Single ultrasonic radar parking space detection correction method and system

Abstract

The application discloses a single ultrasonic radar parking space detection correction method and system, which comprises the following steps: acquiring vehicle data of a current vehicle; setting a radar detection model, and calculating the coordinates of a detection point at each time according to the vehicle data to form a detection point coordinate set; finding a judgment point in the detection point coordinate set; if the number of the judgment points is greater than a preset judgment point threshold, connecting lines between a detection starting point and a detection ending point in the detection point coordinate set are taken as connecting line references, and detection points between the detection starting point and the detection ending point which are greater than a preset distance threshold from the connecting line references are found as a basis to segment the detection point coordinate set to form a plurality of segmented detection point coordinate sets; adjacent detection points in each segmented detection point coordinate set are connected to form line segments of adjacent detection points, and if the adjacent line segments can be connected, the adjacent line segments are merged to finally form a spatial parking space environment map.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of ultrasonic radar parking space detection correction, and more particularly to a single ultrasonic radar parking space detection correction method and system. BACKGROUND

[0002] In the prior art, parking space recognition identifies lateral obstacles through lateral ultrasonic radar, and identifies the size of the space parking space through the accumulation calculation of a small section of distance from the obstacle.

[0003] Because the technical route uses ultrasonic radar, the ultrasonic principle is that A ultrasonic waves can be received by A and other ultrasonic radar B, forming A transmitting A receiving and A transmitting B receiving, B transmitting A receiving, and other groups of distance measurement relationships, and then the radar forms the relative position relationship of the obstacle and the vehicle, which is obtained after the multiple relationships are verified, formed, averaged, and filtered.

[0004] Based on the detection scheme of ultrasonic radar, the cooperation of multiple groups of ultrasonic radar is the core key. However, in the search and detection of lateral parking spaces in the parking system, the detection and transmission of the vehicle lateral parking space are often only participated by one radar on the side, and finally only one group of A transmitting A receiving measurement data can be formed. The distance signal of the pointing signal of the parking system parking space judgment occurs a large amplitude rise and a large amplitude drop twice, but the single group of ultrasonic radar data is easily affected by the environment and fluctuates. False jumps are caused. SUMMARY

[0005] To solve the above technical problems, the application provides a single ultrasonic radar parking space detection correction method, which comprises:

[0006] Obtaining vehicle data of a current vehicle, wherein the vehicle data comprises: vehicle width, vehicle wheelbase, detection distance of an ultrasonic radar, and coordinates of the current vehicle at multiple time points;

[0007] Setting a radar detection model, and calculating the coordinates of the detection points at each time point according to the vehicle data to form a detection point coordinate set;

[0008] Finding a judgment point in the detection point coordinate set, if the number of the judgment points is greater than a preset judgment point threshold, connecting lines between detection start points and detection end points in the detection point coordinate set are taken as connecting line references, and detection points between the detection start points and the detection end points that are greater than a preset distance threshold from the connecting line references are found as a basis to segment the detection point coordinate set to form multiple segmented detection point coordinate sets;

[0009] The coordinates of each segmented detection point are combined with those of adjacent detection points to form line segments. If adjacent line segments can be connected, they are merged to form a spatial parking space environment map.

[0010] Furthermore, the radar detection model is as follows:

[0011]

[0012] Among them, X p Y is the x-coordinate of the probe point at the current moment. p X0 is the ordinate of the detection point at the current moment, L is the wheelbase of the vehicle at the current moment, β0 is the Z-axis coordinate of the vehicle at the current moment, W is the width of the vehicle, d is the detection range of the ultrasonic radar, and Y0 is the Y-axis coordinate of the vehicle at the current moment.

[0013] Furthermore, the radar detection model is dynamically optimized with velocity, specifically as follows:

[0014]

[0015] Among them, V x Let A be the vehicle's speed on the X-axis, t be the vehicle's operating time, and A be the speed of the vehicle on the X-axis. x Let ε be the acceleration of the vehicle along the X-axis. x V represents the sensor error on the X-axis. y Let A be the speed of the vehicle on the Y-axis. y Let ε be the acceleration of the vehicle on the Y-axis. y This represents the sensor error on the Y-axis.

[0016] Furthermore, the step of finding the judgment point in the set of probe point coordinates includes:

[0017] Let P(i) represent the set of coordinates of the detection points. Obtain the difference between P(m) and P(m+1) in P(i). If the difference between P(m) and P(m+1) is greater than the preset judgment point threshold, then P(m+1) is the judgment point.

