An automatic parking road edge detection method and device, a vehicle and a storage medium

Abstract

The application discloses an automatic parking road edge detection method and device, a vehicle and a storage medium, and the method comprises the following steps: when it is detected that the vehicle starts parking, a road edge point coordinate set and a target parking space coordinate set are acquired, the road edge point coordinate set comprises at least one road edge point coordinate, and the target parking space coordinate set comprises at least one target parking space coordinate of a target parking space; coordinate system conversion is performed on each road edge point coordinate to obtain a candidate road edge point coordinate in a vehicle coordinate system at a current time; each candidate road edge point coordinate is filtered according to the target parking space coordinate set to obtain a target road edge point coordinate; and the distance between the target parking space and the road edge is determined according to each target road edge point coordinate, so that the problem that the road edge information is not accurately detected and the cost is high during automatic parking is solved, the method is simple to implement, the detection result is accurate and reliable, a high-cost chip is not needed, and the cost is reduced.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to an automatic parking curb detection method, device, vehicle, and storage medium. Background Technology

[0002] With the booming development of the automotive industry, people's requirements for the functionality and completeness of cars are no longer limited to the previous power performance and comfort. Safety assistance performance has also taken center stage in the automotive industry. Among them, automatic parking system is a driving assistance system function that has been popular in recent years. The intelligence of automatic parking is becoming more and more important. However, there is a very important problem in the automatic parking system in terms of parking space detection, namely the detection of curb information in the parking space.

[0003] Whether it's panoramic automatic parking or ultrasonic automatic parking, it's very common for vehicles in parking spaces to have curbs. Currently, curb detection includes the following solutions: 1. Panoramic automatic parking relies on image recognition, which requires continuous deep learning. Currently, this type of detection technology is still in the learning and development stage, and the technology is not very mature. Moreover, it has high requirements for chips, and the cost of the chips is also high. 2. Ultrasonic automatic parking can identify parking spaces by scanning obstacles of different heights in layers for differentiation. However, directly detecting curbs based on the height of obstacles has low accuracy. Summary of the Invention

[0004] This invention provides an automatic parking curb detection method, device, vehicle, and storage medium to solve the problems of low curb detection accuracy and high cost.

[0005] According to one aspect of the present invention, an automatic parking curb detection method is provided, comprising:

[0006] When the vehicle starts parking, the system acquires a set of curb point coordinates and a set of target parking space coordinates. The set of curb point coordinates includes at least one curb point coordinate, and the set of target parking space coordinates includes at least one target parking space coordinate. The curb point coordinates are determined based on the curb point distance collected by the curb detection device on the vehicle.

[0007] The coordinates of each curb point are transformed to obtain the coordinates of the candidate curb points in the vehicle coordinate system at the current time.

[0008] The coordinates of each candidate roadside point are filtered according to the target parking space coordinate set to obtain the target roadside point coordinates;

[0009] The distance between the target parking space and the curb is determined based on the coordinates of each target curb point.

[0010] According to another aspect of the present invention, an automatic parking curb detection device is provided, comprising:

[0011] The coordinate acquisition module is used to acquire a set of roadside point coordinates and a set of target parking space coordinates after detecting that the vehicle has started parking. The set of roadside point coordinates includes at least one roadside point coordinate, and the set of target parking space coordinates includes at least one target parking space coordinate. The roadside point coordinates are determined based on the distance of the roadside points collected by the roadside detection device on the vehicle.

[0012] The coordinate transformation module is used to transform the coordinate system of each of the roadside points to obtain the coordinates of the candidate roadside points in the vehicle coordinate system at the current time.

[0013] The coordinate filtering module is used to filter the coordinates of each candidate roadside point according to the target parking space coordinate set to obtain the target roadside point coordinates;

[0014] The curb distance determination module is used to determine the distance between the target parking space and the curb based on the coordinates of each target curb point.

[0015] According to another aspect of the present invention, a vehicle is provided, the vehicle comprising:

[0016] A curb detection device is used to collect distances from curb points;

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the automatic parking curb detection method according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the automatic parking curb detection method according to any embodiment of the present invention.

[0021] The technical solution of this invention, upon detecting vehicle initiation for parking, acquires a set of curb point coordinates and a set of target parking space coordinates. The set of curb point coordinates includes at least one curb point coordinate, and the set of target parking space coordinates includes at least one target parking space coordinate. Coordinate system transformation is performed on each curb point coordinate to obtain candidate curb point coordinates in the vehicle coordinate system at the current moment. The candidate curb point coordinates are then filtered according to the target parking space coordinate set to obtain the target curb point coordinates. Finally, the distance between the target parking space and the curb is determined based on the target curb point coordinates. This solution solves the problems of inaccurate curb information detection and high costs during automatic parking. This application employs a curb detection device to detect the distance to curb points, and determines the coordinates of these points based on the distance. Upon detecting vehicle initiation and parking, it acquires a set of curb point coordinates and performs coordinate system transformation to obtain candidate curb point coordinates in the current vehicle coordinate system. These candidate coordinates are then filtered against the target parking space coordinates, removing points with significant errors to obtain the target curb point coordinates. The curb is then determined using these target coordinates, further defining the distance between the target parking space and the curb. This method is simple to implement, requiring only basic mathematical processing of the curb point coordinates without model training. The curb detection device only needs to collect the distance to determine the curb point coordinates, resulting in accurate and reliable detection. It also eliminates the need for expensive chips, thus reducing costs.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of an automatic parking curb detection method according to Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of an automatic parking curb detection method according to Embodiment 2 of the present invention;

