Parallel driving steering track data processing method and device
By calibrating and fitting the pixel coordinates of the steering wheel image, a parallel driving steering trajectory line is generated, which solves the problem that remote operators cannot perceive the position and distance ahead, thus improving the safety of parallel driving.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHIDAO NETWORK TECH (BEIJING) CO LTD
- Filing Date
- 2022-11-07
- Publication Date
- 2026-06-16
AI Technical Summary
Remote operators cannot directly perceive the position and distance ahead in a parallel driving system, leading to safety hazards during driving.
By calibrating the image pixel coordinates of the steering wheel at different angles during the steering process, a set of steering trajectory coordinates is fitted, and the coordinates of the vehicle front outline are removed to generate a parallel driving steering trajectory line, which is displayed on the cockpit screen.
It provides driving prediction information to avoid collisions caused by excessive distance or lack of steering guidance, thus improving the safety of remote control.
Smart Images
Figure CN115620255B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of trajectory data processing technology, and in particular to a method and apparatus for processing parallel driving steering trajectory data. Background Technology
[0002] With the continuous evolution and advancement of car intelligence, many autonomous driving assistance systems have emerged.
[0003] Parallel driving systems, as an auxiliary system for autonomous driving, enable remote operation by allowing the driver to operate a simulator from the cockpit and send simulator commands to the vehicle. However, when remotely controlling the vehicle from the parallel cockpit, the operator cannot accurately perceive the position and distance ahead through the cockpit display, posing a significant safety hazard during driving. Summary of the Invention
[0004] This application provides a parallel driving steering trajectory data processing method and apparatus to provide driving assistance to remote operators by drawing driving trajectory lines.
[0005] The embodiments of this application adopt the following technical solutions:
[0006] In a first aspect, embodiments of this application provide a method for processing parallel driving steering trajectory data, wherein the method includes:
[0007] The image pixel coordinates of the steering wheel at different steering angles and the same steering distance during the steering process are calibrated, and the first trajectory coordinate set and the second trajectory coordinate set generated by the steering wheel at different steering angles are obtained by fitting the image pixel coordinates.
[0008] The first trajectory coordinate set and the second trajectory coordinate set are fitted to obtain the left and right turning trajectory coordinate sets;
[0009] By removing the vehicle front outline coordinates from the left and right steering trajectory coordinate sets, the steering trajectory line for parallel driving is obtained.
[0010] In some embodiments, the process of fitting the first trajectory coordinate set and the second trajectory coordinate set to obtain a left and right turning trajectory coordinate set further includes:
[0011] Based on Euclidean distance, calculate the inner starting position of the line segment of the left and right turning trajectories at the same turning distance;
[0012] The endpoint position of the inner line is determined based on the starting position of the inner line;
[0013] The inner line segment is obtained based on the starting position and ending position of the inner line.
[0014] In some embodiments, the step of removing the vehicle front profile coordinates from the left and right steering trajectory coordinate sets to obtain the parallel driving steering trajectory line includes:
[0015] Obtain the coordinate position set of the vehicle front outline;
[0016] Remove the pixel coordinates of the left and right turning trajectory coordinate group from the vehicle front outline coordinate position group.
[0017] In some embodiments, the step of removing the vehicle front profile coordinates from the left and right steering trajectory coordinate sets to obtain the parallel driving steering trajectory line further includes:
[0018] By removing the vehicle front outline coordinates from the left and right turning trajectory coordinate sets, the turning trajectory line for any turn can be obtained;
[0019] The steering trajectory of any one of the turns is mirrored and flipped to obtain the steering trajectory of the other turn.
[0020] In some embodiments, fitting the first trajectory coordinate set and the second trajectory coordinate set to obtain the left and right turning trajectory coordinate set further includes:
[0021] The left and right turning trajectories are smoothed using Bézier curves.
[0022] In some embodiments, fitting the first trajectory coordinate set and the second trajectory coordinate set to obtain the left and right turning trajectory coordinate set further includes:
[0023] By adding a new coordinate that fits the front of the vehicle and fitting it with the coordinate points in the first trajectory coordinate group and the coordinate points in the second trajectory coordinate group, the left and right turning trajectory coordinate groups are obtained.