[0018] Furthermore, the step of connecting adjacent detection points in the coordinate set of each segmented detection point to form line segments of adjacent detection points, and merging adjacent line segments if they can be connected, includes:

[0019] Linear regression is performed on the detection points in the coordinate set of each segmented detection point, and adjacent detection points are connected to form line segments l of adjacent detection points. n and its angle β with the coordinate axis m If two adjacent line segments l n and l n+1 The included angle β n and βn+1 If the difference between the two angles is less than a preset connection threshold, then the line segments l n and l n+1 are merged.

[0020] Alternatively, if the average variance of the two angles β n and β n+1 is less than a preset average variance threshold, then the line segments l n and l n+1 are merged.

[0021] The application also provides a single ultrasonic radar parking space detection correction system, comprising:

[0022] a data acquisition module configured to acquire vehicle data of a current vehicle, wherein the vehicle data comprises a vehicle width, a vehicle wheelbase, a detection distance of an ultrasonic radar, and coordinates of the current vehicle at multiple time points;

[0023] a model setting module configured to set a radar detection model and calculate coordinates of detection points at each time point based on the vehicle data to form a detection point coordinate set;

[0024] a segmentation module configured to find a judgment point in the detection point coordinate set, and if the number of the judgment points is greater than a preset judgment point threshold, connect a line between a detection start point and a detection end point in the detection point coordinate set as a connection line reference, find detection points between the detection start point and the detection end point that are greater than a preset distance threshold from the connection line reference, and segment the detection point coordinate set based on the detection points to form multiple segmented detection point coordinate sets;

[0025] a merging module configured to connect adjacent detection points in each segmented detection point coordinate set to form line segments of adjacent detection points, and if adjacent line segments can be connected, merge the adjacent line segments to finally form a spatial parking space environment map.

[0026] Further, the radar detection model is:

[0027]

[0028] wherein X p is a horizontal coordinate of a detection point at a current time point, Y p is a vertical coordinate of the detection point at the current time point, X0 is an X-axis coordinate of the current vehicle, L is a vehicle wheelbase, β0 is a Z-axis coordinate of the current vehicle, W is a vehicle width, d is a detection distance of the ultrasonic radar, and Y0 is a Y-axis coordinate of the current vehicle.

[0029] Further, the radar detection model is dynamically optimized with speed, specifically:

[0030]

[0031] wherein V x is the speed of the vehicle in the X-axis, t is the vehicle operation time, A x is the acceleration of the vehicle in the X-axis, ε x is the sensor error in the X-axis, V y is the speed of the vehicle in the Y-axis, A y is the acceleration of the vehicle in the Y-axis, ε y is the sensor error in the Y-axis.

[0032] Further, the finding of the judgment point in the set of probe point coordinates comprises:

[0033] using P(i) to represent the set of probe point coordinates, obtaining the difference between P(m) and P(m+1) in P(i), and if the difference between P(m) and P(m+1) is greater than a preset judgment point threshold, then P(m+1) is the judgment point.

[0034] Further, the connecting of adjacent probe points in each segmented set of probe point coordinates to form a line segment of adjacent probe points, and the merging if the adjacent line segments can be connected, comprises:

[0035] performing linear regression on each probe point in the segmented set of probe point coordinates, and connecting adjacent probe points to form a line segment l n and the included angle β n with the coordinate axis, if the difference between the included angles β n and β n+1 of the adjacent two line segments l n and l n+1 is less than a preset connection threshold, then the line segments l n and l n+1 are merged;

[0036] or, if the average variance of the included angles β n and β n+1 is less than a preset average variance threshold, then the line segments l n and l n+1 are merged.

[0037] Overall, compared with the prior art, the above technical scheme conceived by the present application has the following beneficial effects:

[0038] The present application has the following beneficial effects:

[0039] Safety benefit: the present application improves the accuracy of vehicle side obstacle detection, and ensures the safety of side parking in vehicle automatic parking.

[0040] Economic benefits: the design of the application is completed without increasing additional controllers and parts, and the function improvement is realized in a 0-cost manner.

[0041] Potential customer benefits: a safer parking system can popularize automatic parking function systems to various vehicle models and give enterprises a new functional selling point (function decentralization) for the safety of the general public.

