A parking space parking state analysis method, a vehicle-mounted device, a storage medium and a vehicle

Abstract

The application discloses a parking space parking state analysis method, a vehicle-mounted device, a storage medium and a vehicle. The parking space parking state analysis method comprises the following steps: generating a judgment area on a parking path of each target parking space according to the attributes of the target parking space and surrounding obstacle information, the frame of the judgment area intersects with the frame of the target parking space, and the judgment area covers the minimum parking area on the inside of the target parking space, the entrance of the target parking space, the minimum parking area on the lateral side of the target parking space or the minimum parking area at the road space in front of the target parking space; in response to the fact that there is no obstacle in the judgment area, it is determined that the target parking space is available for parking; and filtering analysis is performed on the basis of each frame of judgment result of each target parking space in a preset time window to generate a final parking state of each target parking space.

Description

Technical Field

[0001] This application relates to the field of autonomous driving, and in particular to a parking space availability analysis method, on-board equipment, storage medium, and vehicle. Background Technology

[0002] In existing technologies, the status analysis of parking spaces mainly adopts methods based on direct classification of models, methods based on pre-planning, or methods based on ultrasonic detection.

[0003] Among them, the model-based direct classification method may be obscured by large objects such as vehicles, walls, and pillars from certain perspectives, resulting in inaccurate model output and poor robustness; the pre-planning method is too time-consuming, and if each candidate parking space is judged, the calculation time is usually on the order of seconds, which affects the user experience; the ultrasonic detection method generally has a maximum detection distance of only about four meters, while the length of a parking space is usually more than five meters, which cannot cover the entire scene. Summary of the Invention

[0004] This application mainly provides a parking space availability status analysis method, vehicle-mounted equipment, storage medium, and vehicle to solve the problem of low accuracy in parking space status detection under complex parking scenarios.

[0005] To address the aforementioned technical problems, this application provides a method for analyzing the parking availability of a parking space, comprising: generating a determination region on the parking path of each target parking space based on the attributes of each target parking space and surrounding obstacle information; the border of the determination region intersects with the parking space border of the target parking space; the determination region covers the parking space interior, the parking space entrance, the minimum parking area on the side of each target parking space, and the minimum parking area in the road space in front of each target parking space; in response to the absence of obstacles in the determination region, determining that the target parking space is available for parking; and performing filtering analysis based on the determination results of each frame of each target parking space within a preset time window to generate the final parking availability state of each target parking space.

[0006] In some embodiments, the determination area includes an entrance determination area, a lateral determination area, or a road space determination area. The entrance determination area is used to determine whether there are obstacles inside the target parking space and at the entrance of the parking space. The lateral determination area is used to determine whether there are obstacles in the minimum lateral parking area of ​​the target parking space. The road space determination area is used to determine whether there are obstacles in the minimum lateral parking area of ​​the road space in front of the target parking space. The lateral direction is perpendicular to the entrance direction of the target parking space.

[0007] In some embodiments, the method further includes: determining that the target parking space is unavailable if an obstacle exists in any of the entrance determination area, the lateral determination area, and the road space determination area.

[0008] In some embodiments, generating at least one determination area on the parking path of the target parking space based on the attributes of the target parking space and surrounding obstacle information includes: generating an entrance determination area on the parking path of the target parking space based on the attributes of the target parking space and surrounding obstacle information; generating the lateral determination area in response to the absence of obstacles in the entrance determination area; generating the road space determination area in response to the absence of obstacles in the lateral determination area; determining that the target parking space is available for parking in response to the absence of obstacles in each of the determination areas includes: determining that the target parking space is available for parking in response to the road space determination area.

[0009] In some embodiments, the target parking space is a square parking space, the entrance determination area is a closed quadrilateral formed by the border of the entrance side of the target parking space extending outward in parallel and the border of the non-entrance side contracting in parallel inward; the lateral determination area is the area between obstacles perpendicular to the entrance direction of the target parking space; the road space determination area is a closed quadrilateral whose wide side coincides with the border of the entrance side of the target parking space and extends outward along the entrance direction of the target parking space based on the length of the vehicle.

[0010] In some embodiments, the target parking space is a side parking space, the entrance determination area is a closed quadrilateral formed by the border of the entrance side of the target parking space extending outward in parallel and the border of the non-entrance side contracting in parallel inward; the lateral determination area is the area between obstacles perpendicular to the entrance direction of the target parking space; the road space determination area is a closed rectangle whose long side coincides with the border of the entrance side of the target parking space and extends outward along the entrance direction of the target parking space based on the length of the vehicle.

