Parking space identification method, vehicle, storage medium and computer program product

Abstract

The invention provides a parking space identification method, a vehicle, a storage medium and a computer program product. The method comprises the following steps: acquiring historical driving data and parking space map data of a target vehicle; performing gear analysis based on the historical driving data, and determining candidate parking points; parking matching analysis is carried out on the candidate parking points by using the parking space map data to obtain a target parking space; and performing parking space mapping processing according to the target parking space to obtain a parking space mapping result. According to the invention, the technical problem of low accuracy of a parking space identification method provided in the prior art is solved.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and more specifically, to a parking space recognition method, a vehicle, a storage medium, and a computer program product. Background Technology

[0002] With the continuous advancement of autonomous driving technology, accurately identifying a vehicle's parking location in complex and ever-changing parking environments has become a critical issue that urgently needs to be addressed. While traditional parking recognition technologies can handle parking space determination in intelligent parking scenarios, their accuracy is low in manual parking or atypical parking situations. Especially under conditions such as sensor errors, brief stops, and multiple gear shifts, misjudgments are prone to occur, such as misidentifying temporary parking as parking spaces or failing to accurately distinguish between the different logics of reversing into a parking space and forward parking. This not only affects the user experience but may also lead to the waste or misuse of parking space resources.

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

[0004] This disclosure provides a parking space identification method, a vehicle, a storage medium, and a computer program product to at least solve the technical problem of low accuracy in parking space identification methods provided in related technologies.

[0005] According to one aspect of the present disclosure, a parking space identification method is provided, comprising: acquiring historical driving data of a target vehicle and parking space map data, wherein the historical driving data represents the driving status data of the target vehicle within a historical time period, and the parking space map data represents the parking space perception data of the target vehicle during driving; performing gear analysis based on the historical driving data to determine candidate parking points, wherein the candidate parking points represent candidate parking positions corresponding to the target vehicle; performing parking matching analysis on the candidate parking points using the parking space map data to obtain a target parking space, wherein the target parking space represents the actual parking position corresponding to the target vehicle; and performing parking space mapping processing based on the target parking space to obtain a parking space mapping result, wherein the parking space mapping result is used to determine the parking plan of the target vehicle in the target parking space.

[0006] Optionally, the historical driving data includes: driving trajectory information, driving gear information, and first timestamp information. The driving trajectory information is used to represent the trajectory position sequence of the target vehicle within a historical time period. The driving gear information is used to represent the gear change record of the target vehicle within a historical time period. The first timestamp information is used to represent the time annotation result corresponding to the driving trajectory information and driving gear information. The parking space map data includes: perceived parking space information and second timestamp information of the target vehicle during driving. The perceived parking space information is used to represent the parking space position generated by perceiving the driving environment of the target vehicle. The second timestamp information is used to represent the time annotation result corresponding to the perceived parking space information.

[0007] Optionally, based on historical driving data, gear position analysis is performed to determine candidate parking points, including: performing gear position analysis based on driving gear information to obtain gear position analysis results, wherein the gear position analysis results are used to determine whether there is a reverse gear in the driving gear information; determining the parking behavior type corresponding to the target vehicle based on the gear position analysis results; and determining candidate parking points using the parking behavior type.

[0008] Optionally, the parking behavior type corresponding to the target vehicle is determined based on the gear analysis results, including: if the driving gear information shows a reverse gear based on the gear analysis results, the parking behavior type is determined to be reverse parking; if the driving gear information shows no reverse gear based on the gear analysis results, the parking behavior type is determined to be front parking.

[0009] Optionally, determining candidate parking points using parking behavior type includes: in response to the parking behavior type being reverse parking, traversing the driving gear information using a first gear constraint and a reverse gear to obtain a first target gear, wherein the first gear constraint is a gear shifting rule pre-set based on the reverse parking behavior, and the first target gear is used to represent the parking end gear after the target vehicle reverses into the parking space; determining a first parking duration based on the first timestamp information corresponding to the subsequent parking gear or neutral gear; and in response to the first parking duration being greater than a first preset threshold, determining the driving trajectory position corresponding to the first target gear as a candidate parking point.

[0010] Optionally, determining candidate parking points using parking behavior types includes: responding to the parking behavior type being a front-end parking type, traversing the driving gear information to obtain a second target gear, wherein the second target gear represents the parking gear or neutral gear in the driving gear information; using the second gear constraint and the second target gear to continue traversing the driving gear information to obtain a third target gear, wherein the second gear constraint is a gear shift rule pre-set according to the front-end parking behavior, and the third target gear represents the parking end gear of the target vehicle after front-end parking; determining a second parking duration based on the first timestamp corresponding to the second target gear and the first timestamp corresponding to the third target gear; and responding to the second parking duration being greater than a second preset threshold, determining the driving trajectory position corresponding to the third target gear as a candidate parking point.

[0011] Optionally, using parking space map data to perform parking matching analysis on candidate parking points to obtain target parking spaces includes: performing location matching on candidate parking points based on perceived parking space information to obtain spatial matching results, wherein the spatial matching results are used to determine whether a candidate parking point is located within the parking space range of the perceived parking space information; performing time comparison analysis on the first timestamp information corresponding to the candidate parking point using the second timestamp information corresponding to the perceived parking space information to obtain time comparison results, wherein the time comparison results are used to determine whether the time difference between the second timestamp information and the first timestamp information corresponding to the candidate parking point is less than or equal to a third preset threshold; and filtering candidate parking points based on the spatial matching results and the time comparison results to obtain target parking spaces.

[0012] Optionally, the candidate parking points are filtered based on the spatial matching results and the time comparison results to obtain the target parking space, including: determining that the candidate parking point is located within the parking space of the perceived parking space information based on the spatial matching results, and determining that the time difference is less than or equal to a third preset threshold based on the time comparison results, and determining the candidate parking point as the target parking space.