[0042] Enterprise benefits: the application is simple and practical, applicable to all vehicle models, and can interact with various types of reversing radar systems and operate modularly. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 is a flowchart of the method of embodiment 1 of the application;

[0044] Figure 2 is a structure diagram of the system of embodiment 2 of the application;

[0045] Figure 3 is a structure diagram of the system of embodiment 5 of the application;

[0046] Figure 4 is a schematic diagram of the detection points of embodiment 5 of the application;

[0047] Figure 5 is a schematic diagram of the segmentation of the detection point set of embodiment 5 of the application;

[0048] Figure 6 is a spatial parking space environment map of embodiment 5 of the application, which is not disturbed by environmental disturbances in a real parking scenario. DETAILED DESCRIPTION

[0049] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in combination with the drawings in the specification and specific embodiments.

[0050] The method provided by the application can be implemented in a terminal environment, which can include one or more of the following components: a processor, a storage medium and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0051] The processor can include one or more processing cores. The processor connects various parts in the entire terminal through various interfaces and lines, executes the instructions, programs, code sets or instruction sets stored in the storage medium, and calls the data stored in the storage medium to perform various functions and process data of the terminal.

[0052] The storage medium can include random access memory (RAM) and can also include read-only memory (ROM). The storage medium can be used to store instructions, programs, codes, code sets, or instructions.

[0053] The display screen is used to display the user interface of each application program.

[0054] All subscripts in the formula of the present application are only used to distinguish parameters and have no actual meaning.

[0055] In addition, those skilled in the art can understand that the structure of the terminal described above does not constitute a limitation on the terminal, and the terminal can include more or fewer components, or combine certain components, or different component arrangements. For example, the terminal also includes radio frequency circuitry, an input unit, a sensor, audio circuitry, a power supply, and the like, which are not described here.

[0056] Embodiment 1

[0057] As shown in Figure 1 The present application provides a single ultrasonic radar parking space detection correction method, which comprises the following steps:

[0058] Step 101, obtaining vehicle data of a current vehicle, wherein the vehicle data comprises vehicle width, vehicle wheelbase, detection distance of an ultrasonic radar, and coordinates of the current vehicle at multiple time points;

[0059] Step 102, setting a radar detection model, and calculating coordinates of a detection point at each time point according to the vehicle data to form a detection point coordinate set;

[0060] Specifically, the radar detection model is:

[0061]

[0062] Wherein, X p is the horizontal coordinate of the detection point at the current time, Y p is the vertical coordinate of the detection point at the current time, X0 is the X-axis coordinate of the vehicle at the current time, L is the wheelbase of the vehicle, β0 is the Z-axis coordinate of the vehicle at the current time, W is the width of the vehicle, d is the detection distance of the ultrasonic radar, and Y0 is the Y-axis coordinate of the vehicle at the current time.

[0063] Specifically, the radar detection model is dynamically optimized with speed, specifically:

[0064]

[0065] Wherein, V x is the speed of the vehicle on the X-axis, t is the vehicle operation time, A xis the acceleration of the vehicle in the X-axis, ε x is the sensor error in the X-axis, V y is the velocity of the vehicle in the Y-axis, A y is the acceleration of the vehicle in the Y-axis, ε y is the sensor error in the Y-axis.

[0066] In step 103, a judgment point in the set of probe point coordinates is searched for. If the number of the judgment points is greater than a preset judgment point threshold, a connection line between a probe starting point and a probe ending point in the set of probe point coordinates is taken as a connection line reference, and a probe point between the probe starting point and the probe ending point that is greater than a preset distance threshold from the connection line reference is searched for, so as to segment the set of probe point coordinates and form a plurality of segmented sets of probe point coordinates.

[0067] Specifically, the searching for the judgment point in the set of probe point coordinates comprises the following steps.

[0068] P(i) is used to represent the set of probe point coordinates, a difference between P(m) and P(m+1) in P(i) is obtained, and P(m+1) is taken as the judgment point if the difference between P(m) and P(m+1) is greater than a preset judgment point threshold.

[0069] In step 104, adjacent probe points in each segmented set of probe point coordinates are connected to form line segments of adjacent probe points, and the adjacent line segments are merged if the adjacent line segments can be connected, so as to finally form a spatial parking space environment map.

[0070] Further, the connecting of the adjacent probe points in each segmented set of probe point coordinates to form the line segments of adjacent probe points and the merging of the adjacent line segments if the adjacent line segments can be connected comprises the following steps.

