Method and system for calibrating transformational relationship between two roadside sensors

Abstract

The invention discloses a method and a system for calibrating a conversion relation between two roadside sensors, and relates to the technical field of roadside sensor calibration, and the method comprises the steps: carrying out the time alignment of a first preset roadside sensor and a second preset roadside sensor; obtaining a first track set corresponding to the first preset roadside sensor and a second track set corresponding to the second preset roadside sensor; respectively sampling from the first track set and the second track set, then determining a current homographic transformation matrix, and calculating a third track set of all tracks which are not sampled in the second track set in the coordinate system used by the first preset roadside sensor; and calculating an average distance between the first track set and the third track set, judging whether the average distance is smaller than a preset distance threshold, and if so, determining the current homography transformation matrix as a final homography transformation matrix. According to the method, a more accurate homographic transformation matrix can be obtained, and accurate transformation of position coordinates can be realized.

Description

Background Art

[0002] Roadside sensors are used to detect information about traffic participants on the road. The sensors need to provide accurate location information of traffic participants and are an important part of vehicle-road collaboration and digital twin systems. The current technical solutions for calibrating different roadside sensors are as follows:

[0003] 1) In the invention patent with the publication number of "CN111383285A" and the subject name of "A calibration method and system based on millimeter-wave radar and camera sensor fusion", it is necessary to use artificial calibration objects for calibration, such as engineers holding corner reflectors and walking in straight lines in different areas of the scene. There is a certain risk for engineers to collect data at urban intersections or highways. If the road closure needs to be applied to the traffic control department, it will not only affect normal traffic, but also require the application for road closure again to replace the roadside sensor, which is very inefficient.

[0004] 2) The invention patent with publication number "CN112558023A" and subject name "Sensor calibration method and device" proposes a method that does not require road closures. Specifically, a mapping relationship between sensors is established through high-precision maps, but there are often no high-precision maps for reference on actual roads.

[0005] 3) The invention patent with publication number "CN112836737A" and subject name "A method for online calibration of roadside combined perception equipment based on vehicle-road data fusion", as well as the invention patent with publication number "WO2022206978A1" and subject name "A method for roadside millimeter-wave radar calibration based on vehicle-mounted positioning device" both proposed a technical solution for calculating the sensor mapping relationship by providing calibration target data through a vehicle-mounted high-precision positioning device, but it requires relatively expensive professional equipment to record and feedback data in real time, and also requires the vehicle equipped with the positioning device to drive multiple times within the detection range to complete the calibration. Summary of the invention

[0006] The technical problem to be solved by the present invention is to address the deficiencies of the prior art and specifically provide a method and system for calibrating the conversion relationship between two roadside sensors, as follows:

[0007] 1) In a first aspect, the present invention provides a method for calibrating a conversion relationship between two roadside sensors, and the specific technical solution is as follows:

[0008] After time alignment of the first preset roadside sensor and the second preset roadside sensor, the first preset roadside sensor and the second preset roadside sensor are used to track the target in the same preset area, respectively, to obtain a first trajectory set corresponding to the first preset roadside sensor and a second trajectory set corresponding to the second preset roadside sensor;

[0009] Sampling is performed from the first trajectory set and the second trajectory set respectively, and the target corresponding to the trajectory sampled from the first trajectory set is the same as the target corresponding to the trajectory sampled from the second trajectory set;

[0010] Determine the current homography transformation matrix based on multiple trajectories obtained from the current sampling;

[0011] Calculate, according to the current homography transformation matrix, a third trajectory set of all unsampled trajectories in the second trajectory set in a coordinate system used by the first preset roadside sensor;

[0012] Calculating an average distance between the first trajectory set and the third trajectory set, and determining whether the average distance is less than a preset distance threshold to obtain a determination result;

[0013] When the judgment result is yes, the current homography transformation matrix is ​​determined as the final homography transformation matrix.

