Method, apparatus, device, medium, and vehicle for determining the true values ​​of three-dimensional coordinates

Abstract

The present invention provides a method, apparatus, device, medium, and vehicle for specifying the true three-dimensional coordinates of a vehicle. 【Solution means】In this method, K groups of own vehicle position information collected at K stops by the inertial sensor of the auxiliary collection vehicle and K groups of main sensing data packets collected by the main collection vehicle are obtained. Based on the K groups of own vehicle position information and the K groups of main sensing data packets, a coordinate transformation matrix between the powered-on vehicle coordinate system of the main collection vehicle and the powered-on vehicle coordinate system of the auxiliary collection vehicle is calculated. Based on the coordinate transformation matrix and the own vehicle position information collected at a predetermined distance position by the inertial sensor of the auxiliary collection vehicle, the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle is calculated, and the projected coordinate information is used as the true three-dimensional coordinates of the auxiliary collection vehicle, and the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold. According to the present invention, the true three-dimensional coordinates of a vehicle at an ultra-long distance can be obtained.

Description

Technical Field

[0001] The present invention relates to the field of smart driving technology, and more specifically to a method, device, equipment, medium, and vehicle for determining the true three-dimensional coordinates of a vehicle.

Background Art

[0002] During the driving of a driverless vehicle, it is necessary to detect the vehicles that appear on the road. Thereby, accidents such as collisions can be avoided, and the safety of driving can be guaranteed.

[0003] Specifically, a vehicle-end sensor, for example, a lidar, can be attached to the driverless vehicle, and the surrounding environment during the driving of the driverless vehicle can be sensed by the lidar to obtain the true three-dimensional coordinates of each sensed vehicle.

[0004] The sensing distance of a normal lidar is only 60 meters to 120 meters. When the distance exceeds the upper limit of 120 meters, the lidar cannot obtain any three-dimensional sensing results. Therefore, currently, the true three-dimensional coordinates of vehicles at ultra-long distances cannot be obtained.

Summary of the Invention

Problems to be Solved by the Invention

[0005] The present invention provides a method, device, equipment, medium, and vehicle for determining the true three-dimensional coordinates of a vehicle that can obtain the true three-dimensional coordinates of a vehicle at ultra-long distances. The specific solutions are as follows.

Means for Solving the Problems

[0006] In a first embodiment, an embodiment of the present invention provides a method for determining the true value of three-dimensional vehicle coordinates. In the method for determining the true value of three-dimensional vehicle coordinates, in the initial state, both the main collection vehicle and the auxiliary collection vehicle are located at the initial point, and the vehicle end sensors of both the main collection vehicle and the auxiliary collection vehicle are facing forward, and when the auxiliary collection vehicle is traveling forward, the vehicle end sensors of both vehicles simultaneously collect sensing data packets for a predetermined time each time the main collection vehicle is stationary and the auxiliary collection vehicle travels at a predetermined distance interval and stops, and at that time the vehicle end sensors of both vehicles simultaneously collect sensing data packets for the predetermined time, and the method for determining the true value of three-dimensional vehicle coordinates is as follows: A step of acquiring K groups of vehicle position information collected by the inertial sensor of the auxiliary collection vehicle during K stops, and K groups of main sensing data packets collected by the main collection vehicle, wherein K is greater than a predetermined number of times, each group of main sensing data packets consists of sensing data with timestamps of multiple frames, the sensing data with timestamps of each frame includes three-dimensional coordinate information of the sensing vehicle, and the sensing vehicle includes at least the auxiliary collection vehicle. A step of calculating a coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle, based on the self-position information of the K group and the main sensing data packets of the K group, wherein the power-on vehicle coordinate system is a vehicle coordinate system whose origin is the position of the vehicle's onboard computer when it is powered on, A step of calculating projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle position information collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle, and setting the projected coordinate information to the true three-dimensional coordinates of the auxiliary collection vehicle, the step of determining that the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold.

[0007] Selectively, the step of calculating a coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle based on the self-position information of the K group and the main sensing data packets of the K group is: The first group of main sensing data packets from the K group of main sensing data packets is taken as the main sensing data packets of the current group, and a calculation is performed using the nearest neighbor method with respect to the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of each frame in the current group of main sensing data packets to obtain a first relative distance error, the three-dimensional coordinate information of the sensing vehicle corresponding to the smallest first relative distance error is identified as the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the current group of main sensing data packets, and the first self-position information is identified as the self-position information of the auxiliary collection vehicle corresponding to the timestamp of the first frame in the current group of main sensing data packets, For each frame other than the timestamp of the first frame in the main sensing data packets of the current group, a calculation is performed on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of the frame and the first three-dimensional coordinate information to obtain a second relative distance error, the three-dimensional coordinate information of the sensing vehicle corresponding to a second relative distance error smaller than a predetermined distance error threshold is identified as the second three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the frame, a calculation is performed on the first group's own vehicle position information with the second three-dimensional coordinate information according to the nearest neighbor method to obtain a third relative distance error, and the own vehicle position information corresponding to the smallest third relative distance error is identified as the own vehicle position information of the auxiliary collection vehicle corresponding to the timestamp of the frame, The steps include: calculating a transformation matrix corresponding to the main sensing data packets of the current group based on the three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of each frame, the self-position information of the auxiliary collection vehicle corresponding to the timestamp of each frame, and a predetermined general-purpose diagram optimization formula, and setting the transformation matrix as the current transformation matrix; The process includes the step of taking the main sensing data packet of the group following the main sensing data packet of the current group as the main sensing data packet of the current group, calculating the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the main sensing data packet of the current group based on the self-position information of the group following the self-position information of the first group and the current transformation matrix, and returning to the step of obtaining a second relative distance error by performing calculations on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of the frame and the first three-dimensional coordinate information for each frame other than the timestamp of the first frame in the main sensing data packet of the current group until the transformation matrix corresponding to the main sensing data packet of the final group among the main sensing data packets of the K group is obtained, and setting the transformation matrix corresponding to the main sensing data packet of the final group as the coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle.

[0008] Optionally, the step of calculating the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle position information collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle is: The process includes multiplying the coordinate transformation matrix by the self-position information of the auxiliary collection vehicle collected at a predetermined distance by the inertial sensor of the auxiliary collection vehicle from the left, and obtaining the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle.

[0009] Selectively, the method for determining the true three-dimensional coordinates of a vehicle is as follows: After calculating the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle position information collected at a predetermined distance position by the inertial sensor of the auxiliary collection vehicle, The method further includes receiving a two-dimensional marking box of the auxiliary collection vehicle that has been manually marked on the target main sensing data packet, performing a two-dimensional-to-three-dimensional matching between the two-dimensional marking box and the three-dimensional boundary box corresponding to the projected coordinate information, and, if the matching is successful, performing a step of setting the projected coordinate information to the true three-dimensional coordinates of the auxiliary collection vehicle, wherein the target main sensing data packet is a main sensing data packet collected by the vehicle-end sensor of the main collection vehicle when the auxiliary collection vehicle continues to drive and stops at a predetermined distance.

[0010] The optional step is to perform a two-dimensional to three-dimensional matching between the two-dimensional marking box and the three-dimensional bounding box corresponding to the projected coordinate information. The steps include: projecting a three-dimensional bounding box corresponding to the aforementioned projected coordinate information onto the image plane where the two-dimensional marking box is located to obtain a two-dimensional projected bounding box; The method includes the steps of calculating the first area of ​​the intersection and the second area of ​​the union between the two-dimensional marking box and the two-dimensional projection boundary box, calculating the division value of the first area and the second area, and determining that the matching was successful when the division value is greater than a predetermined value.

[0011] Selectively, after the step of converting the projected coordinate information to the true three-dimensional coordinates of the auxiliary collection vehicle, the method for determining the true three-dimensional coordinates of the vehicle is as follows: The process further includes the step of receiving an adjustment for the vehicle height in the true three-dimensional coordinates of the auxiliary collection vehicle and obtaining the true three-dimensional coordinates of the auxiliary collection vehicle after the adjustment.

[0012] Selectively, after the step of converting the projected coordinate information to the true three-dimensional coordinates of the auxiliary collection vehicle, the method for determining the true three-dimensional coordinates of the vehicle is as follows: The method further includes the step of calculating the true three-dimensional coordinates of each sensing vehicle in the vehicle coordinate system of the main collection vehicle, based on the projected coordinate information and the three-dimensional coordinate information of each sensing vehicle in the auxiliary sensing data packets collected at a predetermined distance position by the vehicle end sensor of the auxiliary collection vehicle.