[0024] In some embodiments, fitting the image pixel coordinate positions to obtain a first trajectory coordinate set and a second trajectory coordinate set generated by the steering wheel when it is turned at different angles includes:
[0025] The steering angle range of 0-540 degrees when the steering wheel is turned in one direction is divided into 6 steering intervals by dividing the steering wheel into 90-degree intervals;
[0026] Determine the total number of pixels within each 90-degree turning interval, and calculate the number of pixels that need to be moved per degree.
[0027] Based on the number of pixels that need to be moved at 1 degree, determine multiple position coordinates corresponding to the target turning angle. Among them, the position coordinates include at least 8, which are the coordinate points of four points on the left and right turning trajectories at positions of 10m, 7.5m, 5m, and 2.5m.
[0028] Secondly, embodiments of this application also provide a parallel driving steering trajectory data processing device, wherein the device includes:
[0029] The calibration and fitting module is used to calibrate the image pixel coordinate positions of the steering wheel when it is at different steering angles and the same steering distance during the steering process, and to obtain the first trajectory coordinate group and the second trajectory coordinate group generated by the steering wheel when it is turned at different angles by fitting the image pixel coordinate positions.
[0030] The trajectory generation module is used to fit the first trajectory coordinate set and the second trajectory coordinate set to obtain a left and right turning trajectory coordinate set;
[0031] The processing module is used to remove the vehicle front outline coordinate position from the left and right steering trajectory coordinate group to obtain the steering trajectory line for parallel driving.
[0032] Thirdly, embodiments of this application also provide an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the above-described method.
[0033] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the above-described method.
[0034] The at least one technical solution adopted in this application embodiment can achieve the following beneficial effects: Based on the processing requirements of the steering trajectory, firstly, the image pixel coordinate positions corresponding to different steering angles and the same steering distance during the steering process are calibrated. Then, by fitting the image pixel coordinate positions, a first trajectory coordinate group and a second trajectory coordinate group generated by the steering wheel at different steering angles are obtained. Next, the first trajectory coordinate group and the second trajectory coordinate group are fitted to obtain a left and right steering trajectory coordinate group. Finally, to obtain a better display effect, the vehicle front outline coordinate position is removed from the left and right steering trajectory coordinate group to obtain the parallel driving steering trajectory line. The parallel driving steering trajectory line can be displayed on the cockpit screen. Since the parallel driving steering trajectory line also has distance information, it provides driving prediction information during vehicle driving (the steering trajectory line will still be displayed if the steering wheel is straightened, i.e., no steering, at which time the steering angle is 0 degrees). Attached Figure Description
[0035] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0036] Figure 1 This is a flowchart illustrating the parallel driving steering trajectory data processing method in an embodiment of this application.
[0037] Figure 2 This is a schematic diagram of the parallel driving steering trajectory data processing device in the embodiments of this application;
[0038] Figure 3 This is a schematic diagram illustrating the implementation process of the parallel driving steering trajectory data processing method in a preferred embodiment of this application;
[0039] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation
[0040] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0041] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.
[0042] This application provides a method for processing parallel driving steering trajectory data, such as... Figure 1 The diagram shows a flowchart of a parallel driving steering trajectory data processing method in an embodiment of this application. The method includes at least the following steps S110 to S130:
[0043] Step S110: Calibrate the image pixel coordinate positions of the steering wheel at different steering angles and the same steering distance during the steering process, and obtain the first trajectory coordinate group and the second trajectory coordinate group generated by the steering wheel when steering at different angles by fitting the image pixel coordinate positions.
[0044] In real-world scenarios, the steering wheel of a physical vehicle is calibrated. To obtain more steering scenarios, the steering wheel needs to be rotated to different steering angles and calibrated. The calibration results include all angles of the steering guide lines. The steering guide lines serve as the final result of the parallel driving steering trajectory data processing in this embodiment. During actual driving, the remote operator enters the parallel cockpit and can see the steering guide lines on the cockpit display.
[0045] Different steering angles and the same steering distance refer to marking the corresponding image pixel positions at multiple 90-degree intervals, such as when the steering wheel turns left (or right), with each interval marked by the same distance length of 10m, 7.5m, 5m, and 2.5m, within a range of 0 to 540 degrees. In other words, the corresponding image pixel positions are marked and obtained within each interval.