[0071] Linear regression is performed on the probe points in each segmented set of probe point coordinates, and the adjacent probe points are connected to form line segments l n and an included angle β n between the line segments and a coordinate axis n and l n+1 , if a difference between the included angles β n and β n+1 of the adjacent two line segments l n and l n+1 is less than a preset connection threshold, the line segments l n and l n+1 are merged.

[0072] Or, if an average variance of the included angles β n and β n+1的 is less than a preset average variance threshold, the line segments l n and l n+1 are merged.

[0073] Embodiment 2

[0074] As Figure 2 shown in the drawings, the embodiment of the application also provides a single ultrasonic radar parking space detection correction system, comprising:

[0075] an acquisition data module, configured to acquire vehicle data of a current vehicle, wherein the vehicle data comprises a vehicle width, a vehicle wheelbase, a detection distance of an ultrasonic radar, and coordinates of the current vehicle at multiple time points;

[0076] a model setting module, configured to set a radar detection model, and calculate coordinates of a detection point at each time point according to the vehicle data, to form a detection point coordinate set;

[0077] Specifically, the radar detection model is:

[0078]

[0079] wherein X p is a horizontal coordinate of a detection point at a current time point, Y p is a vertical coordinate of the detection point at the current time point, X0 is an X-axis coordinate of the current vehicle, L is a vehicle wheelbase, β0 is a Z-axis coordinate of the current vehicle, W is the vehicle width, d is the detection distance of the ultrasonic radar, and Y0 is a Y-axis coordinate of the current vehicle.

[0080] Specifically, the radar detection model is dynamically optimized according to a speed, and specifically:

[0081]

[0082] wherein V x is a speed of the vehicle on the X-axis, t is a vehicle operation time, A x is an acceleration of the vehicle on the X-axis, ε x is a sensor error on the X-axis, V y is a speed of the vehicle on the Y-axis, A y is an acceleration of the vehicle on the Y-axis, ε y is a sensor error on the Y-axis.

[0083] a segmentation module, configured to find a judgment point in the detection point coordinate set, if a number of the judgment points is greater than a preset judgment point threshold, to take a connecting line between a detection start point and a detection end point in the detection point coordinate set as a connecting line reference, find a detection point between the detection start point and the detection end point which is greater than a preset distance threshold from the connecting line reference, and segment the detection point coordinate set based on the detection point to form multiple segmented detection point coordinate sets;

[0084] Specifically, the finding of the judgment point in the detection point coordinate set comprises:

[0085] Let P(i) represent the set of coordinates of the detection points. Obtain the difference between P(m) and P(m+1) in P(i). If the difference between P(m) and P(m+1) is greater than the preset judgment point threshold, then P(m+1) is the judgment point.

[0086] The merging module is used to combine the coordinates of each segmented detection point and connect adjacent detection points to form line segments of adjacent detection points. If adjacent line segments can be connected, they are merged to finally form a spatial parking space environment map.

[0087] Furthermore, the step of connecting adjacent detection points in the coordinate set of each segmented detection point to form line segments of adjacent detection points, and merging adjacent line segments if they can be connected, includes:

[0088] Linear regression is performed on the detection points in the coordinate set of each segmented detection point, and adjacent detection points are connected to form line segments l of adjacent detection points. n and its angle β with the coordinate axis n If two adjacent line segments l n and l n+1 The included angle β n and β n+1 If the difference is less than the preset connection threshold, then for line segment l n and l n+1 Merge;

[0089] Or, if the included angle β n and β n+1 If the average variance is less than the preset average variance threshold, then for line segment l n and l n+1 Merge.

[0090] Example 3

[0091] This invention also proposes a storage medium storing multiple instructions for implementing the single ultrasonic radar parking space detection correction method.

[0092] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0093] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: Step 101, obtaining vehicle data of the current vehicle, wherein the vehicle data includes: vehicle width, vehicle wheelbase, ultrasonic radar detection distance and coordinates of the current vehicle at multiple times;

[0094] Step 102, setting a radar detection model, and calculating coordinates of each detection point at each time according to the vehicle data to form a detection point coordinate set;

[0095] Specifically, the radar detection model is:

[0096]

[0097] Wherein, X p is the horizontal coordinate of the detection point at the current time, Y p is the vertical coordinate of the detection point at the current time, X0 is the X-axis coordinate of the vehicle at the current time, L is the wheelbase of the vehicle, β0 is the Z-axis coordinate of the vehicle at the current time, W is the width of the vehicle, d is the detection distance of the ultrasonic radar, and Y0 is the Y-axis coordinate of the vehicle at the current time.