[0013] In a second embodiment, an embodiment of the present invention provides a vehicle three-dimensional coordinate true value identification device. In the initial state, both the main collection vehicle and the auxiliary collection vehicle are located at the initial point, and the vehicle end sensors of both the main collection vehicle and the auxiliary collection vehicle are facing forward, and when the auxiliary collection vehicle is traveling forward, the vehicle end sensors of both vehicles simultaneously collect sensing data packets for a predetermined time each time the main collection vehicle is stationary and the auxiliary collection vehicle travels at a predetermined distance interval and stops, and when the number of stops reaches K, the auxiliary collection vehicle continues to travel and stops at a predetermined distance position, and at that time the vehicle end sensors of both vehicles simultaneously collect sensing data packets for the predetermined time, and the vehicle three-dimensional coordinate true value identification device comprises an acquisition module, a coordinate transformation matrix identification module, and a first coordinate true value identification module. The acquisition module is configured to acquire K groups of self-position information collected by the inertial sensor of the auxiliary collection vehicle during K stops, and K groups of main sensing data packets collected by the main collection vehicle, wherein K is greater than a predetermined number of times, and each group of main sensing data packets consists of sensing data with timestamps of multiple frames, and the sensing data with timestamps of each frame includes three-dimensional coordinate information of the sensing vehicle, and the sensing vehicle includes at least the auxiliary collection vehicle. The coordinate transformation matrix identification module is configured to calculate a coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle based on the self-position information of the K group and the main sensing data packets of the K group, wherein the power-on vehicle coordinate system is a vehicle coordinate system with the position of the vehicle's onboard computer at the time of power-on as the coordinate system origin. The first coordinate true value identification module is configured to calculate projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle position information collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle, and to use the projected coordinate information as the true three-dimensional coordinates of the auxiliary collection vehicle, wherein the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold.

[0014] Selectively, the coordinate transformation matrix identification module includes a first calculation submodule, a second calculation submodule, a current transformation matrix identification submodule, and a third calculation submodule. The first calculation submodule is configured to take the first group of main sensing data packets from the K group as the main sensing data packets of the current group, and to perform a calculation with the first self-position information from the first group of self-position information over the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of each frame in the current group of main sensing data packets according to the nearest neighbor method to obtain a first relative distance error, to identify the three-dimensional coordinate information of the sensing vehicle corresponding to the smallest first relative distance error as the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the current group of main sensing data packets, and to identify the first self-position information as the self-position information of the auxiliary collection vehicle corresponding to the timestamp of the first frame in the current group of main sensing data packets. The second calculation submodule is configured to obtain a second relative distance error by performing calculations on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of each frame other than the timestamp of the first frame in the main sensing data packets of the current group, and the first three-dimensional coordinate information, and to identify the three-dimensional coordinate information of the sensing vehicle corresponding to the second relative distance error that is smaller than a predetermined distance error threshold as the second three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of that frame, and to obtain a third relative distance error by performing calculations on the first group's own vehicle position information with the second three-dimensional coordinate information according to the nearest neighbor method, and to identify the own vehicle position information corresponding to the smallest third relative distance error as the own vehicle position information of the auxiliary collection vehicle corresponding to the timestamp of that frame. The current transformation matrix identification submodule is configured to calculate a transformation matrix corresponding to the main sensing data packets of the current group based on the three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of each frame, the self-position information of the auxiliary collection vehicle corresponding to the timestamp of each frame, and a predetermined general-purpose diagram optimization formula, and to set the transformation matrix as the current transformation matrix. The third calculation submodule is configured to use the main sensing data packet of the group following the main sensing data packet of the current group as the main sensing data packet of the current group, and to calculate the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the main sensing data packet of the current group based on the self-position information of the group following the self-position information of the first group and the current transformation matrix, and to return to the step of obtaining the second relative distance error by performing calculations on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of the frame and the first three-dimensional coordinate information for each timestamp of each frame in the main sensing data packet of the current group other than the timestamp of the first frame until the transformation matrix corresponding to the main sensing data packet of the final group of the main sensing data packets of the K group is obtained, and to set the transformation matrix corresponding to the main sensing data packet of the final group as the coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle.

[0015] Optionally, the first coordinate true value identification module specifically multiplies the coordinate transformation matrix from left to right by the vehicle position information collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle to obtain the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle.

[0016] As an option, the above vehicle three-dimensional coordinate true value identification device further comprises a receiving module, The receiving module calculates the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle position information collected by the inertial sensor of the auxiliary collection vehicle at the predetermined distance position, and then receives the two-dimensional marking box of the auxiliary collection vehicle manually marked in the target main sensing data packet. Two-dimensional-three-dimensional matching is performed on the two-dimensional marking box and the three-dimensional boundary box corresponding to the projected coordinate information. When the matching is successful, it is configured to trigger the projected coordinate information to be used as the true three-dimensional coordinates of the auxiliary collection vehicle. The target main sensing data packet is the main sensing data packet collected by the vehicle end sensor of the main collection vehicle when the auxiliary collection vehicle continues to travel and stops at the predetermined distance position.

[0017] Optionally, the receiving module a projection sub-module configured to project a three-dimensional boundary box corresponding to the projected coordinate information onto the image plane where the two-dimensional marking box is located to obtain a two-dimensional projected boundary box; calculate the first area of the intersection set and the second area of the union set between the two-dimensional marking box and the two-dimensional projected boundary box, calculate the division value of the first area and the second area, and when the division value is greater than a predetermined value, be configured to identify that the matching is successful, and includes a matching sub-module.

[0018] Optionally, the above vehicle true three-dimensional coordinate identification device further includes an adjustment module. The adjustment module is configured to receive an adjustment to the vehicle height in the true three-dimensional coordinates of the auxiliary collection vehicle after using the projected coordinate information as the true three-dimensional coordinates of the auxiliary collection vehicle, and obtain the adjusted true three-dimensional coordinates of the auxiliary collection vehicle.

[0019] Optionally, the above vehicle true three-dimensional coordinate identification device further includes a second coordinate true value identification module. After the second coordinate true value specifying module uses the projection coordinate information as the three-dimensional coordinate true value of the auxiliary collection vehicle, based on the projection coordinate information and the three-dimensional coordinate information of each sensing vehicle in the auxiliary sensing data packet collected by the vehicle end sensor of the auxiliary collection vehicle at the predetermined distance position, it is configured to calculate the three-dimensional coordinate true value of each sensing vehicle in the vehicle coordinate system of the main collection vehicle.

[0020] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium. A computer program is stored in the computer-readable storage medium, and when the program is executed by a processor, the vehicle three-dimensional coordinate true value specifying method according to any embodiment of the present invention is implemented.

[0021] In a fourth aspect, an embodiment of the present invention provides an electronic device. The electronic device includes one or more processors, the processor is coupled to a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the electronic device is caused to implement the vehicle three-dimensional coordinate true value specifying method according to any embodiment of the present invention.

[0022] In a fifth aspect, an embodiment of the present invention provides a vehicle. The vehicle includes the vehicle three-dimensional coordinate true value specifying device according to any embodiment of the present invention, or the electronic device according to any embodiment of the present invention.

[0023] As can be seen from the above description, the vehicle three-dimensional coordinate true value identification method, apparatus, equipment, medium, and vehicle according to the embodiment of the present invention can acquire K groups of vehicle position information collected by the inertial sensor of the auxiliary collection vehicle during K stops, and K groups of main sensing data packets collected by the main collection vehicle, where K is greater than a predetermined number, each group of main sensing data packets consists of sensing data with timestamps of multiple frames, each frame's timestamp includes the three-dimensional coordinate information of the sensing vehicle, the sensing vehicle includes at least the auxiliary collection vehicle, and the K groups of vehicle position information and K groups Based on the main sensing data packets, a coordinate transformation matrix is ​​calculated between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle. Here, the power-on vehicle coordinate system is a vehicle coordinate system with the position of the vehicle's onboard computer at the time of power-on as the coordinate system origin. Based on the coordinate transformation matrix and the vehicle's own position information collected at a predetermined distance by the auxiliary collection vehicle's inertial sensor, projected coordinate information of the auxiliary collection vehicle in the main collection vehicle's vehicle coordinate system is calculated, and the projected coordinate information is taken as the true three-dimensional coordinate value of the auxiliary collection vehicle. Here, the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold. In an embodiment of the present invention, through cooperation between the main collection vehicle and the auxiliary collection vehicle, a coordinate transformation matrix is ​​calculated between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle based on the self-position information of group K and the main sensing data packets of group K. Then, based on the coordinate transformation matrix, the self-position information of the auxiliary collection vehicle is projected onto the vehicle coordinate system of the main collection vehicle to obtain the true three-dimensional coordinates of the auxiliary collection vehicle. Since the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold, the obtained true three-dimensional coordinates of the auxiliary collection vehicle are true three-dimensional coordinates at an extremely long distance, enabling the main collection vehicle to sense the true three-dimensional coordinates of the vehicle at an extremely long distance. Of course, it is not necessary to have all of the above-mentioned advantages simultaneously in order to implement any of the products or methods of the present invention. [Effects of the Invention]