[0011] In some embodiments, the step of performing filtering analysis based on the judgment results of each frame of each target parking space within a preset time window to generate the final parking status of each target parking space includes: collecting the judgment results of each frame of each target parking space within the time window; weighting the judgment results of each frame based on a preset weighting rule, and calculating the weighted average result of the judgment results of each frame within the time window as the final parking status of the target parking space.

[0012] To solve the above-mentioned technical problems, another technical solution adopted in this application is to provide a storage medium storing program data, wherein the program data, when executed by a processor, implements the steps of the parking space availability analysis method described above.

[0013] This application also provides an in-vehicle device, including a processor and a memory interconnected, the memory storing a computer program, and the processor executing the computer program to implement the steps of the parking space availability analysis method described above.

[0014] This application also provides a vehicle that includes the vehicle-mounted equipment as described above.

[0015] The beneficial effects of this application are as follows: Unlike existing technologies, this application discloses a parking space availability analysis method, in-vehicle equipment, storage medium, and vehicle. Based on the attributes of each target parking space and surrounding obstacle information, a determination region is generated along the parking path of each target parking space. The border of the determination region intersects with the border of the target parking space. The determination region covers at least the area within the target parking space, the parking space entrance, the minimum available parking area on the side of each target parking space, or the minimum available parking area in the road space in front of each target parking space. Different determination region generation methods are provided for different parking space types, enabling more comprehensive scenario coverage. Furthermore, a progressive determination from easy to difficult is performed from the parking space path, the side spaces, to the entrance road space, further improving the accuracy of determining available parking space. If no obstacles are found in the determination region, the target parking space is determined to be available for parking. Based on the frame determination results of each target parking space within a preset time window, filtering analysis is performed to generate the final available parking state of each target parking space. Multi-frame rate filtering improves the robustness of the final analysis results. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein:

[0017] Figure 1 This is a flowchart illustrating an embodiment of the parking space availability analysis method provided in this application;

[0018] Figure 2 This is a schematic diagram showing the location of an embodiment of the parking space entrance determination area in this application;

[0019] Figure 3 This is a schematic diagram showing the location of an embodiment of the lateral determination area of ​​the parking space in this application;

[0020] Figure 4 This is a schematic diagram showing the location of an embodiment of the parking space road space determination area in this application;

[0021] Figure 5 This is a schematic diagram showing the location of an embodiment of the side parking space entrance determination area in this application;

[0022] Figure 6 This is a schematic diagram showing the location of an embodiment of the lateral parking space determination area of ​​this application;

[0023] Figure 7 This is a schematic diagram of the location of an embodiment of the side parking space road space determination area of ​​this application;

[0024] Figure 8 This is a schematic diagram of the structure of an embodiment of the storage medium provided in this application;

[0025] Figure 9 This is a schematic diagram of the structure of an embodiment of the vehicle-mounted device provided in this application;

[0026] Figure 10 This is a structural schematic diagram of an embodiment of the vehicle provided in this application. Detailed Implementation

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0028] The terms "first," "second," and "third" used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. 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 device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0030] See Figure 1, Figure 1 This is a flowchart illustrating an embodiment of the parking space availability analysis method provided in this application. The parking space availability analysis method includes the following steps:

[0031] 10: Generate a judgment area on the parking path of each target parking space based on the attributes of each target parking space and the surrounding obstacle information. The border of the judgment area intersects with the border of the target parking space. The judgment area covers the parking space inside each target parking space, the parking space entrance, the minimum parking area on the side of each target parking space, and the minimum parking area in the road space in front of each target parking space.

[0032] To avoid errors in detection accuracy, the boundary of the parking space needs to be modified to form a judgment area, leaving redundant space, to determine whether there are obstacles in the parking path of the vehicle to each target parking space. If there are obstacles in this area, the parking space is directly determined to be unsuitable for parking.

[0033] The border of the judgment area intersects with the border of the target parking space, including but not limited to the border of the judgment area coinciding with the border of the target parking space, or the coverage space of the judgment area and the target parking space partially overlapping.

