Method, device and storage medium for drawing obstacle envelope lines based on vehicle-mounted radar
Through vehicle-mounted radar acquisition and Bezier curve fitting, the problem of inaccurate display of obstacle profiles in the prior art is solved, and the accurate, efficient and beautiful display of obstacle profiles is achieved, which improves driving safety.
Patent Information
- Application Number
- CN202111219115.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-10-20
- Publication Date
- 2025-07-25
- Estimated Expiration
- 2041-10-20
AI Technical Summary
The prior art is difficult to accurately display obstacle profiles, especially in the case of multiple obstacles, and it is difficult to distinguish and fit smooth obstacle envelopes.
Obstacle information is collected through vehicle-mounted radar, radar points are classified, polar coordinate systems are established for sorting and grouping, and the Bezier curve fitting is used to display the obstacle envelope in real time.
It realizes accurate, efficient and beautiful display of obstacle profiles, accurately distinguishing different obstacles, and improving driving safety.
Smart Images

Figure CN113960603B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of image processing in automotive assisted driving, and particularly to a method, device, and storage medium for drawing an obstacle envelope line based on an in-vehicle radar. Background Art
[0002] With the improvement of the intelligence level of automobiles, the issue of driving safety has become increasingly prominent, and advanced driver assistance systems have emerged as the times require. Radar detection is widely used in the technology of automotive driving assistance systems. Vehicle surrounding environment information is mainly obtained through radar sensors installed around the vehicle body. Among them, ultrasonic radars have obvious advantages in short-distance measurement and are widely used in automotive autonomous driving and assisted driving, including parking distance measurement, auxiliary obstacle avoidance, etc., reducing the frequency of traffic accidents.
[0003] Most of the existing products on the market are based on radar distance data, and use regular shield-shaped images to discretely or continuously identify the general positions of obstacles, without depicting the specific contour lines of the obstacles facing the vehicle; when there are multiple obstacles around the vehicle, it is difficult to distinguish different obstacles using the shield-shaped radar lines drawn based on radar distance; there is a lack of an accurate and efficient fitting method to fit discrete radar coordinate points into a smooth obstacle envelope line that passes through each radar point to display the obstacle contour.
[0004] In order to accurately display the obstacle contour line, accurately distinguish different obstacles and display them separately, and at the same time make the fitting curve fit the actual obstacle position to achieve accuracy, efficiency, and aesthetics, there is an urgent need for a new method for calculating the obstacle envelope line. Summary of the Invention
[0005] In view of the above problems, the present invention provides a method, device, and storage medium for drawing an obstacle envelope line based on an in-vehicle radar, which can draw an obstacle envelope line based on in-vehicle radar coordinate data; display the obstacle contour lines one by one for precise obstacle avoidance; use a method of fitting a smooth curve to radar coordinate points, which is accurate, efficient, and aesthetic, obtain vehicle surrounding environment information, safely respond to complex situations encountered during vehicle driving, and has strong real-time performance.
[0006] Its technical solution is as follows: A method for drawing an obstacle envelope line based on an in-vehicle radar, characterized by comprising the following steps:
[0007] Step 1: Collect obstacle information through an in-vehicle radar; obtain the coordinate information of obstacle radar points in the world coordinate system;
[0008] Step 2: Classify the obstacle radar points according to the front area, rear area, and left and right areas of the vehicle;
[0009] Step 3: Establish polar coordinate systems in the front area and rear area of the vehicle respectively, convert to obtain the coordinate information of the obstacle radar points in the polar coordinate systems, sort the obstacle radar points in the front area and rear area of the vehicle according to the polar coordinate angle, and sort the obstacle radar points in the left and right areas of the vehicle according to the magnitude of the ordinate in the world coordinate system;
[0010] Step 4: Calculate the distance between adjacent obstacle radar points sorted in Step 3 in the world coordinate system, and group the obstacle radar points according to the distance magnitude;
[0011] Step 5: According to the grouping, perform interpolation to fit curves on the sorted obstacle radar points in segments to obtain the coordinate points of the fitted curves;
[0012] Step 6: According to the proportional relationship between the world coordinates and the image coordinates, obtain the obstacle envelope line through the coordinate points of the fitted curves, and display the obstacle envelope line on the image in real time.