[0024] The innovative aspects of the embodiments of the present invention include the following: 1. Through coordination between the main collection vehicle and the auxiliary collection vehicle, a coordinate transformation matrix is ​​calculated between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle based on the self-position information of group K and the main sensing data packets of group K. Then, based on the coordinate transformation matrix, the self-position information of the auxiliary collection vehicle is projected onto the vehicle coordinate system of the main collection vehicle to obtain the true three-dimensional coordinates of the auxiliary collection vehicle. Since the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold, the obtained true three-dimensional coordinates of the auxiliary collection vehicle are true three-dimensional coordinates at an extremely long distance, enabling the main collection vehicle to sense the true three-dimensional coordinates of the vehicle at an extremely long distance. 2. In the embodiment of the present invention, the true three-dimensional coordinates of a vehicle at an extremely long distance can be accurately obtained simply by coordinating between the main collection vehicle and the auxiliary collection vehicle, without the need to add any sensors. 3. Based on the vehicle position information of group K, the main sensing data packets of group K, and the nearest neighbor method, it is possible to calculate a coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle. 4. By receiving adjustments for the vehicle height in the true three-dimensional coordinates of the auxiliary collection vehicle, the accuracy of the adjusted true three-dimensional coordinates of the auxiliary collection vehicle in the height direction is improved. 5. Using a coordinate transformation method, the three-dimensional coordinate information of each sensing vehicle in the auxiliary sensing data packets collected by the auxiliary collection vehicle at a predetermined distance is all converted to the vehicle coordinate system of the main collection vehicle, and the true three-dimensional coordinate values ​​of the three-dimensional coordinate information of each sensing vehicle detected by the auxiliary collection vehicle at an extremely long distance are obtained in the vehicle coordinate system of the main collection vehicle. To more clearly illustrate the embodiments of the present invention or the technical concepts in the prior art, the following is a brief introduction to the drawings necessary for use in the embodiments or the prior art. Clearly, the drawings described below represent only a few embodiments of the present invention. Those skilled in the art can obtain other drawings from these without expending the necessary work to demonstrate inventiveness. [Brief explanation of the drawing]

[0025] [Figure 1] This is a schematic flowchart of a method for determining the true values ​​of three-dimensional vehicle coordinates according to an embodiment of the present invention. [Figure 2]This is a schematic diagram illustrating how the vehicle-end sensors of the main collection vehicle and the vehicle-end sensors of the auxiliary collection vehicle collect sensing data packets according to an embodiment of the present invention. In Figure 2, 1 is the main collection vehicle, 2 is the auxiliary collection vehicle, 3 is another vehicle, and h is a predetermined distance interval. [Figure 3] This is a schematic diagram of the structure of a vehicle three-dimensional coordinate true value determination device according to an embodiment of the present invention. [Figure 4] This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. [Figure 5] This is a schematic diagram of the structure of a vehicle according to an embodiment of the present invention. [Modes for carrying out the invention]

[0026] The following describes the technical concepts in embodiments of the present invention clearly and completely, with reference to the drawings of the embodiments. Clearly, the embodiments described are only a selection of embodiments of the present invention, not all embodiments. All other embodiments made by those skilled in the art based on the embodiments of the present invention without expending work worthy of inventive step are all within the scope of the protection of the present invention.

[0027] It should be noted that any term "includes," "equips," or any variation thereof in the embodiments and drawings of the present invention is intended to cover non-exclusive inclusion. For example, a series of steps or means of a process, method, system, product, or apparatus included may not be limited to the listed steps or means, but may preferably include steps or means not listed, or other steps or means specific to these processes, methods, products, or apparatus.

[0028] Embodiments of the present invention provide a method, apparatus, equipment, medium, and vehicle for determining the true three-dimensional coordinates of a vehicle, enabling the acquisition of the true three-dimensional coordinates of a vehicle at extremely long distances. Embodiments of the present invention will be described in detail below.

[0029] Figure 1 is a schematic flowchart of a method for determining the true values ​​of three-dimensional vehicle coordinates according to an embodiment of the present invention. This method is applied to electronic devices.

[0030] Figure 2 is a schematic diagram illustrating how the vehicle-end sensors of the main collection vehicle 1 and the auxiliary collection vehicle 2 collect sensing data packets according to an embodiment of the present invention. Referring to Figure 2, in the initial state, both the main collection vehicle 1 and the auxiliary collection vehicle 2 are located at the initial point, and the vehicle-end sensors of both vehicles are pointing forward, that is, in the direction of the arrows in Figure 2. When the auxiliary collection vehicle 2 is traveling forward, that is, traveling along the direction of the arrows, the main collection vehicle 1 is stationary.

[0031] Each time the auxiliary collection vehicle 2 travels a predetermined distance interval h and stops, the vehicle-end sensors of both vehicles simultaneously collect sensing data packets for a predetermined time. When the number of stops reaches K, the auxiliary collection vehicle 2 continues traveling and stops at a predetermined distance point A. At that time, the vehicle-end sensors of both vehicles simultaneously collect sensing data packets for a predetermined time, and when the auxiliary collection vehicle 2 stops at point A, there is another vehicle 3 passing point A, and the main collection vehicle 1 is not in P range while stationary.

[0032] Based on this, the above method specifically includes the following steps S110 to S130.

[0033] In S110, the auxiliary collection vehicle's inertial sensor acquires K groups of its own vehicle position information collected during K stops, and the main sensing data packets of the K groups collected by the main collection vehicle are acquired. If K is greater than a predetermined number of times, and the main sensing data packets of each group consist of sensing data with timestamps of multiple frames, and the sensing data with timestamps of each frame includes the three-dimensional coordinate information of the sensing vehicle, the sensing vehicle includes at least the auxiliary collection vehicle.

[0034] While the auxiliary collection vehicle 2 is in motion, its own inertial sensors collect its own position information, egopose, in real time. Since the auxiliary collection vehicle 2 stops every time it travels a predetermined distance interval h, and the sensors at the end of the auxiliary collection vehicle 2 collect sensing data packets for a predetermined time, the inertial sensors of the auxiliary collection vehicle 2 can collect one group of its own position information corresponding to a predetermined time each time it stops. Thus, after K stops, K groups of its own position information are acquired.

[0035] When the auxiliary collection vehicle 2 stops after traveling a predetermined distance interval h, the vehicle-end sensors of both vehicles simultaneously collect sensing data packets for a predetermined time. Therefore, although the main collection vehicle 1 remains stationary, it acquires K groups of main sensing data packets when it stops K times. Here, each group of main sensing data packets consists of sensing data with timestamps of multiple frames, and the sensing data with timestamps of each frame includes the three-dimensional coordinate information of the sensing vehicle. K is greater than a predetermined number of times, and as an example, the predetermined number of times is 3.

[0036] As auxiliary collection vehicle 2 moves forward while main collection vehicle 1 remains stationary, the vehicle-end sensors of main collection vehicle 1 can continuously detect auxiliary collection vehicle 2. Therefore, the vehicles detected by main collection vehicle 1 include at least the auxiliary collection vehicle.

[0037] To obtain the true three-dimensional coordinates of a vehicle at a very long distance, the electronic equipment acquires K groups of vehicle position information collected by the auxiliary collection vehicle's inertial sensors during K stops, and K groups of main sensing data packets collected by the main collection vehicle.

[0038] Here, the main collection vehicle 1 is the vehicle that should acquire the true three-dimensional coordinates of vehicles at extremely long distances, and the auxiliary collection vehicle 2 is the vehicle that assists the main collection vehicle 1 in acquiring the true three-dimensional coordinates of vehicles at extremely long distances.

[0039] In S120, a coordinate transformation matrix is ​​calculated between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle based on the self-position information of group K and the main sensing data packets of group K. The power-on vehicle coordinate system is a vehicle coordinate system whose origin is the position of the vehicle's onboard computer when it is powered on.

[0040] After acquiring the vehicle position information and main sensing data packets of group K, the electronic device needs to calculate a coordinate transformation matrix between the power-on vehicle coordinate system of main collection vehicle 1 and the power-on vehicle coordinate system of auxiliary collection vehicle 2 based on the vehicle position information and main sensing data packets of group K. The power-on vehicle coordinate system is a vehicle coordinate system with the position of the vehicle's onboard computer at the time of power-on as the coordinate system origin.

