Virtual parking space generation method, vehicle and computer readable storage medium

Abstract

The embodiment of the application provides a virtual parking space generation method, a vehicle and a computer readable storage medium, the method comprises the following steps: in response to the target vehicle driving to the target parking area, acquiring the visual perception data corresponding to the target vehicle and the standardized configuration parameters corresponding to the target parking area; analyzing and processing the visual perception data to obtain a physical boundary reference line; generating an outer edge line corresponding to the virtual parking space based on the physical boundary reference line and a safe off-shore distance; and constructing the virtual parking space based on the standard parking length, the standard parking width, the physical boundary reference line and the outer edge line. The application solves the technical problems of low safety and poor adaptability of the virtual parking space generation method provided in the related art.

Description

Technical Field

[0001] This application relates to the field of autonomous driving environmental perception and decision-making planning technology, specifically to a virtual parking space generation method, a vehicle, and a computer-readable storage medium. Background Technology

[0002] The commercial operation of autonomous taxis relies on pre-designated pick-up and drop-off points. In complex urban road environments, many operating points are located in temporary roadside parking areas. Due to urban planning constraints or road surface wear, there are often no visually defined parking space boundaries on the ground. Vehicles typically only obtain a single Global Positioning System (GPS) coordinate point from a high-precision map as a navigation target. When actually performing a roadside parking task, without clear visual boundary constraints, the perception system struggles to output an accurate parking posture, which can easily lead to the vehicle being too far from the curb, affecting passenger boarding and alighting, or the tires scraping against the curb due to positioning drift.

[0003] There is currently no good solution to the above problems. Summary of the Invention

[0004] This application provides a method for generating virtual parking spaces, a vehicle, and a computer-readable storage medium to at least solve the technical problems of low security and poor adaptability in the virtual parking space generation methods provided in the related art.

[0005] According to one aspect of the embodiments of this application, a method for generating a virtual parking space is provided, comprising: in response to a target vehicle driving to a target parking area, acquiring visual perception data corresponding to the target vehicle and standardized configuration parameters corresponding to the target parking area, wherein the visual perception data is obtained by acquiring data from the road edge corresponding to the target parking area through an on-board image acquisition component, and the standardized configuration parameters include a standard parking length, a standard parking width, and a safe offshore distance; analyzing and processing the visual perception data to obtain a physical boundary baseline; generating an outer edge line corresponding to the virtual parking space based on the physical boundary baseline and the safe offshore distance; and constructing a virtual parking space based on the standard parking length, the standard parking width, the physical boundary baseline, and the outer edge line.

[0006] Further, the visual perception data is analyzed and processed to obtain the physical boundary baseline, including: performing semantic segmentation on the visual perception data to obtain the edge mask corresponding to the target parking area, wherein the edge mask is used to represent multiple discrete pixels corresponding to the road edge; and performing fitting processing on the edge mask corresponding to the target parking area to obtain the physical boundary baseline.

[0007] Furthermore, based on the physical boundary baseline and the safe offshore distance, generating the outer edge line corresponding to the virtual parking space includes: obtaining the normal vector direction corresponding to the physical boundary baseline, wherein the normal vector direction is used to represent a unit vector perpendicular to the physical boundary baseline and pointing to the inside of the road in the target parking area; and translating the physical boundary baseline based on the normal vector direction and the safe offshore distance to obtain the outer edge line.

[0008] Furthermore, based on the standard parking length, standard parking width, physical boundary baseline, and outer edge line, the construction of the virtual parking space includes: obtaining the orthogonal projection point of the rear axle center of the target vehicle relative to the physical boundary baseline, wherein the orthogonal projection point is used to determine the longitudinal reference center corresponding to the virtual parking space; generating an initial rectangular envelope based on the orthogonal projection point, standard parking length, and standard parking width, wherein the initial rectangular envelope is used to determine the parking area corresponding to the virtual parking space; and constructing the virtual parking space based on the initial rectangular envelope.

[0009] Furthermore, generating the initial rectangular envelope based on the orthogonal projection points, standard docking length, and standard docking width includes: longitudinally truncating the physical boundary baseline based on the orthogonal projection points and standard docking length to obtain the first endpoint and the second endpoint, wherein the distance between the first endpoint and the second endpoint is equal to the standard docking length; and generating the initial rectangular envelope based on the first endpoint, the second endpoint, and the standard docking width.

[0010] Furthermore, generating an initial rectangular envelope based on the first endpoint, the second endpoint, and the standard docking width includes: determining the third endpoint and the fourth endpoint based on the first endpoint, the second endpoint, and the standard docking width, wherein the distance between the first endpoint and the third endpoint is equal to the standard docking width, and the distance between the second endpoint and the fourth endpoint is equal to the standard docking width; and generating an initial rectangular envelope based on the first endpoint, the second endpoint, the third endpoint, and the fourth endpoint.

[0011] Furthermore, constructing a virtual parking space based on the initial rectangular envelope includes: performing obstacle detection on the initial rectangular envelope to obtain the occupancy ratio of obstacles in the initial rectangular envelope; and constructing a virtual parking space based on the occupancy ratio and the initial rectangular envelope.

[0012] Furthermore, based on the occupancy ratio and the initial rectangular envelope, the construction of the virtual parking space includes: in response to the occupancy ratio being greater than or equal to a preset ratio threshold, performing iterative displacement calculation on the initial rectangular envelope based on the tangent direction corresponding to the physical boundary baseline and a preset step size to obtain the target rectangular envelope; in response to the obstacle's occupancy ratio in the target rectangular envelope being less than a preset ratio threshold, determining the target rectangular envelope as a virtual parking space.

[0013] According to another aspect of the embodiments of this application, a virtual parking space generation device is also provided, comprising: an acquisition module, configured to acquire visual perception data corresponding to the target vehicle and standardized configuration parameters corresponding to the target parking area in response to a target vehicle driving to a target parking area, wherein the visual perception data is obtained by acquiring data from the road edge corresponding to the target parking area through an on-board image acquisition component, and the standardized configuration parameters include a standard parking length, a standard parking width, and a safe offshore distance; an analysis module, configured to analyze and process the visual perception data to obtain a physical boundary baseline; a generation module, configured to generate an outer edge line corresponding to the virtual parking space based on the physical boundary baseline and the safe offshore distance; and a construction module, configured to construct the virtual parking space based on the standard parking length, standard parking width, physical boundary baseline, and outer edge line.

[0014] Furthermore, the analysis module is also used to: perform semantic segmentation processing on the visual perception data to obtain the edge mask corresponding to the target parking area, wherein the edge mask is used to represent multiple discrete pixels corresponding to the road edge; and perform fitting processing on the edge mask corresponding to the target parking area to obtain the physical boundary baseline.