[0014] The beneficial effects of a method for calibrating a conversion relationship between two roadside sensors provided by the present invention are as follows:

[0015] The position coordinates of the target obtained by any roadside sensor are the coordinates of the coordinate system used by the roadside sensor. In practical applications, the position coordinates of the targets obtained by different roadside sensors need to be converted. Since the conversion between the position coordinates of the targets obtained by any two roadside sensors needs to be completed through the homography transformation matrix corresponding to the two roadside sensors, the accuracy of the homography transformation matrix determines whether the conversion of the position coordinates is accurate. The present invention can obtain a more accurate homography transformation matrix based on the judgment of the distance, and the acquisition process of the homography transformation matrix is ​​simpler and low-cost than the prior art (for example: the invention patent with publication number "CN112836737A" and the subject name "A roadside combined perception device online calibration method based on vehicle-road data fusion", and the invention patent with publication number "WO2022206978A1" and the subject name "A roadside millimeter-wave radar calibration method based on a vehicle-mounted positioning device"). Through the homography transformation matrix, the accurate conversion of position coordinates in different coordinate systems (coordinate systems used by different roadside sensors) can be achieved.

[0016] On the basis of the above solution, a method for calibrating the conversion relationship between two roadside sensors of the present invention can be further improved as follows.

[0017] Furthermore, it also includes:

[0018] When the judgment result is no, sampling is performed again from the first trajectory set and the second trajectory set respectively.

[0019] Further, sampling is performed from the first trajectory set and the second trajectory set respectively, including:

[0020] The trajectories of two targets are obtained by random sampling from the first trajectory set, and the trajectories of two targets are selected from the second trajectory set.

[0021] Further, the first preset roadside sensor is a camera device, and the second preset roadside sensor is a radar, or the first preset roadside sensor is a radar, and the second preset roadside sensor is a camera device.

[0022] 2) In a second aspect, the present invention further provides a system for calibrating a conversion relationship between two roadside sensors, and the specific technical solution is as follows:

[0023] It includes a trajectory set acquisition module, a sampling module, a homography transformation matrix calculation module, a trajectory transformation module, a calculation and judgment module and a homography transformation matrix determination module;

[0024] The trajectory set acquisition module is used to: after time alignment of the first preset roadside sensor and the second preset roadside sensor, respectively use the first preset roadside sensor and the second preset roadside sensor to track the target in the same preset area, and obtain a first trajectory set corresponding to the first preset roadside sensor and a second trajectory set corresponding to the second preset roadside sensor;

[0025] The sampling module is used to: perform sampling from the first trajectory set and the second trajectory set respectively, and the target corresponding to the trajectory sampled from the first trajectory set is the same as the target corresponding to the trajectory sampled from the second trajectory set;

[0026] The homography transformation matrix calculation module is used to: determine the current homography transformation matrix according to the multiple trajectories obtained by current sampling;

[0027] The trajectory transformation module is used to: calculate a third trajectory set of all unsampled trajectories in the second trajectory set in a coordinate system used by the first preset roadside sensor according to the current homography transformation matrix;

[0028] The calculation and judgment module is used to: calculate the average distance between the first trajectory set and the third trajectory set, and judge whether the average distance is less than a preset distance threshold to obtain a judgment result;

[0029] The homography transformation matrix determination module is used to: when the judgment result is yes, determine the current homography transformation matrix as the final homography transformation matrix.

[0030] On the basis of the above solution, the system for calibrating the conversion relationship between two roadside sensors of the present invention can also be improved as follows.

[0031] Furthermore, it also includes a calling module, which is used to: when the judgment result is no, call the sampling module to re-sample from the first trajectory set and the second trajectory set respectively.

[0032] Furthermore, the sampling module is specifically used to: randomly sample from the first trajectory set to obtain the trajectories of the two targets, and select the trajectories of the two targets from the second trajectory set.

[0033] Further, the first preset roadside sensor is a camera device, and the second preset roadside sensor is a radar, or the first preset roadside sensor is a radar, and the second preset roadside sensor is a camera device.

[0034] 3) In a third aspect, the present invention also provides an electronic device, which includes a processor, the processor is coupled to a memory, and at least one computer program is stored in the memory. The at least one computer program is loaded and executed by the processor so that the electronic device can implement any of the above-mentioned methods for calibrating the conversion relationship between two roadside sensors.

[0035] 4) In a fourth aspect, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is loaded and executed by a processor so that the computer implements any of the above-mentioned methods for calibrating the conversion relationship between two roadside sensors.

