Parking space recommendation method, electronic equipment and vehicle

Abstract

The invention provides a parking space recommendation method, electronic equipment and a vehicle, and is applied to the technical field of vehicle intelligent control, and the method comprises the steps: responding to a received parking request, and recognizing an unoccupied parking space; in response to determining that the plurality of unoccupied parking spaces exist, determining identification information of the plurality of unoccupied parking spaces, and determining a plurality of candidate parking spaces in the plurality of unoccupied parking spaces according to the identification information; and obtaining geometric information of all obstacles around the plurality of candidate parking spaces, determining available areas of the plurality of candidate parking spaces according to the geometric information, determining recommended parking spaces of which the available areas meet safe parking conditions in the plurality of candidate parking spaces, and displaying the recommended parking spaces. According to the invention, the parking space with the available area severely occupied by the obstacle is prevented from being selected, and the vehicle can be safely parked and driven out of the recommended parking space, so that the collision risk when the vehicle is parked and driven out of the parking space is avoided.

Description

Technical Field

[0001] The present application relates to the field of vehicle intelligent control technology, and in particular to a parking space recommendation method, electronic equipment and a vehicle. Background Art

[0002] Existing automatic parking systems usually rely on vehicle sensors (such as radar, ultrasonic sensors and cameras) to detect parking spaces and use simple algorithms to evaluate the availability of parking spaces. However, existing technologies mainly evaluate the availability of parking spaces based on their size and location, ignoring multiple influencing factors such as the risk of scratches, resulting in inaccurate parking space selection and an inability to fully evaluate the actual availability and safety of parking spaces. Summary of the invention

[0003] In view of this, the purpose of the present application is to propose a parking space recommendation method, electronic device and vehicle to avoid the risk of collision in the recommended parking space.

[0004] Based on the above purpose, this application provides a parking space recommendation method, including:

[0005] In response to receiving the parking request, identifying an available parking space;

[0006] In response to determining that there are a plurality of vacant parking spaces, determining identification information of the plurality of vacant parking spaces, and determining a plurality of candidate parking spaces from the plurality of vacant parking spaces according to the identification information;

[0007] Acquire geometric information of all obstacles around the multiple candidate parking spaces, and determine available areas of the multiple candidate parking spaces according to the geometric information;

[0008] A recommended parking space whose available area satisfies a safe parking condition is determined among the plurality of candidate parking spaces, and the recommended parking space is displayed.

[0009] Based on the same inventive concept, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method as described above when executing the computer program.

[0010] Based on the same inventive concept, the present application also provides a vehicle, which includes the above-mentioned electronic device.

[0011] As can be seen from the above, the parking space recommendation method, electronic device and vehicle provided by the present application, wherein the method includes: in response to receiving a parking request, identifying an available parking space; in response to determining that there are multiple available parking spaces, determining identification information of the multiple available parking spaces, and determining multiple candidate parking spaces from the multiple available parking spaces based on the identification information; obtaining geometric information of all obstacles around the multiple candidate parking spaces, and determining available areas of the multiple candidate parking spaces based on the geometric information, determining a recommended parking space whose available area meets the safe parking conditions from the multiple candidate parking spaces, and displaying the recommended parking space to avoid selecting a parking space whose available area is seriously occupied by obstacles, thereby ensuring that the vehicle can be safely parked in and out of the recommended parking space, thereby avoiding the risk of collision when the vehicle is parked and out of the parking space. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 The process of the parking space recommendation method of the present application embodiment Figure 1 ;

[0014] Figure 2 The process of the parking space recommendation method of the present application embodiment Figure 2 ;

[0015] Figure 3 This is a schematic diagram of a parking space recommendation device according to an embodiment of the present application;

[0016] Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0018] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0019] In the related art, with the rapid development of smart car technology, the automatic parking function has become one of the standard features of modern cars. This technology can assist the driver or complete the parking operation of the vehicle autonomously, greatly improving the convenience and safety of parking. However, in actual use, the conditions of different parking spaces vary greatly, which directly affects the effect of automatic parking and user experience. Existing automatic parking systems usually rely on vehicle sensors (such as radar, ultrasonic sensors and cameras) to detect parking spaces and use simple algorithms to evaluate the availability of parking spaces. However, these systems have the following major defects in practical applications: the existing technology mainly evaluates the availability of parking spaces by the size and location of parking spaces, ignoring multiple influencing factors such as parking space quality, parking complexity, parking complexity, and scratch risk, resulting in inaccurate parking space selection. Existing systems usually only consider a single or a few indicators, such as the width and length of the parking space, and ignore other important factors, such as the distance of obstacles around the parking space, etc., and cannot fully evaluate the actual availability and safety of the parking space, resulting in a risk of collision when the vehicle is parked and driving out of the recommended parking space.

[0020] Based on the above problems, the applicant found that: in response to receiving a parking request, an available parking space is identified; in response to determining that there are multiple available parking spaces, identification information of the multiple available parking spaces is determined, and multiple candidate parking spaces are determined from the multiple available parking spaces based on the identification information; geometric information of all obstacles around the multiple candidate parking spaces is obtained, and available areas of the multiple candidate parking spaces are determined based on the geometric information; recommended parking spaces whose available areas meet safe parking conditions are determined from the multiple candidate parking spaces, and the recommended parking spaces are displayed. By obtaining geometric information of obstacles around the parking spaces, determining the available area of ​​each candidate parking space, and judging whether the available area meets safe parking conditions, it is ensured that the vehicle can be parked and driven out safely, thereby improving parking safety. Recommending suitable parking spaces can reduce the time and effort of users in finding parking spaces and improve the convenience of parking.

