle has moved to the calibration site, and a second instruction is sent to the target vehicle, wherein the second instruction includes a third type, and the third type included in the second instruction is used to instruct the target vehicle to start parameter calibration, so that after receiving the second instruction, the target vehicle determines that the parameter calibration needs to be started based on the third type included in the second instruction, completes vehicle ignition and vehicle start, and then starts the parameter calibration process. During the parameter calibration process, the camera extrinsic parameters of the camera deployed on the target vehicle are obtained, and the camera extrinsic parameters are stored; receiving a second response returned by the target vehicle, wherein the second response includes information of the target vehicle and a fourth type, wherein the fourth type included in the second response indicates that parameter calibration of the target vehicle has been completed; wherein the target vehicle automatically turns off the engine after returning the second response; After receiving a second response returned by the target vehicle, based on the information of the target vehicle and the fourth type included in the second response, it is determined that the parameter calibration of the target vehicle has been completed, and a third instruction is sent to the robot, wherein the third instruction includes a fifth type, and the fifth type included in the third instruction is used to instruct the robot to move the target vehicle outside the calibration site, so that after receiving the third instruction, the robot learns that the target vehicle needs to be moved outside the calibration site based on the fifth type included in the third instruction, and moves the target vehicle from the center position of the calibration site to a designated parking position outside the calibration site; receiving a third response returned by the robot, wherein the third response includes information of the target vehicle and a sixth type, wherein the sixth type included in the third response indicates that the robot has moved the target vehicle to a designated parking position outside the calibration site; The camera extrinsic parameters represent the conversion relationship between the world coordinate system and the camera coordinate system of the camera, and the camera extrinsic parameters include rotation parameters and translation parameters.

Images