[0013] Further, in Step 1, the world coordinate system adopts a two-dimensional rectangular coordinate system, with the center point of the current vehicle as the coordinate origin, the due right direction of the vehicle as the positive x-axis direction, and the due front direction as the positive y-axis direction.
[0014] Further, in Step 2, the area with the ordinate greater than the ordinate of the front axle of the vehicle in the world coordinate system is divided into the front area of the vehicle, the area with the ordinate less than the ordinate of the rear axle of the vehicle is divided into the rear area of the vehicle, and the area with the ordinate less than the ordinate of the front axle of the vehicle and greater than the ordinate of the rear axle of the vehicle is divided into the left and right areas of the vehicle;
[0015] Further, in Step 3, the polar coordinate system in the front area of the vehicle takes the center point of the front axle of the vehicle as the origin, and the right direction as the positive polar axis direction; the polar coordinate system in the rear area of the vehicle takes the center point of the front axle of the vehicle as the origin, and the right direction as the positive polar axis direction.
[0016] Further, in Step 3, the conversion relationship between the obstacle radar points in the front area of the vehicle in the polar coordinate system of the front area of the vehicle and the world coordinate system is as follows:
[0017]
[0018]
[0019] Among them, (x, y) is the coordinate of the obstacle radar point in the front area of the vehicle in the world coordinate system, (r f , θ f ) is the coordinate of the obstacle radar point in the front area of the vehicle in the polar coordinate system of the front area of the vehicle, L is the vehicle length, and L f is the front overhang, that is, the distance from the front axle to the front of the vehicle;
[0020] The conversion relationship between the obstacle radar points in the rear area of the vehicle in the polar coordinate system and the world coordinate system in the rear area of the vehicle is as follows:
[0021]
[0022]
[0023] Wherein, (x, y) are the coordinates of the obstacle radar points in the rear area of the vehicle in the world coordinate system, and (r r , θ r ) are the coordinates of the obstacle radar points in the rear area of the vehicle in the polar coordinate system of the rear area of the vehicle. Among them, L is the vehicle length, and L r is the rear overhang, that is, the distance from the rear axle to the rear of the vehicle.
[0024] Furthermore, in step 4, calculate the distance between adjacent coordinate points in the world coordinate system. That is, for two adjacent coordinate points (x1, y1) and (x2, y2), the distance d is
[0025]
[0026] Set the distance threshold d ε , when d ≤ d ε , group the adjacent obstacle radar points into one group. When d > d ε , group the adjacent obstacle radar points into different groups. In this embodiment, the threshold range can be set to 20 cm to 50 cm, indicating that if the distance between two points exceeds this distance, they are divided into different groups.
[0027] In step 5, the interpolation and fitting curve includes interpolation calculation and fitting calculation;
[0028] The interpolation calculation is specifically performed as follows:
[0029] Step A: Take each group of obstacle radar points as the original points, calculate the midpoints P1′ and P2′ of three adjacent original points P1, P2, and P3, connect the adjacent midpoints to obtain a line segment, and translate the line segment so that the midpoint of the line segment coincides with point P2. The two end points of the translated line segment are used as interpolation points;
[0030] Step B: Repeat step A until all adjacent three original points in each group of obstacle radar points are calculated, and all interpolation points of each group of obstacle radar points are obtained.
[0031] The fitting calculation is specifically performed as follows:
[0032] Use Bezier curves to perform piecewise fitting on every two original obstacle radar points with interpolation points added. Among them, there is one interpolation point between the first two original points and the last two original points, and a second-order Bezier curve is used for fitting. There are two interpolation points between every other two original points, and a third-order Bezier curve is used for fitting. For n points P0, P1, P2, …, P n The recurrence calculation formula for the points on the k-th order Bezier curve of
[0033]
[0034] is as follows: where t is the independent variable, and its value range is from 0 to 1. Calculate the fitting curve segment by segment through the recurrence calculation formula, so that each group of obstacle radar points obtains a set of fitting curve coordinate points.