[0026] Figure 3 This is a illustrative example diagram of a vehicle and coordinate system provided according to Embodiment 2 of the present invention;

[0027] Figure 4This is a schematic diagram illustrating a target parking space and candidate curb points according to Embodiment 2 of the present invention;

[0028] Figure 5 This is a schematic diagram illustrating a target parking space and a target curb point according to Embodiment 2 of the present invention;

[0029] Figure 6 This is a schematic diagram illustrating a target parking space and curb according to Embodiment 2 of the present invention;

[0030] Figure 7 This is a schematic diagram of the structure of an automatic parking curb detection device according to Embodiment 3 of the present invention;

[0031] Figure 8 This is a schematic diagram of the structure of a vehicle implementing the automatic parking curb detection method of this invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] Example 1

[0035] Figure 1 This is a flowchart of an automatic parking curb detection method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where curbs are detected during automatic parking. The method can be executed by an automatic parking curb detection device, which can be implemented in hardware and / or software and can be configured in a vehicle. Figure 1As shown, the method includes:

[0036] S101. When the vehicle starts parking, the system acquires a set of curb point coordinates and a set of target parking space coordinates. The set of curb point coordinates includes at least one curb point coordinate, and the set of target parking space coordinates includes at least one target parking space coordinate. The curb point coordinates are determined based on the distance of the curb points collected by the curb detection device on the vehicle.

[0037] In this embodiment, the set of curb point coordinates can be understood as a dataset storing curb point coordinates; the target parking space can be understood as a parking space where parking is permitted, and the target parking space coordinates can be understood as coordinates used to represent the target parking space. The target parking space is typically a rectangle; therefore, the target parking space coordinates can be determined by one coordinate and the length and width of the parking space, or by four coordinates, or by the coordinates of two diagonal points, or any other method that uniquely identifies a rectangle; the set of target parking space coordinates can be understood as a dataset storing target parking space coordinates. The curb detection device can be understood as a device used for curb detection, such as an APA ultrasonic probe; the curb point distance can be understood as the distance from the curb point to the curb detection device.

[0038] Specifically, a curb detection device is installed on the vehicle to collect distances between curb points. Since the curb is composed of a large number of curb points, when collecting curb distances, the curb detection device can collect the distances between all available curb points and the device itself, or it can collect only the horizontal distances between the device and the curb points. This application preferably collects the distances between the horizontal curb points of the device. The curb point coordinates are determined based on the curb point distances and stored in a curb point coordinate set. This set can be stored locally on the vehicle or on a server. After detecting that the vehicle has started parking, the curb point coordinate set is retrieved from the corresponding storage space. When parking, the vehicle needs to determine a target parking space before parking can proceed. The target parking space is located using a 360-degree panoramic view or a USS ultrasonic system, and its coordinates are stored in a target parking space coordinate set. This set can also be stored locally on the vehicle or on a server. After detecting that the vehicle has started parking, the target parking space coordinate set is retrieved.

[0039] S102. Perform coordinate system transformation on the coordinates of each roadside point to obtain the coordinates of the candidate roadside points in the vehicle coordinate system at the current time.

[0040] In this embodiment, the vehicle coordinate system can be specifically understood as a coordinate system established based on the current position of the vehicle. For example, the vehicle coordinate system has the center point of the rear axle of the vehicle as the origin, the direction the vehicle is facing as the positive Y-axis, and the right side of the vehicle as the positive X-axis. The vehicle coordinate system changes as the vehicle's position changes. The candidate curb point coordinates can be specifically understood as the coordinates of candidate points used to determine the curb.

[0041] The coordinates of each roadside point in this application are the coordinates in the vehicle coordinate system at different vehicle positions. The coordinates of each roadside point are transformed to correspond to the coordinates in the vehicle coordinate system at the current vehicle position. The coordinate transformation can be performed by pre-determining a coordinate transformation formula, and then applying the formula to transform the coordinates of each roadside point to obtain the candidate roadside point coordinates corresponding to each roadside point.

[0042] This application collects the coordinates of different curb points during vehicle movement. When parking, it is only necessary to determine the coordinates of curb points near the target parking space, without needing to collect all curb points. Therefore, the curb point coordinate set of this application can be stored according to time (e.g., storing the coordinates of curb points within 5 minutes), or according to quantity (e.g., storing the coordinates of 100 curb points), storing only the coordinates of curb points near the target parking space; alternatively, all curb point coordinates can be stored, but during curb detection (i.e., coordinate system transformation), the curb point coordinates are obtained and processed according to time or quantity.

[0043] S103. Filter the coordinates of each candidate curb point according to the target parking space coordinate set to obtain the target curb point coordinates.

[0044] In this embodiment, the target curb point coordinates can be specifically understood as the coordinates of the points that constitute the curb. The location of the target parking space can be determined based on the target parking space coordinate set. The coordinates of each candidate curb point are then filtered based on the location of the target parking space. For example, coordinate points that are far away are filtered out, and coordinate points with large errors are removed by filtering, thus obtaining the target curb point coordinates.