[0041] Specifically, step S120 is, The first group of main sensing data packets from the K group of main sensing data packets is taken as the main sensing data packets of the current group, and a first relative distance error is obtained by performing a calculation with the first self-position information from the first group of self-position information over the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of each frame in the main sensing data packets of the current group according to the nearest neighbor method, the three-dimensional coordinate information of the sensing vehicle corresponding to the smallest first relative distance error is identified as the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the main sensing data packets of the current group, and the first self-position information is identified as the self-position information of the auxiliary collection vehicle corresponding to the timestamp of the first frame in the main sensing data packets of the current group, For the timestamps of each frame other than the timestamp of the first frame in the current group of main sensing data packets, a calculation is performed on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of the frame and the first three-dimensional coordinate information to obtain a second relative distance error, the three-dimensional coordinate information of the sensing vehicle corresponding to a second relative distance error smaller than a predetermined distance error threshold is identified as the second three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of that frame, a calculation is performed on the first group of vehicle position information with the second three-dimensional coordinate information according to the nearest neighbor method to obtain a third relative distance error, and the vehicle position information corresponding to the smallest third relative distance error is identified as the vehicle position information of the auxiliary collection vehicle corresponding to the timestamp of that frame, The process involves calculating a transformation matrix corresponding to the main sensing data packets of the current group based on the three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of each frame, the self-position information of the auxiliary collection vehicle corresponding to the timestamp of each frame, and a predetermined general-purpose diagram optimization formula, and setting the transformation matrix as the current transformation matrix. The process may include the step of setting the main sensing data packet of the group following the main sensing data packet of the current group as the main sensing data packet of the current group, calculating the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the main sensing data packet of the current group based on the self-position information of the group following the self-position information of the first group and the current transformation matrix, and returning to the step of obtaining the second relative distance error by performing calculations on the three-dimensional coordinate information of the sensing vehicle and the first three-dimensional coordinate information corresponding to the timestamp of the frame for each frame in the main sensing data packet of the current group other than the timestamp of the first frame until the transformation matrix corresponding to the main sensing data packet of the final group of main sensing data packets of the K group is obtained, and setting the transformation matrix corresponding to the main sensing data packet of the final group as the coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle.

[0042] When the main collection vehicle 1 collects the first group of main sensing data packets, it is relatively close to the auxiliary collection vehicle 2. In order to obtain the three-dimensional coordinate information of the auxiliary collection vehicle 2 in the main collection vehicle 1 at that time, the first group of main sensing data packets out of the K group of main sensing data packets is used as the current group of main sensing data packets, and a calculation is performed using the nearest neighbor method to obtain the first relative distance error by comparing the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of each frame in the current group of main sensing data packets with the first vehicle position information from the first group of vehicle position information. The three-dimensional coordinate information of the sensing vehicle corresponding to the smallest first relative distance error is identified as the first three-dimensional coordinate information of the auxiliary collection vehicle 2 collected by the main collection vehicle 1 at the timestamp of the first frame in the current group of main sensing data packets, where the first group of vehicle position information is the first group of vehicle position information out of the K group of vehicle position information.

[0043] In other words, the three-dimensional coordinate information corresponding to the smallest first relative distance error is the three-dimensional coordinate information collected by the auxiliary collection vehicle 2 at the timestamp of the first frame in the main collection vehicle 1. Subsequently, the first self-position information is identified as the self-position information of the auxiliary collection vehicle 2 corresponding to the timestamp of the first frame in the main sensing data packet of the current group.

[0044] Currently, only the three-dimensional coordinate information of the auxiliary collection vehicle 2 at the timestamp of the first frame in the first group of main sensing data packets has been obtained. In order to obtain the three-dimensional coordinate information of the auxiliary collection vehicle 2 at other timestamps, for each frame other than the timestamp of the first frame in the current group of main sensing data packets, it is necessary to calculate the second relative distance error by comparing the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of that frame with the first three-dimensional coordinate information, and to identify the three-dimensional coordinate information of the sensing vehicle corresponding to the second relative distance error smaller than a predetermined distance error threshold as the second three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of that frame. In this way, the three-dimensional coordinate information of the auxiliary collection vehicle 2 at other timestamps in the first group of main sensing data packets has been obtained. For example, the predetermined distance error threshold may be 1 m.

[0045] Subsequently, calculations were performed using the nearest neighbor method to obtain the third relative distance error by comparing the first group of vehicle position information with the second three-dimensional coordinate information. The vehicle position information corresponding to the smallest third relative distance error was identified as the vehicle position information of the auxiliary collection vehicle 2 corresponding to the timestamp of that frame. Finally, the three-dimensional coordinate information of the auxiliary collection vehicle 2 collected by the main collection vehicle 1 at the timestamp of each frame and the vehicle position information of the auxiliary collection vehicle 2 corresponding to the timestamp of each frame were obtained.

[0046] After the main collection vehicle 1 has acquired the three-dimensional coordinate information of the auxiliary collection vehicle 2 collected at the timestamp of each frame, and the self-position information of the auxiliary collection vehicle 2 corresponding to the timestamp of each frame, a transformation matrix corresponding to the main sensing data packet of the current group is calculated based on the three-dimensional coordinate information of the auxiliary collection vehicle 2 collected at the timestamp of each frame by the main collection vehicle 1, the self-position information of the auxiliary collection vehicle 2 corresponding to the timestamp of each frame, and a predetermined general-purpose diagram optimization formula. This transformation matrix is ​​set as the current transformation matrix, and as an example, the current transformation matrix is ​​a 4x4 transformation matrix.

[0047] In this way, the processing of the first group of main sensing data packets was completed, and a current transformation matrix was obtained that represents the transformation relationship between the three-dimensional coordinate information of the auxiliary collection vehicle 2 collected by the main collection vehicle 1 and the self-position information of the auxiliary collection vehicle 2.

[0048] The three-dimensional coordinate information of auxiliary collection vehicle 2 in the vehicle coordinate system of main collection vehicle 1 and the self-position information of auxiliary collection vehicle 2 satisfy the following equation.

[0049]

number

[0050] However, B is the vehicle coordinate system of the auxiliary collection vehicle, A is the vehicle coordinate system of the main collection vehicle, argmin is the smallest numerical value that satisfies the equation, i is the count point, b is vehicle B, exp is the exponential map, and ||||² is the 2-norm.

[0051] In the following, we process the main sensing data packets of the K group, excluding the main sensing data packets of the 1st group. We then take the main sensing data packet of the group following the current group as the current group's main sensing data packet. When the main collection vehicle 1 is collecting the 2nd group's main sensing data packets, there is an error between the 2nd group's self-position information and the 3D coordinate information of the 2nd group's self-position information within the main collection vehicle 1 because the distance to the auxiliary collection vehicle 2 is relatively far. Therefore, it is necessary to use the above-calculated current transformation matrix to substitute the 2nd group's self-position information and obtain the 3D coordinate information of the 2nd group's self-position information within the main collection vehicle 1 at that time.

[0052] Specifically, based on the self-position information of the next group of self-position information of the first group and the current transformation matrix, the first three-dimensional coordinate information of the auxiliary collection vehicle 2 collected by the main collection vehicle 1 at the timestamp of the first frame in the main sensing data packet of the current group is calculated. Furthermore, until the transformation matrix corresponding to the main sensing data packet of the final group of main sensing data packets among the K group of main sensing data packets is obtained, the process returns to the step of obtaining the second relative distance error by performing calculations on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of the frame and the first three-dimensional coordinate information for each frame other than the timestamp of the first frame in the main sensing data packet of the current group, and the transformation matrix corresponding to the main sensing data packet of the final group is set as the coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle 1 and the power-on vehicle coordinate system of the auxiliary collection vehicle 2.

[0053] This makes it possible to calculate a coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle, based on the self-position information of group K, the main sensing data packets of group K, and the nearest neighbor method.

[0054] In S130, based on the coordinate transformation matrix and the vehicle position information collected at a predetermined distance by the auxiliary collection vehicle's inertial sensor, the projected coordinate information of the auxiliary collection vehicle in the main collection vehicle's vehicle coordinate system is calculated. The projected coordinate information is used as the true three-dimensional coordinate value of the auxiliary collection vehicle, and the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold.

[0055] When the auxiliary collection vehicle 2 is traveling forward, the main collection vehicle 1 remains stationary. Therefore, the main collection vehicle 1's vehicle coordinate system becomes the power-on vehicle coordinate system. Consequently, the coordinate transformation matrix can be considered as the transformation matrix of the auxiliary collection vehicle 2's power-on vehicle coordinate system to the main collection vehicle 1's power-on vehicle coordinate system. Thus, at a predetermined distance, the three-dimensional coordinate information of the auxiliary collection vehicle 2 within the main collection vehicle 1 becomes the coordinate information of the auxiliary collection vehicle 2 in the main collection vehicle 1's power-on vehicle coordinate system.

[0056] Therefore, after the coordinate transformation matrix is ​​obtained, the projected coordinate information of the auxiliary collection vehicle 2 in the vehicle coordinate system of the main collection vehicle 1 can be obtained based on the coordinate transformation matrix and the vehicle position information collected at point A at a predetermined distance by the inertial sensor of the auxiliary collection vehicle 2, and the projected coordinate information is used as the true three-dimensional coordinate value of the auxiliary collection vehicle 2. Here, the distance between the predetermined distance point and the main collection vehicle 1 is greater than a predetermined distance threshold. As an example, the predetermined distance threshold is 300m.

[0057] If the distance between the predetermined distance location and the main collection vehicle 1 is greater than the predetermined distance threshold, it means that the predetermined distance location is far away from the main collection vehicle 1. Therefore, the acquired three-dimensional coordinate true value of the auxiliary collection vehicle 2 is the three-dimensional coordinate true value at an extremely long distance.

