Method and system for determining installation angle of intersection radar based on multi-dimensional coordinates

Abstract

The present invention discloses a method and system for determining the installation angle of a road intersection radar based on multi-dimensional coordinates, which relates to the field of intelligent vehicle management at road intersections and includes: performing dual coordinate compensation of the radar and the camera on the radar tracking coordinates and camera tracking coordinates respectively corresponding to a target in different time frames, and filtering the installation angles obtained from the radar tracking coordinates and camera tracking coordinates respectively corresponding to different time frames after compensation, thereby realizing a method for determining the installation angle of the radar based on multi-dimensional compensation measures, which can improve the determination accuracy of the installation angle; at the same time, the present invention obtains the pixel error weight coefficient of the target on the preset pixel plane after perspective transformation according to the selected true camera tracking coordinates and the camera tracking coordinates of the corresponding frames. Since the target trajectory can be made parallel to the normal direction of the radar device after perspective transformation, the target coordinates after angle correction can be directly obtained, and the versatility is relatively strong.

Description

Technical Field

[0001] The present invention relates to the field of intelligent vehicle management at intersections, and particularly to a method and system for determining the installation angle of a radar at an intersection based on multi-dimensional coordinates. Background Art

[0002] With the continuous increase in the number of urban cars, the road conditions have become increasingly complex. Especially in various intersection areas, vehicles, non-motor vehicles, pedestrians, etc. converge. Therefore, the vehicle targets at multiple intersections are usually tracked and detected by combining radar and camera. In order to better combine the data of the target points collected by the radar with the data of the target points collected by the camera, strict requirements are imposed on the installation angle of the radar.

[0003] Currently, when obtaining the radar installation angle, usually two targets are placed on both sides of the vehicle respectively, with a certain distance between them. The line connecting these two targets is parallel to the longitudinal axis of the vehicle. Then, the distances and angles measured by the radar for the two targets on one side are output to determine the angle between the longitudinal axis of the vehicle and the normal direction of the radar, and thus the true installation angle of the radar is obtained. However, since the calculation result of the installation angle depends on the line connecting the two targets being parallel to the longitudinal axis of the vehicle, if the line connecting the two targets is not strictly parallel to the longitudinal center axis of the vehicle body, it will lead to errors in the calculation result, resulting in a large error in the obtained radar installation angle. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a method and system for determining the installation angle of a radar at an intersection based on multi-dimensional coordinates, which can solve the problem of large errors in the currently obtained radar installation angle.

[0005] To achieve the above object, on the one hand, the present invention provides a method for determining the installation angle of a radar at an intersection based on multi-dimensional coordinates, the method comprising:

[0006] Obtaining the radar tracking coordinates and camera tracking coordinates respectively corresponding to a target in different time frames;

[0007] Screening the camera tracking coordinates respectively corresponding to the target in different time frames to obtain true camera tracking coordinates;

[0008] Obtaining the camera tracking coordinates of the screened corresponding frame according to the true camera tracking coordinates and the camera tracking coordinates of the previous pre-set frame;

[0009] Obtaining the pixel error weight coefficient of the target on the pixel plane after pre-set perspective transformation according to the screened true camera tracking coordinates and the camera tracking coordinates of the screened corresponding frame;

[0010] Obtain the corrected true camera coordinates corresponding to the target according to the camera tracking coordinates corresponding to the target in different time frames and the pixel error weight coefficient of the target.

[0011] Correct the radar tracking coordinates corresponding to the target in different time frames according to a preset differential filtering algorithm, and obtain the radar installation tilt angle according to the corrected radar tracking coordinates corresponding to different time frames and the corrected true camera coordinates corresponding to the target.

[0012] Further, the step of obtaining the pixel error weight coefficient of the target on the pixel plane after preset perspective transformation according to the filtered true camera tracking coordinates and the camera tracking coordinates of the corresponding frame includes:

[0013] Perform an inverse plane transformation on the filtered true camera tracking coordinates and the camera tracking coordinates of the corresponding frame to obtain the corresponding measured pixel coordinates and true pixel coordinates.

[0014] Obtain the pixel error weight coefficient of the target according to the measured pixel coordinates and the true pixel coordinates.

[0015] Further, after the step of obtaining the pixel error weight coefficient of the target according to the measured pixel coordinates and the true pixel coordinates, the method further includes:

[0016] Perform mean filtering on the weight coefficient vector to obtain the filtered weight coefficient.