[0036] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0038] Figure 1 A schematic flow chart of a method for calibrating a conversion relationship between two roadside sensors according to an embodiment of the present invention;

[0039] Figure 2 A schematic diagram of the structure of a system for calibrating a conversion relationship between two roadside sensors according to an embodiment of the present invention;

[0040] Figure 3 The figure is a schematic diagram of the structure of an electronic system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0042] like Figure 1 As shown, a method for calibrating a conversion relationship between two roadside sensors according to an embodiment of the present invention includes the following steps:

[0043] S1, after time alignment of a first preset roadside sensor and a second preset roadside sensor, respectively use the first preset roadside sensor and the second preset roadside sensor to track a target in the same preset area, to obtain a first trajectory set corresponding to the first preset roadside sensor and a second trajectory set corresponding to the second preset roadside sensor;

[0044] Among them, the preset area can be set according to actual conditions, such as a designated road area, etc.

[0045] Among them, the first trajectory set corresponding to the first preset roadside sensor includes: the trajectory of each target obtained after tracking the target in the preset area by the first preset roadside sensor, the trajectory of each target in the first trajectory set is generated in the coordinate system used by the first preset roadside sensor, and the coordinate system used by the first preset roadside sensor can be established according to actual conditions.

[0046] Among them, the second trajectory set corresponding to the second preset roadside sensor includes: the trajectory of each target obtained after tracking the target in the preset area by the second preset roadside sensor, the trajectory of each target in the second trajectory set is generated in the coordinate system used by the second preset roadside sensor, and the coordinate system used by the second preset roadside sensor can be established according to actual conditions.

[0047] S2, sampling is performed from the first trajectory set and the second trajectory set respectively, and the target corresponding to the trajectory sampled from the first trajectory set is the same as the target corresponding to the trajectory sampled from the second trajectory set, specifically:

[0048] For example, two target trajectories are obtained by random sampling from the first trajectory set, and the trajectories of the two targets are selected from the second trajectory set.

[0049] The number of target trajectories obtained by random sampling from the first trajectory set can be set according to actual conditions.

[0050] S3, determining the current homography transformation matrix according to the multiple trajectories obtained by current sampling;

[0051] S4. Calculate, according to the current homography transformation matrix, a third trajectory set of all unsampled trajectories in the second trajectory set in the coordinate system used by the first preset roadside sensor;

[0052] S5, calculating the average distance between the first trajectory set and the third trajectory set, and determining whether the average distance is less than a preset distance threshold, to obtain a determination result;

[0053] S6. When the judgment result is yes, the current homography transformation matrix is ​​determined as the final homography transformation matrix.

[0054] Optionally, in the above technical solution, it also includes:

[0055] S7. When the judgment result is no, re-sample from the first trajectory set and the second trajectory set respectively, and return to execute S3 until the judgment result is yes.

[0056] Optionally, in the above technical solution, the first preset roadside sensor is a camera device, and the second preset roadside sensor is a radar, or the first preset roadside sensor is a radar, and the second preset roadside sensor is a camera device, wherein the camera device can be a camera, and the radar can be a millimeter-wave radar, or other radars can be selected according to actual conditions.

[0057] The invention is illustrated by the following examples.

[0058] In this embodiment, the first preset roadside sensor is a camera device, and the second preset roadside sensor is a radar. A method for calibrating a conversion relationship between two roadside sensors in an embodiment of the present invention specifically includes:

[0059] S10. First, the camera device and the radar are time-aligned, and then the camera device is used to track the target to obtain tracking data, and the tracking data is tracked by Kalman filter. After a certain period of time (such as 1 hour, etc.), a first trajectory set P of all targets is obtained, and the first trajectory set P includes: the trajectory of each target monitored by the camera device. At the same time, the radar is used to track the target to obtain tracking data, and the tracking data is tracked by Kalman filter. After a certain period of time (such as 1 hour, etc.), a second trajectory set Q of all targets is obtained, and the second trajectory set Q includes the trajectory of each target monitored by the radar.

[0060] Among them, the camera device and the radar track targets in the same preset area, which can be vehicles or pedestrians, etc., and can be set according to actual conditions.

[0061] S11. Sampling:

[0062] 1) Randomly sample the first trajectory set P to obtain the trajectories of two targets. The two targets are recorded as the first target and the second target. The trajectory of the first target is recorded as The trajectory of the second target is recorded as The length of is m1, The length is m2;

[0063] 2) Randomly sample the second trajectory set Q to obtain the trajectories of two targets, which are recorded as the third target and the fourth target. The trajectory of the third target is recorded as The trajectory of the fourth target is recorded as The length of is n1, The length of is n2;

[0064] It should be noted that the first goal and the third goal are the same goal, and the second goal and the fourth goal are the same goal.