[0034] The target parking space's attributes include basic information about several parking spaces surrounding the vehicle. This basic information includes the parking space type and the coordinates of the four corner points of the parking space. The parking space types include square parking spaces and side parking spaces.

[0035] Square parking spaces are those where vehicles are parked from the shorter side, while side parking spaces are those where vehicles are parked from the longer side.

[0036] The lateral direction of a parking space refers to the left and right sides perpendicular to the entrance of the parking space. For a square parking space, the lateral direction is the direction of the two longer sides; for a parallel parking space, the lateral direction is the direction of the two shorter sides.

[0037] Obstacle information includes the detection results of all obstacle detection sensors on the vehicle, such as ultrasonic, lidar, and vision sensors. Basic obstacle information includes obstacle category and obstacle coordinates.

[0038] Furthermore, the determination area includes an entrance determination area, a lateral determination area, or a road space determination area. The entrance determination area is used to determine whether there are obstacles inside the target parking space and at the entrance of the parking space. The lateral determination area is used to determine whether there are obstacles in the minimum lateral parking area of ​​the target parking space. The road space determination area is used to determine whether there are obstacles in the minimum lateral parking area of ​​the road space in front of the target parking space. The lateral direction is perpendicular to the entrance direction of the target parking space.

[0039] The entrance detection zone is a redundant area created by shrinking the parking space along the parking line, making it narrower than the original parking space. The length of the entrance detection zone is adjusted based on the vehicle information and parking space attributes. The entrance detection zone covers both the inside of the target parking space and its entrance. It is used to determine whether there are obstacles inside the parking space or at the entrance. If obstacles exist within this area...

[0040] The lateral judgment area is divided into left and right or front and back zones based on the center line of the parking space. This is used to detect the minimum lateral parking space. If there are obstacles on both sides of the parking space, the sum of the minimum distances from the obstacles on both sides to the center line is calculated, i.e., the size of the lateral space, to determine if it is less than the parking threshold. If the space is too narrow, the parking space is determined to be unsuitable for parking.

[0041] The road space determination area is a specific area covering the road space at the entrance of a parking space when there are obstacles on both sides, making it difficult to use the adjacent space when parking. It is used to detect whether there is enough road space at the entrance. If there are obstacles in this area, or the covered space is less than a threshold, the parking space is determined to be unsuitable for parking.

[0042] Optionally, if an obstacle exists in any of the entrance determination area, the lateral determination area, and the road space determination area, the target parking space is determined to be unavailable for parking.

[0043] Optionally, when making a determination, obstacles can be determined simultaneously in the entrance determination area, the lateral determination area, and the road space determination area, or obstacles can be determined one by one in the entrance determination area, the lateral determination area, and the road space determination area according to a preset determination logic.

[0044] When judging each item, the detection is performed in a preset order, such as "entrance, side, road space" or "side, entrance, road space". If the previous step triggers an unparkable result, the subsequent steps will not be executed.

[0045] The advantage of judging one by one is that it reduces the amount of computation and improves detection efficiency by filtering step by step. For example, when an obstacle is detected in the entrance area, there is no need to perform subsequent time-consuming steps.

[0046] In scenarios with ample computing resources or requiring higher accuracy, obstacle detection can be performed simultaneously in three areas, with a comprehensive judgment based on the combined results. Obstacle information from the entrance, lateral, and road spaces can be acquired and used for judgment at the same time.

[0047] For example, if there are obstacles in the entrance area, it will be judged as "unparkable" regardless of whether other areas are normal; if there are no obstacles in the entrance area but the lateral space is insufficient, it will be judged as "unparkable"; only when all three areas are free of obstacles or the space meets the requirements will it be judged as "parkable".

[0048] At the same time, the judgment is applicable to scenarios that require comprehensive verification or have low real-time requirements, avoiding result deviations caused by misjudgments in a single step.

[0049] Furthermore, step 10 also includes the following steps:

[0050] 11: Generate the entrance determination area on the parking path of the target parking space based on the attributes of the target parking space and the surrounding obstacle information.

[0051] If there are obstacles, such as vehicles or cones, in the entrance judgment area, the target parking space is determined to be unsuitable for parking, and the subsequent judgment is terminated; if there are no obstacles, the generation and judgment of the lateral judgment area will proceed.

[0052] 12: If there are no obstacles in the entrance detection area, a lateral detection area is generated.