[0098] Specifically, the radar detection model is dynamically optimized with speed, specifically:

[0099]

[0100] Wherein, V x is the speed of the vehicle on the X-axis, t is the operation time of the vehicle, A x is the acceleration of the vehicle on the X-axis, ε x is the sensor error on the X-axis, V y is the speed of the vehicle on the Y-axis, A y is the acceleration of the vehicle on the Y-axis, ε y is the sensor error on the Y-axis.

[0101] Step 103, finding a judgment point in the detection point coordinate set, if the number of the judgment point is greater than a preset judgment point threshold, connecting lines between a detection starting point and a detection ending point in the detection point coordinate set are taken as a connecting line reference, and detection points between the detection starting point and the detection ending point to the connecting line reference greater than a preset distance threshold are found as a basis to segment the detection point coordinate set to form a plurality of segmented detection point coordinate sets;

[0102] Specifically, the finding of the judgment point in the detection point coordinate set includes:

[0103] Using P(i) to represent the detection point coordinate set, the difference between P(m) and P(m+1) in P(i) is obtained, and if the difference between P(m) and P(m+1) is greater than a preset judgment point threshold, P(m+1) is taken as a judgment point.

[0104] Step 104, connecting adjacent detection points in each segmented detection point coordinate set to form line segments of adjacent detection points, if the adjacent line segments can be connected, merging is performed, and finally a spatial parking space environment map is formed.

[0105] Furthermore, the step of connecting adjacent detection points in the coordinate set of each segmented detection point to form line segments of adjacent detection points, and merging adjacent line segments if they can be connected, includes:

[0106] Linear regression is performed on the detection points in the coordinate set of each segmented detection point, and adjacent detection points are connected to form line segments l of adjacent detection points. n and its angle β with the coordinate axis n If two adjacent line segments l n and l n+1 The included angle β n and β n+1 If the difference is less than the preset connection threshold, then for line segment l n and l n+1 Merge;

[0107] Or, if the included angle β n and β n+1 If the average variance is less than the preset average variance threshold, then for line segment l n and l n+1 Merge.

[0108] Example 4

[0109] This invention also proposes an electronic device, including a processor and a storage medium connected to the processor. The storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to execute the single ultrasonic radar parking space detection correction method.

[0110] Specifically, the electronic device in this embodiment can be a computer terminal, which may include one or more processors and a storage medium.

[0111] The storage medium can be used to store software programs and modules, such as the single ultrasonic radar parking space detection correction method in this embodiment of the invention. The corresponding program instructions / modules allow the processor to execute various functional applications and data processing by running the software programs and modules stored in the storage medium, thus realizing the aforementioned single ultrasonic radar parking space detection correction method. The storage medium may include high-speed random access storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely configured relative to the processor, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0112] The processor can call the information and application stored in the storage medium through the transmission system to perform the following steps: Step 101, obtain the vehicle data of the current vehicle, wherein the vehicle data includes: vehicle width, vehicle wheelbase, ultrasonic radar detection distance and the coordinates of the current vehicle at multiple times;

[0113] Step 102: Set up a radar detection model and calculate the coordinates of the detection points at each time step based on the vehicle data to form a set of detection point coordinates;

[0114] Specifically, the radar detection model is as follows:

[0115]

[0116] Among them, X p Y is the x-coordinate of the probe point at the current moment. p X0 is the ordinate of the detection point at the current moment, L is the wheelbase of the vehicle at the current moment, β0 is the Z-axis coordinate of the vehicle at the current moment, W is the width of the vehicle, d is the detection range of the ultrasonic radar, and Y0 is the Y-axis coordinate of the vehicle at the current moment.

[0117] Specifically, the radar detection model is dynamically optimized with velocity, as follows:

[0118]

[0119] Among them, V x Let A be the vehicle's speed on the X-axis, t be the vehicle's operating time, and A be the speed of the vehicle on the X-axis. x Let ε be the acceleration of the vehicle along the X-axis. x V represents the sensor error on the X-axis. y Let A be the vehicle's speed on the Y-axis. y Let ε be the acceleration of the vehicle on the Y-axis. y This represents the sensor error on the Y-axis.