[0035] In step 6, according to the ratio Ratio between the world coordinate and the image coordinate, scale the fitting curve coordinate points (x, y) to the image coordinate system (Ratio * x, Ratio * y). Connect the fitting curve coordinate points in groups in the image to obtain the obstacle envelope line, and at the same time mark the vehicle position in the image.
[0036] A device for drawing an obstacle envelope line based on an in-vehicle radar, characterized in that it includes: a processor, a memory, and a program;
[0037] The program is stored in the memory, and the processor calls the program stored in the memory to execute the above method for drawing an obstacle envelope line based on an in-vehicle radar.
[0038] A computer-readable storage medium, characterized in that: the computer-readable storage medium is configured to store a program, and the program is configured to execute the above method for drawing an obstacle envelope line based on an in-vehicle radar.
[0039] The present invention provides a method for drawing an obstacle envelope line based on an in-vehicle radar. It uses radar coordinate point data to fit a smooth curve, and displays the contour lines of the obstacles around the vehicle one by one. By collecting the world coordinates of the obstacle radar points fed back by the in-vehicle radar in real time, and then according to the different positions of the obstacle radar points, the obstacle radar points are divided into different front-vehicle areas, rear-vehicle areas, left-and-right vehicle areas. Sort the coordinates of the obstacle radar points within each area to divide different obstacles. Perform interpolation fitting on the discrete radar points grouped and sorted in segments, and display the radar lines in the image in real time. It can accurately display the contour line of the obstacle facing the vehicle, accurately distinguish different obstacles, display them separately, achieve precise obstacle avoidance, and the fitting curve fits the actual position of the obstacle, being accurate, efficient, and beautiful. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1Schematic diagram of the main steps of the method for drawing an obstacle envelope line based on an in-vehicle radar in the embodiment;
[0041] Figure 2 Schematic diagram of converting the coordinates of the front and rear areas of the vehicle in the embodiment to the polar coordinate system;
[0042] Figure 3 Schematic diagram of the interpolation and fitting curve process in the embodiment;
[0043] Figure 4 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners
[0044] In the prior art, there are also methods to obtain the coordinate information of several obstacles through radar and represent the positions of the obstacles with several discrete coordinates. However, the displayed coordinate data mostly represent the positions of the obstacles by the radar distances from the corresponding obstacles to the edge of the vehicle after being screened and preprocessed at fixed positions and directions, and cannot completely display the outlines of the obstacles. Therefore, the present invention provides a method for drawing an obstacle envelope line based on an in-vehicle radar, which can accurately display the contour line of the obstacle facing the vehicle, accurately distinguish different obstacles and display them separately, achieve precise obstacle avoidance, and make the fitting curve fit the actual position of the obstacle, being accurate, efficient and beautiful.
[0045] See Figure 1 , the method for drawing an obstacle envelope line based on an in-vehicle radar of the present invention at least includes the following steps:
[0046] Step 1: Collect obstacle information through the in-vehicle radar; obtain the coordinate information of the obstacle radar points in the world coordinate system;
[0047] Step 2: Classify the obstacle radar points according to the front area, rear area and left and right areas of the vehicle;
[0048] Step 3: Establish polar coordinate systems in the front area and rear area of the vehicle respectively, convert to obtain the coordinate information of the obstacle radar points in the polar coordinate system, sort the obstacle radar points in the front area and rear area of the vehicle according to the polar coordinate angle, and sort the obstacle radar points in the left and right areas of the vehicle according to the magnitude of the ordinate in the world coordinate system;
[0049] Step 4: Calculate the distances between adjacent obstacle radar points sorted in Step 3 in the world coordinate system, and group the obstacle radar points according to the magnitude of the distances;
[0050] Step 5: Interpolate and fit curves for the sorted obstacle radar points in segments according to the groups to obtain the coordinate points of the fitting curves;
[0051] Step 6: According to the proportional relationship between the world coordinates and the image coordinates, obtain the obstacle envelope line by fitting the curve coordinate points, and display the obstacle envelope line in the image in real time.