[0046] The calibrated steering angle is obtained by calibrating the image pixel coordinates of the steering wheel at different steering angles and the same steering distance during the steering process.
[0047] Since the calibrated steering angle contains multiple pixels, a fitting process is required. After the fitting process, the first trajectory coordinate set and the second trajectory coordinate set generated by the steering wheel when it is turned at different angles are obtained.
[0048] For example, a polynomial curve fitting method is applied to fit the position information equations of the markings. The least squares method is then used to solve the parametric equations, yielding the position information of four coordinate points on the left and right trajectories under the steering wheel angle. Therefore, a total of eight polynomial equations can be solved.
[0049] Step S120: Fit the first trajectory coordinate group and the second trajectory coordinate group to obtain the left and right turning trajectory coordinate group.
[0050] The first and second trajectory coordinate sets constitute the two parallel steering guide lines in the parallel driving steering trajectory data, which the remote operator can see on the cockpit display in the parallel cockpit. They provide driving assistance when remotely controlling the vehicle. However, the first and second trajectory coordinate sets still need to be fitted to obtain the two trajectory equations for the left and right trajectory lines.
[0051] Then, by solving the trajectory equation, the left and right turning trajectories can be obtained. Further, after fitting, the fitted trajectory points need to be connected to obtain the trajectory line. Preferably, to achieve a smoother processing effect, the trajectory line can be smoothed.
[0052] In addition, the guide frame was obtained by connecting the key points obtained after fitting. The key points included four coordinate points and one vehicle head position point.
[0053] Step S130: Remove the vehicle front outline coordinate position from the left and right steering trajectory coordinate group to obtain the steering trajectory line for parallel driving.
[0054] Since the calibration is based on the steering wheel, the left and right steering trajectory coordinate sets include the vehicle's front outline. Therefore, it is necessary to remove the vehicle's front outline coordinate positions from the left and right steering trajectory coordinate sets to obtain the parallel driving steering trajectory lines.
[0055] The parallel driving steering trajectory line provides remote operators with an intuitive display of the vehicle's driving and steering trajectory in a real-world scenario, as well as the distance ahead, thereby avoiding collisions caused by excessive distance or lack of steering guidance.
[0056] In parallel driving systems of related technologies, remote operators often cannot see the forward driving trajectory and the distance to the vehicle / obstacle in front, leading to improper operation during remote control and adversely affecting the remotely controlled vehicle. The method in this application can display the vehicle's steering trajectory line in real time on the cockpit display, thereby providing remote operators with more driving assistance information.
[0057] In one embodiment of this application, the process of fitting the first trajectory coordinate set and the second trajectory coordinate set to obtain a left and right turning trajectory coordinate set further includes: calculating the inner line starting position corresponding to the line segment of the left and right turning trajectory at the same turning distance based on Euclidean distance; determining the inner line ending position based on the inner line starting position; and obtaining the inner line segment based on the inner line starting position and the inner line ending position.
[0058] To optimize the display effect of the steering trajectory line, inner lines can be added to the steering trajectory line obtained in the previous step. These inner line segments can be used to indicate different position distances, including at least 10m, 7.5m, 5m, and 2.5m.
[0059] Preferably, inner lines at positions 10m and 5m are selected. First, the positions on the Bézier curve corresponding to 10m and 5m on the broken line segment are calculated using Euclidean distance, serving as the starting points of the four inner lines. Then, the lengths of the 10m and 5m inner lines are set as D1 and D2, respectively. The equations of the two inner lines are also the lines connecting the starting points on the corresponding 10m and 5m trajectory lines. Finally, the endpoint positions of the two inner lines at 10m and 5m can be obtained by combining the straight line equations and the distance equations.
[0060] In one embodiment of this application, the step of removing the vehicle front outline coordinate position from the left and right steering trajectory coordinate group to obtain the parallel driving steering trajectory line includes: obtaining the vehicle front outline coordinate position group; and removing the pixel coordinates of the left and right steering trajectory coordinate group within the vehicle front outline coordinate position group.