[0015] Furthermore, the generation module is also used to: obtain the normal vector direction corresponding to the physical boundary baseline, wherein the normal vector direction is used to represent a unit vector perpendicular to the physical boundary baseline and pointing to the inside of the road in the target parking area; and translate the physical boundary baseline based on the normal vector direction and the safe offshore distance to obtain the outer edge line.

[0016] Furthermore, the construction module is also used to: obtain the orthogonal projection point of the rear axle center of the target vehicle relative to the physical boundary baseline, wherein the orthogonal projection point is used to determine the longitudinal reference center corresponding to the virtual parking space; generate an initial rectangular envelope based on the orthogonal projection point, the standard parking length, and the standard parking width, wherein the initial rectangular envelope is used to determine the parking area corresponding to the virtual parking space; and construct the virtual parking space based on the initial rectangular envelope.

[0017] Furthermore, the building module is also used to: longitudinally cut the physical boundary baseline based on the orthogonal projection points and the standard docking length to obtain the first endpoint and the second endpoint, wherein the distance between the first endpoint and the second endpoint is equal to the standard docking length; and generate an initial rectangular envelope based on the first endpoint, the second endpoint, and the standard docking width.

[0018] Furthermore, the building module is also used to: determine the third and fourth endpoints based on the first endpoint, the second endpoint, and the standard docking width, wherein the distance between the first and third endpoints is equal to the standard docking width, and the distance between the second and fourth endpoints is equal to the standard docking width; and generate an initial rectangular envelope based on the first, second, third, and fourth endpoints.

[0019] Furthermore, the construction module is also used to: perform obstacle detection on the initial rectangular envelope to obtain the occupancy ratio of the obstacle in the initial rectangular envelope; and construct a virtual docking station based on the occupancy ratio and the initial rectangular envelope.

[0020] Furthermore, the construction module is also used to: in response to the occupancy ratio being greater than or equal to a preset ratio threshold, perform iterative displacement calculation on the initial rectangular envelope based on the tangent direction corresponding to the physical boundary baseline and a preset step size to obtain the target rectangular envelope; in response to the obstacle's occupancy ratio in the target rectangular envelope being less than a preset ratio threshold, determine the target rectangular envelope as a virtual docking position.

[0021] According to another aspect of the embodiments of this application, a vehicle is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0022] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0023] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0024] According to another aspect of the embodiments of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods in various embodiments of this application.

[0025] According to another aspect of the embodiments of this application, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this application.

[0026] In this embodiment, when the target vehicle drives to the target parking area, the visual perception data corresponding to the target vehicle and the standardized configuration parameters corresponding to the target parking area are obtained. The visual perception data is analyzed and processed to obtain the physical boundary baseline. Then, based on the physical boundary baseline and the safe offshore distance, the outer edge line corresponding to the virtual parking space is generated. Finally, based on the standard parking length, standard parking width, physical boundary baseline and outer edge line, the virtual parking space is constructed. This achieves the goal of accurately constructing standardized virtual parking spaces in complex urban scenarios without ground markings and without front and rear reference objects. This improves the safety and adaptability of virtual parking spaces and solves the technical problems of low safety and poor adaptability of virtual parking space generation methods provided in related technologies. Attached Figure Description

[0027] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0028] Figure 1 This is a flowchart of an optional virtual docking station generation method according to an embodiment of this application;

[0029] Figure 2 This is a schematic diagram of an optional physical boundary baseline according to an embodiment of this application;

[0030] Figure 3 This is a schematic diagram of an optional virtual docking station generation method according to an embodiment of this application;

[0031] Figure 4 This is a schematic diagram of another optional virtual parking space generation method according to an embodiment of this application;

[0032] Figure 5 This is a structural block diagram of an optional virtual parking space generation device according to an embodiment of this application. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0034] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application 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 this application 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 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.

[0035] The commercial operation of autonomous taxis relies on pre-designated pick-up and drop-off points. In complex urban road environments, many operating points are located in temporary roadside parking areas. Due to urban planning constraints or road surface wear, there are often no visually defined parking space boundaries on the ground. Vehicles typically only obtain a single GPS coordinate point from a high-precision map as a navigation target. When actually performing a roadside parking task, without clear visual boundary constraints, the perception system struggles to output an accurate parking posture, which can easily lead to the vehicle being too far from the curb, affecting passenger boarding and alighting, or the tires scraping against the curb due to positioning drift.

[0036] Specifically, in related technologies, ground markings or parked vehicles in front and behind are usually used as references to infer the parking area. However, in open stations without markings and without adjacent vehicles, the perception system lacks reliable geometric constraints and cannot generate a stable and consistent parking posture. This results in high randomness in the parking target position output by the planning module. Vehicles often deviate from the ideal parking area due to the accumulation of positioning errors, or cannot establish a lateral safety distance because they cannot identify the physical boundary of the road edge. This leads to safety hazards such as inconvenience for passengers getting on and off the vehicle, doors colliding with the road edge, or tires scraping.

[0037] Furthermore, the dimensions of the parking areas generated by the relevant technologies change dynamically with the environment and lack unified standard constraints, resulting in inconsistent positions of different vehicles when stopping at the same station. This increases the uncertainty of the passenger boarding and alighting experience and also poses significant obstacles to the standardization of fleet scheduling, automatic door control system design, and barrier-free shuttle functions.

[0038] According to an embodiment of this application, a method embodiment for generating a virtual docking station is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0039] This method embodiment can be executed in an electronic device or similar computing device that includes memory and a processor. Taking operation on a computer terminal as an example, the computer terminal may include one or more processors (processors may include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), digital signal processing (DSP) chips, microcontroller units (MCUs), field-programmable gate arrays (FPGAs), neural network processors (NPUs), tensor processors (TPUs), artificial intelligence (AI) type processors, etc.) and memory for storing data. Optionally, the computer terminal may also include transmission devices, input / output devices, and display devices for communication functions. Those skilled in the art will understand that the above structural description is merely illustrative and does not limit the structure of the computer terminal. For example, the computer terminal may include more or fewer components than described above, or have a different configuration than described above.

[0040] The memory can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the virtual docking station generation method in this application embodiment. The processor executes various functional applications and data processing by running the computer program stored in the memory, thereby realizing the aforementioned virtual docking station generation method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0041] The transmission device is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0042] Display devices can be, for example, touchscreen liquid crystal displays (LCDs) and touch displays (also referred to as "touchscreens" or "touch displays"). The LCD allows users to interact with the user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), which allows users to interact with the GUI through finger contact and / or gestures on a touch-sensitive surface. Optional human-computer interaction functions include: creating web pages, drawing, word processing, creating electronic documents, playing games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital video, playing digital music, and / or web browsing, etc. Executable instructions for performing the above human-computer interaction functions are configured / stored in one or more processor-executable computer program products or readable storage media.