[0045] S104. Determine the distance between the target parking space and the curb based on the coordinates of each target curb point.

[0046] In this example, the roadside is determined based on the coordinates of each target roadside point, and the distance between the target parking space and the roadside is calculated. The distance between the target parking space and the roadside can be the distance between a vertex of the target parking space and the roadside, or the distance between the center of the target parking space and the roadside, etc.

[0047] This invention provides an automatic parking curb detection method. Upon detecting vehicle initiation for parking, a set of curb point coordinates and a set of target parking space coordinates are acquired. The curb point coordinate set includes at least one curb point coordinate, and the target parking space coordinate set includes at least one target parking space coordinate. Coordinate system transformation is performed on each curb point coordinate to obtain candidate curb point coordinates in the vehicle's current coordinate system. The candidate curb point coordinates are then filtered according to the target parking space coordinate set to obtain the target curb point coordinates. Finally, the distance between the target parking space and the curb is determined based on the target curb point coordinates. This method solves the problems of inaccurate curb information detection and high cost during automatic parking. This application employs a curb detection device to detect the distance to curb points, and determines the coordinates of these points based on the distance. Upon detecting vehicle initiation and parking, it acquires a set of curb point coordinates and performs coordinate system transformation to obtain candidate curb point coordinates in the current vehicle coordinate system. These candidate coordinates are then filtered against the target parking space coordinates, removing points with significant errors to obtain the target curb point coordinates. The curb is then determined using these target coordinates, further defining the distance between the target parking space and the curb. This method is simple to implement, requiring only basic mathematical processing of the curb point coordinates without model training. The curb detection device only needs to collect the distance to determine the curb point coordinates, resulting in accurate and reliable detection. It also eliminates the need for expensive chips, thus reducing costs.

[0048] Example 2

[0049] Figure 2 This is a flowchart of an automatic parking curb detection method provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiments. Figure 2 As shown, the method includes:

[0050] S201. When a vehicle is detected to be starting a parking space search, a global coordinate system is established based on the vehicle's current position to determine the vehicle's initial coordinates, and the curb detection device on the vehicle is controlled to collect the distance to the curb point.

[0051] In this embodiment, the global coordinate system can be specifically understood as a coordinate system that includes all coordinate points of the vehicle during the process from searching for a parking space to parking. The global coordinate system is established with the origin determined based on the vehicle's current position when the parking space search is initiated. For example, the global coordinate system has the rear axle center point of the vehicle at its current position as the origin, the direction the vehicle is facing as the positive Y-axis, and the right side of the vehicle as the positive X-axis. The global coordinate system does not change with the vehicle's position. The vehicle's initial coordinates can be specifically understood as the position coordinates of the vehicle when the parking space search is initiated.

[0052] Specifically, when a user determines they need to park, they initiate a parking space search by using methods such as buttons, controls, or touchscreen controls on the center console. When the search is detected, the vehicle's current position is determined. Based on this position, the origin, X-axis, and Y-axis are established to form a global coordinate system. Simultaneously, the vehicle's initial coordinates are determined based on information from its movement. When the vehicle is the origin of the global coordinate system, its initial coordinates can be (0,0). Upon detecting the search, the vehicle's curb detection device is activated to collect distances to curb points. The number of curb detection devices can be one or multiple.

[0053] S202. Determine the coordinates of the curb points based on the distance to the curb points and the installation location information of the curb detection device, and store the curb point coordinates and their corresponding acquisition times in the curb point coordinate set.

[0054] Specifically, the installation location information can be understood as the coordinates of the curb detection device in the vehicle coordinate system. The curb detection device is installed on the vehicle, and its position is usually fixed; therefore, the installation location information of the curb detection device on the vehicle is determined. The curb point coordinates are calculated based on the installation location information and the distance to the curb point. Simultaneously, the acquisition time of the curb point distance is used as the acquisition time of the curb point coordinates. The curb point coordinates and their corresponding acquisition times are stored in a curb point coordinate set.

[0055] For example, the distance between the curb points is L, and the installation position information of the curb detection device is A(X1, Y1). Taking the right curb as an example, the coordinates of the curb point in the vehicle coordinate system are determined to be (X1+L, Y1).

[0056] It should be noted that if the set of roadside point coordinates in this application stores a preset number of roadside point coordinates, then the roadside point coordinates are stored in the set of roadside point coordinates according to time. If the number of roadside point coordinates is greater than the preset number, then the data that is furthest in time is deleted and the new data is stored in it.

[0057] S203. When a vehicle is detected to have started searching for parking spaces, obtain and display the information of the available parking spaces.

[0058] In this embodiment, the candidate parking space information can be specifically understood as information on available parking spaces. When a vehicle is detected initiating a parking space search, a search is performed. Once a parking space is found, it is designated as a candidate parking space, and its information is displayed as candidate parking space information. A candidate parking space can be a single space or information on multiple parking spaces. This application can also determine candidate parking space information through a 360° panoramic view or USS ultrasonic system. For example, after a vehicle is detected initiating a parking space search, information is sent to the 360° panoramic view or USS ultrasonic system so that it can perform a parking space search, and the application receives at least one candidate parking space information determined by the 360° panoramic view or USS ultrasonic system. The candidate parking space information can be displayed through text, images, or voice prompts to the user.