[0061] The left and right trajectory lines cover the front of the vehicle, so the trajectory lines covered by the front need to be removed. For calculating the outer contour of the connected region at the front of the vehicle, the Otsu rule can be used to convert the original image to grayscale and then binarize it to obtain the coordinate set of the outer contour of the connected region at the front. Then, the number of regions within the outer contour coordinate set is calculated, and the pixel coordinates of the left and right trajectory lines within the front coordinate set are removed using the ray casting method.
[0062] In one embodiment of this application, the step of removing the vehicle front outline coordinate position from the left and right steering trajectory coordinate group to obtain the steering trajectory line for parallel driving further includes: removing the vehicle front outline coordinate position from the left and right steering trajectory coordinate group to obtain the steering trajectory line for any one steering direction; and mirroring the steering trajectory line of the arbitrary steering direction to obtain the steering trajectory line for another steering direction.
[0063] Since only the turning trajectory in one direction is calculated, and the steering wheel is symmetrical when turning, a mirror image can be used to calculate the corresponding trajectory, reducing the computational load. When a real vehicle turns left or right, it can be considered as symmetrical to the centerline of the vehicle's straight-line direction. Based on this principle, after finding the axis of symmetry, the right turn direction can be considered as the mirror image of the left turn direction about the axis of symmetry. The left turn pixel coordinate group, after being mirrored based on the axis of symmetry, becomes the right turn pixel coordinate group.
[0064] In one embodiment of this application, the step of fitting the first trajectory coordinate group and the second trajectory coordinate group to obtain the left and right turning trajectory coordinate group further includes: smoothing the left and right turning trajectories using Bézier curves.
[0065] The left and right trajectory lines formed by connecting the five feature points mentioned above are not smooth lines. In order to make the line segment visually smooth and conform to the basic curvature rules, the Bézier curve method is used to smooth the line segment.
[0066] In one embodiment of this application, the step of fitting the first trajectory coordinate group and the second trajectory coordinate group to obtain the left and right turning trajectory coordinate group further includes: adding a coordinate that fits the front of the vehicle and fitting it with the coordinate points in the first trajectory coordinate group and the coordinate points in the second trajectory coordinate group to obtain the left and right turning trajectory coordinate group.
[0067] Based on the actual situation, the line connecting the four coordinate points cannot perfectly match the position of the car's front. Therefore, a new coordinate system needs to be added based on the trajectory equation to match the car's front. The vertical coordinate is the function value of the trajectory equation, and the horizontal coordinate is the variable. The formula is as follows:
[0068] The coordinate system of the left and right trajectory lines is represented as follows:
[0069] Where i∈["left", "right"] represents the left and right trajectory lines. j∈[1, 2, 3, 4] represents the coordinates on the trajectory line.
[0070] Trajectory equation formula:
[0071] The newly added coordinates are represented as follows:
[0072] in The ordinate value is set based on the actual situation. The x-coordinate is the variable obtained by solving the corresponding trajectory equation using the least squares method. This coordinate is added to the left group of the trajectory. Where j∈[1, 2, 3, 4, 5].
[0073] In one embodiment of this application, fitting the image pixel coordinate positions to obtain a first trajectory coordinate group and a second trajectory coordinate group generated by the steering wheel when turning at different angles includes: dividing the steering angle range of 0-540 degrees when the steering wheel rotates in one direction into 6 steering intervals with 90-degree intervals as equal intervals; determining the total number of pixels in each 90-degree steering interval and calculating the number of pixels that need to be moved at 1 degree; determining multiple position coordinates corresponding to the target steering angle based on the number of pixels that need to be moved at 1 degree, wherein the position coordinates include at least 8, which are the positions of four coordinate points on the left and right steering trajectories corresponding to 10m, 7.5m, 5m, and 2.5m.
[0074] To obtain more accurate steering trajectory display results, it is necessary to obtain the steering position corresponding to each 1 degree of steering.
[0075] Based on eight polynomial equations, the total number of pixels on the curve segment at each 90-degree turning interval under each equation is calculated, and the total number of pixels is divided into 1-degree steps to obtain the turning position at 1 degree. Then, the steering wheel turns 540 degrees in one direction. Divided into 6 turning intervals by 90 degrees, they are: [0,90], [90,180], [180,270], [270,360], [360,450], [450,540].