[0052] Specifically, in an embodiment of the present invention, in step 1, the world coordinate system adopts a two-dimensional rectangular coordinate system. The world coordinate system takes the center point of the current vehicle as the coordinate origin, the due right direction of the vehicle as the positive direction of the x-axis, and the due front direction as the positive direction of the y-axis. The coordinate information of the obstacle radar points is obtained through the vehicle-mounted radar in the world coordinate system.
[0053] See Figure 2 , in step 2, divide the area according to the vertical coordinate size of the coordinate points in the world coordinate system. Specifically, in the world coordinate system, the area where the vertical coordinate is greater than the vertical coordinate of the front axle of the vehicle is divided into the front area of the vehicle, the area where the vertical coordinate is less than the vertical coordinate of the rear axle of the vehicle is divided into the rear area of the vehicle, and the area where the vertical coordinate is less than the vertical coordinate of the front axle of the vehicle and greater than the vertical coordinate of the rear axle of the vehicle is divided into the left and right areas of the vehicle.
[0054] In step 3, establish polar coordinate systems in the front area and the rear area of the vehicle respectively, and convert to obtain the coordinate information of the obstacle radar points in the polar coordinate system. Specifically, in this embodiment, the polar coordinate system in the front area of the vehicle takes the center point of the front axle of the vehicle as the origin, and the right direction as the positive direction of the polar axis; the polar coordinate system in the rear area of the vehicle takes the center point of the front axle of the vehicle as the origin, and the right direction as the positive direction of the polar axis;
[0055] The conversion relationship between the obstacle radar points in the front area of the vehicle in the polar coordinate system of the front area of the vehicle and the world coordinate system is as follows:
[0056]
[0057]
[0058] Among them, (x, y) is the coordinate of the obstacle radar point in the front area of the vehicle in the world coordinate system, (r f , θ f ) is the coordinate of the obstacle radar point in the front area of the vehicle in the polar coordinate system of the front area of the vehicle, L is the vehicle length, and L f is the front overhang, that is, the distance from the front axle to the front of the vehicle;
[0059] The conversion relationship between the obstacle radar points in the rear area of the vehicle in the polar coordinate system of the rear area of the vehicle and the world coordinate system is as follows:
[0060]
[0061]
[0062] Among them, (x, y) is the coordinate of the obstacle radar point in the rear area of the vehicle in the world coordinate system, (r r , θr ) are the coordinates of the obstacle radar points in the rear area of the vehicle in the polar coordinate system of the rear area of the vehicle, where L is the vehicle length, and L r is the rear overhang, that is, the distance from the rear axle to the rear of the vehicle. Thus, in the radar area of the entire vehicle, a polar coordinate system located at the front and rear and a world coordinate system representing the left and right areas of the vehicle located in the middle are set up.
[0063] There is a certain distance between the obstacles around the vehicle and the vehicle edge. If only the rectangular coordinate system is used, it is not convenient for the coordinate sorting in the subsequent steps, and the arrangement order of the coordinate points will further affect the shape of the fitting curve. Considering that the edges of the front and rear of the vehicle are approximately arc-shaped, and the distribution law of the obstacles with respect to the centers of the front and rear axles is also the same, so taking the two center points of the front and rear axles as the origin respectively, a polar coordinate system is introduced to facilitate the sorting of the coordinate points at the front and rear of the vehicle according to the angle.
[0064] Then, the obstacle radar points in the front area and the rear area of the vehicle are sorted according to the magnitude of the polar coordinate angle, and the obstacle radar points in the left and right areas of the vehicle are sorted according to the magnitude of the ordinate in the world coordinate system; the coordinate points sorted by polar coordinates in the front area and the rear area of the vehicle will not participate in the ordinate sorting of the left and right areas of the vehicle. The points sorted by the ordinate of the left and right areas of the vehicle will not be sorted by polar coordinates in the front area and the rear area of the vehicle either. Because all the obstacle coordinate points have been separated before sorting, the sorting does not affect each other.