[0017] Further, the step of obtaining the corrected true camera coordinates corresponding to the target according to the camera tracking coordinates corresponding to the target in different time frames and the pixel error weight coefficient of the target includes:

[0018] Perform an inverse plane transformation on the camera tracking coordinates corresponding to the target in different time frames to obtain the measured pixel coordinates of the target.

[0019] Perform pixel coordinate correction on the measured pixel coordinates to obtain the corrected pixel coordinates.

[0020] Convert the corrected pixel coordinates into the coordinates of the camera, and obtain the corrected true camera coordinates corresponding to the target according to the coordinates of the camera.

[0021] Further, the step of correcting the radar tracking coordinates corresponding to the target in different time frames according to a preset differential filtering algorithm includes:

[0022] Correct the radar tracking coordinates corresponding to the target in different time frames according to a preset recursive difference equation.

[0023] On the other hand, the present invention provides an intersection radar installation angle determination system based on multi-dimensional coordinates, and the system includes:

[0024] An acquisition unit, configured to acquire radar tracking coordinates and camera tracking coordinates corresponding to a target in different time frames respectively;

[0025] A screening unit, configured to screen the camera tracking coordinates corresponding to the target in different time frames respectively to obtain true camera tracking coordinates;

[0026] The acquisition unit is further configured to acquire the camera tracking coordinates of the corresponding frame after screening according to the true camera tracking coordinates and the camera tracking coordinates of the pre-set previous frame;

[0027] The acquisition unit is further configured to obtain a pixel error weight coefficient of the target on a pre-set pixel plane after perspective transformation according to the true camera tracking coordinates after screening and the camera tracking coordinates of the corresponding frame after screening;

[0028] The acquisition unit is further configured to obtain corrected true camera coordinates corresponding to the target according to the camera tracking coordinates corresponding to the target in different time frames respectively and the pixel error weight coefficient of the target;

[0029] A correction unit, configured to correct the radar tracking coordinates corresponding to the target in different time frames respectively according to a pre-set differential filtering algorithm;

[0030] The acquisition unit is further configured to obtain a radar installation tilt angle according to the radar tracking coordinates corresponding to different time frames after correction and the corrected true camera coordinates corresponding to the target.

[0031] Further, the acquisition unit is specifically configured to perform an inverse plane transformation on the true camera tracking coordinates after screening and the camera tracking coordinates of the corresponding frame after screening to obtain corresponding measured pixel coordinates and true pixel coordinates; and obtain the pixel error weight coefficient of the target according to the measured pixel coordinates and the true pixel coordinates.

[0032] Further, the system further includes: a filtering unit;

[0033] The filtering unit is configured to perform mean filtering on the weight coefficient vector to obtain a filtered weight coefficient.

[0034] Further, the obtaining unit is specifically further configured to perform an anti-plane transformation on the camera tracking coordinates respectively corresponding to the target in different time frames to obtain the measured pixel coordinates of the target; perform pixel coordinate correction on the measured pixel coordinates to obtain the corrected pixel coordinates; convert the corrected pixel coordinates into the coordinates of the camera, and obtain the corrected true camera coordinates corresponding to the target according to the coordinates of the camera.

[0035] Further, the correction unit is specifically configured to correct the radar tracking coordinates respectively corresponding to the target in different time frames according to a preset recursive difference equation.

[0036] A method and system for determining the installation angle of an intersection radar based on multi-dimensional coordinates provided by the present invention perform dual coordinate compensation of radar and camera on the radar tracking coordinates and camera tracking coordinates respectively corresponding to the target in different time frames, and filter the installation angle obtained according to the compensated radar tracking coordinates and camera tracking coordinates corresponding to different time frames respectively, realizing a method for determining the installation angle of a radar based on multi-dimensional compensation measures, which can improve the determination accuracy of the installation angle; at the same time, the present invention obtains the pixel error weight coefficient of the target on the pixel plane after preset perspective transformation according to the filtered true camera tracking coordinates and the camera tracking coordinates of the corresponding frames. Since the target trajectory can be made parallel to the normal direction of the radar device after perspective transformation, the target coordinates after angle correction can be directly obtained, and the versatility is strong. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a flowchart of a method for determining the installation angle of an intersection radar based on multi-dimensional coordinates provided by the present invention;

[0038] Figure 2 is a schematic structural diagram of a system for determining the installation angle of an intersection radar based on multi-dimensional coordinates provided by the present invention;

[0039] Figure 3 is a schematic diagram of a single intersection coordinate system provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] The technical solutions of the present invention will be further described in detail below with reference to the drawings and embodiments.