[0059] S204. Receive the target parking space specified by the user, determine the set of target parking space coordinates, and control the vehicle to start parking.

[0060] After displaying the available parking space information to the user, the user selects a target parking space from the available parking space information. The system receives the target parking space selected by the user, determines the set of coordinates of the target parking space, and controls the vehicle to start parking.

[0061] S205. When the vehicle starts parking, obtain the set of coordinates of the curb point and the set of coordinates of the target parking space.

[0062] The set of curb point coordinates includes at least one curb point coordinate, the set of target parking space coordinates includes at least one target parking space coordinate, and the curb point coordinates are determined based on the curb point distance collected by the curb detection device on the vehicle.

[0063] S206. For each roadside point coordinate, obtain the real-time vehicle location coordinates corresponding to the roadside point coordinates.

[0064] In this embodiment, the real-time vehicle position coordinates can be specifically understood as the real-time position coordinates of the vehicle in the global coordinate system, recording the vehicle's coordinates at each moment. For each roadside point coordinate, the acquisition time of the roadside point coordinates is determined, and the corresponding real-time vehicle position coordinates are determined based on the acquisition time.

[0065] In this application, the vehicle's coordinate information in the global coordinate system can be determined based on parameters such as the vehicle's inertial measurement unit (IMU), wheel count pulses, and vehicle parameters.

[0066] S207. Determine the vehicle offset angle based on the vehicle's real-time position coordinates and initial vehicle coordinates.

[0067] In this embodiment, the vehicle offset angle can be specifically understood as the offset angle of the vehicle relative to its initial position. The offset angle of the vehicle in the longitudinal direction is calculated based on the vehicle's real-time position coordinates and its initial coordinates, and is thus determined as the vehicle offset angle.

[0068] S208. Based on the preset first conversion formula, combined with the real-time vehicle position coordinates and vehicle offset angle, convert the roadside point coordinates into global roadside point coordinates in the global coordinate system.

[0069] In this embodiment, the first transformation formula can be specifically understood as the formula for transforming from the vehicle coordinate system to the global coordinate system. The global curb point coordinates can be specifically understood as the coordinates of the curb point in the global coordinate system.

[0070] By substituting the vehicle's real-time position coordinates, vehicle offset angle, and roadside point coordinates into the first transformation formula, the global roadside point coordinates are calculated.

[0071] For example, this application provides a first conversion formula: (taking two-dimensional coordinates as an example)

[0072] X2=x1+(X1+L)*cos(yaw)-Y1*sin(yaw);

[0073] Y2=y1+(X1+L)*sin(yaw)+Y1*cos(yaw).

[0074] Where (x1, y1) are the real-time position coordinates of the vehicle, and yaw is the vehicle offset angle;

[0075] (X1+L, Y1) are the coordinates of the roadside point, and (X2, Y2) are the coordinates of the global roadside point.

[0076] S209. Based on the preset second conversion formula, combined with the current vehicle position coordinates and vehicle offset angle, convert the global roadside point coordinates into candidate roadside point coordinates in the vehicle coordinate system at the current moment.

[0077] In this embodiment, the second transformation formula can be specifically understood as a formula for transforming from the global coordinate system to the vehicle coordinate system. The current vehicle position coordinates can be specifically understood as the vehicle's position coordinates at the current moment. The candidate curb point coordinates can be specifically understood as the coordinates of the curb point in the vehicle coordinate system at the current moment.

[0078] Substitute the current vehicle position coordinates, vehicle offset angle, and global curb point coordinates into the second transformation formula to obtain the candidate curb point coordinates in the vehicle coordinate system at the current moment.

[0079] For example, this application provides a second conversion formula:

[0080] X3=X2*cos(yaw)+Y2*sin(yaw)–(x2*cos(yaw)+y2*sin(yaw));

[0081] Y3=X2*sin(yaw)+Y2*cos(yaw)–(-x2*sin(yaw)+y2*cos(yaw)).

[0082] Where (X3, Y3) are the coordinates of the candidate roadside point, and (x2, y2) are the coordinates of the current vehicle position.

[0083] For example, Figure 3 Provides a sample diagram illustrating a vehicle and a coordinate system, such as... Figure 3 As shown, when vehicle 31 initiates a parking space search, a global coordinate system is established based on vehicle 31's current position A. During vehicle 31's movement, a vehicle coordinate system is established based on vehicle 31's current position coordinates B. The angle between vehicle 31 at position B (real-time vehicle position coordinates) and its initial position coordinates (point A coordinates) is the vehicle offset angle yaw. Both the global coordinate system and the vehicle coordinate system have the rear axle center point of the vehicle as the origin, the front direction of the vehicle as the positive Y-axis direction, and the right side of the vehicle as the positive X-axis direction.

[0084] S210. Determine the first coordinate range, the second coordinate range, and the reference coordinates based on the target parking space coordinate set. Filter the coordinates of each candidate curb point based on the first coordinate range, and use the coordinates of each candidate curb point within the first coordinate range as the alternative curb point coordinates.