[0120] Step 103: Find the judgment points in the set of detection point coordinates. If the number of judgment points is greater than the preset judgment point threshold, then take the connecting line between the detection start point and the detection end point in the set of detection point coordinates as the connecting line reference, find the detection points between the detection start point and the detection end point that are greater than the preset distance threshold from the connecting line reference, and use them as the basis to divide the set of detection point coordinates into multiple segmented sets of detection point coordinates.

[0121] Specifically, the process of finding the judgment points in the set of probe point coordinates includes:

[0122] Let P(i) represent the set of coordinates of the detection points. Obtain the difference between P(m) and P(m+1) in P(i). If the difference between P(m) and P(m+1) is greater than the preset judgment point threshold, then P(m+1) is the judgment point.

[0123] Step 104: Connect the coordinates of each segmented detection point to adjacent detection points to form line segments of adjacent detection points. If adjacent line segments can be connected, they are merged to finally form a spatial parking space environment map.

[0124] Furthermore, the step of connecting adjacent detection points in the coordinate set of each segmented detection point to form line segments of adjacent detection points, and merging adjacent line segments if they can be connected, includes:

[0125] Linear regression is performed on the detection points in the coordinate set of each segmented detection point, and adjacent detection points are connected to form line segments I of adjacent detection points. n and its angle β with the coordinate axis n If two adjacent line segments l n and l n+1 The included angle β n and β n+1 If the difference is less than the preset connection threshold, then for line segment l n and l n+1 Merge;

[0126] Or, if the included angle β n and β n+1 If the average variance is less than the preset average variance threshold, then for line segment I... n and l n+1 Merge.

[0127] Example 5

[0128] like Figure 3 As shown, the single ultrasonic radar parking space detection correction method designed in this invention includes an ultrasonic radar, a radar controller, a vehicle CAN bus, an ESC inertial measurement unit, and an ESC wheel speed measurement unit.

[0129] The ultrasonic radar is used to determine the distance and position of real obstacles. A radar group composed of multiple ultrasonic radars calculates the echo of the ultrasonic wave emitted by a certain probe (A transmits, A receives) or calculates the echo emitted by other probes (B transmits, A receives), and the multiple sets of data are used to jointly analyze and comprehensively determine the position of the real obstacle. In this invention, the ultrasonic radar is used to detect the distance of the vehicle from lateral obstacles and to identify parking spaces.

[0130] The vehicle CAN bus is used to provide the gear position signal and real-time vehicle speed signal to the radar controller;

[0131] The radar controller uses lateral ultrasonic waves for 1) different functions: turning on and switching between reversing radar and parking space search; 2) storing the core algorithm of this invention.

[0132] The ESC inertial measurement unit is used to: 1) provide the heading angle information required by the present invention (the ESC inertial measurement unit can measure and output the yaw rate, and can integrate the yaw rate to generate the heading angle for output); 2) provide the lateral displacement information required by the present invention (the ESC inertial measurement unit can measure and output the lateral acceleration, and can integrate the lateral acceleration to generate the lateral displacement information for output).

[0133] The ESC wheel speed measurement unit is used to 1) convert the pulse information of the wheel tooth pulse counter into wheel speed; and 2) convert the high-precision wheel speed information into the longitudinal displacement of the vehicle.

[0134] The above technical solution describes a single ultrasonic radar parking space detection correction method, the workflow of which is as follows:

[0135] 1. Establishment of the origin: After the parking system requests the activation of the parking space search function mode, the reversing radar system controls the ultrasonic radar to enter the parking space search function mode. The time of mode switching is used as the origin for the algorithm to calculate the vehicle position.

[0136] 2. Using onboard information parameters and the measurement origin, the positional relationship of obstacles in the global context is obtained. The method is as follows:

[0137]

[0138] In the formula, (X0, Y0, β0) represents the vehicle's position at a certain moment, W is the vehicle width, L is the vehicle wheelbase, and d is the detection range of the ultrasonic radar. Figure 4 As shown, the (X) formed therein P Y P This represents the relationship of obstacles in a spatial coordinate system. The purpose of this step is to convert the distance information, which can only be measured by ultrasonic radar, into coordinate information by combining it with vehicle parameters.

[0139] 3. Obstacle Distance Judgment: The ultrasonic measurement data for each signal cycle is organized into a corresponding array, denoted by P(i), where the ultrasonic measurement result for each signal cycle is P(i), and i = 1, 2, 3, ... n. The difference between P(m) and P(m+1) is obtained. If the difference between P(m) and P(m+1) is greater than a threshold, further judgment is required, and this is recorded as the judgment point; if the difference between P(m) and P(m+1) is less than the threshold, measurement continues.