[0065] S12, get array P s and Q s :

[0066] Let k = min{m1,n1,m2,n2}, that is, k is the minimum value among m1, m2, n1 and n2, and we get the array P s and Q s :

[0067]

[0068] in, Represents: The trajectory of the first target The first position coordinates in Represents: The trajectory of the first target The second position coordinates in Represents: The trajectory of the first target The m1-k+1th position coordinate in, Represents: The trajectory of the second target The first position coordinates in Represents: The trajectory of the second target The second position coordinates in Represents: The trajectory of the second target The second position coordinates in Represents: The trajectory of the second target The m2-k+1th position coordinate in, Indicates: The trajectory of the third target The first position coordinates in Indicates: The trajectory of the third target The second position coordinates in Indicates: The trajectory of the third target The third position coordinates in Indicates: The trajectory of the third target The n1-k+1th position coordinate in, Indicates: The trajectory of the fourth target The first position coordinates in Indicates: The trajectory of the fourth target The second position coordinates in Indicates: The trajectory of the fourth target The third position coordinates in Indicates: The trajectory of the fourth target The n2-k+1th position coordinate in .

[0069] S13. According to P s and Q s Able to calculate the current homography transformation matrix.

[0070] S14. Mark any position in the radar coordinate system as (x ′ ,y ′ ), and (x ′ ,y ′ ) In (x ′ ,y ′ ) in the coordinate system used by the camera device (u ′ ,v ′ ), until the position coordinates of each position coordinate of all unsampled trajectories in the second trajectory set in the coordinate system used by the camera device are obtained, and the position coordinates of each position coordinate of each unsampled trajectory in the second trajectory set in the coordinate system used by the camera device respectively constitute a new trajectory, and the set of all new trajectories is the third trajectory set, which will be recorded as Q ′ .

[0071] in, is the current homography transformation matrix, h 00 、h 01 、h 02 、h 10 、h 11 、h 12 、h 20 、h 21 and h 22 is the element in the current homography transformation matrix, and s represents the coefficient of the homogeneous coordinates.

[0072] S15, calculating the first trajectory set P and the third trajectory set Q ′ The average distance D between them is calculated by the following formula:

[0073]

[0074] Where M represents the number of trajectories in the first trajectory set P, N represents the number of trajectories in the second trajectory set Q, and d(P i ,Q′j )=DWT(P i ,Q′ j ), d(P i ,Q′ j ) represents the i-th trajectory P in the first trajectory set P i With the third track Q ′ The j trajectories Q′ in j The DWT (Dynamic Time Warping) distance between them.

[0075] S16. Determine whether the average distance D is less than a preset distance threshold th, and obtain a determination result. Then:

[0076] 1) When the judgment result is yes, the current homography transformation matrix is ​​determined as the final homography transformation matrix, and the final homography transformation matrix is ​​saved. At this time, the time-aligned camera and radar are used to track the target. The position coordinates of the same target monitored at any same time in the corresponding coordinate system meet the following conditions: Among them, the position coordinates in the coordinate system used by the camera device are (u, v), the position coordinates in the coordinate system used by the radar are (x, y), and (u, v) and (x, y) are: the position coordinates of the same target monitored by the camera device and radar after time alignment at any same time.

[0077] 2) When the judgment result is no, re-sampling is performed from the first trajectory set and the second trajectory set respectively, and the process returns to S12 until the judgment result is yes, and the final homography transformation matrix is ​​determined.

[0078] The beneficial effects of the present invention are as follows:

[0079] The position coordinates of the target obtained by any roadside sensor are the coordinates of the coordinate system used by the roadside sensor. In practical applications, the position coordinates of the targets obtained by different roadside sensors need to be converted. Since the conversion between the position coordinates of the targets obtained by any two roadside sensors needs to be completed through the homography transformation matrix corresponding to the two roadside sensors, the accuracy of the homography transformation matrix determines whether the conversion of the position coordinates is accurate. The present invention can obtain a more accurate homography transformation matrix based on the judgment of the distance, and the acquisition process of the homography transformation matrix is ​​simpler and low-cost than the prior art (for example: the invention patent with publication number "CN112836737A" and the subject name "A roadside combined perception device online calibration method based on vehicle-road data fusion", and the invention patent with publication number "WO2022206978A1" and the subject name "A roadside millimeter-wave radar calibration method based on a vehicle-mounted positioning device"). Through the homography transformation matrix, the accurate conversion of position coordinates in different coordinate systems (coordinate systems used by different roadside sensors) can be achieved.