[0085] In this embodiment, both the first coordinate range and the second coordinate range are ranges of coordinate values, used to filter the coordinates of roadside points from both the horizontal and vertical directions. The reference coordinates can be specifically understood as coordinates used as a reference when filtering candidate roadside point coordinates. The alternative roadside point coordinates can be specifically understood as coordinates obtained by filtering the candidate roadside point coordinates.

[0086] Specifically, the location of the target parking space is determined based on its coordinates. Taking the target parking space being on the right side of the vehicle as an example, the first coordinate range is used for vertical filtering, and the second coordinate range and reference coordinates are used for horizontal filtering. The vertical coordinate range is determined based on the target parking space coordinates and is used as the first coordinate range. The coordinate range of the target parking space is used as the second coordinate range (or the horizontal coordinate range of the target parking space is used as the second coordinate range), and the maximum value of the horizontal coordinate of the target parking space is used as the reference coordinate. The first coordinate range is compared with the coordinates of each candidate roadside point to determine whether the vertical coordinate of each candidate roadside point is within the first coordinate range. The coordinates of each candidate roadside point within the first coordinate range are used as alternative roadside point coordinates.

[0087] S211. Filter the coordinates of each candidate roadside point according to the second coordinate range and the reference coordinates to determine the coordinates of at least one target roadside point.

[0088] Based on the second coordinate range and reference coordinates, the x-coordinates of each candidate roadside point are filtered out, and coordinate points that are far from the target parking space and coordinate points that are in the target parking space are filtered out, so as to obtain at least one target roadside point coordinate.

[0089] As an optional embodiment of this embodiment, this optional embodiment will be further optimized as follows:

[0090] A1. Filter the coordinates of each candidate roadside point according to the second coordinate range, and take the coordinates of each candidate roadside point that is not within the second coordinate range as the coordinates of the first roadside point.

[0091] In this embodiment, the first roadside point coordinates can be specifically understood as coordinates obtained by lateral filtering of the candidate roadside point coordinates. The horizontal coordinates of each candidate roadside point are filtered according to the second coordinate range. Taking the second coordinate range as the coordinate range of the target parking space as an example, coordinates within the second coordinate range are filtered and deleted to obtain the coordinates of each candidate roadside point that are not within the second coordinate range. These coordinates are then used as the first roadside point coordinates.

[0092] A2. The coordinates of each candidate roadside point whose horizontal distance from the reference coordinate does not exceed the first preset distance threshold are taken as the coordinates of the first roadside point.

[0093] In this embodiment, the first preset distance threshold can be understood as a pre-set threshold, for example, 1m. The horizontal distance between the coordinates of each candidate roadside point and the reference coordinates is determined. For example, the absolute value of the difference between the horizontal coordinates is calculated as the horizontal distance, and the coordinates of each candidate roadside point whose horizontal distance does not exceed the first preset distance threshold are taken as the coordinates of the first roadside point. This achieves coarse filtering in the lateral direction.

[0094] A3. Determine the coordinates of the reference road edge point based on the coordinates of each first road edge point, and determine the horizontal distance between the coordinates of each first road edge point and the coordinates of the reference road edge point.

[0095] The reference curb point coordinates can be selected from the coordinates of the first curb points according to rules such as time and coordinates, or they can be obtained by performing calculations on the coordinates of the first curb points, such as calculating the average or minimum value. For example, the data collection times of each first curb point are compared, and the coordinates of the first curb point with the most recent data collection time are determined as the reference curb point coordinates. The horizontal distance between the coordinates of each first curb point and the reference curb point coordinates is determined by calculating the absolute value of the difference in their x-coordinates.

[0096] A4. Determine the coordinates of each first curb point whose horizontal distance is less than the second preset distance threshold as the target curb point coordinates.

[0097] In this embodiment, the second preset distance threshold can be understood as a pre-set threshold, for example, 20cm. The coordinates of each horizontal distance relative to the second preset distance threshold are determined, and the coordinates of each first roadside point whose horizontal distance is less than the second preset distance threshold are identified as the target roadside point coordinates. This achieves further lateral filtering.

[0098] For example, Figure 4 This application provides a schematic diagram illustrating a target parking space and candidate curb points in an embodiment of the present application. Figure 4 As shown, the target parking space is 41, and each candidate curb point 42 (the coordinates of the candidate curb points are the coordinates of the candidate curb points) is distributed near the target parking spaces 41, 43 and 44. The coordinates of each candidate curb point are filtered by the first coordinate range, the second coordinate range and the reference coordinates to obtain the target curb point 45 (the coordinates of the target curb point are the coordinates of the target curb point). Figure 5 This is a schematic diagram illustrating a target parking space and a target curb point, provided as an embodiment of this application. It should be noted that... Figure 4 Similar points are all candidate curb points 42, which are not individually labeled in the figure, but those skilled in the art will recognize them; correspondingly, Figure 5 Similar points in the diagram are all target roadside points, which are not individually marked in the diagram, but those skilled in the art can recognize them.

[0099] S212. Perform data fitting on the coordinates of each target roadside point to determine the roadside.

[0100] After determining the coordinates of each target roadside point, the roadside is obtained by fitting the coordinates of each target roadside point. The fitting method can be the least squares method, etc. The least squares method can fit the final filtered coordinates of each target roadside point into the roadside straight line equation (y=kx+b).