[0041] As Figure 1 shown, a method for determining the installation angle of an intersection radar based on multi-dimensional coordinates provided by an embodiment of the present invention includes the following steps:

[0042] 101. Obtain the radar tracking coordinates and camera tracking coordinates respectively corresponding to the target in different time frames.

[0043] For example, taking a single intersection as an example, as Figure 3As shown, the origin o of the coordinate system is the position of the radar-vision integrated machine, x1oy1 is the corrected coordinate system, and the actual scene is in the skewed coordinate system of x1’oy1’. Specifically, there should be fewer road vehicles in the calibration scene; at the same time, obvious markers should be placed every 3 meters along the roadside until the farthest point of the calibration area; a vehicle traveling straight from near to far is selected as the calibration target. Assume that the target takes N frames of time to travel straight from near to far. Then, by manually screening the radar target id, position, number, and camera target id, position, number, the same target can be determined, and thus the radar tracking coordinates r x 、r y and the camera tracking coordinates Radar tracking x coordinate: r x =[r x1 ,r x2 ,...,r xi ,...,r xN , where i represents the i-th frame, y coordinate: r y =[r y1 ,r y2 ,...,r yi ,...,r yN , camera tracking x coordinate: y coordinate:

[0044] 102. Screen the camera tracking coordinates corresponding to the target at different time frames respectively to obtain the true camera tracking coordinates.

[0045] For the embodiments of the present invention, step 102 may be specifically as follows but is not limited thereto, including: First, screen out the coordinates less than Ymax meters, the farthest distance of the camera calibration point, the number of frames determined by on-site calibration. Assume that the total number of frames meeting the screening conditions is n0, and thus the corresponding measured camera x coordinates and Then observe the actual positions of the camera in the video in the first n0 frames, and screen out the moments when the target reaches the markers respectively: If the target reaches the l-th marker in a certain frame, the horizontal and vertical coordinates of the target in this frame are C yl =3l, C xl =c xl remains unchanged. Among them, the longitudinal coordinate of the target is C′ y =[C ym ,...,C yl ,...,C yn , the horizontal coordinate is C′ x =[C xm ,...,C xl ,...,C xn : where C xmC ym The abscissa and ordinate of the m-th frame at the moment when the target reaches the first marker; C xl C yl The abscissa and ordinate of the L-th frame at the moment when the target reaches the middle marker; C xn C yn The abscissa and ordinate of the n-th frame at the moment when the target reaches the last marker.

[0046] 103. Obtain the camera tracking coordinates of the corresponding frames after screening according to the real camera tracking coordinates and the camera tracking coordinates of the pre-set previous frames.

[0047] For the embodiments of the present invention, step 103 may specifically include: the real camera tracking coordinates C′ x , C′ y , and the coordinates of the previous n0 frames within the calibration area It can be known the corresponding frame numbers when the target passes through each marker, and thus the measured camera tracking coordinates c′ x = [c xm ,..., c xl ,..., c xn , c′ y = [c ym ,..., c yl ,..., c yn can be obtained.

[0048] 104. Obtain the pixel error weight coefficient of the target on the pixel plane after pre-set perspective transformation according to the real camera tracking coordinates after screening and the camera tracking coordinates of the corresponding frames after screening.

[0049] For the embodiments of the present invention, step 104 may specifically include: performing an inverse plane transformation on the real camera tracking coordinates after screening and the camera tracking coordinates of the corresponding frames after screening to obtain the corresponding measured pixel coordinates and real pixel coordinates; obtaining the pixel error weight coefficient of the target according to the measured pixel coordinates and the real pixel coordinates.