[0065] In step 4, for the sorted coordinate points, in the world coordinate system, calculate the distance between adjacent coordinate points, that is, for two adjacent points (x1, y1), (x2, y2), the distance d is
[0066]
[0067] Set the distance threshold d ε , when d ≤ d ε , group the adjacent obstacle radar points into one group, when d > d ε , group the adjacent obstacle radar points into different groups.
[0068] In step 5, according to the grouping, for the sorted obstacle radar points, perform piecewise interpolation to fit the curve to obtain the coordinate points of the fitted curve. In this embodiment, the interpolation to fit the curve includes interpolation calculation and fitting calculation;
[0069] The interpolation calculation is specifically executed as follows:
[0070] Step A: (1) Take each group of obstacle radar points as the original points, and calculate the midpoints P1′, P2′ of three adjacent original points P1, P2, P3; (2) Connect the adjacent midpoints to obtain a line segment; (3) Translate the line segment so that the midpoint of the line segment coincides with point P2, and the two end points of the translated line segment are used as the interpolation points;
[0071] Step B: Repeat Step A until all adjacent three original points in each group of obstacle radar points are calculated, and all interpolation points of each group of obstacle radar points are obtained.
[0072] As Figure 3 shown, Figure 3 there are original points P1, P2, P3, P4. (1) First, calculate the midpoints P1′, P2′, P3′ of two adjacent original points; (2) Connect adjacent midpoints to obtain two line segments; (3) Translate the line segments so that the midpoints of the line segments coincide with the middle points, and the two endpoints of the translated line segments are used as interpolation points.
[0073] The fitting calculation is specifically performed as follows:
[0074] Use Bezier curves to perform piecewise fitting on every two original obstacle radar points plus interpolation points. Among them, there is one interpolation point between the first two original points and the last two original points, and a second-order Bezier curve is used for fitting. There are two interpolation points between other two original points, and a third-order Bezier curve is used for fitting. For n points P0, P1, P2, …, P n The recurrence calculation formula for the points on the k-order Bezier curve of is:
[0075]
[0076] where t is the independent variable, and its value range is from 0 to 1. Calculate the fitting curve in segments through the recurrence calculation formula, so that each group of obstacle radar points obtains a set of fitting curve coordinate points.
[0077] In this embodiment, through the sorting in the previous Step 3, it is more convenient to interpolate the fitting curve. Both interpolation and Bezier curve fitting need to be in order, and the curve shapes calculated by control points in different orders are different. The radar data is discretely distributed in a surrounding shape around the vehicle. Based on this, the head and tail of the vehicle are sorted according to the polar coordinate angle, and both sides of the vehicle are sorted according to the ordinate. The calculated Bezier curve is smooth and regular.
[0078] In Step 6, according to the ratio Ratio between the world coordinate and the image coordinate, scale the fitting curve coordinate points (x, y) to the image coordinate system (Ratio * x, Ratio * y), connect each fitting curve coordinate point in groups in the image to obtain the obstacle envelope line, and mark the vehicle position in the image at the same time.
[0079] In this embodiment, innovative discrete radar coordinate point data that are rarely used are employed in the calculation of the obstacle envelope line. At the same time, a specific sorting and grouping method is set for the radar coordinate fitting curve to distinguish obstacles. Moreover, a specific interpolation and fitting method that conforms to the distribution law of the surrounding obstacles of the vehicle is set. Thus, by using the method for drawing the obstacle envelope line based on the vehicle-mounted radar provided by the present invention, smooth curves are fitted with the radar coordinate point data, and the contour lines of the surrounding obstacles of the vehicle are displayed one by one. The world coordinates of the obstacle radar points fed back by the vehicle-mounted radar are collected in real time, the coordinate information is preprocessed, the coordinates are sorted and grouped to divide different obstacles, the discrete radar points after grouping and sorting are segmented for interpolation and fitting curves, and the radar lines are displayed in the image in real time. It can accurately display the contour line of the obstacle facing the vehicle, accurately distinguish different obstacles, display them separately, achieve precise obstacle avoidance, the fitting curve fits the actual position of the obstacle, and is accurate, efficient, and beautiful.