[0013] According to another aspect of the embodiments of this disclosure, a parking space recognition device is also provided, comprising: an acquisition module, configured to acquire historical driving data and parking space map data of a target vehicle, wherein the historical driving data represents the driving status data of the target vehicle within a historical time period, and the parking space map data represents the parking space perception data of the target vehicle during driving; a determination module, configured to perform gear analysis based on the historical driving data to determine candidate parking points, wherein the candidate parking points represent candidate parking positions corresponding to the target vehicle; a matching module, configured to perform parking matching analysis on the candidate parking points using the parking space map data to obtain a target parking space, wherein the target parking space represents the actual parking position corresponding to the target vehicle; and a processing module, configured to perform parking space mapping processing based on the target parking space to obtain a parking space mapping result, wherein the parking space mapping result is used to determine the parking plan of the target vehicle in the target parking space.

[0014] Optionally, the historical driving data includes: driving trajectory information, driving gear information, and first timestamp information. The driving trajectory information is used to represent the trajectory position sequence of the target vehicle within a historical time period. The driving gear information is used to represent the gear change record of the target vehicle within a historical time period. The first timestamp information is used to represent the time annotation result corresponding to the driving trajectory information and driving gear information. The parking space map data includes: perceived parking space information and second timestamp information of the target vehicle during driving. The perceived parking space information is used to represent the parking space position generated by perceiving the driving environment of the target vehicle. The second timestamp information is used to represent the time annotation result corresponding to the perceived parking space information.

[0015] Optionally, the determining module is further configured to: perform gear analysis based on driving gear information to obtain gear analysis results, wherein the gear analysis results are used to determine whether there is a reverse gear in the driving gear information; determine the parking behavior type corresponding to the target vehicle based on the gear analysis results; and determine candidate parking points using the parking behavior type.

[0016] Optionally, the determining module is also used to: respond to a determination based on the gear analysis results that a reverse gear exists in the driving gear information, and determine the parking behavior type as reverse parking; respond to a determination based on the gear analysis results that a reverse gear does not exist in the driving gear information, and determine the parking behavior type as front parking.

[0017] Optionally, the determining module is further configured to: respond to the parking behavior type being reverse parking, traverse and process the driving gear information using the first gear constraint and the reverse gear to obtain the first target gear, wherein the first gear constraint is a gear change rule pre-set according to the reverse parking behavior, and the first target gear is used to represent the parking end gear after the target vehicle reverses into the parking space; determine the first parking duration based on the first timestamp information corresponding to the subsequent parking gear or neutral gear; and respond to the first parking duration being greater than the first preset threshold, determine the driving trajectory position corresponding to the first target gear as a candidate parking point.

[0018] Optionally, the determining module is further configured to: in response to the parking behavior type being a front-end parking type, traverse the driving gear information to obtain a second target gear, wherein the second target gear is used to represent the parking gear or neutral gear in the driving gear information; continue traversing the driving gear information using the second gear constraint and the second target gear to obtain a third target gear, wherein the second gear constraint is a gear change rule pre-set according to the front-end parking behavior, and the third target gear is used to represent the parking end gear of the target vehicle after front-end parking; determine a second parking duration based on the first timestamp corresponding to the second target gear and the first timestamp corresponding to the third target gear; and in response to the second parking duration being greater than a second preset threshold, determine the driving trajectory position corresponding to the third target gear as a candidate parking point.

[0019] Optionally, the matching module is further configured to: perform location matching on candidate parking points based on the perceived parking space information to obtain a spatial matching result, wherein the spatial matching result is used to determine whether the candidate parking point is located within the parking space range of the perceived parking space information; perform time comparison analysis on the first timestamp information corresponding to the candidate parking point using the second timestamp information corresponding to the perceived parking space information to obtain a time comparison result, wherein the time comparison result is used to determine whether the time difference between the second timestamp information and the first timestamp information corresponding to the candidate parking point is less than or equal to a third preset threshold; and perform filtering processing on the candidate parking points according to the spatial matching result and the time comparison result to obtain the target parking space.

[0020] Optionally, the matching module is further configured to: determine, based on the spatial matching result, that the candidate parking point is located within the parking space of the perceived parking space information, and determine, based on the time comparison result, that the time difference is less than or equal to a third preset threshold, and identify the candidate parking point as the target parking space.

[0021] According to another aspect of the present disclosure, a vehicle is also provided, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the parking space recognition method in the embodiments of the present disclosure.

[0022] According to another aspect of the embodiments of this disclosure, 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 storage medium is located to execute the parking space recognition method of the embodiments of this disclosure.

[0023] According to another aspect of the present disclosure, a computer program product is also provided, the computer program product including computer instructions that, when executed by a processor, implement the parking space recognition method in the present disclosure.

[0024] In this embodiment, historical driving data and parking space map data of the target vehicle are acquired, and gear analysis is performed based on the historical driving data to determine candidate parking points. Then, the parking space map data is used to perform spatiotemporal matching analysis on the candidate parking points to obtain the target parking space. Finally, parking space mapping processing is performed based on the target parking space to obtain the parking space mapping result. This achieves the goal of accurately identifying the available parking location of the vehicle, thereby improving the technical effect of parking space identification accuracy and solving the technical problem of low accuracy in the parking space identification methods provided in related technologies. Attached Figure Description

[0025] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are used to explain the disclosure, but do not constitute an undue limitation of the disclosure. In the drawings:

[0026] Figure 1 This is a flowchart of a parking space identification method according to one embodiment of the present disclosure;

[0027] Figure 2 This is a schematic diagram of a parking space identification method according to one embodiment of the present disclosure;

[0028] Figure 3 This is a structural block diagram of a parking space recognition device according to one embodiment of the present disclosure. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure 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 disclosure 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.

[0031] Traditional parking recognition technology can handle parking space determination in intelligent parking scenarios, but its accuracy is low in manual parking or atypical parking situations. Especially under conditions such as sensor errors, short stops, and multiple gear shifts, it is prone to misjudgment, such as misidentifying temporary parking as parking space entry, or failing to accurately distinguish the different logics of reversing into a parking space and forward parking. This not only affects the user experience, but may also lead to the waste or misuse of parking space resources.