[0050] Specifically, for example, first perform an inverse plane transformation on both the measurement coordinates and the tracking coordinates. Taking the L-th frame as an example, the corresponding measured pixel coordinates p x , p y and real pixel coordinates P x , P y are calculated. The following pixel coordinates all refer to the pixel coordinates of the midpoint of the bottom edge of the camera frame:

[0051] p x = (c xl + edgeW) / MPPW P x = (C xl+(edgeW) / MPPW

[0052] p y = H - (c yl - edgeH) / MPPH P y = H - (C yl - edgeH) / MPPH

[0053] where H is the height of the perspective transformation image; edgeH is the longitudinal distance in the camera coordinate system, the actual measured distance between the bottommost straight line of the perspective transformation and the X-axis, edgeW is the lateral distance in the camera coordinate system, the actual measured distance between the leftmost straight line of the perspective transformation and the Y-axis; MPPH is the true distance represented by each pixel in the x direction in the camera coordinate system, and MPPW is the true distance represented by each pixel in the y direction in the camera coordinate system. Then calculate the pixel x error Δp of the L-th frame x = |p x - P x |, Δp y = |p y - P y |, and take Δp x as f x and substitute it into the pixel error function to obtain the weight coefficient w l .

[0054] Furthermore, in order to further improve the accuracy of the pixel error weight coefficient, the weight coefficient vector can also be subjected to mean filtering to obtain the filtered weight coefficient.

[0055] Specifically, for example, perform the above calculations on a specific frame, and thus the weight coefficient vector w = [w m ,..., w l ,..., w n of the specific frame can be obtained. Finally, perform mean filtering on the weight coefficient vector w = [w m ,..., w l ,..., w n to reduce the error, and the final weight coefficient W x can be obtained. Similarly, take the pixel y error Δp of the L-th frame y as f y and substitute it into the pixel error function to obtain the weight coefficient W y .

[0056] 105. Obtain the corrected true camera coordinates corresponding to the target according to the camera tracking coordinates corresponding to the target in different time frames and the pixel error weight coefficient of the target

[0057] For the embodiments of the present invention, step 105 may specifically include: performing an anti-plane transformation on the camera tracking coordinates respectively corresponding to the target in different time frames to obtain the measured pixel coordinates of the target; performing pixel coordinate correction on the measured pixel coordinates to obtain the corrected pixel coordinates; converting the corrected pixel coordinates into the coordinates of the camera, and obtaining the corrected true camera coordinates corresponding to the target according to the coordinates of the camera.

[0058] Specifically, for example, first perform an anti-plane transformation to first calibrate the correct pixel value of the target. Taking the i-th frame as an example, the corresponding measured pixel coordinates p x 、p y are calculated, where then perform pixel coordinate correction on the measured pixel coordinates p x 、p y to obtain the corrected pixel coordinates P xi 、P yi where finally convert the corrected pixel coordinates P xi 、P yi into the correct coordinates C xi 、C yi of the camera, where thus the corrected coordinates C x 、C y of the camera for N frames can be calculated.

[0059] 106. Correct the radar tracking coordinates respectively corresponding to the target in different time frames according to a preset differential filtering algorithm, and obtain the radar installation tilt angle according to the corrected radar tracking coordinates respectively corresponding to different time frames and the corrected true camera coordinates corresponding to the target.

[0060] Specifically, for example, according to the obtained radar tracking coordinates r x 、r y , since there are also errors in radar ranging and the error is larger for longer distances, differential filtering is used to retain part of the target information of the previous frame to reduce the distance error, and finally the radar filtered coordinates R x =[R x1 ,R x2 ,...,R xi ,...,R xN and R y =[R y1 ,R y2 ,...,R yi ,...,R yN are obtained, where the recursive difference equation is: Then start filtering from the third frame, and the filtering values of the first two frames are set to Then, based on the radar filtering coordinates R x , R y , at this time, the coordinates are the measured values in the oblique coordinates, and the calibrated camera coordinates C x , C y , at this time, the coordinates are the values in the calibrated coordinates. Calculate the tilt angle θ of the installed radar. Among them, set the tilt angle vector as θ’ = [θ1, θ2,..., θ i , θ N , θ i is the calculated tilt angle value of the i-th frame: Then perform mean filtering on the tilt angle vector to obtain the final tilt angle.

[0061] A method for determining the installation angle of an intersection radar based on multi-dimensional coordinates provided by an embodiment of the present invention realizes a method for determining the installation angle of a radar based on multi-dimensional compensation measures by performing dual coordinate compensation of radar and camera on the radar tracking coordinates and camera tracking coordinates respectively corresponding to a target in different time frames, and filtering the installation angles obtained from the radar tracking coordinates and camera tracking coordinates respectively corresponding to different time frames after compensation, which can improve the determination accuracy of the installation angle. At the same time, the present invention obtains the pixel error weight coefficient of the target on the pixel plane after preset perspective transformation according to the filtered true camera tracking coordinates and the camera tracking coordinates of the corresponding frames after screening. Since the target trajectory can be made parallel to the normal direction of the radar device after perspective transformation, the target coordinates after angle correction can be directly obtained, and the universality is strong.