[0076] Eight polynomials correspond to eight positions. These are the coordinates of four points on the left and right trajectory lines at positions of 10m, 7.5m, 5m, and 2.5m.
[0077] This application embodiment also provides a parallel driving steering trajectory data processing device 200, such as... Figure 2 As shown, a schematic diagram of the parallel driving steering trajectory data processing device in this application embodiment is provided. The parallel driving steering trajectory data processing device 200 includes at least: a calibration and fitting module 210, a trajectory generation module 220, and a processing module 230, wherein:
[0078] In one embodiment of this application, the calibration and fitting module 210 is specifically used to: calibrate the image pixel coordinate positions corresponding to different steering angles and the same steering distance during the steering process, and obtain the first trajectory coordinate group and the second trajectory coordinate group generated by the steering wheel when steering at different angles by fitting the image pixel coordinate positions.
[0079] In real-world scenarios, the steering wheel of a real vehicle is calibrated. To obtain more steering scenarios, the steering wheel needs to be rotated to different steering angles and calibrated. The calibration results include all angles of the steering guide lines. The steering guide lines serve as the final result of processing the parallel driving steering trajectory data in this embodiment of the application.
[0080] Different steering angles and the same steering distance refer to the image pixel positions corresponding to different 90-degree intervals, such as turning the steering wheel left (or right), with each interval marked with the same distance length of 10m, 7.5m, 5m, and 2.5m, and the marking range is 0 to 540 degrees. That is, the image pixel positions of the corresponding length are marked and obtained within each interval.
[0081] The calibrated steering angle is obtained by calibrating the image pixel coordinates of the steering wheel at different steering angles and the same steering distance during the steering process.
[0082] Since the calibrated steering angle contains multiple pixels, a fitting process is required. After the fitting process, the first trajectory coordinate set and the second trajectory coordinate set generated by the steering wheel when it is turned at different angles are obtained.
[0083] For example, a polynomial curve fitting method is applied to fit the position information equations of the markings. The least squares method is then used to solve the parametric equations, yielding the position information of four coordinate points on the left and right trajectories under the steering wheel angle. Therefore, a total of eight polynomial equations can be solved.
[0084] In one embodiment of this application, the trajectory generation module 220 is specifically used to: fit the first trajectory coordinate group and the second trajectory coordinate group to obtain a left and right turning trajectory coordinate group.
[0085] The first and second trajectory coordinate sets constitute the two parallel steering guide lines in the parallel driving steering trajectory data, which the remote operator can see on the cockpit display in the parallel cockpit. They provide driving assistance when remotely controlling the vehicle. However, the first and second trajectory coordinate sets still need to be fitted to obtain the two trajectory equations for the left and right trajectory lines.
[0086] Then, by solving the trajectory equation, the left and right turning trajectories can be obtained. Further, after fitting, the fitted trajectory points need to be connected to obtain the trajectory line. Preferably, to achieve a smoother processing effect, the trajectory line can be smoothed.
[0087] In addition, the guide frame was obtained by connecting the key points obtained after fitting, which included four coordinate points and one lane position point.
[0088] In one embodiment of this application, the processing module 230 is specifically used to: remove the vehicle front outline coordinate position from the left and right steering trajectory coordinate group to obtain the steering trajectory line for parallel driving.
[0089] Since the calibration is based on the steering wheel, the left and right steering trajectory coordinate sets include the front outline of the vehicle. Therefore, it is necessary to remove the front outline coordinate positions from the left and right steering trajectory coordinate sets to obtain the parallel driving steering trajectory lines.
[0090] The parallel driving steering trajectory line provides remote operators with an intuitive display of the vehicle's driving and steering trajectory in a real-world scenario, as well as the distance ahead, thereby avoiding collisions caused by excessive distance or lack of steering guidance.
[0091] It is understood that the above-mentioned parallel driving steering trajectory data processing device can implement each step of the parallel driving steering trajectory data processing method provided in the foregoing embodiments. The relevant explanations of the parallel driving steering trajectory data processing method are applicable to the parallel driving steering trajectory data processing device, and will not be repeated here.