[0101] S213. Determine the reference vertex coordinates of the target parking space based on the target parking space coordinate set.

[0102] In this embodiment, the reference vertex coordinates can be specifically understood as the coordinates of the vertex of the target parking space as a reference point. The four vertices of the target parking space are determined based on the target parking space coordinate set. Either of the two vertices furthest from the curb is taken as the reference vertex, and the coordinates of this vertex are determined as the reference vertex coordinates.

[0103] S214. Calculate the distance between the curb and the reference vertex coordinates, and use it as the distance between the target parking space and the curb.

[0104] The distance between the curb and the reference vertex is calculated using the formula for the distance between a point and a line. This distance is then used as the distance between the target parking space and the curb. This distance is also used for path planning during automatic parking to prevent vehicles from colliding with the curb.

[0105] For example, Figure 6 This is a schematic diagram illustrating a target parking space and a curb provided in an embodiment of this application. The relative positions of the target parking space 51 and the curb 52 are shown in the figure. The coordinates of the parking space vertex A are used as reference vertex coordinates, and the distance between the parking space vertex A and the curb 52 is calculated as the distance between the target parking space and the curb.

[0106] This application uses a curb detection device to detect the distance to curb points, calculate the curb depth information, and apply it to automatic parking. This enables flexible vehicle control, preventing vehicle collisions with curbs and damage to tires and rims, and provides high flexibility for vehicle parking control. The algorithm detection method requires low computational power, can be implemented on low-cost hardware, and has strong scalability.

[0107] This invention provides an automatic parking curb detection method, solving the problems of inaccurate curb information detection and high cost during automatic parking. The method involves detecting the distance to curb points using a curb detection device, determining the curb point coordinates based on the distance, and after detecting vehicle initiation for parking, acquiring a set of curb point coordinates and performing coordinate system transformation to obtain candidate curb point coordinates in the vehicle's current coordinate system. These candidate curb point coordinates are then filtered against the target parking space coordinates, removing coordinates with large errors to obtain the target curb point coordinates. The curb is then determined using the target curb point coordinates, further determining the distance between the target parking space and the curb. This method is simple to implement, requiring only simple mathematical processing of the curb point coordinates without model training. The curb detection device only needs to collect the distance to determine the curb point coordinates, resulting in accurate and reliable detection results. It also eliminates the need for high-cost chips, thus reducing costs.

[0108] Example 3

[0109] Figure 7 This is a schematic diagram of an automatic parking curb detection device provided in Embodiment 3 of the present invention. Figure 7 As shown, the device includes: a coordinate acquisition module 61, a coordinate transformation module 62, a coordinate filtering module 63, and a roadside distance determination module 64.

[0110] The coordinate acquisition module 61 is used to acquire a set of roadside point coordinates and a set of target parking space coordinates after detecting that the vehicle has started parking. The set of roadside point coordinates includes at least one roadside point coordinate, and the set of target parking space coordinates includes at least one target parking space coordinate. The roadside point coordinates are determined based on the distance of the roadside points collected by the roadside detection device on the vehicle.

[0111] The coordinate transformation module 62 is used to transform the coordinate system of each of the roadside points to obtain the coordinates of the candidate roadside points in the vehicle coordinate system at the current time.

[0112] The coordinate filtering module 63 is used to filter the coordinates of each candidate roadside point according to the target parking space coordinate set to obtain the target roadside point coordinates;

[0113] The curb distance determination module 64 is used to determine the distance between the target parking space and the curb based on the coordinates of each target curb point.

[0114] This invention provides an automatic parking curb detection device, solving the problems of inaccurate curb information detection and high cost during automatic parking. The device detects the distance to curb points and determines their coordinates based on this distance. After detecting vehicle initiation for parking, it acquires a set of curb point coordinates and performs coordinate system transformation to obtain candidate curb point coordinates in the vehicle's current coordinate system. These candidate coordinates are then filtered against the target parking space coordinates, removing coordinates with significant errors to obtain the target curb point coordinates. The curb is then determined using these target coordinates, further defining the distance between the target parking space and the curb. This invention features a simple method for determining the curb, requiring only basic mathematical processing of the curb point coordinates without the need for model training. The curb detection device only needs to collect the distance to determine the curb point coordinates, resulting in accurate and reliable detection. It also eliminates the need for expensive chips, thus reducing costs.

[0115] Optionally, the device may also include:

[0116] The distance acquisition module is used to establish a global coordinate system based on the vehicle's current position when the vehicle is detected to be starting a parking space search, determine the vehicle's initial coordinates, and control the curb detection device on the vehicle to acquire the distance to the curb point.

[0117] The coordinate storage module is used to determine the coordinates of the roadside points based on the distance between the roadside points and the installation location information of the roadside detection device, and to store the roadside point coordinates and their corresponding acquisition times in the roadside point coordinate set.

[0118] Optionally, the device may also include:

[0119] The parking space display module is used to obtain and display the information of the available parking spaces when a vehicle is detected to have started a parking space search.

[0120] The parking start module is used to receive the target parking space specified by the user, determine the target parking space coordinate set, and control the vehicle to start parking.