[0043] This embodiment provides a method for generating virtual docking spots. Figure 1 This is a flowchart of an optional virtual docking station generation method according to an embodiment of this application, such as... Figure 1 As shown, the process includes the following steps:

[0044] Step S11: In response to the target vehicle driving to the target parking area, obtain the visual perception data corresponding to the target vehicle and the standardized configuration parameters corresponding to the target parking area. The visual perception data is obtained by the vehicle image acquisition component to collect data from the road edge corresponding to the target parking area. The standardized configuration parameters include standard parking length, standard parking width and safe offshore distance.

[0045] For example, the target vehicle described above can be used in applications such as intelligent transportation, logistics and distribution, and industrial transportation. The target vehicle is equipped with various sensors and navigation systems, enabling it to autonomously plan routes, avoid obstacles, and achieve autonomous driving.

[0046] For example, the target vehicle may be, but is not limited to, an autonomous taxi, logistics vehicle, or testing vehicle used in the field of intelligent transportation. It should be noted that this embodiment uses an autonomous taxi as an example to illustrate the virtual parking space generation process, but this does not constitute a specific limitation on the functional type of the target vehicle.

[0047] The aforementioned target parking areas can be temporary roadside parking spots without ground markings, relying solely on the physical structure of the road edge (such as curbs, guardrails, or sidewalk boundaries) as spatial constraints. They do not include any artificially drawn parking lines, markings, or directional signs, and there are no vehicles in front or behind or other significant reference points for calculating parking space before a vehicle enters. These areas are commonly found on non-main roads in cities, at entrances and exits of residential areas, next to bus stops, or in temporary passenger pick-up and drop-off areas not covered by municipal planning.

[0048] The standardized configuration parameters corresponding to the aforementioned target parking areas include standard parking length, standard parking width, and safe off-shore distance. The standard parking length defines the longitudinal dimension of the virtual parking space in the road direction to accommodate the vehicle's length and the door opening space required for passenger boarding and alighting. The standard parking width limits the lateral dimension of the virtual parking space perpendicular to the road edge, ensuring a consistent lateral distance between the vehicle and the curb after parking and providing sufficient operational space. The safe off-shore distance is a fixed threshold offset from the physical road edge to the inside of the road, used to enforce a minimum lateral distance between the vehicle and the curb in unmarked environments, thereby mitigating the risk of tire scraping or door collisions caused by positioning drift or perception errors. All of these parameters are pre-configured according to engineering specifications for the target vehicle type and operating scenario, and mapped to the high-precision map data of the corresponding stations, achieving consistent parking behavior across vehicle types and regions.

[0049] For example, when an autonomous taxi arrives at a temporary pick-up / drop-off point in a residential area, the onboard surround-view camera system simultaneously acquires a high-resolution image sequence of the road edge and generates a bird's-eye view in the vehicle coordinate system through inverse perspective transformation. At the same time, the vehicle positioning module identifies the current station as a preset "standard stop" based on the high-precision map matching results, and loads the standardized configuration parameters corresponding to the station from the cloud configuration database. The standard stopping length is set to 6.0 meters to accommodate the door opening requirements of passenger vehicles, the standard stopping width is 2.5 meters to ensure safe operating space between the passenger side door and the curb, and the safe off-shore distance is fixed at 0.30 meters to prevent the door from scratching or the wheel rim from touching the curb. All parameters are bound to the station ID and embedded in the metadata of the high-precision map.

[0050] By acquiring the visual perception data of the target vehicle and the standardized configuration parameters of the target parking area when the target vehicle drives to the target parking area, an independent and stable input basis can be provided for the geometric construction of the virtual parking space. This ensures that the visual perception data and the target parking area are accurately aligned in the spatial coordinate system, avoiding parameter misuse due to scene uncertainty, and thus improving the accuracy of the virtual parking space.

[0051] Step S12: Analyze and process the visual perception data to obtain the physical boundary baseline;

[0052] The aforementioned physical boundary baseline is a continuous straight line derived by performing semantic segmentation and edge extraction on the visual perception data acquired by the vehicle-mounted image acquisition component.

[0053] Specifically, the aforementioned physical boundary baselines, in the vehicle coordinate system, can typically be the actual spatial orientation of immovable physical structures such as road curbs, guardrails, or sidewalk boundaries. They serve as geometric references for constructing virtual parking spaces in road scenarios where there are no artificial markings or dynamic obstacle information.

[0054] By analyzing and processing visual perception data, physical boundary baselines are obtained, which can eliminate the uncertainty of parking positioning caused by missing or damaged road markings. This provides a stable and reproducible physical reference for the geometric construction of virtual parking spaces, ensuring that even in complex urban roadside scenarios without markings or reference objects, a consistent and predictable spatial constraint baseline can still be generated based on the real road structure.

[0055] Step S13: Based on the physical boundary baseline and the safe offshore distance, generate the outer edge line corresponding to the virtual docking position;

[0056] The outer edge line corresponding to the aforementioned virtual parking space is a parallel straight line obtained by shifting a safe distance off the road inward from the physical boundary baseline. This parallel straight line defines the minimum safe lateral limit between the virtual parking space and the physical edge of the road in the vehicle coordinate system. Its spatial position does not depend on dynamic obstacles or artificial markings, but is determined solely by the static physical boundary and preset safety parameters. This ensures that the vehicle maintains a constant distance off the roadside during parking, thus avoiding the risk of scraping caused by positioning drift, perceived noise, or environmental interference.

[0057] Step S14: Construct a virtual parking space based on the standard parking length, standard parking width, physical boundary baseline, and outer edge line.

[0058] The aforementioned virtual docking position is a rectangular geometric area constrained by the physical boundary baseline, the outer edge line, the standard docking length, and the standard docking width.

[0059] Based on steps S11 to S14 above, when the target vehicle drives to the target parking area, the visual perception data corresponding to the target vehicle and the standardized configuration parameters corresponding to the target parking area are obtained. The visual perception data is analyzed and processed to obtain the physical boundary baseline. Then, based on the physical boundary baseline and the safe offshore distance, the outer edge line corresponding to the virtual parking space is generated. Finally, based on the standard parking length, standard parking width, physical boundary baseline and outer edge line, the virtual parking space is constructed. This achieves the goal of accurately constructing standardized virtual parking spaces in complex urban scenarios without ground markings and without front and rear reference objects. This improves the safety and adaptability of virtual parking spaces and solves the technical problems of low safety and poor adaptability of virtual parking space generation methods provided in related technologies.

[0060] The virtual parking space generation method in the embodiments of this application will be further described below.