[0032] Specifically, traditional parking recognition technology faces the following main problems when handling manual parking and non-standard parking scenarios. First, taking commonly used ultrasonic sensors as an example, their distance measurements are subject to potential drift, easily leading to distorted results. Especially when reflective objects are present around the vehicle, the sensor is highly likely to capture misleading reflected echoes, and the resulting data deviation directly affects the parking recognition system's accurate judgment of parking space availability. Second, in some real-world scenarios, vehicles may need to stop intermittently to find suitable parking spaces, avoid pedestrians, or coordinate with other vehicles. However, inherent recognition algorithms tend to operate from a static perspective, relying solely on the vehicle's instantaneous location information to make decisions about parking space occupancy, without considering the vehicle's dynamic behavior and its underlying functional purpose. Furthermore, in scenarios involving multiple gear shifts, drivers typically need to flexibly change gears according to specific needs during parking, shifting from drive to reverse and then back to drive to complete the parking maneuver, making it difficult to quickly and accurately determine the vehicle's true parking status.

[0033] According to an embodiment of this disclosure, a method embodiment for parking space identification 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.

[0034] This method embodiment can be executed in an electronic device or similar computing device that includes memory and a processor. Taking 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.

[0035] The memory can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the parking space recognition method in this embodiment. The processor executes various functional applications and data processing by running the computer program stored in the memory, thereby realizing the aforementioned parking space recognition 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 such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0036] 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.

[0037] 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.

[0038] Figure 1 This is a flowchart of a parking space recognition method according to one embodiment of the present disclosure, such as... Figure 1 As shown, the method includes the following steps:

[0039] Step S11: Obtain historical driving data and parking space map data of the target vehicle. The historical driving data is used to represent the driving status data of the target vehicle within a historical time period, and the parking space map data is used to represent the parking space perception data of the target vehicle during driving.

[0040] The aforementioned historical driving data is a collection of data generated by the target vehicle during its past driving journey, including but not limited to vehicle trajectory information, gear information, and timestamp information. Historical driving data is an important basis for evaluating vehicle driving habits and parking behavior patterns, and helps the parking space recognition system understand the vehicle's dynamic behavior trajectory and its state changes at different points in time.

[0041] For example, historical driving data of a target vehicle can be obtained by accessing its built-in black box (such as an on-board diagnostic system (OBD) or a vehicle event data recorder (VEDR)) or a cloud database connected to it.

[0042] For example, historical driving data of the target vehicle can also be obtained through the target vehicle's driving data recording module, such as the log files of the in-vehicle infotainment system (IVI), the intelligent driving assistance system, or data recording hardware.

[0043] The aforementioned parking space map data is used to represent the layout and occupancy status of parking spaces within the target area. Its core content includes, but is not limited to, the specific information of the parking spaces perceived by the target vehicle during its journey, as well as the timestamp recorded when the parking space is identified. Specifically, the parking space map data is not limited to static spatial coordinates and dimensions, but also covers dynamic usage, such as the occupancy status of the parking space, whether it is suitable for parking, and its relative positional relationship with surrounding environmental elements.

[0044] For example, the parking space lines and surrounding obstacles can be identified using the target vehicle's camera, and the actual vacancy status of the parking space can be verified by combining radar and lidar data. This data is then uploaded to a cloud server. Further, on the cloud server, artificial intelligence algorithms analyze this data, combining it with static parking space information provided by high-precision map services, and dynamically supplemented by information from infrastructure sensor networks and user crowdsourcing, to construct parking space map data.

[0045] Step S12: Perform gear analysis based on historical driving data to determine candidate parking points, where candidate parking points are used to represent candidate parking positions corresponding to the target vehicle.

[0046] The aforementioned candidate parking spots are potential parking locations derived from a comprehensive analysis of the target vehicle's historical driving data, including gear shifts, speed changes, dwell time, and sensor information.

[0047] For example, when the target vehicle switches from D gear to P gear or N gear, and the vehicle speed gradually decreases from a non-zero state to zero, while remaining stationary for more than a preset time threshold, the position coordinates corresponding to the current P gear or N gear can be determined as a candidate parking point.

[0048] Step S13: Use parking space map data to perform parking matching analysis on candidate parking points to obtain target parking spaces, where the target parking space is used to represent the actual parking position corresponding to the target vehicle.

[0049] The target parking spaces mentioned above are the actual parking locations determined during the spatiotemporal matching analysis process by accurately comparing and matching candidate parking points with existing parking spaces on the parking space map.

[0050] For example, the location coordinates and precise timestamp of each determined candidate parking spot can be mapped to a parking space map database. By setting a spatial range (e.g., ±3 meters) and a time window (e.g., ±2 minutes), all parking space records that meet the geographical and time conditions can be filtered out as target parking spaces.

[0051] Step S14: Perform parking space mapping processing based on the target parking space to obtain the parking space mapping result. The parking space mapping result is used to determine the parking plan for the target vehicle in the target parking space.

[0052] The above parking space mapping process involves creating or updating a parking space map based on the target parking space information, using data processing and analysis algorithms to reflect the latest parking location and parking environment of the target vehicle's area.

[0053] For example, when a user parks their car for the first time in the underground parking garage of a shopping mall, they can preset a target parking space and parking method, which are then saved to the vehicle's memory parking database. The next time the user visits the same shopping mall, the in-vehicle intelligent system can automatically recognize the scenario and recommend previously used target parking spaces, simplifying the parking decision-making process. The user simply taps the screen to confirm, planning the optimal route and guiding the vehicle directly to the parking space, thereby improving parking efficiency and convenience.

[0054] For example, suppose a vehicle is in a large conference center and plans to attend an event but is unfamiliar with the surroundings. By inputting the destination, the intelligent parking space recognition system can quickly filter out available parking spaces around the conference center that are suitable for the vehicle's size using parking space mapping results. On the map interface, available parking spaces can be highlighted with different colors or icons, allowing users to directly select their preferred parking space. Once selected, a detailed navigation route is immediately generated, including directions to the parking lot entrance, turn prompts along the route, and the final path indication before the parking space. Furthermore, the estimated arrival time and the number of remaining parking spaces can be imported into the parking space mapping results in real time, helping users plan their travel time effectively and avoid arriving at a situation where there are not enough parking spaces available.