[0080] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0081] like Figure 2 As shown, a system 200 for calibrating a conversion relationship between two roadside sensors according to an embodiment of the present invention includes a trajectory set acquisition module 201, a sampling module 202, a homography transformation matrix calculation module 203, a trajectory transformation module 204, a calculation and judgment module 205, and a homography transformation matrix determination module 206;

[0082] The trajectory set acquisition module 201 is used to: after time alignment of the first preset roadside sensor and the second preset roadside sensor, respectively use the first preset roadside sensor and the second preset roadside sensor to track the target in the same preset area, and obtain a first trajectory set corresponding to the first preset roadside sensor and a second trajectory set corresponding to the second preset roadside sensor;

[0083] The sampling module 202 is used to: perform sampling from the first trajectory set and the second trajectory set respectively, and the target corresponding to the trajectory sampled from the first trajectory set is the same as the target corresponding to the trajectory sampled from the second trajectory set;

[0084] The homography transformation matrix calculation module 203 is used to: determine the current homography transformation matrix according to the multiple trajectories obtained by current sampling;

[0085] The trajectory transformation module 204 is used to: calculate a third trajectory set of all unsampled trajectories in the second trajectory set in the coordinate system used by the first preset roadside sensor according to the current homography transformation matrix;

[0086] The calculation and judgment module 205 is used to: calculate the average distance between the first trajectory set and the third trajectory set, and judge whether the average distance is less than a preset distance threshold to obtain a judgment result;

[0087] The homography transformation matrix determining module 206 is used to: when the judgment result is yes, determine the current homography transformation matrix as the final homography transformation matrix.

[0088] Optionally, the above technical solution further includes a calling module, which is used to: when the judgment result is no, call the sampling module, re-sample from the first trajectory set and the second trajectory set respectively, and then continue the homography transformation matrix calculation module 203, the trajectory transformation module 204, the calculation judgment module 205 and the homography transformation matrix determination module 206 until the judgment result is yes.

[0089] Optionally, in the above technical solution, the sampling module 202 is specifically used to: randomly sample from the first trajectory set to obtain the trajectories of the two targets, and select the trajectories of the two targets from the second trajectory set.

[0090] It should be noted that the beneficial effects of the system 200 for calibrating the conversion relationship between two roadside sensors provided by the above embodiment are the same as the beneficial effects of the method for calibrating the conversion relationship between two roadside sensors, which will not be repeated here. In addition, when the system provided by the above embodiment realizes its functions, it only takes the division of the above functional modules as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided by the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0091] like Figure 3 As shown, the electronic device 300 of the embodiment of the present invention includes a processor 320, the processor 320 is coupled to a memory 310, and the memory 310 stores at least one computer program 330, and the at least one computer program 330 is loaded and executed by the processor 320, so that the electronic device 300 implements any one of the above methods for calibrating the conversion relationship between two roadside sensors, specifically:

[0092] The electronic device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors 320 (Central Processing Units, CPU) and one or more memories 310, wherein the one or more memories 310 store at least one computer program 330, and the at least one computer program 330 is loaded and executed by the one or more processors 320, so that the electronic device 300 implements any one of the methods for calibrating the conversion relationship between two roadside sensors provided in the above embodiments. Of course, the electronic device 300 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The electronic device 300 may also include other components for realizing the functions of the device, which will not be described in detail here. The electronic device may specifically be a computer, etc.

[0093] The computer-readable storage medium of an embodiment of the present invention stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that the computer implements any of the above-mentioned methods for calibrating the conversion relationship between two roadside sensors.

[0094] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0095] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes any of the above methods for calibrating the conversion relationship between two roadside sensors.