[0062] To implement the method provided by the embodiment of the present invention, an embodiment of the present invention provides a system for determining the installation angle of an intersection radar based on multi-dimensional coordinates, as Figure 2 shown. The system includes: an acquisition unit 21, a screening unit 22, and a calibration unit 23;

[0063] The acquisition unit 21 is configured to acquire the radar tracking coordinates and camera tracking coordinates respectively corresponding to a target in different time frames.

[0064] The screening unit 22 is configured to screen the camera tracking coordinates respectively corresponding to the target in different time frames to obtain the true camera tracking coordinates.

[0065] The acquisition unit 21 is further configured to acquire the camera tracking coordinates of the corresponding frames after screening according to the true camera tracking coordinates and the camera tracking coordinates of the previous preset frames.

[0066] The acquisition unit 21 is further configured to obtain the pixel error weight coefficient of the target on the pixel plane after preset perspective transformation according to the filtered true camera tracking coordinates and the camera tracking coordinates of the corresponding frames after screening.

[0067] The obtaining unit 21 is further configured to obtain the corrected true camera coordinates corresponding to the target according to the camera tracking coordinates corresponding to the target in different time frames and the pixel error weight coefficient of the target.

[0068] The correction unit 23 is configured to correct the radar tracking coordinates corresponding to the target in different time frames according to a preset differential filtering algorithm.

[0069] The obtaining unit 21 is further configured to obtain the radar installation tilt angle according to the corrected radar tracking coordinates corresponding to different time frames and the corrected true camera coordinates corresponding to the target.

[0070] Further, the obtaining unit 21 is specifically configured to perform an anti-plane transformation on the filtered true camera tracking coordinates and the camera tracking coordinates of the corresponding frames to obtain the corresponding measured pixel coordinates and true pixel coordinates; and obtain the pixel error weight coefficient of the target according to the measured pixel coordinates and the true pixel coordinates.

[0071] Further, the system further includes: a filtering unit 24;

[0072] The filtering unit 24 is configured to perform mean filtering on the weight coefficient vector to obtain the filtered weight coefficient.

[0073] Further, the obtaining unit 21 is specifically further configured to perform an anti-plane transformation on the camera tracking coordinates corresponding to the target in different time frames to obtain the measured pixel coordinates of the target; perform pixel coordinate correction on the measured pixel coordinates to obtain the corrected pixel coordinates; convert the corrected pixel coordinates into the coordinates of the camera, and obtain the corrected true camera coordinates corresponding to the target according to the coordinates of the camera.

[0074] Further, the correction unit 23 is specifically configured to correct the radar tracking coordinates corresponding to the target in different time frames according to a preset recursive difference equation.

[0075] An intersection radar installation angle determination system based on multi-dimensional coordinates provided by an embodiment of the present invention realizes a radar installation angle determination method based on multi-dimensional compensation measures by performing dual coordinate compensation of radar and camera on the radar tracking coordinates and camera tracking coordinates respectively corresponding to a target in different time frames, and filtering the installation angles obtained from the radar tracking coordinates and camera tracking coordinates respectively corresponding to different time frames after compensation, which can improve the determination accuracy of the installation angle. At the same time, the present invention obtains the pixel error weight coefficient of the target on the preset pixel plane after perspective transformation according to the selected true camera tracking coordinates and the camera tracking coordinates of the corresponding frames. Since the target trajectory can be made parallel to the normal direction of the radar device after perspective transformation, the target coordinates after angle correction can be directly obtained, and the versatility is relatively strong.

[0076] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of the present disclosure. The appended method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy recited.

[0077] In the above detailed description, various features are combined in a single embodiment to simplify the present disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly recited in each claim. On the contrary, as reflected in the appended claims, the present invention lies in a state with fewer features than all the features of the single disclosed embodiment. Therefore, the appended claims are hereby expressly incorporated into the detailed description, where each claim stands alone as a separate preferred embodiment of the present invention.