[0055] Based on the above steps S11 to S14, by acquiring the historical driving data and parking space map data of the target vehicle, and performing gear analysis based on the historical driving data, candidate parking points are determined. Then, the parking space map data is used to perform spatiotemporal matching analysis on the candidate parking points to obtain the target parking space. Finally, parking space mapping processing is performed based on the target parking space to obtain the parking space mapping result. This achieves the goal of accurately identifying the available parking location of the vehicle, thereby improving the technical effect of parking space identification accuracy and solving the technical problem of low accuracy in the parking space identification methods provided in related technologies.

[0056] Optionally, the historical driving data includes: driving trajectory information, driving gear information, and first timestamp information. The driving trajectory information is used to represent the trajectory position sequence of the target vehicle within a historical time period. The driving gear information is used to represent the gear change record of the target vehicle within a historical time period. The first timestamp information is used to represent the time annotation result corresponding to the driving trajectory information and driving gear information. The parking space map data includes: perceived parking space information and second timestamp information of the target vehicle during driving. The perceived parking space information is used to represent the parking space position generated by perceiving the driving environment of the target vehicle. The second timestamp information is used to represent the time annotation result corresponding to the perceived parking space information.

[0057] The aforementioned driving trajectory information consists of data points recording the driving journey of the target vehicle, including but not limited to parameters such as the target vehicle's position coordinates, direction angle, speed, and acceleration at different times.

[0058] The above gear information refers to the gear status of the target vehicle at various times during driving, including but not limited to the forward (D), reverse (R), neutral (N), and parking (P) gears for automatic or manual transmission vehicles. Specifically, D indicates that the vehicle is preparing to move forward; R indicates that the vehicle is preparing to reverse; N indicates that the vehicle is neither moving forward nor backward, with no power output but free to glide; and P is the safety gear where the vehicle is completely stopped and locked to prevent accidental movement.

[0059] The aforementioned first timestamp information is a time stamp closely related to critical vehicle states or events, such as the exact point in time when the vehicle starts, begins driving, stops, shifts gears, or performs a specific operation (such as turning on the turn signal or braking). First timestamp information provides a timeframe for vehicle operations and is crucial for tracking historical vehicle behavior, fault diagnosis, and event time synchronization in autonomous driving systems.

[0060] The aforementioned perceived parking space information refers to specific details about parking spaces captured and processed by onboard sensors and vision systems, including but not limited to the parking space's location coordinates, size, shape, orientation, and whether it is occupied. This perceived parking space information is crucial for functions such as autonomous navigation and automatic parking within internal roads like parking lots, enabling vehicles to efficiently and accurately find available parking spaces and complete the parking maneuver.

[0061] The aforementioned second timestamp information refers to a specific point in time related to the update of perception data or the triggering of an event. Specifically, it refers to the exact time recorded whenever the perception system (such as sensors like cameras, radar, and lidar) captures and processes new environmental information or detects a specific event (such as an obstacle or a change in traffic signal) during vehicle operation. This second timestamp information helps synchronize perception data with vehicle status information, playing a crucial role in decision-making, event retrospective analysis, and safety performance evaluation for autonomous driving systems.

[0062] Optionally, in step S12, gear analysis is performed based on historical driving data to determine candidate parking points, including:

[0063] Step S121: Perform gear analysis based on driving gear information to obtain gear analysis results, wherein the gear analysis results are used to determine whether there is a reverse gear in the driving gear information.

[0064] Step S122: Determine the parking behavior type corresponding to the target vehicle based on the gear analysis results;

[0065] Step S123: Determine candidate parking locations using parking behavior types.

[0066] The above-mentioned parking behavior types include, but are not limited to, reversing into a parking space, parking with the front of the vehicle in a parking space, parallel parking, and angled parking.

[0067] For example, driving gear information can be obtained from the Electronic Control Unit (ECU) of the target vehicle. The timestamps of gear shifts corresponding to these timestamps can be sorted and time differences calculated to identify the patterns and time intervals of gear changes. For instance, shifting from D to R might indicate that the vehicle is reversing into a parking space, while shifting directly from D to P might correspond to a straight-line parking maneuver. Furthermore, based on the continuity and combination of gear information, the parking behavior type corresponding to the target vehicle can be determined, and then candidate parking spots can be identified using this parking behavior type.

[0068] Based on the above steps S121 to S123, intelligent gear behavior analysis can accurately identify the parking behavior type of the target vehicle and lock in candidate parking points, thereby improving the accuracy of parking space identification.

[0069] Optionally, in step S122, the parking behavior type corresponding to the target vehicle is determined based on the gear analysis results, including:

[0070] Step S1221: Based on the gear analysis results, it is determined that there is a reverse gear in the driving gear information, and the parking behavior type is determined to be reverse parking.

[0071] The above-described reverse parking maneuver refers to the process of driving the vehicle past the target parking space in Drive (D) gear, then switching to Reverse (R) gear to reverse until the vehicle is completely parked in the space and aligned with the parking line, and finally switching to Park (P) gear. This parking method is common in parking lots with clearly marked parking lines. The vehicle needs to drive past the parking space from the front and then reverse into the space. It is typically used when there are other vehicles or obstacles in front and behind to avoid the space shortage that might occur if the vehicle is driven directly front-in.

[0072] For example, if the target vehicle exhibits a continuous gear shift sequence from D to R and then to P during its driving, and the vehicle has a clear reverse movement trajectory during the use of R, it can be determined that the vehicle's parking behavior is a reverse parking type.

[0073] Step S1222: Based on the gear analysis results, it is determined that there is no reverse gear in the driving gear information, and the parking behavior type is determined to be the front-entry parking type.

[0074] The aforementioned "front-end parking" type refers to a vehicle that, during parking, directly enters the target parking space in Drive (D) mode without needing to reverse or adjust its position, until it is fully parked and remains in Park (P) mode. This parking behavior is common in scenarios where there is sufficient space in front of the parking space, allowing the vehicle to drive in directly without reversing.