[0053] When there are no obstacles in the entrance determination area, it is necessary to further detect the minimum parking space on the side of the parking space, that is, whether the space between the obstacles on both sides is sufficient. If the size of the lateral space is less than a preset threshold, the space is too narrow, and the target parking space is determined to be unsuitable for parking, and the subsequent determination is terminated; if the space is sufficient, there are no obstacles, or the distance meets the threshold, the generation and determination of the road space determination area can proceed.

[0054] 13: If there are no obstacles in the lateral detection area, a road space detection area is generated.

[0055] When there are no obstacles in the lateral detection area but obstacles on both sides of the parking space, making it difficult to use the adjacent space when parking, it is necessary to check whether the road space at the entrance is sufficient. If there are obstacles in the road space detection area or the space is less than a preset threshold, and the road is narrow, then the target parking space is determined to be unsuitable for parking; if the road space is sufficient, there are no obstacles, or the distance meets the threshold, then the target parking space is ultimately determined to be suitable for parking.

[0056] If there are no obstacles in any of the detection areas, the target parking space is determined to be available for parking, including:

[0057] 14: In response to the road space determination area, the target parking space is determined to be available for parking.

[0058] The target parking space is determined to be available only when there are no obstacles in the entrance determination area, the lateral determination area, and the road space determination area, or when the space meets the threshold.

[0059] By using a step-by-step judgment logic based on entrance, side, and road space, combined with the area generation rules for different parking space types, a stable parking availability result is finally output.

[0060] Optionally, the order of determining the entrance determination area, the lateral determination area, and the road space determination area can be adjusted according to the actual situation.

[0061] For example, in scenarios where parking lot entrances are narrow, such as in older residential areas or alleyway-style parking lots, and where there is insufficient road space for vehicles to park, the road space determination area should be prioritized. If there is insufficient road space, parking should be directly determined as not possible, skipping the entrance and lateral determination steps. This reduces unnecessary calculations and quickly eliminates parking spaces with insufficient road space.

[0062] In parking lots where parking spaces are primarily horizontal and often obstructed by other vehicles or obstacles on either side, the system prioritizes detecting the lateral judgment area, specifically whether the space between the obstacles in front and behind is sufficient. If the space is too narrow, parking is deemed impossible, skipping the entrance and road space judgment steps. This rapid filtering of core limitations for parallel parking improves detection efficiency.

[0063] In parking lots with various parking space types (vertical, horizontal, and diagonal), or where obstacle distribution varies significantly across areas (e.g., some entrances are prone to congestion while others have narrow roads), the system dynamically selects the order of obstacle detection based on real-time obstacle distribution. If the entrance area has a high historical obstacle rate, it is prioritized for detection; conversely, if the road space has a high historical insufficient rate, it is prioritized for detection. This adapts to complex environments and improves the robustness of the detection results.

[0064] Optionally, the determination area may specifically include one or more of the entrance determination area, the lateral determination area, or the road space determination area, which may be adjusted according to the actual situation.

[0065] By default, all three regions need to be detected, but in different scenarios, only some regions can be selected to reduce computing costs or meet specific needs.

[0066] For example, in scenarios with ample parking spaces, such as open-air parking lots, lateral and road space is usually sufficient. In this case, only the entrance determination area needs to be generated and detected. If there are no obstacles in the entrance area, parking is directly determined to be available. This can significantly reduce the amount of computation and is suitable for scenarios with high real-time requirements.

[0067] In newly built standard parking lots and other parking areas that primarily use perpendicular parking spaces and where road space is usually sufficient, but where the sides of the parking spaces are often occupied by other vehicles or pillars, the system can detect the entrance area and then only detect the lateral areas. If there is sufficient lateral space, parking can be directly determined as possible.

[0068] By designing adjustable decision regions and selectively determining entrance, lateral, or road space decision regions, the detection priority is dynamically optimized based on high-frequency limiting factors in obstacle distribution. Necessary detection regions are selected according to scene complexity, reducing computational costs. Ultimately, this flexible configuration makes the parking space availability detection method applicable to more practical application scenarios.

[0069] Specifically, see Figure 2The target parking space is a square parking space. The entrance determination area is a closed quadrilateral formed by the parallel outward extension of the border on the entrance side of the target parking space and the parallel inward contraction of the border on the non-entrance side. The shaded area in the figure represents the space covered by the entrance determination area.