[0140] 4. Macro-level data statistics. Let W be the total number of judgment points in the parking space search. If W is greater than a threshold, it is determined to be a judgment group requiring further work in this invention. Proceed with subsequent steps, or skip the steps outlined in this invention.

[0141] 5. Segmented processing of the parking space search process: If there are enough judgment points in step 4, perform a comprehensive judgment in step 5. The judgment method is to use the line connecting the starting point P(1) and the ending point P(n) of the parking space search as the reference; if the monitored P(k) in P(2)...P(n-1) is... x (i.e., P(k1), P(k2)...) If P(k... x If the distance from the reference line to the connection line is greater than the set value h, then P(k) x Segmentation is based on ) such as Figure 5 As shown.

[0142] 6: Continue segmented processing: Using the same judgment method, connect the parking space search starting point P(1) and P(k) x (e.g., P(k1)) its connecting line is the reference; if P(2)...P(k x The monitored P(kx2) (e.g., P(k2)) if P(k x 2) If the distance to the reference line is greater than the set value h, then P(k) x2 Segmentation is performed based on the baseline. If there are no points with a distance greater than the set value h from the reference line, then the process continues to determine P(k). x From P(n) to P(n).

[0143] 7: Eliminating abnormal data segments: Remove data segments whose number of data points in the probe point set after segmentation is less than the threshold A.

[0144] 8: Linearization and merging of set points: Perform linear regression on the points in {P(i)|i=p,p+1...,q-1,q} to obtain the linear regression line l. n The angle between it and the coordinate axis is β. n If two adjacent segments l n and l n+1 The included angle β n and β n+1 If the difference is less than the threshold B, the two line segments are merged. Otherwise, the next line segment is compared.

[0145] 9: Similar to step 8, segmentation and merging of the set points: Perform linear regression on the points in {P(i)|i=p,p+1...,q-1,q} to obtain the linear regression line l. n The average variance of the point coordinates and the regression line is E. If two adjacent segments l n and l n+1 The included angle β nand β n+1 If the average variance is less than the threshold C, then the two line segments are merged. Otherwise, the next line segment is compared.

[0146] 10: For example Figure 6 As shown, the remaining fitted line segments are labeled to form a spatial parking space environment map that is not affected by environmental disturbances in a real parking scenario.

[0147] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0148] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0149] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0150] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0151] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0152] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, read-only storage media (ROM), random access storage media (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.

[0153] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A single ultrasonic radar parking space detection correction method, characterized in that, include: Obtain vehicle data for the current vehicle, wherein the vehicle data includes: vehicle width, vehicle wheelbase, ultrasonic radar detection distance, and coordinates of the current vehicle at multiple times; Set up a radar detection model and calculate the coordinates of the detection points at each moment based on the vehicle data to form a set of detection point coordinates; Find the judgment points in the set of detection point coordinates. If the number of judgment points is greater than the preset judgment point threshold, then take the line connecting the detection start point and the detection end point in the set of detection point coordinates as the line reference, find the detection points between the detection start point and the detection end point that are greater than the preset distance threshold from the line reference, and use them as the basis to divide the set of detection point coordinates into multiple segmented sets of detection point coordinates. The coordinates of each segmented detection point are combined with those of adjacent detection points to form line segments. If adjacent line segments can be connected, they are merged to form a spatial parking space environment map.

2. The single ultrasonic radar parking space detection correction method as described in claim 1, characterized in that, The radar detection model is as follows: Among them, X p Y is the x-coordinate of the probe point at the current moment. p X0 is the ordinate of the detection point at the current moment, L is the wheelbase of the vehicle at the current moment, β0 is the Z-axis coordinate of the vehicle at the current moment, W is the width of the vehicle, d is the detection range of the ultrasonic radar, and Y0 is the Y-axis coordinate of the vehicle at the current moment.

3. The single ultrasonic radar parking space detection correction method as described in claim 2, characterized in that, The radar detection model is dynamically optimized with velocity, specifically as follows: Among them, V x Let A be the vehicle's speed on the X-axis, t be the vehicle's travel time, and A be the speed of the vehicle on the X-axis. x Let ε be the acceleration of the vehicle along the X-axis. x V represents the sensor error on the X-axis. y Let A be the speed of the vehicle on the Y-axis. y Let ε be the acceleration of the vehicle on the Y-axis. y This represents the sensor error on the Y-axis.