[0061] Further, in step S12, the visual perception data is analyzed and processed to obtain the physical boundary baseline, including:

[0062] Step S121: Perform semantic segmentation on the visual perception data to obtain the edge mask corresponding to the target parking area, wherein the edge mask is used to represent multiple discrete pixels corresponding to the road edge;

[0063] The edge mask corresponding to the aforementioned target parking area is a binary mask image generated by performing pixel-level classification of the road edge area in the bird's-eye view under the vehicle coordinate system through a semantic segmentation network.

[0064] Specifically, a pixel value of 1 indicates that the current location belongs to a physical hard boundary structure such as a curb, guardrail, or sidewalk boundary, while a value of 0 indicates that the current location belongs to a non-boundary area.

[0065] For example, a bird's-eye view in the vehicle coordinate system generated from the original image captured by the vehicle's surround-view camera after distortion correction and extrinsic parameter transformation can be input into a pre-trained lightweight semantic segmentation network for semantic segmentation processing. The output is a probability map containing five semantic labels: background, road surface, curb, sidewalk, and dynamic obstacles. Furthermore, a confidence threshold (e.g., 0.6) can be applied to the probability map of the curb passage for binarization, retaining the high-confidence curb pixel regions, thereby generating a binarized edge mask containing only 0 and 1 values.

[0066] By performing semantic segmentation on visual perception data, the edge mask corresponding to the target parking area is obtained. This enables the accurate separation of roadside, guardrail, or sidewalk edge areas with physical hard boundary attributes from complex road scenes. It effectively suppresses misclassification caused by interference factors such as road surface texture, shadows, water accumulation, and fallen leaves, providing a highly reliable discrete point set input for subsequent geometric modeling, thereby improving the stability and semantic consistency of physical boundary recognition.

[0067] Step S122: Fit the edge mask corresponding to the target docking area to obtain the physical boundary baseline.

[0068] For example, the coordinates of all pixels with a value of 1 in the edge mask can be extracted to construct a discrete point set. A robust straight-line fitting algorithm using Random Sample Consensus (RANSAC) is then applied to this discrete point set to eliminate false detections caused by fallen leaves, shadows, or noise. Subsequently, the least squares method is used to fit the selected set of interior points to obtain the physical boundary baseline equation. A Kalman filter is then used to temporally smooth the baseline parameters of consecutive frames to suppress single-frame detection jitter. If the number of points in the current frame is less than a preset threshold (e.g., 50), the filtered baseline parameters from the previous frame are automatically reused to ensure the continuity and stability of the system output.

[0069] Figure 2 This is a schematic diagram of an optional physical boundary baseline according to an embodiment of this application, such as... Figure 2 As shown, the car travels at a speed of X v When driving, the roadside pixel mask is the edge mask that includes multiple discrete pixels, and the physical boundary baseline is a straight line generated after fitting multiple discrete pixels.

[0070] For example, in the vehicle coordinate system, the physical boundary baseline can be expressed as a linear equation y=kx+b, whose slope k and intercept b can be calculated from the set of interior points optimized by the least squares method.

[0071] Based on steps S121 to S122 above, semantic segmentation processing is performed on the visual perception data to obtain the edge mask corresponding to the target parking area. Then, the edge mask corresponding to the target parking area is fitted to obtain the physical boundary baseline. This can extract the road physical boundary expression with geometric consistency from the original perception noise and unstructured environmental interference, effectively eliminating the jitter and false detection of discrete pixels caused by local occlusion, illumination changes or sensor noise, forming a stable, continuous and mathematically analyzable baseline model. This provides a high-precision, low-drift spatial reference for the subsequent geometric reconstruction of virtual parking spaces, thereby improving the robustness and temporal consistency of boundary recognition in dynamic and complex urban scenarios.

[0072] Further, in step S13, based on the physical boundary baseline and the safe offshore distance, the outer edge line corresponding to the virtual berth is generated, including:

[0073] Step S131: Obtain the normal vector direction corresponding to the physical boundary baseline, wherein the normal vector direction is used to represent the unit vector perpendicular to the physical boundary baseline and pointing to the inside of the road in the target parking area;

[0074] The normal vector direction corresponding to the aforementioned physical boundary baseline is a unit vector obtained by rotating the tangent vector of the physical boundary baseline clockwise by 90 degrees in the vehicle coordinate system. Its direction always points to the inside of the road, that is, the side of the vehicle's driving direction, thereby ensuring that the outer edge line of the virtual parking space generated after translation maintains a safe distance from the road edge and maintains spatial consistency with the vehicle's direction of movement.

[0075] Step S132: The physical boundary baseline is translated based on the normal vector direction and the safe offshore distance to obtain the outer edge line.

[0076] Figure 3 This is a schematic diagram of an optional virtual parking space generation method according to an embodiment of this application, such as... Figure 3 As shown, the direction of the arrow pointing from the physical boundary baseline to the outer edge line is the direction of the normal vector corresponding to the physical boundary baseline, and the distance between the physical boundary baseline and the outer edge line is the safe offshore distance.

[0077] For example, when the physical boundary baseline is fitted to a straight line equation in the vehicle coordinate system using a set of points, its tangent vector can be calculated and normalized using the coordinate difference between two adjacent points. Furthermore, when obtaining the tangent vector corresponding to the physical boundary baseline, a 90-degree clockwise rotation can be performed on the tangent vector to obtain a unit normal vector perpendicular to the baseline and pointing inwards towards the road. Specifically, regardless of how the physical boundary baseline is tilted or deflected on the plane, its translation direction is accurately aligned with the vehicle's drivable area, thereby achieving a constant safe distance between the outer edge of the virtual parking space and the actual road edge, avoiding lateral positioning deviations caused by changes in road slope, curvature, or sensor viewing angle.

[0078] Based on steps S131 to S132 above, the normal vector direction corresponding to the physical boundary baseline is obtained. Then, the physical boundary baseline is translated based on the normal vector direction and the safe offshore distance to obtain the outer edge line. Based on the physical reference, a geometric constraint line that maintains a constant lateral distance from the hard boundary of the road can be accurately constructed in the vehicle coordinate system. This provides a stable and drift-free lateral boundary reference for the subsequent generation of the longitudinal envelope of the virtual parking space, effectively avoiding the risk of lateral displacement of the parking position due to positioning error or sensor noise, thereby improving the safety of the virtual parking space.

[0079] Further, in step S14, based on the standard docking length, standard docking width, physical boundary baseline, and outer edge line, the virtual docking position is constructed, including:

[0080] Step S141: Obtain the orthogonal projection point of the rear axle center of the target vehicle relative to the physical boundary baseline, wherein the orthogonal projection point is used to determine the longitudinal reference center corresponding to the virtual parking space.

[0081] The rear axle center of the aforementioned target vehicle is the geometric intersection of the two wheel axles of the rear axle in the vehicle chassis structure. This point is located on the longitudinal plane of symmetry of the vehicle and is the core reference point used in the vehicle kinematic model to describe the vehicle's attitude and posture.