[0058] Specifically, calculating the projected coordinate information of the auxiliary collection vehicle 2 in the vehicle coordinate system of the main collection vehicle 1 based on the coordinate transformation matrix and the vehicle position information collected at a predetermined distance by the inertial sensor of the auxiliary collection vehicle 2 is: The process may also include multiplying the coordinate transformation matrix by the self-position information of the auxiliary collection vehicle 2, collected at a predetermined distance by the inertial sensor of the auxiliary collection vehicle 2, from the left, to obtain the projected coordinate information of the auxiliary collection vehicle 2 in the vehicle coordinate system of the main collection vehicle 1.

[0059] As can be seen from the above description, in the embodiment of the present invention, it is possible to acquire K groups of self-position information collected by the inertial sensor of the auxiliary collection vehicle during K stops, and K groups of main sensing data packets collected by the main collection vehicle, where K is greater than a predetermined number of times, each group of main sensing data packets consists of sensing data with timestamps of multiple frames, each frame's timestamp of sensing data includes three-dimensional coordinate information of the sensing vehicle, the sensing vehicle includes at least the auxiliary collection vehicle, and based on the K groups of self-position information and the K groups of main sensing data packets... Next, a coordinate transformation matrix is ​​calculated between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle. Here, the power-on vehicle coordinate system is a vehicle coordinate system with the position of the vehicle's onboard computer at the time of power-on as the coordinate system origin. Based on the coordinate transformation matrix and the vehicle's own position information collected at a predetermined distance by the auxiliary collection vehicle's inertial sensor, projected coordinate information of the auxiliary collection vehicle in the main collection vehicle's vehicle coordinate system is calculated, and the projected coordinate information is taken as the true three-dimensional coordinate value of the auxiliary collection vehicle. Here, the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold. In an embodiment of the present invention, through cooperation between the main collection vehicle and the auxiliary collection vehicle, a coordinate transformation matrix is ​​calculated between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle based on the self-position information of group K and the main sensing data packets of group K. Then, based on the coordinate transformation matrix, the self-position information of the auxiliary collection vehicle is projected onto the vehicle coordinate system of the main collection vehicle to obtain the true three-dimensional coordinates of the auxiliary collection vehicle. Since the distance between the predetermined distance position and the main collection vehicle 1 is greater than a predetermined distance threshold, the obtained true three-dimensional coordinates of the auxiliary collection vehicle 2 are true three-dimensional coordinates at an extremely long distance, and the main collection vehicle realizes sensing the true three-dimensional coordinates of a vehicle at an extremely long distance.

[0060] Furthermore, in the embodiments of the present invention, the true three-dimensional coordinates of vehicles at extremely long distances can be accurately obtained simply by coordinating between the main collection vehicle and the auxiliary collection vehicle, without the need to add any additional sensors.

[0061] In one implementation method, after step S130, the method for determining the true three-dimensional coordinates of the vehicle may further include the step of receiving an adjustment for the vehicle height in the true three-dimensional coordinates of the auxiliary collection vehicle and obtaining the true three-dimensional coordinates of the auxiliary collection vehicle after the adjustment.

[0062] Because the road surface does not have a complete lack of height, the acquired three-dimensional coordinate values ​​of the auxiliary collection vehicle 2 have a certain offset in the height direction, and the height needs to be manually adjusted. The electronic equipment receives the adjustment for the vehicle height in the three-dimensional coordinate values ​​of the auxiliary collection vehicle 2 and obtains the adjusted three-dimensional coordinate values ​​of the auxiliary collection vehicle 2.

[0063] This allows for adjustments to be made to the vehicle height within the true three-dimensional coordinates of the auxiliary collection vehicle, thereby improving the accuracy of the adjusted true three-dimensional coordinates of the auxiliary collection vehicle in the height direction.

[0064] In another implementation, after step S130, the method for determining the true three-dimensional coordinates of the vehicles may further include the step of calculating the true three-dimensional coordinates of each sensing vehicle in the vehicle coordinate system of the main collection vehicle, based on projected coordinate information and three-dimensional coordinate information of each sensing vehicle in auxiliary sensing data packets collected at a predetermined distance position by the vehicle end sensors of the auxiliary collection vehicle.

[0065] As described above, if the projected coordinate information is taken as the true three-dimensional coordinate of the auxiliary collection vehicle 2, then the true three-dimensional coordinate of the auxiliary collection vehicle 2, which was sensed at a very long distance by the main collection vehicle 1, has only been obtained. Furthermore, the three-dimensional coordinate information of each sensing vehicle in the auxiliary sensing data packets collected at a predetermined distance by the auxiliary collection vehicle 2 may all be converted to the vehicle coordinate system of the main collection vehicle 1. That is, the true three-dimensional coordinate of each sensing vehicle in the vehicle coordinate system of the main collection vehicle is calculated based on the projected coordinate information and the three-dimensional coordinate information of each sensing vehicle in the auxiliary sensing data packets collected at a predetermined distance by the vehicle end sensor of the auxiliary collection vehicle.

[0066] Specifically, calculating the true three-dimensional coordinates of each sensing vehicle in the vehicle coordinate system of the main collection vehicle based on projected coordinate information and the three-dimensional coordinate information of each sensing vehicle in the auxiliary sensing data packets collected at a predetermined distance by the vehicle-end sensors of the auxiliary collection vehicle is: This may also include multiplying the three-dimensional coordinate information of each sensing vehicle in the auxiliary sensing data packets collected at a predetermined distance by the vehicle-end sensors of the auxiliary collection vehicle by projected coordinate information from the left to obtain the true three-dimensional coordinate values ​​of each sensing vehicle in the vehicle coordinate system of the main collection vehicle.

[0067] In this way, using the coordinate transformation method, the three-dimensional coordinate information of each sensing vehicle in the auxiliary sensing data packets collected by the auxiliary collection vehicle 2 at a predetermined distance is all converted to the vehicle coordinate system of the main collection vehicle 1, and the true three-dimensional coordinate values ​​of the three-dimensional coordinate information of each sensing vehicle sensed by the auxiliary collection vehicle 2 at an extremely long distance are obtained in the vehicle coordinate system of the main collection vehicle 1.

[0068] In another implementation method, after obtaining the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle's own position information collected at a predetermined distance by the auxiliary collection vehicle's inertial sensor, the above-mentioned method for determining the true value of the vehicle's three-dimensional coordinates is as follows: The process may further include receiving a two-dimensional marking box of an auxiliary collection vehicle that has been manually marked on a target main sensing data packet, performing a two-dimensional-to-three-dimensional matching between the two-dimensional marking box and a three-dimensional boundary box corresponding to the projected coordinate information, and, if the matching is successful, performing a step of setting the projected coordinate information to the true three-dimensional coordinates of the auxiliary collection vehicle, where the target main sensing data packet is a main sensing data packet collected by the vehicle-end sensor of the main collection vehicle when the auxiliary collection vehicle continues to drive and stops at a predetermined distance.

[0069] Since the acquired projected coordinate information is not necessarily accurate, it is necessary to determine whether or not the projected coordinate information is accurate. Specifically, the two-dimensional marking box of the auxiliary collection vehicle 2, which has been manually marked on the target main sensing data packet, is received, and a two-dimensional-to-three-dimensional matching is performed between the two-dimensional marking box and the three-dimensional boundary box corresponding to the projected coordinate information. If the matching is successful, it means that the acquired projected coordinate information is accurate. At that time, the step of setting the projected coordinate information to the true three-dimensional coordinates of the auxiliary collection vehicle is performed. Here, the target main sensing data packet is the main sensing data packet collected by the vehicle-end sensor of the main collection vehicle 1 when the auxiliary collection vehicle 2 continues to travel and stops at a predetermined distance position A.

[0070] Specifically, performing a two-dimensional-to-three-dimensional matching between a two-dimensional marking box and a three-dimensional boundary box corresponding to projected coordinate information is: This involves projecting a three-dimensional bounding box corresponding to the projected coordinate information onto the image plane where the two-dimensional marking box is located to obtain a two-dimensional projected bounding box, and The method may also include calculating the first area of ​​the intersection and the second area of ​​the union between a two-dimensional marking box and a two-dimensional projection boundary box, calculating the division value between the first area and the second area, and determining that the matching was successful when the division value is greater than a predetermined value.

[0071] The method for performing two-dimensional-to-three-dimensional matching between a two-dimensional marking box and a three-dimensional bounding box corresponding to projected coordinate information involves first reducing the three-dimensional object to two dimensions, and then matching it with the two-dimensional marking box. Specifically, the three-dimensional bounding box corresponding to the projected coordinate information is projected onto the image plane where the two-dimensional marking box is located, and the two-dimensional projected bounding box is obtained. The first area of ​​the intersection and the second area of ​​the union between the two-dimensional marking box and the two-dimensional projected bounding box are calculated, and the division value of the first area and the second area is calculated. If the division value is greater than a predetermined value, it means that the two are similar, and the matching is identified as successful.