[0075] For example, if the vehicle's driving trajectory does not show any record of using reverse (R) gear, but instead directly switches from drive (D) to park (P), and the vehicle's position when switching to park coincides with the location of a known or potential parking space, it can be determined that the vehicle's parking behavior is a front-in parking maneuver. Front-in parking is generally simpler and more direct, suitable for parking environments with ample space, reducing the extra space and time required for reversing into a parking space.

[0076] Based on the steps S1221 to S1222 above, by intelligently analyzing the dynamic matching of the vehicle's gear shift sequence and driving trajectory, it can not only quickly determine the parking type, but also further optimize the vehicle navigation and assisted parking strategies, providing drivers with customized parking guidance, reducing operational errors and time waste during the parking process, and thus improving parking safety and comfort.

[0077] Optionally, in step S123, candidate parking locations are determined using parking behavior types, including:

[0078] Step S21: In response to the parking behavior type being reverse parking, the driving gear information is traversed using the first gear constraint and the reverse gear to obtain the first target gear. The first gear constraint is a gear change rule pre-set according to the reverse parking behavior, and the first target gear is used to represent the parking end gear after the target vehicle reverses into the parking space.

[0079] The aforementioned first-level constraint requires that during the parking maneuver classified as reverse parking, there must be at least one shift between neutral (N) and park (P) gears between D and R gears to ensure the vehicle has come to a smooth stop before the reverse operation is performed, avoiding potential safety hazards from direct shifts between forward and reverse. Furthermore, the dwell time in N / P gears must meet certain requirements, exceeding a brief threshold to eliminate misjudgments caused by brief deceleration or gear shifting.

[0080] The aforementioned target gear indicates the final parking gear after the vehicle has reversed into a parking space, i.e., N or P. Specifically, after reversing into a parking space, the vehicle is usually placed in P or N to ensure that the vehicle will not move unexpectedly while parked, and also to facilitate the driver's exit from the vehicle.

[0081] For example, the vehicle's driving gear information is iterated until the reverse (R) gear is found. After finding the R gear, the process continues downwards to find the first vehicle gear information that is not R, N, or P, i.e., D gear. Further, the duration of the last N / P gear following the R gear is calculated based on timestamps. If the duration is greater than 2 minutes, then the D gear is the final parking gear after reversing into the parking space. Conversely, if the duration of the last N / P gear following the R gear is less than 2 minutes, the process needs to be repeated until all reversing stop points are found.

[0082] Step S22: Determine the first parking duration based on the first timestamp information corresponding to the parking gear or neutral gear following the reverse gear.

[0083] The aforementioned first parking time is the period from the moment the target vehicle last leaves R gear and shifts to P or N gear, until the vehicle leaves N or P gear again and enters D gear or reverse gear. The first parking time reflects the process of the vehicle completing reverse parking until it comes to a complete stop, and is a key parameter for determining whether the parking behavior has ended and identifying the exact parking point.

[0084] Step S23: In response to the first parking duration being greater than the first preset threshold, the driving trajectory position corresponding to the first target gear is determined as a candidate parking point.

[0085] For example, suppose that during the parking process, the target vehicle's gear information changes in the order of D, N / P, R, N / P, and D. When the system detects that the vehicle has returned from R to N / P and remains in this gear for more than a first preset threshold, it is determined that the vehicle has completed the reversing maneuver and entered a stable parking state. At this time, the parking space recognition system will trace back to the last D gear trajectory point before the vehicle switched from D to N / P, i.e., before preparing to reverse, and identify this location as a candidate parking point.

[0086] Based on steps S21 to S23 above, by intelligently analyzing the sequence of vehicle gear shifts and corresponding timestamps, combined with the first gear constraint, candidate parking points for reversing into a parking space can be accurately identified. This process eliminates interference caused by brief gear shifts or non-parking behaviors, ensuring a smooth stop for the vehicle during the transition from D to R gears, effectively improving the accuracy of parking recognition, and providing drivers with safer and more reliable parking space information.

[0087] Optionally, in step S123, candidate parking locations are determined using parking behavior types, including:

[0088] Step S31: In response to the parking behavior type being the front-end parking type, the driving gear information is traversed to obtain the second target gear, wherein the second target gear is used to represent the parking gear or neutral gear in the driving gear information.

[0089] Step S32: Use the second gear constraint and the second target gear to continue traversing the driving gear information to obtain the third target gear. The second gear constraint is a gear change rule preset according to the vehicle's front-end parking behavior. The third target gear is used to represent the parking end gear of the target vehicle after the front end of the vehicle enters the parking space.

[0090] The second constraint mentioned above stipulates that when the parking behavior is determined to be a front-end parking maneuver, the vehicle directly shifts from D to P or N, pauses in N / P for a period of time, and then re-enters D to move forward. This constraint is used to capture brief pauses before reaching the target parking space, ensuring that the identified parking behavior is an actual parking operation rather than a temporary stop caused by other reasons. Furthermore, the time the vehicle spends in N / P must exceed a short threshold to exclude momentary stops caused by external factors such as traffic signals or pedestrian avoidance, thereby preventing false identification.

[0091] For example, the vehicle's driving gear information is traversed until either N or P gear is found, and upon finding N or P gear, the parking start timestamp is recorded. Then, the traversal continues downwards to find the first driving gear other than N or P gear, i.e., R or D gear, and the parking end timestamp is recorded. Further, the parking time is calculated based on the parking start and end timestamps. When the parking time exceeds 10 minutes, the found R or D gear is the parking end gear after the vehicle's front end is in the parking space.

[0092] Step S33: Determine the second parking duration based on the first timestamp corresponding to the second target gear and the first timestamp corresponding to the third target gear;

[0093] The aforementioned second parking duration refers to the time from when the target vehicle switches to N / P gear until the vehicle leaves N / P gear and enters D gear again. The second parking duration reflects the state of the vehicle when it stops in front of the target parking space until it is ready to move forward, and is one of the key indicators for judging the vehicle's parking behavior.