[0078] In order to enable any person skilled in the art to implement or use the present invention, the above-described disclosed embodiments have been described. For those skilled in the art, various modification methods of these embodiments are obvious, and the general principles defined herein can also be applied to other embodiments without departing from the spirit and scope of the present disclosure. Therefore, the present disclosure is not limited to the embodiments given herein, but is consistent with the broadest scope of the principles and novel features disclosed in this application.

[0079] The foregoing description includes examples of one or more embodiments. Of course, it is not possible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but those of ordinary skill in the art should recognize that the various embodiments can be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, this term is inclusive in a manner similar to the term "including", as is explained when "including" is used as a transitional word in a claim. In addition, any use of the term "or" in the specification or claims is to mean "non-exclusive or".

[0080] Those skilled in the art can also understand that the various illustrative logical blocks, units, and steps listed in the embodiments of the present invention can be implemented by electronic hardware, computer software, or a combination of both. To clearly show the interchangeability of hardware and software, the functions of the above various illustrative components, units, and steps have been generally described. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art can use various methods to implement the described functions for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of the present invention.

[0081] The various illustrative logical blocks or units described in the embodiments of the present invention can be implemented or operated to perform the described functions by a general-purpose processor, a digital signal processor, an application specific integrated circuit (ASIC), a field programmable gate array or other programmable logic system, discrete gate or transistor logic, discrete hardware components, or any combination of the above designs. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented by a combination of computing systems, such as a digital signal processor and a microprocessor, multiple microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0082] In the embodiments of the present invention, the steps of the methods or algorithms described may be directly implemented in hardware, software modules executed by a processor, or a combination of the two. The software modules may be stored in a RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium in the art. Exemplarily, the storage medium may be connected to the processor such that the processor can read information from the storage medium and write information to the storage medium. Optionally, the storage medium may also be integrated into the processor. The processor and the storage medium may be disposed in an ASIC, and the ASIC may be disposed in a user terminal. Optionally, the processor and the storage medium may also be disposed in different components of the user terminal.

[0083] In one or more exemplary designs, the above-described functions of the embodiments of the present invention may be implemented in hardware, software, firmware, or any combination of the three. If implemented in software, these functions may be stored on a computer-readable medium or transmitted on a computer-readable medium in the form of one or more instructions or codes. A computer-readable medium includes a computer storage medium and a communication medium that facilitates transfer of a computer program from one place to another. The storage medium may be any available medium accessible by a general or special-purpose computer. For example, such a computer-readable medium may include, but is not limited to, RAM, ROM, EEPROM, CD-ROM, or other optical disk storage, magnetic disk storage, or other magnetic storage systems, or any other medium that can be used to carry or store program code in the form of instructions or data structures and that can be read by a general or special-purpose computer, or a general or special-purpose processor. In addition, any connection may be properly defined as a computer-readable medium, for example, if software is transmitted from a website, server, or other remote source via a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wirelessly, such as infrared, wireless, and microwave, it is also included in the defined computer-readable medium. The disks and discs include compact disks, laser disks, optical disks, DVDs, floppy disks, and Blu-ray disks. Disks typically reproduce data magnetically, while discs typically reproduce data optically with a laser. The above combinations may also be included in the computer-readable medium.

[0084] The specific embodiments described above further elaborate on the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for determining the installation angle of an intersection radar based on multi-dimensional coordinates, characterized in that The method includes: Obtaining the radar tracking coordinates and camera tracking coordinates respectively corresponding to the target at different time frames; Screening the camera tracking coordinates respectively corresponding to the target at different time frames to obtain the true camera tracking coordinates; Obtaining the camera tracking coordinates of the corresponding frame after screening according to the true camera tracking coordinates and the camera tracking coordinates of the previous preset frame; Obtaining the pixel error weight coefficient of the target on the pixel plane after preset perspective transformation according to the true camera tracking coordinates after screening and the camera tracking coordinates of the corresponding frame after screening; Obtaining the corrected true camera coordinates corresponding to the target according to the camera tracking coordinates respectively corresponding to the target at different time frames and the pixel error weight coefficient of the target; Correcting the radar tracking coordinates respectively corresponding to the target at different time frames according to the preset differential filtering algorithm, and obtaining the radar installation tilt angle according to the corrected radar tracking coordinates respectively corresponding to different time frames and the corrected true camera coordinates corresponding to the target.