[0070] Square parking spaces include perpendicular parking spaces such as those in shopping mall parking lots (see...) Figure 2 (left side), and angled parking spaces such as those in highway service area parking lots (see left side). Figure 2 (Right side).

[0071] The entrance detection area covers the entrance to the target parking space and the space inside the parking space. It can detect whether the entrance to the target parking space is obstructed and whether there are vehicles or other obstacles on the target parking space, thereby determining whether the target parking space is available for parking.

[0072] The width of the entrance judgment area is adjusted according to the width of the target parking space and the width of the vehicle. The length of the entrance judgment area is the length of the vehicle plus the maximum length that the front of the vehicle can extend beyond the parking space after it is parked in the target parking space.

[0073] See Figure 3 , Figure 3 The diagram shows the lateral detection zone for perpendicular and angled parking spaces. The lateral detection zone is the area between obstacles perpendicular to the entrance direction of the target parking space. The shaded area in the diagram represents the space covered by the lateral detection zone.

[0074] The lateral detection area covers both sides of the target parking space and part of the space inside the parking space. It can detect whether the parking space is narrow and whether it is large enough for a car to park, thereby determining whether the parking space is available for parking.

[0075] The width of the lateral judgment area can be the size of the space between the target parking space and the obstacles on both sides, or the minimum space required for the vehicle to park in the target parking space.

[0076] See Figure 4 , Figure 4 The diagram shows the location of the road space determination area for vertical and angled parking spaces. The road space determination area is a closed quadrilateral whose wide side coincides with the border of the entrance side of the target parking space and extends outward along the entrance direction of the target parking space based on the length of the vehicle. The shaded area in the diagram represents the space covered by the road space determination area.

[0077] The road space determination area covers the road space in the direction of the target parking space entrance. It can detect whether there is enough space in front of the target parking space to complete the parking action of the vehicle, thereby determining whether the parking space is available for parking.

[0078] The width of the road space determination area can be the same as the width of the target parking space, and the length of the road space determination area can be extended with reference to the length of the vehicle.

[0079] See Figure 5 The target parking space is a side parking space. The entrance determination area is a closed quadrilateral formed by the parallel outward extension of the border on the entrance side of the target parking space and the parallel inward contraction of the border on the non-entrance side. The shaded area in the figure represents the space covered by the entrance determination area.

[0080] The length of the side parking space entrance determination area is adjusted according to the length of the target parking space and the length of the vehicle. The width of the entrance determination area is the width of the vehicle plus the maximum width that the side of the vehicle can extend beyond the width of the parking space after the vehicle is parked in the target parking space.

[0081] See Figure 6 The lateral detection zone is the area between obstacles perpendicular to the entrance direction of the target parking space. The shaded area in the diagram represents the space covered by the lateral detection zone.

[0082] The width of the lateral judgment area can be the size of the space between the target parking space and the obstacles in front and behind, or the minimum space required for the vehicle to park in the target parking space.

[0083] See Figure 7 The road space determination area is a closed rectangle whose long side coincides with the border of the entrance to the target parking space and extends outward along the entrance direction of the target parking space based on the length of the vehicle. The shaded area in the figure represents the space covered by the road space determination area.

[0084] The width of the road space determination area can be the same as or wider than the target parking space, and the length of the road space determination area is extended with reference to the vehicle length and parking posture.

[0085] 20: If there are no obstacles in the detection area, the target parking space is determined to be available for parking.

[0086] The entrance judgment area is free of obstacles to ensure that the vehicle can smoothly drive into the parking space; the lateral judgment area is free of obstacles and has sufficient space to avoid collisions with adjacent vehicles or pillars when parking; the road space judgment area is free of obstacles and has sufficient extension length or width to ensure that the vehicle has enough operating space to complete the parking action.

[0087] This rule enables the parking space availability detection method to effectively cover common limiting factors in real-world parking scenarios, such as entrance congestion, narrow lateral access, and insufficient road space, thereby improving the accuracy and practicality of the detection results.

[0088] A parking space is only deemed available if the three main assessment areas—the entrance, the sides, and the road space—are free of obstacles and meet the spatial requirements. This rule, through multi-dimensional verification, ensures the reliability of the parking space's availability and provides crucial technical support for automated parking systems and intelligent parking lot management.