[0094] Step S34: In response to the second parking duration being greater than the second preset threshold, the driving trajectory position corresponding to the third target gear is determined as a candidate parking point.

[0095] For example, assuming the target vehicle is parking in a parking space with its front end facing inwards, the driving gear information changes in the order of D, N / P, and D again. If the parking time in N / P before the second D gear activation exceeds a second preset threshold, then the last trajectory point before the end of the first D gear driving is considered a candidate parking point.

[0096] It should be noted that the second preset threshold in this embodiment is less than the first preset threshold, and the specific value can be set according to the actual situation of the vehicle, and is not limited here.

[0097] Based on steps S31 to S34 above, by monitoring the vehicle's gear position information, it is possible to effectively distinguish between brief stops and actual parking behaviors, thereby accurately identifying the last position before parking as a candidate parking point. This strategy based on gear position information and time window analysis can improve the accuracy of parking space identification.

[0098] Optionally, in step S13, parking matching analysis is performed on candidate parking points using parking space map data to obtain target parking spaces including:

[0099] Step S131: Based on the perceived parking space information, perform location matching on the candidate parking points to obtain spatial matching results, wherein the spatial matching results are used to determine whether the candidate parking point is located within the parking space range of the perceived parking space information.

[0100] The spatial matching result described above is achieved by comparing vehicle location information with parking space map data to analyze whether the coordinates of candidate parking points coincide with the coordinate range of a specific parking space. If the candidate parking point is located within the area of ​​the parking space where the parking space information is perceived, the spatial matching result is "match"; otherwise, it is "mismatch".

[0101] Step S132: Use the second timestamp information corresponding to the perceived parking space information to perform time comparison analysis on the first timestamp information corresponding to the candidate parking point to obtain the time comparison result. The time comparison result is used to determine whether the time difference between the second timestamp information and the first timestamp information corresponding to the candidate parking point is less than or equal to a third preset threshold.

[0102] The aforementioned third preset threshold is used to measure the time interval between the parking space perception time and the actual parking time of the candidate parking point. It is usually set to a short time period, such as 30 seconds.

[0103] Step S133: Based on the spatial matching results and time comparison results, the candidate parking points are filtered to obtain the target parking space.

[0104] For example, suppose that during a driving record, multiple potential parking spaces have been detected by various sensors, and several candidate parking points have been marked based on the vehicle's driving trajectory and gear information. For each candidate parking point, its location coordinates can be compared with the coordinate range of each parking space on the parking space map to check whether it is completely located within a certain parking space. If the candidate point matches the parking space coordinates, i.e., it falls within the parking space, then the spatial matching result is "match"; otherwise, it is "mismatch". If the spatial matching result of the candidate parking point is "match", the difference between the timestamp of the parking point and the corresponding parking space detection timestamp will be further compared to see if it is within a third preset threshold. Only when both the "spatial matching" and "time comparison" conditions are met can the parking space be identified as the target parking space.

[0105] Based on the above steps S131 to S133, by comprehensively using the dual verification mechanism of spatial matching and time comparison, the target parking space can be accurately screened and confirmed, effectively eliminating interference information caused by time and space mismatch, thereby ensuring that the output parking space information not only matches the actual parking location but also satisfies the time logic, thus providing drivers with real-time and accurate parking space feedback.

[0106] Optionally, in step S133, candidate parking points are filtered based on spatial matching results and temporal comparison results to obtain target parking spaces, including:

[0107] The response determines the candidate parking point as the target parking space based on the spatial matching result and the time difference is less than or equal to the third preset threshold.

[0108] For example, suppose that at 12:00:00, the intelligent parking system detects an available parking space with coordinates within the X-axis range of 34.053250 to 34.053350 and the Y-axis range of -118.245450 to -118.245350 on the parking lot floor plan, and the perception timestamp of this parking space is 1684972800 seconds. Subsequently, in the same driving record, a parking behavior record appears, with one parking point timestamped at 1684972820 seconds, i.e., 12:00:20, and location coordinates (X = 34.053280, Y = -118.245420). Based on the above data, it can be determined that the parking point is completely located within the available parking space, meeting the spatial matching requirement. Furthermore, since the time difference between the perception time of this parking point and the parking space is 20 seconds, which is less than the third preset threshold—a 30-second time window—the time comparison condition is met. Therefore, since the parking spot is consistent with the perceived parking space information in both spatial and temporal dimensions, it can be identified that the parking space where the parking spot is located is the target parking space.

[0109] Based on the above optional embodiments, by combining spatial coordinate comparison with time window verification, it can be ensured that the parking space determination conforms to both geographical coordinate positioning and parking behavior timeline, effectively avoiding misjudgments caused by environmental interference and sensor errors, thereby improving the accuracy of parking space recognition.

[0110] Figure 2 This is a schematic diagram of a parking space recognition method according to one embodiment of the present disclosure, as shown below. Figure 2 As shown, the arcs represent vehicle trajectories, and the rectangles represent parking spaces. Black rectangles indicate occupied spaces, while white rectangles represent vacant spaces. During parking space recognition, drivers can select a specific parking space as their target, thus enabling point-to-point path planning.

[0111] 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 disclosure, 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 disclosure.

[0112] This disclosure also provides a parking space recognition device for implementing the above embodiments and preferred embodiments, which will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0113] Figure 3 This is a structural block diagram of a parking space recognition device according to one embodiment of the present disclosure, such as... Figure 3 As shown, the device includes:

[0114] The acquisition module 301 is used to acquire the historical driving data and parking space map data of the target vehicle. The historical driving data is used to represent the driving status data of the target vehicle within a historical time period, and the parking space map data is used to represent the parking space perception data of the target vehicle during driving.

[0115] The determination module 302 is used to perform gear analysis based on historical driving data to determine candidate parking points, wherein the candidate parking points are used to represent the candidate parking positions corresponding to the target vehicle;

[0116] The matching module 303 is used to perform parking matching analysis on candidate parking points using parking space map data to obtain the target parking space, wherein the target parking space is used to represent the actual parking position corresponding to the target vehicle.