[0092] like Figure 3 As shown, to better illustrate the parallel driving steering trajectory data processing method in this application, a schematic diagram of the implementation flow of the parallel driving steering trajectory data processing method in a preferred embodiment of this application is presented, which specifically includes the following implementation steps:
[0093] S1 marks the image pixel positions corresponding to 10m, 7.5m, 5m, and 2.5m for each 90-degree angle when the steering wheel turns left, with a marking range of 0 to 540 degrees.
[0094] S2 uses a polynomial fitting method to fit the position information equations of the annotations. The least squares method is used to solve the parametric equations. Therefore, a total of eight polynomial equations can be solved. The formula for solving a single polynomial is as follows:
[0095] The labeled image pixel coordinates are: (x1, y1), (x2, y2), ..., (x... m y m ).
[0096] The polynomial formula is:
[0097] Sample input method:
[0098] Based on the coordinate data, the fitting function H(x) is given, and the residual is: r i =H(x) i )-y iUsing L2 regularization, solve for H(x) = w0 + w1x + w2x 2 +…+w n x n .
[0099] The objective function is: The solution method is to minimize the objective function.
[0100] The eight polynomial equations are in the form of the fitting function H(x). The fitting process involves fitting the line and marking the points; 90-degree angles are also marked points.
[0101] S3, based on eight polynomial equations, calculates the total number of pixels on the curve segment at each 90-degree turning interval under each equation, and then segments the total number of pixels in 1-degree increments to obtain the turning position at 1 degree. The formula is as follows:
[0102] The steering wheel has a total 540-degree turning angle in one direction. Divided into 90-degree intervals, this can be categorized into 6 turning zones: [0, 90], [90, 180], [180, 270], [270, 360], [360, 450], [450, 540]. Each 90-degree turning zone contains k pixels: (x1, y1), (x2, y2), ..., (x...). k y k The value of k may differ in different intervals.
[0103] Calculate the number of pixels needed to move at 1 degree:
[0104] Therefore, the distance traveled at a steering angle of α is: in This indicates rounding down to the nearest whole number.
[0105] Therefore, the position corresponding to a steering angle of α is:
[0106] Eight polynomials correspond to eight positions. These are the coordinates of four points on the left and right trajectory lines at positions of 10m, 7.5m, 5m, and 2.5m.
[0107] S4. Based on the four coordinate points obtained in step S3 on the left and right trajectory lines, use polynomial fitting to fit the four coordinate points on the left and right trajectory lines respectively, thus obtaining two trajectory equations for the left and right trajectory lines. The solution method is the same as in step S2. Due to the actual situation, the line connecting the four coordinate points cannot perfectly match the position of the car's front. Therefore, a coordinate that can match the front of the car needs to be added based on the trajectory equations. The vertical coordinate is the function value of the trajectory equation, and the horizontal coordinate is the variable.
[0108] The coordinate system of the left and right trajectory lines is represented as follows: Where i∈["left", "right"] represents the left and right trajectory lines. j∈[1, 2, 3, 4] represents the coordinates on the trajectory line.
[0109] Trajectory equation formula:
[0110] The newly added coordinates are represented as follows: in The ordinate value is set based on the actual situation. The x-coordinate is the variable obtained by solving the corresponding trajectory equation using the least squares method. This coordinate is added to the left group of the trajectory. Where j∈[1, 2, 3, 4, 5].
[0111] S5, the left and right trajectory lines of the line segment formed by connecting five points are not smooth. In order to make the line segment visually smooth and conform to the basic curvature, the Bézier curve method is used to smooth the line segment.
[0112] Preferably, the embodiments of this application use a fourth-order Bézier curve.
[0113] S6 uses Euclidean distance to calculate the positions on the Bézier curve corresponding to 10m and 5m on the broken line segment, which are used as the starting points of the four inner lines.
[0114] S7, let the lengths of the 10m and 5m inner lines be D1 and D2 respectively. The equations of the two inner line straight lines are also the lines connecting the starting points on the corresponding 10m and 5m trajectory lines. Therefore, the endpoint positions of the two inner lines for each of the 10m and 5m can be obtained by combining the straight line equations and the distance equations. The formula is as follows:
[0115] Given: Two points on a trajectory line approximately 10m long The trajectory line is about 5 meters long and has two points. Based on the equation of the straight line y=kx+b, the slope of the corresponding line k∈[k 10m k 5m ], bias b∈[b 10m b 5m ].