[0089] 30: Based on the frame determination results of each target parking space within the preset time window, perform filtering analysis to generate the final parking status of each target parking space.

[0090] The determination of parking space availability in a single frame may be misjudged due to instantaneous interference. For example, a camera may mistakenly identify a shadow on the ground as an obstacle due to a sudden change in light; a pedestrian or non-motorized vehicle may briefly pass through the parking area, causing a frame to be determined as "unavailable"; and the target detection algorithm may miss or falsely detect obstacles in a frame due to calculation errors.

[0091] Based on the dynamic nature of the parking space scenario, typical filtering strategies such as majority voting, confidence-weighted average, and Kalman filtering are selected.

[0092] After filtering analysis, if most frames or high-confidence frames within the window are judged as "parkable" and there are no consecutive frames as "unparkable", then the target parking space is judged to be stably "parkable". If most frames within the window are judged as "unparkable", or there are persistent obstacles, then the target parking space is judged to be stably "unparkable". If the judgment results within the window fluctuate drastically, such as "parkable" and "unparkable" alternating, then it is marked as "pending", and the time window needs to be extended or the sensor needs to be recalibrated.

[0093] Furthermore, step 30 includes the following steps:

[0094] 31: Judgment results of each frame of each target parking space within the acquisition time window.

[0095] The scene dynamically adjusts the preset time window length, such as 2.5s, 3s, 3.2s, etc., and obtains the judgment result of "landing available" or "not landing available" for each frame, which is stored in the sliding window queue.

[0096] 32: Based on the preset weighting rules, the judgment results of each frame are weighted, and the weighted average result of the judgment results of each frame within the time window is calculated as the final parking status of the target parking space.

[0097] The pre-defined weighting rules should reflect the principle that "recent data is more reliable" or "high-confidence data is more important." Because recent data better reflects the current state, frames closer to the current moment have a greater impact on the final result; if the confidence level of a frame's judgment result is higher, it should be given greater weight; when assigning weights, both time decay and confidence level can be considered simultaneously to ensure that the final output result is more reliable.

[0098] See Figure 8 , Figure 8 This is a schematic diagram of an embodiment of the storage medium provided in this application.

[0099] The storage medium 300 stores program data 310, which, when executed by the processor, implements, as follows: Figure 1The steps of the described parking space availability analysis method.

[0100] The program data 310 is stored in a storage medium 300 and includes several instructions for causing a network device (which may be a router, personal computer, server, or other network device) or processor to execute all or part of the steps of the methods described in the various embodiments of this application.

[0101] Optionally, the storage medium 300 can be any medium capable of storing program data, such as a USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), disk, or optical disc.

[0102] See Figure 9 , Figure 9 This is a schematic diagram of the structure of an embodiment of the vehicle-mounted device provided in this application.

[0103] The vehicle-mounted device 400 is installed in the vehicle and is a computer-type device. It works in conjunction with various sensing modules and control modules in the vehicle to realize visual perception, sensor data processing and image display. The vehicle-mounted device 400 includes a processor 420 and a memory 410 that are connected to each other. The memory 410 stores a computer program. When the processor 420 executes the computer program, it implements the steps of the parking space availability analysis method described above.

[0104] See Figure 10 , Figure 10 A vehicle 500 is provided, including the on-board equipment 400 as described above. During operation, the vehicle 500 can perform a parking space availability analysis process under the control of the on-board equipment 400.

[0105] Unlike existing technologies, this application divides the detection of parking space availability into three sub-regions: an entrance determination region, a lateral determination region, and a road space determination region. The existence of obstacles and spatial conditions in each region are verified separately, and the final result is output through joint verification across multiple regions. By detecting the entrance, lateral, and road space separately, the application solves the problem that a single region cannot cover the combined requirements of entrance accessibility, lateral width, and operational space. Joint verification across multiple regions avoids overall result deviations caused by misjudgments in a single region, improving the comprehensiveness and accuracy of the detection. It is applicable to different types of parking spaces, such as perpendicular and parallel parking spaces, enhancing the method's universality. This application also collects the judgment results of each frame within a preset time window, eliminates instantaneous interference through statistical or dynamic estimation methods, and outputs a stable final state. This eliminates single-frame misjudgments caused by sensor noise, short-term occlusion, or algorithm fluctuations. In dynamic scenarios such as temporary road parking spaces, smoothing processing in the time dimension avoids frequent switching of detection results, ensuring the stability of subsequent decisions. This represents a technological upgrade from single-time perception to continuous reliable output, providing a reliable parking space status detection solution for automatic parking systems or intelligent parking lot management.