[0121] Optionally, the coordinate transformation module 62 includes:

[0122] The real-time coordinate acquisition unit is used to acquire the real-time position coordinates of the vehicle corresponding to each roadside point coordinate.

[0123] Offset angle determination unit, used to determine the vehicle offset angle based on the vehicle's real-time position coordinates and the vehicle's initial coordinates;

[0124] The first coordinate transformation unit is used to convert the roadside point coordinates into global roadside point coordinates in the global coordinate system according to the preset first transformation formula and the real-time position coordinates of the vehicle and the vehicle offset angle.

[0125] The second coordinate transformation unit is used to convert the global roadside point coordinates into candidate roadside point coordinates in the vehicle coordinate system at the current moment by combining the current vehicle position coordinates and the vehicle offset angle according to the preset second transformation formula.

[0126] Optionally, the coordinate filtering module 63 includes:

[0127] The first filtering unit is used to determine a first coordinate range, a second coordinate range, and a reference coordinate based on the target parking space coordinate set, filter the coordinates of each candidate roadside point based on the first coordinate range, and use the coordinates of each candidate roadside point within the first coordinate range as the candidate roadside point coordinates.

[0128] The second filtering unit is used to filter the coordinates of each of the candidate roadside points according to the second coordinate range and the reference coordinates, and determine the coordinates of at least one target roadside point.

[0129] Optionally, the second filtering unit is specifically used to: filter the coordinates of each candidate roadside point according to the second coordinate range, and take the coordinates of each candidate roadside point that are not within the second coordinate range as the coordinates of the first roadside point; take the coordinates of each candidate roadside point that are horizontally at least as a first preset distance threshold from the reference coordinate as the coordinates of the first roadside point; determine the coordinates of the reference roadside point according to the coordinates of each first roadside point, and determine the horizontal distance between the coordinates of each first roadside point and the coordinates of the reference roadside point; and determine the coordinates of each first roadside point that are horizontally at least as the coordinates of the target roadside point.

[0130] Optionally, the curb distance determination module 64 includes:

[0131] The data fitting unit is used to perform data fitting on the coordinates of each of the target roadside points to determine the roadside.

[0132] A reference coordinate determination unit is used to determine the reference vertex coordinates of the target parking space based on the target parking space coordinate set;

[0133] The distance determination unit is used to calculate the distance between the curb and the reference vertex coordinates, which is used as the distance between the target parking space and the curb.

[0134] The automatic parking curb detection device provided in this embodiment of the invention can execute the automatic parking curb detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0135] Example 4

[0136] Figure 8 A schematic diagram of a vehicle structure that can be used to implement embodiments of the present invention is shown. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0137] like Figure 8 As shown, the vehicle includes a curb detection device 70 for collecting distances to curb points. The number of curb detection devices 70 can be one or more. Figure 8 Taking one example, the vehicle includes at least one processor 71 and a memory, such as a read-only memory (ROM) 72 and a random access memory (RAM) 73, communicatively connected to the at least one processor 71. The memory stores computer programs executable by the at least one processor. The processor 71 can perform various appropriate actions and processes based on the computer program stored in the ROM 72 or loaded into the RAM 73 from storage unit 78. The RAM 73 can also store various programs and data required for vehicle operation. The processor 71, ROM 72, and RAM 73 are interconnected via a bus 74. An input / output (I / O) interface 75 is also connected to the bus 74.

[0138] Multiple components in the vehicle are connected to the I / O interface 75, including: an input unit 76, such as a keyboard, mouse, etc.; an output unit 77, such as various types of displays, speakers, etc.; a storage unit 78, such as a disk, optical disk, etc.; and a communication unit 79, such as a network card, modem, wireless transceiver, etc. The communication unit 79 allows the vehicle to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0139] Processor 71 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 71 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 71 performs the various methods and processes described above, such as the automatic parking curb detection method.

[0140] In some embodiments, the automatic parking curb detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 78. In some embodiments, part or all of the computer program may be loaded and / or installed on the vehicle via ROM 72 and / or communication unit 79. When the computer program is loaded into RAM 73 and executed by processor 71, one or more steps of the automatic parking curb detection method described above may be performed. Alternatively, in other embodiments, processor 71 may be configured to perform the automatic parking curb detection method by any other suitable means (e.g., by means of firmware).