[0072] In this way, the two-dimensional-to-three-dimensional matching method determines whether a two-dimensional marking box matches the three-dimensional bounding box corresponding to the projected coordinate information.

[0073] Figure 3 is a schematic diagram of the structure of a vehicle three-dimensional coordinate true value identification device according to an embodiment of the present invention. Referring to Figure 3, in the initial state, both the main collection vehicle and the auxiliary collection vehicle are located at the initial point, and the vehicle end sensors of both the main collection vehicle and the auxiliary collection vehicle are facing forward, and when the auxiliary collection vehicle is traveling forward, the main collection vehicle comes to a standstill, and each time the auxiliary collection vehicle travels at a predetermined distance interval, the vehicle end sensors of both vehicles simultaneously collect sensing data packets for a predetermined time, and when the number of stops reaches K, the auxiliary collection vehicle continues to travel and stops at a predetermined distance position, at which time the vehicle end sensors of both vehicles simultaneously collect sensing data packets for the predetermined time, and the vehicle three-dimensional coordinate true value identification device may include an acquisition module 310, a coordinate transformation matrix identification module 320, and a first coordinate true value identification module 330.

[0074] The acquisition module 310 is configured to acquire K groups of self-position information collected by the inertial sensor of the auxiliary collection vehicle during K stops, and K groups of main sensing data packets collected by the main collection vehicle, where K is greater than a predetermined number of times, and each group of main sensing data packets consists of sensing data with timestamps of multiple frames, and the sensing data with timestamps of each frame includes three-dimensional coordinate information of the sensing vehicle, and the sensing vehicle includes at least the auxiliary collection vehicle.

[0075] The coordinate transformation matrix identification module 320 is configured to calculate a coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle based on the self-position information of the K group and the main sensing data packets of the K group, wherein the power-on vehicle coordinate system is a vehicle coordinate system whose origin is the position of the vehicle's onboard computer when it is powered on.

[0076] The first coordinate true value identification module 330 is configured to calculate projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle position information collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle, and to use the projected coordinate information as the true three-dimensional coordinates of the auxiliary collection vehicle, wherein the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold.

[0077] The apparatus according to an embodiment of the present invention is capable of acquiring K groups of self-position information collected by the inertial sensor of an auxiliary collection vehicle during K stops, and K groups of main sensing data packets collected by the main collection vehicle, where K is greater than a predetermined number of times, each group of main sensing data packets consists of sensing data with timestamps of multiple frames, the sensing data with timestamps of each frame includes three-dimensional coordinate information of the sensing vehicle, the sensing vehicle includes at least an auxiliary collection vehicle, and the main sensing data packets are acquired based on the self-position information of the K groups and the main sensing data packets of the K groups. A coordinate transformation matrix is ​​calculated between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle. Here, the power-on vehicle coordinate system is a vehicle coordinate system with the position of the vehicle's onboard computer at the time of power-on as the coordinate system origin. Based on the coordinate transformation matrix and the vehicle's own position information collected at a predetermined distance by the auxiliary collection vehicle's inertial sensor, projected coordinate information of the auxiliary collection vehicle in the main collection vehicle's vehicle coordinate system is calculated, and the projected coordinate information is taken as the true three-dimensional coordinate value of the auxiliary collection vehicle. Here, the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold. In an embodiment of the present invention, through cooperation between the main collection vehicle and the auxiliary collection vehicle, a coordinate transformation matrix is ​​calculated between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle based on the self-position information of group K and the main sensing data packets of group K. Then, based on the coordinate transformation matrix, the self-position information of the auxiliary collection vehicle is projected onto the vehicle coordinate system of the main collection vehicle to obtain the true three-dimensional coordinates of the auxiliary collection vehicle. Since the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold, the obtained true three-dimensional coordinates of the auxiliary collection vehicle are true three-dimensional coordinates at an extremely long distance, enabling the main collection vehicle to sense the true three-dimensional coordinates of a vehicle at an extremely long distance.

[0078] In one implementation method, the coordinate transformation matrix identification module 320 may include a first calculation submodule, a second calculation submodule, a current transformation matrix identification submodule, and a third calculation submodule.

[0079] The first calculation submodule is configured to take the first group of main sensing data packets from the K group as the main sensing data packets of the current group, and to perform a calculation with the first self-position information from the first group of self-position information over the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of each frame in the current group of main sensing data packets according to the nearest neighbor method to obtain a first relative distance error, to identify the three-dimensional coordinate information of the sensing vehicle corresponding to the smallest first relative distance error as the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the current group of main sensing data packets, and to identify the first self-position information as the self-position information of the auxiliary collection vehicle corresponding to the timestamp of the first frame in the current group of main sensing data packets.

[0080] The second calculation submodule is configured to obtain a second relative distance error by performing calculations on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of the frame and the first three-dimensional coordinate information for each frame other than the timestamp of the first frame in the main sensing data packets of the current group, and to identify the three-dimensional coordinate information of the sensing vehicle corresponding to the second relative distance error that is smaller than a predetermined distance error threshold as the second three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of that frame, and to obtain a third relative distance error by performing calculations on the first group's own vehicle position information with the second three-dimensional coordinate information according to the nearest neighbor method, and to identify the own vehicle position information corresponding to the smallest third relative distance error as the own vehicle position information of the auxiliary collection vehicle corresponding to the timestamp of that frame.

[0081] The current transformation matrix identification submodule is configured to calculate a transformation matrix corresponding to the main sensing data packets of the current group based on the three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of each frame, the self-position information of the auxiliary collection vehicle corresponding to the timestamp of each frame, and a predetermined general-purpose diagram optimization formula, and to set the transformation matrix as the current transformation matrix.

[0082] The third calculation submodule is configured to use the main sensing data packet of the group following the main sensing data packet of the current group as the main sensing data packet of the current group, and calculate the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the main sensing data packet of the current group based on the self-position information of the group following the self-position information of the first group and the current transformation matrix, and to return to the step of obtaining the second relative distance error by performing calculations on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of the frame and the first three-dimensional coordinate information for each frame other than the timestamp of the first frame in the main sensing data packet of the current group until the transformation matrix corresponding to the main sensing data packet of the final group among the main sensing data packets of the K group is obtained, and to set the transformation matrix corresponding to the main sensing data packet of the final group as the coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle.

[0083] In terms of selectability, the first coordinate true value identification module 330 specifically, The coordinate transformation matrix may be multiplied from the left by the self-position information of the auxiliary collection vehicle collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle to obtain the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle.

[0084] Optionally, the above vehicle three-dimensional coordinate true value identification device further comprises a receiving module. The receiving module calculates the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle position information collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle. It then receives the two-dimensional marking box of the auxiliary collection vehicle that has been manually marked on the target main sensing data packet, performs two-dimensional-to-three-dimensional matching between the two-dimensional marking box and the three-dimensional boundary box corresponding to the projected coordinate information, and is configured to trigger the system to set the projected coordinate information as the true three-dimensional coordinate value of the auxiliary collection vehicle when the matching is successful. The target main sensing data packet is the main sensing data packet collected by the vehicle end sensor of the main collection vehicle when the auxiliary collection vehicle continues to drive and stops at the predetermined distance position.

[0085] Optionally, the receiving module may include a projection submodule and a matching submodule. The projection submodule is configured to obtain a two-dimensional projection boundary box by projecting a three-dimensional boundary box corresponding to the projection coordinate information onto the image plane where the two-dimensional marking box is located. The matching submodule is configured to calculate the first area of ​​the intersection and the second area of ​​the union between the two-dimensional marking box and the two-dimensional projection boundary box, calculate the division value of the first area and the second area, and determine that the matching was successful when the division value is greater than a predetermined value.

[0086] Optionally, the above-mentioned vehicle three-dimensional coordinate true value determination device may further include an adjustment module. The adjustment module is configured to convert the projected coordinate information into the true three-dimensional coordinates of the auxiliary collection vehicle, then receive adjustments for the vehicle height in the true three-dimensional coordinates of the auxiliary collection vehicle, and obtain the true three-dimensional coordinates of the auxiliary collection vehicle after adjustment.

[0087] Optionally, the above-mentioned vehicle three-dimensional coordinate true value identification device may further comprise a second coordinate true value identification module. The second coordinate true value identification module is configured to determine the true three-dimensional coordinates of each sensing vehicle in the vehicle coordinate system of the main collection vehicle, after the projected coordinate information has been converted to the true three-dimensional coordinates of the auxiliary collection vehicle, and then calculate the true three-dimensional coordinates of each sensing vehicle in the vehicle coordinate system of the main collection vehicle based on the projected coordinate information and the three-dimensional coordinate information of each sensing vehicle in the auxiliary sensing data packets collected at a predetermined distance position by the vehicle end sensor of the auxiliary collection vehicle.