[0080] In an embodiment of the present invention, there is also provided a device for the method of drawing an obstacle envelope line based on a vehicle-mounted radar, which includes: a processor, a memory, and a program;
[0081] The program is stored in the memory, and the processor calls the program stored in the memory to execute the above-mentioned method for drawing an obstacle envelope line based on a vehicle-mounted radar.
[0082] The computer device may be a terminal, and its internal structure diagram may be as Figure 4 shown. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected through a bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements the method for drawing an obstacle envelope line based on a vehicle-mounted radar. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.
[0083] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. Among them, the memory is used to store programs, and the processor executes the programs after receiving execution instructions.
[0084] The processor can be an integrated circuit chip with the ability to process signals. The above-mentioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc. The processor can also be other general-purpose processors, 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, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.
[0085] Those skilled in the art can understand that Figure 4 the structure shown in [the figure] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.
[0086] In an embodiment of the present invention, there is also provided a computer-readable storage medium, which is configured to store a program, and the program is configured to execute the above-mentioned method for drawing an obstacle envelope line based on an in-vehicle radar.
[0087] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a computer device, or a computer program product. Therefore, the embodiments of the present invention can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0088] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, computer devices, or computer program products according to the embodiments of the present invention. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing terminal devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing terminal devices generate a device for realizing the functions specified in the flowcharts and / or block diagrams.
[0089] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that realizes the functions specified in the flowchart.
[0090] The above has introduced in detail the application of the method, computer device, and computer-readable storage medium for drawing an obstacle envelope line based on an in-vehicle radar provided by the present invention. Specific examples are used herein to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.
Claims
1. A method for drawing an obstacle envelope based on an in-vehicle radar, characterized in that, Including the following steps: Step 1: Collect obstacle information through on-vehicle radar; Obtain the coordinate information of obstacle radar points in the world coordinate system; Step 2: Classify the obstacle radar points according to the front area, rear area, left and right areas of the vehicle; Step 3: Establish polar coordinate systems in the front area and rear area of the vehicle respectively, convert to obtain the coordinate information of obstacle radar points in the polar coordinate system, sort the obstacle radar points in the front area and rear area according to the polar coordinate angle, and sort the obstacle radar points in the left and right areas of the vehicle according to the magnitude of the ordinate in the world coordinate system; Step 4: Calculate the distance between adjacent obstacle radar points sorted in Step 3 in the world coordinate system, and group the obstacle radar points according to the distance magnitude; Step 5: According to the grouping, perform interpolation to fit curves on the sorted obstacle radar points in segments to obtain the coordinate points of the fitted curves; Step 6: According to the proportional relationship between the world coordinates and the image coordinates, obtain the obstacle envelope line through the coordinate points of the fitted curves, and display the obstacle envelope line in the image in real time.
2. The method for drawing an obstacle envelope based on in-vehicle radar according to claim 1, wherein: In Step 1, the world coordinate system adopts a two-dimensional rectangular coordinate system, with the center point of the current vehicle as the coordinate origin, the positive right direction of the vehicle as the positive x-axis direction, and the positive front direction as the positive y-axis direction.
3. The method for drawing an obstacle envelope line based on an in-vehicle radar according to claim 2, wherein: In Step 2, in the world coordinate system, the area with the ordinate greater than the ordinate of the front axle of the vehicle is divided into the front area of the vehicle, the area with the ordinate less than the ordinate of the rear axle of the vehicle is divided into the rear area of the vehicle, and the area with the ordinate less than the ordinate of the front axle of the vehicle and greater than the ordinate of the rear axle of the vehicle is divided into the left and right areas of the vehicle.
4. The method for drawing an obstacle envelope based on in-vehicle radar according to claim 3, wherein: In Step 3, the polar coordinate system in the front area of the vehicle takes the center point of the front axle of the vehicle as the origin, and the right direction as the positive direction of the polar axis; the polar coordinate system in the rear area of the vehicle takes the center point of the front axle of the vehicle as the origin, and the right direction as the positive direction of the polar axis.