[0117] The processing module 304 is used to perform parking space mapping processing based on the target parking space to obtain the parking space mapping result, wherein the parking space mapping result is used to determine the planning of the target vehicle parking in the target parking space.

[0118] Optionally, the historical driving data includes: driving trajectory information, driving gear information, and first timestamp information. The driving trajectory information is used to represent the trajectory position sequence of the target vehicle within a historical time period. The driving gear information is used to represent the gear change record of the target vehicle within a historical time period. The first timestamp information is used to represent the time annotation result corresponding to the driving trajectory information and driving gear information. The parking space map data includes: perceived parking space information and second timestamp information of the target vehicle during driving. The perceived parking space information is used to represent the parking space position generated by perceiving the driving environment of the target vehicle. The second timestamp information is used to represent the time annotation result corresponding to the perceived parking space information.

[0119] Optionally, the determining module 302 is further configured to: perform gear analysis based on the driving gear information to obtain gear analysis results, wherein the gear analysis results are used to determine whether there is a reverse gear in the driving gear information; determine the parking behavior type corresponding to the target vehicle based on the gear analysis results; and determine candidate parking points using the parking behavior type.

[0120] Optionally, the determining module 302 is further configured to: respond to a determination based on the gear analysis results that a reverse gear exists in the driving gear information, and determine the parking behavior type as reverse parking; respond to a determination based on the gear analysis results that a reverse gear does not exist in the driving gear information, and determine the parking behavior type as front parking.

[0121] Optionally, the determining module 302 is further configured to: in response to the parking behavior type being reverse parking, traverse the driving gear information using the first gear constraint and the reverse gear to obtain the first target gear, wherein the first gear constraint is a gear change rule pre-set according to the reverse parking behavior, and the first target gear is used to represent the parking end gear after the target vehicle reverses into the parking space; determine the first parking duration based on the first timestamp information corresponding to the subsequent parking gear or neutral gear; and in response to the first parking duration being greater than the first preset threshold, determine the driving trajectory position corresponding to the first target gear as a candidate parking point.

[0122] Optionally, the determining module 302 is further configured to: in response to the parking behavior type being a front-end parking type, traverse the driving gear information to obtain a second target gear, wherein the second target gear is used to represent the parking gear or neutral gear in the driving gear information; continue traversing the driving gear information using the second gear constraint and the second target gear to obtain a third target gear, wherein the second gear constraint is a gear change rule pre-set according to the front-end parking behavior, and the third target gear is used to represent the parking end gear of the target vehicle after front-end parking; determine a second parking duration based on the first timestamp corresponding to the second target gear and the first timestamp corresponding to the third target gear; in response to the second parking duration being greater than a second preset threshold, determine the driving trajectory position corresponding to the third target gear as a candidate parking point.

[0123] Optionally, the matching module 303 is further configured to: perform location matching on candidate parking points based on the perceived parking space information to obtain a spatial matching result, wherein the spatial matching result is used to determine whether the candidate parking point is located within the parking space range of the perceived parking space information; perform time comparison analysis on the first timestamp information corresponding to the candidate parking point using the second timestamp information corresponding to the perceived parking space information to obtain a time comparison result, wherein the time comparison result is used to determine whether the time difference between the second timestamp information and the first timestamp information corresponding to the candidate parking point is less than or equal to a third preset threshold; and perform filtering processing on the candidate parking points according to the spatial matching result and the time comparison result to obtain the target parking space.

[0124] Optionally, the matching module 303 is further configured to: determine, based on the spatial matching result, that the candidate parking point is located within the parking space of the perceived parking space information, and determine, based on the time comparison result, that the time difference is less than or equal to a third preset threshold, and identify the candidate parking point as the target parking space.

[0125] 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.

[0126] According to another aspect of the present disclosure, a vehicle is also provided, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the parking space recognition method in the embodiments of the present disclosure.

[0127] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0128] S1, acquire the target vehicle's historical driving data and parking space map data. The historical driving data is used to represent the target vehicle's driving status data within a historical time period, and the parking space map data is used to represent the target vehicle's parking space perception data during driving.

[0129] S2, based on historical driving data, perform gear analysis to determine candidate parking points, where candidate parking points are used to represent the candidate parking positions corresponding to the target vehicle;

[0130] S3, using parking space map data to perform parking matching analysis on candidate parking points to obtain target parking spaces, where the target parking space is used to represent the actual parking position corresponding to the target vehicle;

[0131] S4. Perform parking space mapping based on the target parking space to obtain the parking space mapping result. The parking space mapping result is used to determine the parking plan for the target vehicle in the target parking space.

[0132] According to another aspect of the embodiments of this disclosure, 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 storage medium is located to execute the parking space recognition method of the embodiments of this disclosure.

[0133] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0134] S1, acquire the target vehicle's historical driving data and parking space map data. The historical driving data is used to represent the target vehicle's driving status data within a historical time period, and the parking space map data is used to represent the target vehicle's parking space perception data during driving.

[0135] S2, based on historical driving data, perform gear analysis to determine candidate parking points, where candidate parking points are used to represent the candidate parking positions corresponding to the target vehicle;

[0136] S3, using parking space map data to perform parking matching analysis on candidate parking points to obtain target parking spaces, where the target parking space is used to represent the actual parking position corresponding to the target vehicle;

[0137] S4. Perform parking space mapping based on the target parking space to obtain the parking space mapping result. The parking space mapping result is used to determine the parking plan for the target vehicle in the target parking space.

[0138] 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.

[0139] According to another aspect of the present disclosure, a computer program product is also provided, the computer program product including computer instructions that, when executed by a processor, implement the parking space recognition method in the present disclosure.

[0140] Optionally, in this embodiment, the above-mentioned computer program product can be configured as a computer program that performs the following steps:

[0141] S1, acquire the target vehicle's historical driving data and parking space map data. The historical driving data is used to represent the target vehicle's driving status data within a historical time period, and the parking space map data is used to represent the target vehicle's parking space perception data during driving.