[0082] Specifically, the coordinates of the rear axle center are determined by the track width, wheelbase, and suspension geometry parameters in the vehicle body coordinate system. They are not affected by vehicle body deformation or load distribution, and the center remains rigidly connected to the chassis during vehicle driving and parking. Therefore, it can serve as a reference for calculating position and heading angle in vehicle trajectory planning and control algorithms.

[0083] The above-mentioned orthogonal projection point is the vertical projection position of the rear axle center of the target vehicle on the plane where the physical boundary baseline is located.

[0084] Specifically, the orthogonal projection point is determined by the foot of the perpendicular drawn from the rear axle center of the target vehicle to the physical boundary baseline. Its coordinates are uniquely determined by the geometric equation of the physical boundary baseline and the spatial coordinates of the rear axle center through analytical geometric relationships. The projection process does not depend on any external reference objects or environmental features, but only performs mathematical calculations based on the precise position of the rear axle center in the vehicle body coordinate system and the fitting parameters of the baseline. This provides a stable and drift-free geometric reference for the longitudinal positioning of the virtual parking space.

[0085] Step S142: Based on the orthogonal projection points, standard docking length, and standard docking width, generate an initial rectangular envelope, wherein the initial rectangular envelope is used to determine the docking area corresponding to the virtual docking position;

[0086] The aforementioned initial rectangular envelope is a closed rectangular area formed by extending half the standard parking length symmetrically along the tangent direction of the physical boundary baseline with the orthogonal projection point as the longitudinal geometric center, and extending the standard parking width laterally into the road with the outer edge line of the virtual parking space as one side boundary to form the other side boundary.

[0087] Specifically, in the vehicle coordinate system, the aforementioned initial rectangular envelope is determined by four endpoints, and its length and width dimensions are constrained by the standard docking length and standard docking width parameters.

[0088] Specifically, the area of ​​the initial rectangular envelope must be strictly matched with the space required for the actual parking of the vehicle. Its length and width are fixed according to the standard parking length and standard parking width parameters to ensure that the enclosed area can just accommodate the minimum necessary space where the rear axle center of the vehicle is located at the geometric center, the vehicle body is completely within the envelope, and the doors can be opened safely. In this way, without relying on environmental references, the virtual parking space can accurately correspond to the body outline of the target vehicle on a geometric scale, avoiding space waste and path planning redundancy caused by the vehicle body being too large or too small due to the envelope being too small. This achieves the standardization of parking area and consistency of vehicle adaptability.

[0089] Based on orthogonal projection points, standard parking length, and standard parking width, an initial rectangular envelope is generated. This allows the vehicle coordinate system to serve as the sole reference frame, and the geometric boundary of a standardized parking area with constant dimensions can be constructed through analytical geometric relationships. This ensures that the longitudinal positioning of the virtual parking space is driven by the vehicle's own key kinematic reference points, avoiding parking area offsets or deformations caused by perceived noise, positioning drift, or interference from external obstacles. This provides a stable and reproducible initial geometric constraint basis for subsequent dynamic obstacle avoidance correction.

[0090] Step S143: Construct a virtual docking station based on the initial rectangular envelope.

[0091] For example, the coordinates of the four endpoints of the initial rectangular envelope can be standardized and encapsulated in the vehicle coordinate system to form a parking area model with a fixed geometric topology. Specifically, the longitudinal boundary of this model is defined by half the standard parking length extended forward and backward along the tangent direction of the orthogonal projection point along the baseline, and the lateral boundary is jointly defined by the outer edge line of the virtual parking space and the inner edge line parallel to this edge line and offset towards the roadside from the standard parking width, thereby ensuring that the rectangular area strictly satisfies the parameter constraints in both the lateral and longitudinal directions.

[0092] Furthermore, the initial rectangular envelope can be mapped to the global map coordinate system through coordinate transformation. Combined with the station anchor point information in the high-precision map, the spatial alignment of the virtual parking position in the urban navigation coordinate system is completed. Subsequently, based on the angle between the vehicle's real-time heading angle and the tangent direction of the baseline, the rectangular envelope is rigidly rotated and corrected to ensure that the virtual parking position always maintains a geometrically consistent orientation with the physical boundary of the road. Thus, without relying on ground markings or external references, a parking target area that is synchronized with the actual road direction, has constant size, and stable attitude is constructed.

[0093] Based on steps S141 to S143 above, the orthogonal projection point of the rear axle center of the target vehicle relative to the physical boundary baseline is obtained. Based on the orthogonal projection point, standard parking length, and standard parking width, an initial rectangular envelope is generated. Then, based on the initial rectangular envelope, a virtual parking space is constructed. It can use the vehicle's own posture as a geometric reference and, according to the preset standardized dimensions, uniquely determine a rectangular parking area within the physical boundary of the road that maintains a fixed lateral offset from the road edge, has a controllable longitudinal length, and is consistent with the road direction, thereby providing deterministic target geometric constraints for trajectory planning.

[0094] Further, in step S142, generating the initial rectangular envelope based on the orthogonal projection points, standard docking length, and standard docking width includes:

[0095] Step S1421: Based on the orthogonal projection points and the standard docking length, the physical boundary baseline is longitudinally cut to obtain the first endpoint and the second endpoint, wherein the distance between the first endpoint and the second endpoint is equal to the standard docking length;

[0096] The first endpoint mentioned above is the geometric point corresponding to the position of half the standard parking length of the orthogonal projection point of the rear axle center of the target vehicle on the physical boundary baseline along the tangent direction of the baseline.

[0097] The second endpoint is the geometric point corresponding to the orthogonal projection of the rear axle center of the target vehicle onto the physical boundary baseline, extending backward along the tangent direction of the baseline to half the standard parking length.

[0098] Based on the orthogonal projection points and standard parking length, the physical boundary baseline is longitudinally intercepted to obtain the first endpoint and the second endpoint. The orthogonal projection point of the rear axle center of the target vehicle on the physical boundary baseline can be used as the geometric reference to accurately delineate the longitudinal parking interval that matches the vehicle size. This ensures that the longitudinal range of the virtual parking space is always symmetrically distributed with the vehicle as the reference center, avoiding longitudinal offset of the parking space caused by projection point offset or baseline orientation error, thereby improving the safety of the virtual parking space.

[0099] Step S1422: Generate an initial rectangular envelope based on the first endpoint, the second endpoint, and the standard docking width.

[0100] like Figure 3 As shown, the orthogonal projection point is the projection point of the rear axle center of the target vehicle relative to the physical boundary baseline. Both the first endpoint and the second endpoint are located on the outer edge line, and the distance between the first endpoint and the second endpoint is equal to the standard parking length.

[0101] Furthermore, after obtaining the first and second endpoints, an initial rectangular envelope can be generated based on their own coordinate positions and standard docking width.