[0141] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0143] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0144] To provide interaction with the user, the systems and technologies described herein can be implemented in a vehicle having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the vehicle. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0145] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0146] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0147] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0148] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An automatic parking curb detection method, characterized in that, include: When the vehicle starts parking, the system acquires a set of curb point coordinates and a set of target parking space coordinates. The set of curb point coordinates includes at least one curb point coordinate, and the set of target parking space coordinates includes at least one target parking space coordinate. The curb point coordinates are determined based on the curb point distance collected by the curb detection device on the vehicle. The coordinates of each curb point are transformed to obtain the coordinates of the candidate curb points in the vehicle coordinate system at the current time. The coordinates of each candidate roadside point are filtered according to the target parking space coordinate set to obtain the target roadside point coordinates; The distance between the target parking space and the curb is determined based on the coordinates of each target curb point. Specifically, the process of filtering the coordinates of each candidate roadside point based on the target parking space coordinate set to obtain the target roadside point coordinates includes: The first coordinate range, the second coordinate range, and the reference coordinates are determined based on the target parking space coordinate set. The coordinates of each candidate roadside point are filtered based on the first coordinate range, and the coordinates of each candidate roadside point within the first coordinate range are used as alternative roadside point coordinates. The coordinates of each candidate roadside point are filtered according to the second coordinate range, and the coordinates of each candidate roadside point that are not within the second coordinate range are taken as the coordinates of the first roadside point. The coordinates of the first roadside point are obtained by horizontally filtering the coordinates of the candidate roadside points. The coordinates of each of the candidate roadside points whose horizontal distance from the reference coordinates does not exceed a first preset distance threshold are taken as the coordinates of the first roadside point. Based on the coordinates of each of the first roadside points, determine the coordinates of the reference roadside points, and determine the horizontal distance between the coordinates of each of the first roadside points and the coordinates of the reference roadside points; The coordinates of each of the first roadside points whose horizontal distance is less than the second preset distance threshold are determined as the coordinates of the target roadside point.

2. The method according to claim 1, characterized in that, Before obtaining the set of curb point coordinates and the target parking space coordinates after detecting that the vehicle has started parking, the process includes: When a vehicle is detected to have started searching for a parking space, a global coordinate system is established based on the vehicle's current position to determine the vehicle's initial coordinates, and the curb detection device on the vehicle is controlled to collect the distance to the curb point. The coordinates of the curb points are determined based on the distance to the curb points and the installation location information of the curb detection device, and the coordinates of the curb points and their corresponding acquisition times are stored in the curb point coordinate set.

3. The method according to claim 1, characterized in that, Before obtaining the set of curb point coordinates and the target parking space coordinates after detecting that the vehicle has started parking, the process includes: Once a vehicle is detected to have started searching for parking spaces, the available parking space information is retrieved and displayed. Receive the target parking space specified by the user, determine the target parking space coordinate set, and control the vehicle to start parking.

4. The method according to claim 2, characterized in that, The step of performing coordinate system transformation on the coordinates of each of the roadside points to obtain the coordinates of the candidate roadside points in the vehicle coordinate system at the current time includes: For each roadside point coordinate, obtain the real-time vehicle position coordinates corresponding to the roadside point coordinates; The vehicle offset angle is determined based on the vehicle's real-time position coordinates and initial vehicle coordinates; Based on the preset first conversion formula, the real-time vehicle position coordinates and vehicle offset angle are combined to convert the roadside point coordinates into global roadside point coordinates in the global coordinate system. Based on the preset second conversion formula, the global curb point coordinates are converted into candidate curb point coordinates in the vehicle coordinate system at the current moment by combining the current vehicle position coordinates and the vehicle offset angle.

5. The method according to claim 1, characterized in that, Determining the distance between the target parking space and the curb based on the coordinates of each target curb point includes: Data fitting is performed on the coordinates of each target roadside point to determine the roadside; The reference vertex coordinates of the target parking space are determined based on the set of target parking space coordinates; Calculate the distance between the curb and the reference vertex coordinates, and use it as the distance between the target parking space and the curb.

6. An automatic parking curb detection device, characterized in that, include: The coordinate acquisition module is used to acquire a set of roadside point coordinates and a set of target parking space coordinates after detecting that the vehicle has started parking. The set of roadside point coordinates includes at least one roadside point coordinate, and the set of target parking space coordinates includes at least one target parking space coordinate. The roadside point coordinates are determined based on the distance of the roadside points collected by the roadside detection device on the vehicle. The coordinate transformation module is used to transform the coordinate system of each of the roadside points to obtain the coordinates of the candidate roadside points in the vehicle coordinate system at the current time. The coordinate filtering module is used to filter the coordinates of each candidate roadside point according to the target parking space coordinate set to obtain the target roadside point coordinates; The curb distance determination module is used to determine the distance between the target parking space and the curb based on the coordinates of each target curb point; The coordinate filtering module includes: The first filtering unit is used to determine a first coordinate range, a second coordinate range, and a reference coordinate based on the target parking space coordinate set, filter the coordinates of each candidate roadside point based on the first coordinate range, and use the coordinates of each candidate roadside point within the first coordinate range as the candidate roadside point coordinates. The second filtering unit is used to filter the coordinates of each candidate roadside point according to the second coordinate range, and to take the coordinates of each candidate roadside point that is not within the second coordinate range as the coordinates of the first roadside point, wherein the coordinates of the first roadside point are obtained by horizontally filtering the coordinates of the candidate roadside points; to take the coordinates of each candidate roadside point that are horizontally at a distance not exceeding a first preset distance threshold from the reference coordinates as the coordinates of the first roadside point; to determine the coordinates of the reference roadside point according to the coordinates of each first roadside point, and to determine the horizontal distance between the coordinates of each first roadside point and the coordinates of the reference roadside point; and to determine the coordinates of each first roadside point that are horizontally at a distance less than a second preset distance threshold as the coordinates of the target roadside point.

7. A vehicle, characterized in that, The vehicles include: A curb detection device is used to collect distances from curb points; At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the automatic parking curb detection method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the automatic parking curb detection method according to any one of claims 1-5.

Images