5. The method for drawing an obstacle envelope line based on an in-vehicle radar according to claim 4, wherein: In Step 3, the conversion relationship between the obstacle radar points in the front area of the vehicle in the polar coordinate system of the front area of the vehicle and the world coordinate system is as follows: where (x, y) are the coordinates of the obstacle radar points in the front area of the vehicle in the world coordinate system, (r f , θ f ) are the coordinates of the obstacle radar points in the front area of the vehicle in the polar coordinate system of the front area, L is the vehicle length, and L f is the front overhang, that is, the distance from the front axle to the vehicle head; The conversion relationship between the obstacle radar points in the rear area of the vehicle in the polar coordinate system of the rear area of the vehicle and the world coordinate system is as follows: where (x, y) are the coordinates of the obstacle radar points in the rear area of the vehicle in the world coordinate system, (r r , θ r ) are the coordinates of the obstacle radar points in the rear area of the vehicle in the polar coordinate system of the rear area of the vehicle, where L is the vehicle length, and L r is the rear overhang, that is, the distance from the rear axle to the rear of the vehicle.
6. The method for drawing an obstacle envelope line based on an in-vehicle radar according to claim 5, wherein: In Step 4, calculate the distance between adjacent coordinate points in the world coordinate system, that is, for two adjacent coordinate points (x1, y1), (x2, y2), the distance d is Set the spacing threshold d ε , when d ≤ d ε , group adjacent obstacle radar points into one group, when d > d ε , group adjacent obstacle radar points into different groups.
7. The method for drawing an obstacle envelope line based on in-vehicle radar according to claim 6, wherein: In Step 5, the interpolation to fit curve includes interpolation calculation and fitting calculation; The interpolation calculation is specifically executed as follows: Step A: Take each group of obstacle radar points as the original points, calculate the midpoints P1′, P2′ of three adjacent original points P1, P2, P3, connect the adjacent midpoints to obtain a line segment, translate the line segment so that the midpoint of the line segment coincides with the middle P2 point, and the two end points of the translated line segment are used as the interpolation points; Step B: Repeat Step A until all adjacent three original points in each group of obstacle radar points are calculated, and all interpolation points of each group of obstacle radar points are obtained; The fitting calculation is specifically executed as follows: Where t is the independent variable, and the value range is from 0 to 1. Calculate the fitted curve in segments through the recurrence calculation formula, so that each group of obstacle radar points obtains a group of coordinate points of the fitted curve. Use Bessel curves to perform piecewise fitting on every two original obstacle radar points with interpolation points added. Among them, there is one interpolation point between the first two original points and the last two original points, and a second-order Bessel curve is used for fitting. There are two interpolation points between every other two original points, and a third-order Bessel curve is used for fitting. For n points P0, P1, P2, …, P n The recurrence calculation formula for the points on the k-th order Bessel curve of 8. The method for drawing an obstacle envelope line based on an on-vehicle radar according to claim 1, characterized in that: In step 6, according to the ratio Ratio between the world coordinates and the image coordinates, the coordinate points (x, y) of the fitted curve are scaled to the image coordinate system as (Ratio * x, Ratio * y). In the image, the coordinate points of each fitted curve are connected according to the grouping to obtain the obstacle envelope, and the vehicle position is marked in the image at the same time.
9. An apparatus for drawing an obstacle envelope based on on-vehicle radar, characterized in that, It includes: a processor, a memory, and a program; The program is stored in the memory, and the processor calls the program stored in the memory to execute the method for drawing an obstacle envelope based on an in-vehicle radar according to any one of claims 1-8.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is configured to store a program, and the program is configured to execute the method for drawing an obstacle envelope based on an in-vehicle radar according to any one of claims 1-8.
Citation Information
Patent Citations
Network-connected vehicle positioning method based on 3D laser radar and V2X
CN108983248A
Obstacle detection method and apparatus for vehicle-mounted radar system
US20180088228A1