[0102] Based on steps S1421 to S1422 above, the physical boundary baseline is longitudinally intercepted based on the orthogonal projection points and the standard parking length to obtain the first endpoint and the second endpoint. Then, based on the first endpoint, the second endpoint, and the standard parking width, an initial rectangular envelope is generated. Without relying on external reference objects, the longitudinal start and end boundaries of the virtual parking space can be accurately determined based on the geometric relationship between the vehicle's own position and the physical boundary baseline. Combined with the preset standard parking width, a rectangular initial parking area with a defined size and direction is constructed.

[0103] Further, in step S1422, generating the initial rectangular envelope based on the first endpoint, the second endpoint, and the standard docking width includes:

[0104] Step S21: Based on the first endpoint, the second endpoint, and the standard docking width, determine the third endpoint and the fourth endpoint, wherein the distance between the first endpoint and the third endpoint is equal to the standard docking width, and the distance between the second endpoint and the fourth endpoint is equal to the standard docking width;

[0105] Step S22: Generate an initial rectangular envelope based on the first endpoint, the second endpoint, the third endpoint, and the fourth endpoint.

[0106] For example, the first and second endpoints can be used as references to extend the standard parking width along the normal vector direction of the physical boundary baseline to the inside of the road, thereby obtaining the third and fourth endpoints. The third endpoint is the point corresponding to the first endpoint after it has been translated by the standard parking width along the normal vector direction, and the fourth endpoint is the point corresponding to the second endpoint after it has been translated by the standard parking width along the same normal vector direction.

[0107] Furthermore, the closed quadrilateral formed by connecting the first, second, third, and fourth endpoints in sequence is the initial rectangular envelope. The two long sides of this rectangular envelope are parallel to the physical boundary baseline and the distance between them is equal to the standard parking width. The two short sides are perpendicular to the physical boundary baseline and connect to the corresponding endpoints. Thus, without relying on any external reference objects, a standardized virtual parking space geometric profile can be accurately constructed with the rear axle center of the vehicle as the longitudinal symmetry reference and the lateral limitation of the safe offshore distance.

[0108] like Figure 3 As shown, the distance between the first and third endpoints is equal to the standard docking width, and the distance between the second and fourth endpoints is equal to the standard docking width.

[0109] Based on steps S21 to S22 above, the third and fourth endpoints are determined based on the first endpoint, the second endpoint, and the standard docking width. Then, based on the first endpoint, the second endpoint, the third endpoint, and the fourth endpoint, an initial rectangular envelope is generated. Using the physical boundary baseline as a geometric reference, a rectangular docking area with a fixed distance from the road edge and standardized size is accurately constructed through the relationship between lateral offset and vertical projection. This provides an initial target pose space with a clear topological structure for subsequent dynamic obstacle avoidance correction.

[0110] Further, in step S143, constructing the virtual docking station based on the initial rectangular envelope includes:

[0111] Step S1431: Perform obstacle detection on the initial rectangular envelope to obtain the occupancy ratio of obstacles in the initial rectangular envelope;

[0112] The aforementioned obstacle occupancy ratio in the initial rectangular envelope refers to the ratio of the number of grid cells within the rectangular area determined to be occupied by obstacles to the total number of grid cells within the initial rectangular envelope after mapping the initial rectangular envelope area of ​​the virtual parking space to the local occupancy grid map in the vehicle coordinate system.

[0113] Specifically, the above occupancy ratio reflects the spatial distribution density of physical obstacles within the geometric area of ​​the virtual parking space. It is used to quantitatively assess whether the area has safe parking conditions. The higher the ratio, the denser the spatial coverage of obstacles in the area, and the lower the parking safety.

[0114] For example, the size of each grid cell in the aforementioned local occupancy grid map can be 10 cm × 10 cm, and its occupancy status can be determined by the vehicle perception system based on the probability values ​​output by the LiDAR point cloud, the semantic segmentation results of the surround-view camera, and the fusion of multiple sensors. When the occupancy probability of a certain grid cell is higher than a preset threshold, it is marked as occupancy.

[0115] Step S1432: Construct a virtual docking station based on the occupancy ratio and the initial rectangular envelope.

[0116] For example, when performing obstacle detection on the initial rectangular envelope, the local occupancy grid map output by the perception module can first be spatially aligned with the geometric boundary of the virtual parking space. This local occupancy grid map covers a 5m x 5m area around the vehicle with a resolution of 10cm x 10cm, and each grid cell stores its probability value of being occupied by an obstacle. Then, the coordinates of the four endpoints of the virtual parking space are mapped from the vehicle coordinate system to the grid coordinate system of the local occupancy grid map, and the set of all grid cells covered by the rectangular area is determined through interpolation or boundary clipping. Next, the average occupancy probability of all grid cells in this area is calculated, or the proportion of grids with an occupancy probability exceeding a preset threshold (e.g., 0.7) is counted out of the total number of grid cells. If the occupancy ratio is lower than a set safety threshold (e.g., 15%), it can be determined that the area is free of obstacle interference and can be directly used as a valid parking space. If the occupancy ratio exceeds the threshold, it can be determined that the current virtual parking space has a potential collision risk.

[0117] Based on steps S1431 to S1432 above, obstacle detection is performed on the initial rectangular envelope to obtain the occupancy ratio of obstacles in the initial rectangular envelope. Then, based on the occupancy ratio and the initial rectangular envelope, a virtual parking space is constructed, which can dynamically avoid the encroachment of local obstacles on the parking area and ensure that the generated virtual parking space has real-time reachability and security under geometric constraints.

[0118] Further, in step S1432, constructing the virtual docking station based on the occupancy ratio and the initial rectangular envelope includes:

[0119] Step S31: In response to the occupancy ratio being greater than or equal to a preset ratio threshold, the initial rectangular envelope is iteratively displacement calculated based on the tangent direction corresponding to the physical boundary baseline and a preset step size to obtain the target rectangular envelope.

[0120] Step S32: In response to the fact that the proportion of the obstacle in the target rectangular envelope is less than a preset proportion threshold, the target rectangular envelope is determined to be a virtual docking position.

[0121] The aforementioned iterative displacement calculation refers to translating the initial rectangular envelope forward and backward sequentially along the tangent direction of the physical boundary baseline, with a preset step size as the unit. After each translation, the occupancy ratio of the obstacle in the new envelope area is recalculated until the first valid position with an occupancy ratio lower than the preset ratio threshold is found. The rectangular envelope corresponding to this position is the target rectangular envelope.

[0122] For example, an initial rectangular envelope can be mapped to a local occupancy grid, and the proportion of the grid occupied by dynamic and static obstacles within it can be calculated. If this proportion exceeds a preset threshold, the initial rectangular envelope is slid along the tangent direction of the physical boundary baseline with a preset step size, and the occupancy rate of each candidate position is detected one displacement at a time until a free area with an occupancy rate lower than the threshold is detected, and this area is taken as the final virtual parking space. If no free area that meets the safety requirements is found within a preset search range, a parking space blockage warning can be triggered to inform the driver that the current area cannot be parked safely.