4. A single ultrasonic radar parking space detection correction method as described in claim 2 or 3, characterized in that, The judgment points for finding the coordinate set of the detection points include: Let P(i) represent the set of coordinates of the detection points. Obtain the difference between P(m) and P(m+1) in P(i). If the difference between P(m) and P(m+1) is greater than the preset judgment point threshold, then set P(m+1) as the judgment point.

5. The single ultrasonic radar parking space detection correction method as described in claim 4, characterized in that, The step of connecting adjacent detection points in the coordinate set of each segmented detection point to form a line segment of adjacent detection points, and merging adjacent line segments if they can be connected, includes: Linear regression is performed on the detection points in the coordinate set of each segmented detection point, and adjacent detection points are connected to form line segments l of adjacent detection points. n and its angle β with the coordinate axis n If two adjacent line segments l n and l n+1 The included angle β n and β n+1 If the difference is less than the preset connection threshold, then for line segment l n and l n+1 Merge; Or, if the included angle β n and β n+1 If the average variance is less than the preset average variance threshold, then for line segment l n and l n+1 Merge.

6. A single ultrasonic radar parking space detection and correction system, characterized in that, include: The data acquisition module is used to acquire the vehicle data of the current vehicle, wherein the vehicle data includes: vehicle width, vehicle wheelbase, ultrasonic radar detection distance and the coordinates of the current vehicle at multiple times; The model setting module is used to set up the radar detection model and calculate the coordinates of the detection points at each time moment based on the vehicle data, forming a set of detection point coordinates. The segmentation module is used to find the judgment points in the detection point coordinate set. If the number of judgment points is greater than the preset judgment point threshold, the connecting line between the detection start point and the detection end point in the detection point coordinate set is used as the connecting line reference. The detection points between the detection start point and the detection end point that are greater than the connecting line reference are found. The detection point coordinate set is segmented based on these points to form multiple segmented detection point coordinate sets. The merging module sets the coordinates of each segmented detection point together and connects adjacent detection points to form line segments of adjacent detection points. If adjacent line segments can be connected, they are merged to finally form a spatial parking space environment map.

7. The single ultrasonic radar parking space detection and correction system as described in claim 6, characterized in that, The radar detection model is as follows: Among them, X p Y is the x-coordinate of the probe point at the current moment. p X0 is the ordinate of the detection point at the current moment, L is the wheelbase of the vehicle at the current moment, β0 is the Z-axis coordinate of the vehicle at the current moment, W is the width of the vehicle, d is the detection range of the ultrasonic radar, and Y0 is the Y-axis coordinate of the vehicle at the current moment.

8. The single ultrasonic radar parking space detection and correction system as described in claim 7, characterized in that, The radar detection model is dynamically optimized with velocity, specifically as follows: Among them, V x Let A be the vehicle's speed on the X-axis, t be the vehicle's travel time, and A be the speed of the vehicle on the X-axis. x Let ε be the acceleration of the vehicle along the X-axis. x V represents the sensor error on the X-axis. y Let A be the speed of the vehicle on the Y-axis. y Let ε be the acceleration of the vehicle on the Y-axis. y This represents the sensor error on the Y-axis.

9. A single ultrasonic radar parking space detection and correction system as described in claim 7 or 8, characterized in that, The judgment points for finding the coordinate set of the detection points include: Let P(i) represent the set of coordinates of the detection points. Obtain the difference between P(m) and P(m+1) in P(i). If the difference between P(m) and P(m+1) is greater than the preset judgment point threshold, then set P(m+1) as the judgment point.

10. The single ultrasonic radar parking space detection and correction system as described in claim 9, characterized in that, The step of connecting adjacent detection points in the coordinate set of each segmented detection point to form a line segment of adjacent detection points, and merging adjacent line segments if they can be connected, includes: Linear regression is performed on the detection points in the coordinate set of each segmented detection point, and adjacent detection points are connected to form line segments l of adjacent detection points. n and its angle β with the coordinate axis n If two adjacent line segments l n and l n+1 The included angle β n and β n+1 If the difference is less than the preset connection threshold, then for line segment l n and l n+1 Merge; Or, if the included angle β n and β n+1 If the average variance is less than the preset average variance threshold, then for line segment l n and l n+1 Merge.

Images