[0116] Joint parametric equations: Where i∈[10m, 5m], D∈[D1, D2].
[0117] The joint parametric equation can be transformed into a quadratic equation in one variable. In practice, the equation has two real roots. The valid root of the solution located between the two trajectory lines is retained; this is the x-coordinate of the endpoint. Substituting this root into the equation of the straight line yields the y-coordinate. The coordinates of the endpoints corresponding to the four inner lines are then obtained. Connecting the corresponding starting and ending points gives the inner lines.
[0118] S8. Since the left and right trajectory lines cover the front of the car, it is necessary to remove the trajectory lines covered by the front of the car. This paper uses the Otsu method to perform binarization processing on the original image after grayscale conversion to obtain the outer contour coordinate set of the connected region of the front of the car.
[0119] S9 uses a ray-mapping method to remove pixel coordinates of the left and right trajectory lines within the vehicle's front coordinate group. It calculates how many pixels are within the contour.
[0120] S10, when a vehicle turns left or right, it can be considered as symmetrical to the centerline of the vehicle's straight-line direction. Based on this principle, after finding the axis of symmetry, the right turn direction can be considered as the mirror image of the left turn direction about the axis of symmetry. The left turn pixel coordinate group, after being mirrored based on the axis of symmetry, becomes the right turn pixel coordinate group.
[0121] S11. Finally, draw the left and right turning trajectory lines and the four inner lines on the image for the left or right turn direction.
[0122] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.
[0123] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.
[0124] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.
[0125] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming a parallel driving steering trajectory data processing device at the logical level. The processor executes the program stored in memory and specifically performs the following operations:
[0126] The image pixel coordinates of the steering wheel at different steering angles and the same steering distance during the steering process are calibrated, and the first trajectory coordinate set and the second trajectory coordinate set generated by the steering wheel at different steering angles are obtained by fitting the image pixel coordinates.
[0127] The first trajectory coordinate set and the second trajectory coordinate set are fitted to obtain the left and right turning trajectory coordinate sets;
[0128] By removing the vehicle front outline coordinates from the left and right steering trajectory coordinate sets, the steering trajectory line for parallel driving is obtained.
[0129] The above is as stated in this application. Figure 1 The method executed by the parallel driving steering trajectory data processing device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.
[0130] The electronic device can also perform Figure 1The method for executing the parallel driving steering trajectory data processing device, and the implementation of the parallel driving steering trajectory data processing device in... Figure 1 The functions of the embodiments shown are not described in detail here.
[0131] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the parallel driving steering trajectory data processing device in the illustrated embodiment is specifically used to perform:
[0132] The image pixel coordinates of the steering wheel at different steering angles and the same steering distance during the steering process are calibrated, and the first trajectory coordinate set and the second trajectory coordinate set generated by the steering wheel at different steering angles are obtained by fitting the image pixel coordinates.
[0133] The first trajectory coordinate set and the second trajectory coordinate set are fitted to obtain the left and right turning trajectory coordinate sets;
[0134] By removing the vehicle front outline coordinates from the left and right steering trajectory coordinate sets, the steering trajectory line for parallel driving is obtained.