[0123] For example, when the current parking area is in a "blocked state", a "parking space unavailable" event can be reported to the cloud dispatch system, carrying the current GPS coordinates, obstacle distribution heat map and timestamp, and prompting "The current station is occupied, please go to the nearest available station" on the in-vehicle human-machine interface. At the same time, the "nearby station recommendation" module is automatically activated, recommending multiple nearest available alternative parking points based on map topology and real-time traffic data, and guiding the target vehicle to the optimal option.

[0124] For example, the preset step size can be set between 0.2 meters and 0.5 meters, without limitation. In practical applications, the step size can be dynamically adjusted according to the vehicle's minimum turning radius and the smoothness constraints of the planned trajectory. For example, a step size of 0.3 meters can be used in low-speed (<5km / h) parking scenarios, and it can be reduced to 0.1 meters with the support of high-precision positioning to improve the final pose accuracy.

[0125] Figure 4 This is a schematic diagram of another optional virtual parking space generation method according to an embodiment of this application, such as... Figure 4 As shown, the dashed box on the left is the initial rectangular envelope, the circular symbols are obstacles in the initial rectangular envelope, and the rectangular box on the right is the target rectangular envelope obtained after iterative displacement calculation of the initial rectangular envelope with a preset step size.

[0126] Based on steps S31 to S32 above, when the occupancy ratio is greater than or equal to a preset ratio threshold, the initial rectangular envelope is iteratively displacement calculated based on the tangent direction corresponding to the physical boundary baseline and a preset step size to obtain the target rectangular envelope. Then, in response to the obstacle's occupancy ratio in the target rectangular envelope being less than the preset ratio threshold, the target rectangular envelope is determined as a virtual parking space. Without relying on external reference objects, it can adaptively avoid static and dynamic obstacles through local environment dynamic perception and geometric sliding search mechanisms, ensuring that the generated virtual parking space is passable and safe to park in the physical space. At the same time, it maintains a fixed lateral distance constraint from the physical roadside to avoid parking space failure or conflict caused by local obstacle interference, thereby improving the robustness and real-time response capability of the system in complex urban roadside scenarios.

[0127] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0128] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0129] According to an embodiment of this application, an apparatus embodiment for a virtual docking station generation method is provided. It should be noted that the apparatus can be used to execute the above-described virtual docking station generation method.

[0130] Figure 5 This is a structural block diagram of an optional virtual parking space generation device according to an embodiment of this application, such as... Figure 5 As shown, the device includes:

[0131] The acquisition module 501 is used to acquire visual perception data of the target vehicle and standardized configuration parameters of the target parking area in response to the target vehicle driving to the target parking area. The visual perception data is obtained by the vehicle image acquisition component to collect data from the road edge of the target parking area. The standardized configuration parameters include standard parking length, standard parking width and safe offshore distance.

[0132] Analysis module 502 is used to analyze and process visual perception data to obtain physical boundary baselines;

[0133] The generation module 503 is used to generate the outer edge line corresponding to the virtual berth based on the physical boundary baseline and the safe offshore distance;

[0134] Module 504 constructs a virtual docking station based on the standard docking length, standard docking width, physical boundary baseline, and outer edge line.

[0135] Furthermore, the analysis module 502 is also used to: perform semantic segmentation processing on the visual perception data to obtain the edge mask corresponding to the target parking area, wherein the edge mask is used to represent multiple discrete pixel points corresponding to the road edge; and perform fitting processing on the edge mask corresponding to the target parking area to obtain the physical boundary baseline.

[0136] Furthermore, the generation module 503 is also used to: obtain the normal vector direction corresponding to the physical boundary baseline, wherein the normal vector direction is used to represent a unit vector perpendicular to the physical boundary baseline and pointing to the inside of the road in the target parking area; and translate the physical boundary baseline based on the normal vector direction and the safe offshore distance to obtain the outer edge line.

[0137] Furthermore, the construction module 504 is also used to: obtain the orthogonal projection point of the rear axle center of the target vehicle relative to the physical boundary baseline, wherein the orthogonal projection point is used to determine the longitudinal reference center corresponding to the virtual parking space; generate an initial rectangular envelope based on the orthogonal projection point, the standard parking length and the standard parking width, wherein the initial rectangular envelope is used to determine the parking area corresponding to the virtual parking space; and construct the virtual parking space based on the initial rectangular envelope.

[0138] Furthermore, the construction module 504 is also used to: longitudinally cut the physical boundary baseline based on the orthogonal projection point and the standard docking length to obtain the first endpoint and the second endpoint, wherein the distance between the first endpoint and the second endpoint is equal to the standard docking length; and generate an initial rectangular envelope based on the first endpoint, the second endpoint and the standard docking width.

[0139] Furthermore, the construction module 504 is also used to: determine the third and fourth endpoints based on the first endpoint, the second endpoint, and the standard docking width, wherein the distance between the first and third endpoints is equal to the standard docking width, and the distance between the second and fourth endpoints is equal to the standard docking width; and generate an initial rectangular envelope based on the first, second, third, and fourth endpoints.

[0140] Furthermore, the construction module 504 is also used to: perform obstacle detection on the initial rectangular envelope to obtain the occupancy ratio of the obstacle in the initial rectangular envelope; and construct a virtual docking station based on the occupancy ratio and the initial rectangular envelope.

[0141] Furthermore, the construction module 504 is also used to: in response to the occupancy ratio being greater than or equal to a preset ratio threshold, perform iterative displacement calculation on the initial rectangular envelope based on the tangent direction corresponding to the physical boundary baseline and a preset step size to obtain the target rectangular envelope; in response to the obstacle's occupancy ratio in the target rectangular envelope being less than a preset ratio threshold, determine the target rectangular envelope as a virtual docking position.

[0142] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0143] Embodiments of this application also provide a vehicle, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods described in various embodiments of this application when it runs.

[0144] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0145] Step S11: In response to the target vehicle driving to the target parking area, obtain the visual perception data corresponding to the target vehicle and the standardized configuration parameters corresponding to the target parking area. The visual perception data is obtained by the vehicle image acquisition component to collect data from the road edge corresponding to the target parking area. The standardized configuration parameters include standard parking length, standard parking width and safe offshore distance.

[0146] Step S12: Analyze and process the visual perception data to obtain the physical boundary baseline;

[0147] Step S13: Based on the physical boundary baseline and the safe offshore distance, generate the outer edge line corresponding to the virtual docking position;

[0148] Step S14: Construct a virtual parking space based on the standard parking length, standard parking width, physical boundary baseline, and outer edge line.