[0106] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, the storage medium embodiments and computer device embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0107] This application can be used in a wide range of general-purpose or specialized in-vehicle computing system environments or configurations. Examples include: personal computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, network PCs, minicomputers, and distributed computing environments including any of the above systems or devices.

[0108] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative; multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed.

[0109] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0110] 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.

[0111] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method of analyzing a parking space parkable state, characterized by, The method comprises the following steps: generating a determination area on a parking path of each target parking space according to attributes of the target parking space and surrounding obstacle information, a frame of the determination area intersects with a frame of the target parking space, and the determination area covers a minimum parking area in each target parking space, a minimum parking area at a parking entrance of each target parking space, a minimum parking area on a lateral side of each target parking space, and a minimum parking area at a road space in front of each target parking space; the determination area comprises an entrance determination area, a lateral determination area, or a road space determination area, the entrance determination area is used to determine whether there is an obstacle in the target parking space and the parking entrance of the target parking space, the lateral determination area is used to determine whether there is an obstacle in the minimum parking area on the lateral side of the target parking space, and the road space determination area is used to determine whether there is an obstacle in the minimum parking area at the road space in front of the target parking space, the lateral side is a direction perpendicular to the entrance of the target parking space; in response to the determination area being free of obstacles, it is determined that the target parking space is available for parking; or, in response to any one of the entrance determination area, the lateral determination area, and the road space determination area having an obstacle, it is determined that the target parking space is unavailable for parking; filtering and analyzing each frame determination result of each target parking space within a preset time window to generate a final parking availability of each target parking space.

2. The method of claim 1, wherein The method comprises the following steps: generating a determination area on a parking path of each target parking space according to attributes of the target parking space and surrounding obstacle information, a frame of the determination area intersects with a frame of the target parking space, and the determination area covers a minimum parking area in each target parking space, a minimum parking area at a parking entrance of each target parking space, a minimum parking area on a lateral side of each target parking space, and a minimum parking area at a road space in front of each target parking space; generating an entrance determination area on a parking path of each target parking space according to attributes of the target parking space and surrounding obstacle information; in response to the entrance determination area being free of obstacles, generating a lateral determination area; in response to the lateral determination area being free of obstacles, generating a road space determination area; in response to each determination area being free of obstacles, it is determined that the target parking space is available for parking; 3. The method according to claim 2, wherein in response to the road space determination area, it is determined that the target parking space is available for parking. The target parking space is a square parking space, the entrance determination area is a closed quadrilateral formed by extending the frame of the entrance side of the target parking space outward in parallel and shrinking the frame of the non-entrance side inward in parallel; the lateral determination area is a region between obstacles in a direction perpendicular to the entrance of the target parking space; 4. The method of claim 2, wherein the road space determination area is a closed quadrilateral with a wide side coinciding with the frame of the entrance side of the target parking space and extending outward along the entrance direction of the target parking space based on the length of the vehicle. The target parking space is a side parking space, the entrance determination area is a closed quadrilateral formed by extending the frame of the entrance side of the target parking space outward in parallel and shrinking the frame of the non-entrance side inward in parallel; the lateral determination area is a region between obstacles in a direction perpendicular to the entrance of the target parking space; 5. The method of claim 1, wherein the road space determination area is a closed rectangle with a long side partially coinciding with the frame of the entrance side of the target parking space and extending outward along the entrance direction of the target parking space based on the length of the vehicle. The method comprises the following steps: collecting a determination result of each frame of each target parking space in the time window; weighting the determination result of each frame based on a preset weighting rule, and calculating a weighted average result of the determination result of each frame in the time window as a final parkable state of the target parking space.

6. A storage medium having stored thereon program data, characterized in that The program data, when executed by a processor, implements the steps of the parking space parkable state analysis method according to any one of claims 1-5.

7. An in-vehicle device characterized by comprising: A device comprising a processor and a memory connected to each other, wherein the memory stores a computer program, and the processor, when executing the computer program, implements the steps of the parking space parkable state analysis method according to any one of claims 1-5.

8. A vehicle characterized by comprising: The vehicle comprises the on-vehicle device according to claim 7.

Images