[0088] The above apparatus embodiment corresponds to the method embodiment and has the same technical effects as the method embodiment. For details, please refer to the method embodiment. The apparatus embodiment was obtained based on the method embodiment, and a detailed explanation can be found in the section on the method embodiment, so it will not be repeated here.

[0089] Figure 4 is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. As shown in Figure 4, the electronic device comprises one or more processors 410. The processor 410 is coupled to a storage device 420, which stores one or more programs. When one or more of the aforementioned programs are executed by the one or more processors 410, the electronic device is made to perform a vehicle three-dimensional coordinate true value determination method according to any embodiment of the present invention.

[0090] Based on the above embodiments, another embodiment of the present invention provides a vehicle. The vehicle is equipped with a vehicle three-dimensional coordinate true value identification device according to any embodiment of the present invention, or electronic equipment according to any embodiment of the present invention.

[0091] Figure 5 is a schematic diagram of a vehicle according to an embodiment of the present invention. As shown in Figure 5, the vehicle is equipped with a speed sensor 51, an ECU (Electronic Control Unit) 52, a GPS (Global Positioning System) positioning device 53, and a T-Box (Telematics Box) 54. The speed sensor 51 measures the vehicle speed and uses the vehicle speed as the empirical speed for model training. The GPS positioning device 53 acquires the vehicle's current geographical position. The T-Box 54 may communicate with a server as a gateway. The ECU 52 may execute the above-described method for determining the true values ​​of the vehicle's three-dimensional coordinates.

[0092] The vehicle may also be equipped with a V2X (Vehicle-to-Everything) module 55, a radar 56, and a camera 57. The V2X module 55 communicates with other vehicles, roadside equipment, etc. The radar 56 or camera 57 senses road environment information in front and / or other directions and acquires original point cloud data. The radar 56 and / or camera 57 may be located at the front and / or rear of the vehicle.

[0093] Based on the above embodiment of the method, another embodiment of the present invention provides a computer-readable storage medium. A computer program is stored in the computer-readable storage medium, and when the program is executed by a processor, the vehicle three-dimensional coordinate true value determination method according to any embodiment of the present invention is performed.

[0094] As those skilled in the art will understand, the drawings are merely schematic diagrams of one embodiment, and the modules or flows in the drawings are not necessarily essential for carrying out the present invention.

[0095] As those skilled in the art will understand, the modules in the apparatus in the embodiment may be distributed in the apparatus of the embodiment in accordance with the description of the embodiment, or they may be located in one or more different apparatuses as appropriate. The modules of the above embodiment may be integrated into a single module, or they may be further divided into multiple submodules.

[0096] Finally, it should be noted that the above embodiments are merely for illustrating the technical aspects of the present invention and do not constitute a limitation thereon. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art will understand that the technical aspects described in the above embodiments are still modifiable, or that some of their technical features can be substituted with equivalents, and furthermore, such modifications or substitutions do not cause the gist of the corresponding technical aspects to deviate from the spirit and scope of the technical aspects of each embodiment of the present invention.

Claims

1. A method for determining the true values ​​of a vehicle's three-dimensional coordinates, In the initial state, both the main collection vehicle and the auxiliary collection vehicle are located at the initial point, and the vehicle end sensors of both the main collection vehicle and the auxiliary collection vehicle are facing forward, and the auxiliary collection vehicle is traveling forward. When the main collection vehicle comes to a standstill and the auxiliary collection vehicle stops each time it travels at a predetermined distance interval, the vehicle end sensors of both vehicles simultaneously collect sensing data packets for a predetermined time. When the number of stops reaches K, the auxiliary collection vehicle continues to travel and stops at a predetermined distance position, at which point the vehicle end sensors of both vehicles simultaneously collect sensing data packets for the predetermined time. The method for determining the true value of the vehicle's three-dimensional coordinates is as follows: A step of acquiring K groups of self-position information collected by the inertial sensor of the auxiliary collection vehicle during K stops, and main sensing data packets of K groups collected by the main collection vehicle, wherein K is greater than a predetermined value, each group's main sensing data packet consists of sensing data with timestamps of multiple frames, the sensing data with timestamps of each frame includes three-dimensional coordinate information of the sensing vehicle, and the sensing vehicle includes at least the auxiliary collection vehicle. A step of calculating a coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle, based on the self-position information of the K group and the main sensing data packets of the K group, wherein the power-on vehicle coordinate system is a vehicle coordinate system whose origin is the position of the vehicle's onboard computer when it is powered on; A method for determining the true three-dimensional coordinates of a vehicle, comprising the steps of: calculating projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle position information collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle, and using the projected coordinate information as the true three-dimensional coordinates of the auxiliary collection vehicle, wherein the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold.

2. The step of calculating a coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle, based on the self-position information of the K group and the main sensing data packets of the K group, is: The first group of main sensing data packets from the K group of main sensing data packets is taken as the main sensing data packets of the current group, and a calculation is performed using the nearest neighbor method with respect to the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of each frame in the current group of main sensing data packets to obtain a first relative distance error, the three-dimensional coordinate information of the sensing vehicle corresponding to the smallest first relative distance error is identified as the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the current group of main sensing data packets, and the first self-position information is identified as the self-position information of the auxiliary collection vehicle corresponding to the timestamp of the first frame in the current group of main sensing data packets, For each frame other than the timestamp of the first frame in the main sensing data packets of the current group, a calculation is performed on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of the frame and the first three-dimensional coordinate information to obtain a second relative distance error, the three-dimensional coordinate information of the sensing vehicle corresponding to a second relative distance error smaller than a predetermined distance error threshold is identified as the second three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the frame, a calculation is performed on the second three-dimensional coordinate information over the self-position information of the first group according to the nearest neighbor method to obtain a third relative distance error, and the self-position information of the auxiliary collection vehicle corresponding to the smallest third relative distance error is identified as the self-position information of the auxiliary collection vehicle corresponding to the timestamp of the frame, The steps include: calculating a transformation matrix corresponding to the main sensing data packets of the current group based on the three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of each frame, the self-position information of the auxiliary collection vehicle corresponding to the timestamp of each frame, and a predetermined general-purpose diagram optimization formula, and setting the transformation matrix as the current transformation matrix; A method for determining the true value of a vehicle's three-dimensional coordinates according to claim 1, comprising the steps of: setting the main sensing data packet of the group following the main sensing data packet of the current group as the main sensing data packet of the current group; calculating the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the main sensing data packet of the current group based on the self-position information of the group following the self-position information of the first group and the current transformation matrix; and returning to the step of obtaining a second relative distance error by performing calculations on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of the frame and the first three-dimensional coordinate information for each timestamp of each frame in the main sensing data packet of the current group other than the timestamp of the first frame until the transformation matrix corresponding to the main sensing data packet of the final group among the main sensing data packets of the K group is obtained; and setting the transformation matrix corresponding to the main sensing data packet of the final group as the coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle.

3. The step of calculating the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle, based on the coordinate transformation matrix and the vehicle position information collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle, is as follows: The method for determining the true three-dimensional coordinates of a vehicle according to claim 1 or 2, characterized in that it includes the step of multiplying the coordinate transformation matrix by the vehicle position information collected at a predetermined distance position by the inertial sensor of the auxiliary collection vehicle from the left, and obtaining the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle.

4. After the step of calculating the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle position information collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle, the vehicle three-dimensional coordinate true value determination method is as follows: The process further includes receiving a two-dimensional marking box of the auxiliary collection vehicle that has been manually marked on the target main sensing data packet, performing a two-dimensional-to-three-dimensional matching between the two-dimensional marking box and the three-dimensional boundary box corresponding to the projected coordinate information, and, if the matching is successful, performing the step of setting the projected coordinate information to the true three-dimensional coordinates of the auxiliary collection vehicle. The method for determining the true value of a vehicle's three-dimensional coordinates according to claim 1, characterized in that the target main sensing data packet is a main sensing data packet collected by the vehicle end sensor of the main collection vehicle when the auxiliary collection vehicle continues to drive and stops at a predetermined distance.

5. The step of performing a two-dimensional-to-three-dimensional matching between the two-dimensional marking box and the three-dimensional boundary box corresponding to the projected coordinate information is: The steps include: projecting a three-dimensional bounding box corresponding to the aforementioned projected coordinate information onto the image plane where the two-dimensional marking box is located to obtain a two-dimensional projected bounding box; The method for determining the true value of a vehicle's three-dimensional coordinates according to claim 4, comprising the steps of: calculating the first area of ​​the intersection and the second area of ​​the union between the two-dimensional marking box and the two-dimensional projection boundary box; calculating the division value of the first area and the second area; and determining that the matching was successful when the division value is greater than a predetermined value.

6. After the step of converting the projected coordinate information into the true three-dimensional coordinates of the auxiliary collection vehicle, the method for determining the true three-dimensional coordinates of the vehicle is as follows: The method for determining the true three-dimensional coordinates of a vehicle according to claim 1, further comprising the step of receiving an adjustment for the vehicle height in the true three-dimensional coordinates of the auxiliary collection vehicle and obtaining the true three-dimensional coordinates of the auxiliary collection vehicle after the adjustment.