[0135] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0136] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0137] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0138] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0139] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0140] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0141] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0142] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0143] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0144] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for processing parallel driving steering trajectory data, wherein, The method includes: The image pixel coordinates of the steering wheel at different steering angles and the same steering distance during the steering process are calibrated, and the first trajectory coordinate set and the second trajectory coordinate set generated by the steering wheel at different steering angles are obtained by fitting the image pixel coordinates. The first trajectory coordinate set and the second trajectory coordinate set are fitted to obtain the left and right turning trajectory coordinate sets; The vehicle front outline coordinate position is removed from the left and right steering trajectory coordinate set to obtain the parallel driving steering trajectory line; The process of fitting the first trajectory coordinate set and the second trajectory coordinate set to obtain the left and right turning trajectory coordinate sets further includes: Based on Euclidean distance, calculate the inner starting position of the line segment of the left and right turning trajectories at the same turning distance; The endpoint position of the inner line is determined based on the starting position of the inner line; The inner line segment is obtained based on the starting position and ending position of the inner line; The step of removing the vehicle front outline coordinates from the left and right steering trajectory coordinate sets to obtain the parallel driving steering trajectory line includes: Obtain the coordinate position set of the vehicle front outline; Remove the pixel coordinates of the left and right turning trajectory coordinate group from the vehicle front outline coordinate position group; The step of removing the vehicle front outline coordinate position from the left and right steering trajectory coordinate sets to obtain the parallel driving steering trajectory line also includes: By removing the vehicle front outline coordinates from the left and right turning trajectory coordinate sets, the turning trajectory line for any turn can be obtained; The steering trajectory of any one of the turns is mirrored and flipped to obtain the steering trajectory of the other turn; The step of fitting the first trajectory coordinate group and the second trajectory coordinate group to obtain the left and right turning trajectory coordinate group further includes: smoothing the left and right turning trajectory coordinate group using a Bézier curve. The step of fitting the first trajectory coordinate group and the second trajectory coordinate group to obtain the left and right turning trajectory coordinate group further includes: adding a coordinate that fits the front of the vehicle and fitting it with the coordinate points in the first trajectory coordinate group and the coordinate points in the second trajectory coordinate group to obtain the left and right turning trajectory coordinate group.
2. The method as described in claim 1, wherein, Fitting the image pixel coordinate positions yields a first trajectory coordinate set and a second trajectory coordinate set generated by the steering wheel when it is turned at different angles, including: The steering angle range of 0-540 degrees when the steering wheel is turned in one direction is divided into 6 steering intervals by dividing the steering wheel into 90-degree intervals; Determine the total number of pixels within each 90-degree turning interval, and calculate the number of pixels that need to be moved per degree. Based on the number of pixels that need to be moved at 1 degree, determine multiple position coordinates corresponding to the target turning angle. Among them, the position coordinates include at least 8, which are the coordinate points of four points on the left and right turning trajectories at positions of 10m, 7.5m, 5m, and 2.5m.
3. A parallel driving steering trajectory data processing device, wherein, The device includes: The calibration and fitting module is used to calibrate the image pixel coordinate positions of the steering wheel when it is at different steering angles and the same steering distance during the steering process, and to obtain the first trajectory coordinate group and the second trajectory coordinate group generated by the steering wheel when it is turned at different angles by fitting the image pixel coordinate positions. The trajectory generation module is used to fit the first trajectory coordinate set and the second trajectory coordinate set to obtain a left and right turning trajectory coordinate set; The processing module is used to remove the vehicle front outline coordinate position from the left and right steering trajectory coordinate group to obtain the steering trajectory line for parallel driving. The process of fitting the first trajectory coordinate set and the second trajectory coordinate set to obtain the left and right turning trajectory coordinate sets further includes: Based on Euclidean distance, calculate the inner starting position of the line segment of the left and right turning trajectories at the same turning distance; The endpoint position of the inner line is determined based on the starting position of the inner line; The inner line segment is obtained based on the starting position and ending position of the inner line; The step of removing the vehicle front outline coordinates from the left and right steering trajectory coordinate sets to obtain the parallel driving steering trajectory line includes: Obtain the coordinate position set of the vehicle front outline; Remove the pixel coordinates of the left and right turning trajectory coordinate group from the vehicle front outline coordinate position group; The step of removing the vehicle front outline coordinate position from the left and right steering trajectory coordinate sets to obtain the parallel driving steering trajectory line also includes: By removing the vehicle front outline coordinates from the left and right turning trajectory coordinate sets, the turning trajectory line for any turn can be obtained; The steering trajectory of any one of the turns is mirrored and flipped to obtain the steering trajectory of the other turn; The step of fitting the first trajectory coordinate group and the second trajectory coordinate group to obtain the left and right turning trajectory coordinate group further includes: smoothing the left and right turning trajectory coordinate group using a Bézier curve. The step of fitting the first trajectory coordinate group and the second trajectory coordinate group to obtain the left and right turning trajectory coordinate group further includes: adding a coordinate that fits the front of the vehicle and fitting it with the coordinate points in the first trajectory coordinate group and the coordinate points in the second trajectory coordinate group to obtain the left and right turning trajectory coordinate group.
4. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 2.
5. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method of any one of claims 1 to 2.