2. The method for determining the installation angle of intersection radar based on multi-dimensional coordinates according to claim 1, wherein The step of obtaining the pixel error weight coefficient of the target on the pixel plane after preset perspective transformation according to the true camera tracking coordinates after screening and the camera tracking coordinates of the corresponding frame after screening includes: Performing an inverse plane transformation on the true camera tracking coordinates after screening and the camera tracking coordinates of the corresponding frame after screening to obtain the corresponding measured pixel coordinates and true pixel coordinates; Obtaining the pixel error weight coefficient of the target according to the measured pixel coordinates and the true pixel coordinates.

3. The method for determining the installation angle of the intersection radar based on multi-dimensional coordinates according to claim 2, wherein After the step of obtaining the pixel error weight coefficient of the target according to the measured pixel coordinates and the true pixel coordinates, the method further includes: Performing mean filtering on the weight coefficient vector to obtain the filtered weight coefficient.

4. A method for determining the installation angle of an intersection radar based on multi-dimensional coordinates according to claim 1, characterized in that, The step of obtaining the corrected true camera coordinates corresponding to the target according to the camera tracking coordinates respectively corresponding to the target at different time frames and the pixel error weight coefficient of the target includes: Performing an inverse plane transformation on the camera tracking coordinates respectively corresponding to the target at different time frames to obtain the measured pixel coordinates of the target; Performing pixel coordinate correction on the measured pixel coordinates to obtain the corrected pixel coordinates; Converting the corrected pixel coordinates into the coordinates of the camera, and obtaining the corrected true camera coordinates corresponding to the target according to the coordinates of the camera.

5. A method for determining the installation angle of an intersection radar based on multi-dimensional coordinates according to claim 1, characterized in that The step of correcting the radar tracking coordinates respectively corresponding to the target at different time frames according to the preset differential filtering algorithm includes: Correcting the radar tracking coordinates respectively corresponding to the target at different time frames according to the preset recursive difference equation.

6. An intersection radar installation angle determination system based on multi-dimensional coordinates, characterized in that, The system includes: An acquisition unit, configured to acquire the radar tracking coordinates and camera tracking coordinates respectively corresponding to the target at different time frames; A screening unit, configured to screen the camera tracking coordinates respectively corresponding to the target at different time frames to obtain the true camera tracking coordinates; The acquisition unit is further configured to obtain the camera tracking coordinates of the corresponding frame after screening according to the true camera tracking coordinates and the camera tracking coordinates of the previous preset frame; The obtaining unit is further configured to obtain a pixel error weight coefficient of the target on a preset perspective-transformed pixel plane according to the filtered real camera tracking coordinates and the camera tracking coordinates of the corresponding frame after filtering; The obtaining unit is further configured to obtain a corrected real camera coordinate corresponding to the target according to the camera tracking coordinates corresponding to the target in different time frames and the pixel error weight coefficient of the target; The correction unit is configured to correct the radar tracking coordinates corresponding to the target in different time frames according to a preset differential filtering algorithm; The obtaining unit is further configured to obtain a radar installation tilt angle according to the corrected radar tracking coordinates corresponding to different time frames and the corrected real camera coordinate corresponding to the target.

7. The intersection radar installation angle determination system based on multi-dimensional coordinates according to claim 6, wherein The obtaining unit is specifically configured to perform an inverse plane transformation on the filtered real camera tracking coordinates and the camera tracking coordinates of the corresponding frame after filtering to obtain corresponding measured pixel coordinates and real pixel coordinates; and obtain the pixel error weight coefficient of the target according to the measured pixel coordinates and the real pixel coordinates.

8. The intersection radar installation angle determination system based on multi-dimensional coordinates according to claim 7, characterized in that, The system further includes: a filtering unit; The filtering unit is configured to perform mean filtering on the weight coefficient vector to obtain a filtered weight coefficient.

9. The intersection radar installation angle determination system based on multi-dimensional coordinates according to claim 6, wherein The obtaining unit is specifically further configured to perform an inverse plane transformation on the camera tracking coordinates corresponding to the target in different time frames to obtain the measured pixel coordinates of the target; perform pixel coordinate correction on the measured pixel coordinates to obtain corrected pixel coordinates; convert the corrected pixel coordinates into the coordinates of the camera, and obtain the corrected real camera coordinate corresponding to the target according to the coordinates of the camera.

10. The intersection radar installation angle determination system based on multi-dimensional coordinates according to claim 7, wherein The correction unit is specifically configured to correct the radar tracking coordinates corresponding to the target in different time frames according to a preset recursive difference equation.

Images