7. After the step of converting the projected coordinate information into the true three-dimensional coordinates of the auxiliary collection vehicle, the method for determining the true three-dimensional coordinates of the vehicle is as follows: The method for determining the true three-dimensional coordinates of a vehicle according to claim 1, further comprising the step of calculating the true three-dimensional coordinates of each sensing vehicle in the vehicle coordinate system of the main collection vehicle, based on the projected coordinate information and the three-dimensional coordinate information of each sensing vehicle in the auxiliary sensing data packets collected at a predetermined distance position by the vehicle end sensor of the auxiliary collection vehicle.

8. A vehicle three-dimensional coordinate true value determination device, In the initial state, both the main collection vehicle and the auxiliary collection vehicle are located at the initial point, and the vehicle end sensors of both the main collection vehicle and the auxiliary collection vehicle are facing forward, and the auxiliary collection vehicle is traveling forward. When the main collection vehicle comes to a standstill and the auxiliary collection vehicle stops each time it travels at a predetermined distance interval, the vehicle end sensors of both vehicles simultaneously collect sensing data packets for a predetermined time. When the number of stops reaches K, the auxiliary collection vehicle continues to travel and stops at a predetermined distance position, at which point the vehicle end sensors of both vehicles simultaneously collect sensing data packets for the predetermined time. The vehicle three-dimensional coordinate true value identification device comprises an acquisition module, a coordinate transformation matrix identification module, and a first coordinate true value identification module. The acquisition module is configured to acquire K groups of self-position information collected by the inertial sensor of the auxiliary collection vehicle during K stops, and K groups of main sensing data packets collected by the main collection vehicle, wherein K is greater than a predetermined value, and each group of main sensing data packets consists of sensing data with timestamps of multiple frames, and the sensing data with timestamps of each frame includes three-dimensional coordinate information of the sensing vehicle, and the sensing vehicle includes at least the auxiliary collection vehicle. The coordinate transformation matrix identification module is configured to calculate a coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle based on the self-position information of the K group and the main sensing data packets of the K group, wherein the power-on vehicle coordinate system is a vehicle coordinate system with the position of the vehicle's onboard computer at the time of power-on as the coordinate system origin. The first coordinate true value determination module is configured to calculate projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle position information collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle, and to use the projected coordinate information as the true three-dimensional coordinate of the auxiliary collection vehicle, and the distance between the predetermined distance position and the main collection vehicle is greater than a predetermined distance threshold, characterized in that the vehicle three-dimensional coordinate true value determination device.

9. The coordinate transformation matrix identification module includes a first calculation submodule, a second calculation submodule, a current transformation matrix identification submodule, and a third calculation submodule. The first calculation submodule is configured to take the first group of main sensing data packets from the K group as the main sensing data packets of the current group, and to perform a calculation with the first self-position information from the first group of self-position information over the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of each frame in the current group of main sensing data packets according to the nearest neighbor method to obtain a first relative distance error, to identify the three-dimensional coordinate information of the sensing vehicle corresponding to the smallest first relative distance error as the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the current group of main sensing data packets, and to identify the first self-position information as the self-position information of the auxiliary collection vehicle corresponding to the timestamp of the first frame in the current group of main sensing data packets. The second calculation submodule is configured to obtain a second relative distance error by performing calculations on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of the frame and the first three-dimensional coordinate information for each frame other than the timestamp of the first frame in the main sensing data packets of the current group, and to identify the three-dimensional coordinate information of the sensing vehicle corresponding to the second relative distance error that is smaller than a predetermined distance error threshold as the second three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of that frame, and to obtain a third relative distance error by performing calculations on the first group's own vehicle position information with the second three-dimensional coordinate information according to the nearest neighbor method, and to identify the own vehicle position information corresponding to the smallest third relative distance error as the own vehicle position information of the auxiliary collection vehicle corresponding to the timestamp of that frame. The current transformation matrix identification submodule is configured to calculate a transformation matrix corresponding to the main sensing data packets of the current group based on the three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of each frame, the self-position information of the auxiliary collection vehicle corresponding to the timestamp of each frame, and a predetermined general-purpose diagram optimization formula, and to set the transformation matrix as the current transformation matrix. The third calculation submodule is configured to use the main sensing data packets of the group following the main sensing data packets of the current group as the main sensing data packets of the current group, calculate the first three-dimensional coordinate information of the auxiliary collection vehicle collected by the main collection vehicle at the timestamp of the first frame in the main sensing data packets of the current group based on the self-position information of the group following the self-position information of the first group and the current transformation matrix, and return to the step of obtaining the second relative distance error by performing calculations on the three-dimensional coordinate information of the sensing vehicle corresponding to the timestamp of the frame and the first three-dimensional coordinate information for each timestamp of each frame in the main sensing data packets of the current group other than the timestamp of the first frame until the transformation matrix corresponding to the main sensing data packets of the final group among the main sensing data packets of the K group is obtained, and the transformation matrix corresponding to the final group of main sensing data packets is configured to be the coordinate transformation matrix between the power-on vehicle coordinate system of the main collection vehicle and the power-on vehicle coordinate system of the auxiliary collection vehicle, as described in claim 8.

10. The first coordinate true value determination module is, The vehicle three-dimensional coordinate true value determination device according to claim 8 or 9, characterized in that the coordinate transformation matrix is ​​multiplied from the left by the vehicle position information collected at the predetermined distance position by the inertial sensor of the auxiliary collection vehicle to obtain the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle.

11. The vehicle three-dimensional coordinate true value identification device further comprises a receiving module, The receiving module calculates the projected coordinate information of the auxiliary collection vehicle in the vehicle coordinate system of the main collection vehicle based on the coordinate transformation matrix and the vehicle position information collected at a predetermined distance by the inertial sensor of the auxiliary collection vehicle. It then receives the two-dimensional marking box of the auxiliary collection vehicle that has been manually marked on the target main sensing data packet, performs two-dimensional-to-three-dimensional matching between the two-dimensional marking box and the three-dimensional boundary box corresponding to the projected coordinate information, and, upon successful matching, triggers the module to set the projected coordinate information as the true three-dimensional coordinate value of the auxiliary collection vehicle. The vehicle three-dimensional coordinate true value identification device according to claim 8, characterized in that the target main sensing data packet is a main sensing data packet collected by the vehicle end sensor of the main collection vehicle when the auxiliary collection vehicle continues to drive and stops at a predetermined distance.

12. The receiving module is A projection submodule is configured to obtain a two-dimensional projected boundary box by projecting a three-dimensional boundary box corresponding to the aforementioned projected coordinate information onto the image plane where the two-dimensional marking box is located, The vehicle three-dimensional coordinate true value identification device according to claim 11, comprising a matching submodule configured to calculate a first area of ​​the intersection and a second area of ​​the union between the two-dimensional marking box and the two-dimensional projection boundary box, calculate the division value of the first area and the second area, and determine that matching is successful when the division value is greater than a predetermined value.

13. The vehicle three-dimensional coordinate true value identification device further comprises an adjustment module, The vehicle three-dimensional coordinate true value identification device according to claim 8, characterized in that the adjustment module is configured to obtain the adjusted three-dimensional coordinate true value of the auxiliary collection vehicle after the projection coordinate information has been converted to the three-dimensional coordinate true value of the auxiliary collection vehicle.

14. The vehicle three-dimensional coordinate true value identification device further comprises a second coordinate true value identification module, The vehicle three-dimensional coordinate true value identification device according to claim 8, characterized in that the second coordinate true value identification module is configured to determine the three-dimensional coordinate true value of the auxiliary collection vehicle after the projected coordinate information has been converted to the three-dimensional coordinate true value of the auxiliary collection vehicle, and then calculates the three-dimensional coordinate true value of each sensing vehicle in the vehicle coordinate system of the main collection vehicle based on the projected coordinate information and the three-dimensional coordinate information of each sensing vehicle in the auxiliary sensing data packets collected at a predetermined distance position by the vehicle end sensor of the auxiliary collection vehicle.

15. A computer-readable storage medium in which computer programs are stored, A computer-readable storage medium characterized in that, when the computer program is executed by a processor, the method for determining the true values ​​of the three-dimensional coordinates of a vehicle according to any one of claims 1 to 2 and 4 to 7 is implemented.

16. It is an electronic device, Equipped with one or more processors, The processor is coupled to a memory device for storing one or more programs. An electronic device characterized in that, when the one or more programs are executed by the one or more processors, the electronic device is made to perform the vehicle three-dimensional coordinate true value determination method described in any one of claims 1 to 2 and 4 to 7.

17. A vehicle characterized by being equipped with a vehicle three-dimensional coordinate true value determination device according to any one of claims 8 to 9 and 11 to 14.

18. A vehicle characterized by being equipped with the electronic equipment described in Claim 16.

Images