[0142] S2, based on historical driving data, perform gear analysis to determine candidate parking points, where candidate parking points are used to represent the candidate parking positions corresponding to the target vehicle;

[0143] S3, using parking space map data to perform parking matching analysis on candidate parking points to obtain target parking spaces, where the target parking space is used to represent the actual parking position corresponding to the target vehicle;

[0144] S4. Perform parking space mapping based on the target parking space to obtain the parking space mapping result. The parking space mapping result is used to determine the parking plan for the target vehicle in the target parking space.

[0145] The sequence numbers of the embodiments disclosed above are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0146] In the above embodiments of this disclosure, 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.

[0147] In the several embodiments provided in this disclosure, 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 couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0148] 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.

[0149] Furthermore, the functional units in the various embodiments of this disclosure 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.

[0150] 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 disclosure, 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 disclosure. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0151] The above description is only a preferred embodiment of this disclosure. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principles of this disclosure, and these improvements and modifications should also be considered within the scope of protection of this disclosure.

Claims

1. A parking space recognition method, characterized in that, include: The historical driving data and parking space map data of the target vehicle are obtained, wherein the historical driving data is used to represent the driving status data of the target vehicle within a historical time period, and the parking space map data is used to represent the parking space perception data of the target vehicle during driving. Based on the historical driving data, gear analysis is performed to determine candidate parking points, wherein the candidate parking points are used to represent the candidate parking positions corresponding to the target vehicle; Using the parking space map data, a parking matching analysis is performed on the candidate parking points to obtain the target parking space, wherein the target parking space is used to represent the actual parking position corresponding to the target vehicle; Based on the target parking space, a parking space mapping process is performed to obtain the parking space mapping result, wherein the parking space mapping result is used to determine the planning of the target vehicle parking in the target parking space.

2. The parking space identification method according to claim 1, characterized in that, The historical driving data includes: driving trajectory information, driving gear information, and first timestamp information. The driving trajectory information is used to represent the trajectory position sequence of the target vehicle within the historical time period. The driving gear information is used to represent the gear change record of the target vehicle within the historical time period. The first timestamp information is used to represent the time annotation result corresponding to the driving trajectory information and the driving gear information. The parking space map data includes: perceived parking space information and second timestamp information of the target vehicle during its driving process. The perceived parking space information is used to represent the parking space location generated by perceiving the driving environment of the target vehicle, and the second timestamp information is used to represent the time labeling result corresponding to the perceived parking space information.

3. The parking space identification method according to claim 2, characterized in that, The step of analyzing gear positions based on the historical driving data to determine the candidate parking points includes: Based on the driving gear information, a gear analysis is performed to obtain a gear analysis result, wherein the gear analysis result is used to determine whether there is a reverse gear in the driving gear information. The parking behavior type corresponding to the target vehicle is determined based on the gear analysis results. The candidate parking spots are determined using the parking behavior type.

4. The parking space identification method according to claim 3, characterized in that, Determining the parking behavior type corresponding to the target vehicle based on the gear analysis results includes: Based on the gear analysis results, the response determines that there is a reverse gear in the driving gear information and determines that the parking behavior type is reverse parking. Based on the gear analysis results, the response determines that there is no reverse gear in the driving gear information, and determines that the parking behavior type is the front-in parking type.

5. The parking space identification method according to claim 4, characterized in that, The step of determining the candidate parking spot using the parking behavior type includes: In response to the parking behavior type being the reverse parking type, the driving gear information is traversed using the first gear constraint and the reverse gear to obtain the first target gear. The first gear constraint is a gear shifting rule pre-set according to the reverse parking behavior, and the first target gear is used to represent the parking end gear after the target vehicle reverses into the parking space. The first parking duration is determined based on the first timestamp information corresponding to the subsequent parking gear or neutral gear after the reverse gear is engaged. In response to the first parking duration being greater than a first preset threshold, the driving trajectory position corresponding to the first target gear is determined as the candidate parking point.

6. The parking space identification method according to claim 4, characterized in that, The step of determining the candidate parking spot using the parking behavior type includes: In response to the parking behavior type being the vehicle front-entry parking type, the driving gear information is traversed to obtain a second target gear, wherein the second target gear is used to represent the parking gear or neutral gear in the driving gear information; The driving gear information is further traversed using the second gear constraint and the second target gear to obtain the third target gear. The second gear constraint is a gear change rule preset according to the vehicle's front-end parking behavior. The third target gear is used to represent the parking end gear of the target vehicle after the front end of the vehicle enters the parking space. The second parking duration is determined based on the first timestamp corresponding to the second target gear and the first timestamp corresponding to the third target gear; In response to the second parking duration being greater than the second preset threshold, the driving trajectory position corresponding to the third target gear is determined as the candidate parking point.

7. The parking space identification method according to claim 2, characterized in that, The method of using the parking space map data to perform parking matching analysis on candidate parking points to obtain the target parking spaces includes: Based on the perceived parking space information, the candidate parking point is matched in terms of location to obtain a spatial matching result, wherein the spatial matching result is used to determine whether the candidate parking point is located within the parking space range of the perceived parking space information. The second timestamp information corresponding to the perceived parking space information is used to perform time comparison analysis on the first timestamp information corresponding to the candidate parking point to obtain a time comparison result. The time comparison result is used to determine whether the time difference between the second timestamp information and the first timestamp information corresponding to the candidate parking point is less than or equal to a third preset threshold. The candidate parking spots are filtered based on the spatial matching results and the temporal comparison results to obtain the target parking space.

8. The parking space identification method according to claim 7, characterized in that, The step of filtering the candidate parking points based on the spatial matching result and the temporal comparison result to obtain the target parking space includes: The response determines that the candidate parking point is located within the parking space range of the perceived parking space information based on the spatial matching result, and determines that the time difference is less than or equal to a third preset threshold based on the time comparison result, and identifies the candidate parking point as the target parking space.

9. A vehicle, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the parking space identification 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 parking space identification method according to any one of claims 1 to 8.

11. A computer program product, characterized in that, The computer program product includes computer instructions that, when executed by a processor, implement the parking space identification method according to any one of claims 1 to 8.

Images