[0096] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and represent the definition of a specific order or sequence. The order of use of similar objects can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0097] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0098] Any combination of one or more computer-readable media can be used. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0099] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for calibrating a conversion relationship between two roadside sensors, characterized in that: include: After time alignment of the first preset roadside sensor and the second preset roadside sensor, the first preset roadside sensor and the second preset roadside sensor are used to track a target in the same preset area, respectively, to obtain a first trajectory set corresponding to the first preset roadside sensor and a second trajectory set corresponding to the second preset roadside sensor; Sampling is performed from the first trajectory set and the second trajectory set respectively, and the target corresponding to the trajectory sampled from the first trajectory set is the same as the target corresponding to the trajectory sampled from the second trajectory set; Determine the current homography transformation matrix based on multiple trajectories obtained from the current sampling; Calculate, according to the current homography transformation matrix, a third trajectory set of all unsampled trajectories in the second trajectory set in the coordinate system used by the first preset roadside sensor; Calculating an average distance between the first trajectory set and the third trajectory set, and determining whether the average distance is less than a preset distance threshold to obtain a determination result; When the judgment result is yes, the current homography transformation matrix is ​​determined as the final homography transformation matrix.

2. A method for calibrating a conversion relationship between two roadside sensors according to claim 1, characterized in that: Also includes: When the judgment result is no, sampling is performed again from the first trajectory set and the second trajectory set respectively.

3. A method for calibrating a conversion relationship between two roadside sensors according to claim 1, characterized in that: Sampling respectively from the first trajectory set and the second trajectory set includes: The trajectories of two targets are obtained by random sampling from the first trajectory set, and the trajectories of the two targets are selected from the second trajectory set.

4. A method for calibrating a conversion relationship between two roadside sensors according to claim 1 or 2, characterized in that: The first preset roadside sensor is a camera device, and the second preset roadside sensor is a radar, or the first preset roadside sensor is a radar, and the second preset roadside sensor is a camera device.

5. A system for calibrating the conversion relationship between two roadside sensors, characterized in that: It includes a trajectory set acquisition module, a sampling module, a homography transformation matrix calculation module, a trajectory transformation module, a calculation and judgment module and a homography transformation matrix determination module; The trajectory set acquisition module is used to: after time alignment of the first preset roadside sensor and the second preset roadside sensor, respectively use the first preset roadside sensor and the second preset roadside sensor to track the target in the same preset area, so as to obtain a first trajectory set corresponding to the first preset roadside sensor and a second trajectory set corresponding to the second preset roadside sensor; The sampling module is used to: perform sampling from the first trajectory set and the second trajectory set respectively, and the target corresponding to the trajectory sampled from the first trajectory set is the same as the target corresponding to the trajectory sampled from the second trajectory set; The homography transformation matrix calculation module is used to: determine the current homography transformation matrix according to the multiple trajectories obtained by current sampling; The trajectory transformation module is used to: calculate a third trajectory set of all unsampled trajectories in the second trajectory set in the coordinate system used by the first preset roadside sensor according to the current homography transformation matrix; The calculation and judgment module is used to: calculate the average distance between the first trajectory set and the third trajectory set, and judge whether the average distance is less than a preset distance threshold to obtain a judgment result; The homography transformation matrix determination module is used to: when the judgment result is yes, determine the current homography transformation matrix as the final homography transformation matrix.

6. A system for calibrating the conversion relationship between two roadside sensors according to claim 5, characterized in that: The method further comprises a calling module, wherein the calling module is used to: when the judgment result is no, call the sampling module to resample from the first trajectory set and the second trajectory set respectively.

7. A system for calibrating the conversion relationship between two roadside sensors according to claim 5 or 6, characterized in that: The sampling module is specifically used to: randomly sample from the first trajectory set to obtain the trajectories of two targets, and select the trajectories of the two targets from the second trajectory set.

8. A system for calibrating the conversion relationship between two roadside sensors according to claim 5 or 6, characterized in that: The first preset roadside sensor is a camera device, and the second preset roadside sensor is a radar, or the first preset roadside sensor is a radar, and the second preset roadside sensor is a camera device.

9. An electronic device, characterized in that The electronic device includes a processor, the processor is coupled to a memory, and at least one computer program is stored in the memory. The at least one computer program is loaded and executed by the processor so that the electronic device implements a method for calibrating the conversion relationship between two roadside sensors as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by the processor so that the computer implements a method for calibrating a conversion relationship between two roadside sensors as described in any one of claims 1 to 4.

Images