[0149] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0150] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0151] Step S11: In response to the target vehicle driving to the target parking area, obtain the visual perception data corresponding to the target vehicle and the standardized configuration parameters corresponding to the target parking area. The visual perception data is obtained by the vehicle image acquisition component to collect data from the road edge corresponding to the target parking area. The standardized configuration parameters include standard parking length, standard parking width and safe offshore distance.

[0152] Step S12: Analyze and process the visual perception data to obtain the physical boundary baseline;

[0153] Step S13: Based on the physical boundary baseline and the safe offshore distance, generate the outer edge line corresponding to the virtual docking position;

[0154] Step S14: Construct a virtual parking space based on the standard parking length, standard parking width, physical boundary baseline, and outer edge line.

[0155] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0156] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0157] Optionally, in this embodiment, the above-mentioned computer program product can be configured as a computer program that performs the following steps:

[0158] Step S11: In response to the target vehicle driving to the target parking area, obtain the visual perception data corresponding to the target vehicle and the standardized configuration parameters corresponding to the target parking area. The visual perception data is obtained by the vehicle image acquisition component to collect data from the road edge corresponding to the target parking area. The standardized configuration parameters include standard parking length, standard parking width and safe offshore distance.

[0159] Step S12: Analyze and process the visual perception data to obtain the physical boundary baseline;

[0160] Step S13: Based on the physical boundary baseline and the safe offshore distance, generate the outer edge line corresponding to the virtual docking position;

[0161] Step S14: Construct a virtual parking space based on the standard parking length, standard parking width, physical boundary baseline, and outer edge line.

[0162] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of this application.

[0163] Optionally, in this embodiment, the above-mentioned computer program product can be configured as a computer program that performs the following steps:

[0164] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of this application.

[0165] Optionally, in this embodiment, the above-mentioned computer program product can be configured as a computer program that performs the following steps:

[0166] Step S11: In response to the target vehicle driving to the target parking area, obtain the visual perception data corresponding to the target vehicle and the standardized configuration parameters corresponding to the target parking area. The visual perception data is obtained by the vehicle image acquisition component to collect data from the road edge corresponding to the target parking area. The standardized configuration parameters include standard parking length, standard parking width and safe offshore distance.

[0167] Step S12: Analyze and process the visual perception data to obtain the physical boundary baseline;

[0168] Step S13: Based on the physical boundary baseline and the safe offshore distance, generate the outer edge line corresponding to the virtual docking position;

[0169] Step S14: Construct a virtual parking space based on the standard parking length, standard parking width, physical boundary baseline, and outer edge line.

[0170] In the above embodiments of this application, 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.

[0171] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0172] 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0173] Furthermore, the functional units in the various embodiments of this application 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.

[0174] 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 this application, 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 this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0175] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for generating virtual parking spaces, characterized in that, include: In response to a target vehicle arriving at a target parking area, visual perception data corresponding to the target vehicle and standardized configuration parameters corresponding to the target parking area are acquired. The visual perception data is obtained by collecting data from the road edge corresponding to the target parking area through an on-board image acquisition component. The standardized configuration parameters include standard parking length, standard parking width, and safe offshore distance. The visual perception data is analyzed and processed to obtain the physical boundary baseline; Based on the physical boundary baseline and the safe offshore distance, the outer edge line corresponding to the virtual docking position is generated; The virtual parking space is constructed based on the standard parking length, the standard parking width, the physical boundary baseline, and the outer edge line.

2. The method according to claim 1, characterized in that, The process of analyzing and processing the visual perception data to obtain the physical boundary baseline includes: The visual perception data is semantically segmented to obtain the edge mask corresponding to the target parking area, wherein the edge mask is used to represent multiple discrete pixels corresponding to the road edge; The edge mask corresponding to the target docking area is fitted to obtain the physical boundary baseline.

3. The method according to claim 1, characterized in that, The process of generating the outer edge line corresponding to the virtual docking station based on the physical boundary baseline and the safe offshore distance includes: Obtain the normal vector direction corresponding to the physical boundary baseline, wherein the normal vector direction is used to represent a unit vector perpendicular to the physical boundary baseline and pointing to the inside of the road in the target parking area; The physical boundary baseline is translated based on the normal vector direction and the safe offshore distance to obtain the outer edge line.

4. The method according to claim 1, characterized in that, The process of constructing the virtual parking space based on the standard parking length, the standard parking width, the physical boundary baseline, and the outer edge line includes: Obtain the orthogonal projection point of the rear axle center of the target vehicle relative to the physical boundary baseline, wherein the orthogonal projection point is used to determine the longitudinal reference center corresponding to the virtual parking space; Based on the orthogonal projection points, the standard docking length, and the standard docking width, an initial rectangular envelope is generated, wherein the initial rectangular envelope is used to determine the docking area corresponding to the virtual docking position; The virtual docking station is constructed based on the initial rectangular envelope.

5. The method according to claim 4, characterized in that, The process of generating the initial rectangular envelope based on the orthogonal projection points, the standard docking length, and the standard docking width includes: Based on the orthogonal projection points and the standard docking length, the physical boundary baseline is longitudinally intercepted to obtain a first endpoint and a second endpoint, wherein the distance between the first endpoint and the second endpoint is equal to the standard docking length; The initial rectangular envelope is generated based on the first endpoint, the second endpoint, and the standard docking width.

6. The method according to claim 5, characterized in that, The process of generating the initial rectangular envelope based on the first endpoint, the second endpoint, and the standard docking width includes: Based on the first endpoint, the second endpoint, and the standard docking width, a third endpoint and a fourth endpoint are determined, wherein the distance between the first endpoint and the third endpoint is equal to the standard docking width, and the distance between the second endpoint and the fourth endpoint is equal to the standard docking width; The initial rectangular envelope is generated based on the first endpoint, the second endpoint, the third endpoint, and the fourth endpoint.

7. The method according to claim 4, characterized in that, The process of constructing the virtual docking station based on the initial rectangular envelope includes: Obstacle detection is performed on the initial rectangular envelope to obtain the proportion of obstacles occupying the initial rectangular envelope; The virtual docking space is constructed based on the occupancy ratio and the initial rectangular envelope.

8. The method according to claim 7, characterized in that, The process of constructing the virtual docking station based on the occupancy ratio and the initial rectangular envelope includes: In response to the occupancy ratio being greater than or equal to a preset ratio threshold, the initial rectangular envelope is iteratively displaced based on the tangent direction corresponding to the physical boundary baseline and a preset step size to obtain the target rectangular envelope; In response to the obstacle occupying a smaller proportion of the target rectangular envelope than the preset proportion threshold, the target rectangular envelope is determined to be the virtual docking spot.

9. A vehicle, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the method according to any one of claims 1 to 8.

Images