[0021] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0022] This application provides a parking space recommendation method, such as Figure 1 As shown, in some embodiments, the method is executed by a vehicle controller or a data processor independently provided by the vehicle controller. The subsequent embodiments are all illustrated by taking the vehicle controller as an example; the method includes:

[0023] S101, in response to receiving a parking request, identifying an available parking space;

[0024] In practice, parking requests may be issued in different ways, such as the driver pressing a parking button, voice commands, touch screen operations, or remote commands sent through a smartphone application. Once a parking request is received, the parking space identification process is initiated, and various sensors on the vehicle, such as cameras, ultrasonic sensors, lidar, etc., are usually activated to obtain real-time information about the surrounding environment. The camera can capture images of the surrounding environment, and ultrasonic sensors and radars can measure the distance and position of surrounding objects. The environmental images captured by the camera are processed and object detection is performed using computer vision and machine learning algorithms. The object detection algorithm identifies parking space lines, vacant parking spaces, parking signs, and other relevant information in the image. The object detection algorithm can be based on deep learning models, such as convolutional neural networks (CNNs), to improve the accuracy and robustness of recognition. Determine which parking spaces are vacant, that is, parking spaces that are not occupied by other vehicles; it can also be combined with data from other sensors, such as distance information detected by ultrasonic sensors, to further confirm the vacancy status of parking spaces, thereby identifying vacant parking spaces.

[0025] S102, in response to determining that there are a plurality of vacant parking spaces, determining identification information of the plurality of vacant parking spaces, and determining a plurality of candidate parking spaces from the plurality of vacant parking spaces according to the identification information;

[0026] In specific implementation, if it is determined that there are multiple vacant parking spaces, the multiple vacant parking spaces may be distributed in different locations, with different sizes and surrounding environments. Therefore, the identification information of the vacant parking spaces is determined, including but not limited to the specific location of the vacant parking spaces in the parking lot or on the street, the confidence score (indicating the accuracy and credibility of the parking space identification), and other information. Based on the collected identification information, multiple vacant parking spaces are screened to determine suitable candidate parking spaces. For example, the parking spaces are screened based on the confidence score, and the parking spaces with high confidence scores are more likely to be real vacant parking spaces.

[0027] S103, obtaining geometric information of all obstacles around the multiple candidate parking spaces, and determining available areas of the multiple candidate parking spaces according to the geometric information;

[0028] In specific implementation, the geometric information of all obstacles around the multiple candidate parking spaces can be obtained through various sensors on the vehicle, including cameras, ultrasonic sensors, laser radar (LiDAR), etc. The camera can provide visual information, such as other vehicles, pedestrians, walls, pillars, etc. around. Ultrasonic sensors and laser radars can provide accurate distance and position data to build a three-dimensional model of the surrounding environment, thereby obtaining geometric information of obstacles, such as the shape, size, position and relative distance of the obstacles. Specifically, the geometric information may include the specific coordinates of the obstacle in three-dimensional space, the length, width and height of the obstacle, the geometric shape of the obstacle, such as rectangle, cylinder, etc., and the relative position and distance between the obstacle and the candidate parking space. Determine the available area of ​​the multiple candidate parking spaces based on the geometric information, for example, determine the outline of each obstacle based on the geometric information of the obstacle, and calculate the projection of these outlines on the ground to understand the actual impact of the obstacle on the parking space. Projection can help determine which areas are occupied by obstacles, thereby affecting the parking operation of the vehicle. For each candidate parking space, the available area of ​​the candidate parking space can be determined based on the projection information of the obstacles to evaluate whether the available area of ​​each candidate parking space meets the safe parking conditions, thereby determining the recommended parking space.

[0029] S104: Determine a recommended parking space whose available area satisfies a safe parking condition among the multiple candidate parking spaces, and display the recommended parking space.

[0030] In specific implementation, judging whether the available area meets the safe parking conditions usually includes determining whether the area of ​​the available area is large enough to accommodate the vehicle and allow safe boarding and disembarking operations; whether the distance between the available area and the surrounding obstacles is safe enough to avoid collisions between vehicles during parking. For example, when it is determined that the available area of ​​a candidate parking space includes the target area of ​​the candidate parking space (the area covered by the largest inscribed ellipse in the candidate parking space) and the area of ​​the available area is greater than or equal to the preset area (exemplarily, the preset area can be set to 90% of the area of ​​the candidate parking space), it indicates that there is an effective parking space, i.e., the target area, in the candidate parking space, and the area of ​​the candidate parking space is large enough and is not excessively occupied by other obstacles. Therefore, the candidate parking space is determined to be a recommended parking space whose available area meets the safe parking conditions. After determining that one or more recommended parking spaces are obtained, the recommended parking spaces can be recommended and displayed. There are many ways to display, for example: displaying the information of the recommended parking space on the central control display screen of the vehicle, including the location of the parking space, path guidance, etc. Provide users with information and navigation guidance of recommended parking spaces through a voice assistant. If a user sends a parking request through a smartphone application, information about the recommended parking space can be displayed in the application. Users can choose a parking space based on recommended parking spaces. After the user selects a parking space, the system will continue to provide navigation and parking assistance, or directly perform automatic parking to help the user complete the parking operation smoothly.

[0031] In this embodiment, the parking spaces are screened by confidence scores to ensure that the recommended parking spaces are real vacant parking spaces, and multiple candidate parking spaces are determined from the multiple vacant parking spaces according to the identification information of the vacant parking spaces, thereby reducing the possibility of misjudgment and wrong recommendation. By obtaining the geometric information of obstacles around the parking spaces, calculating the projection of the obstacles, determining the available area of ​​each candidate parking space, and judging whether the available area meets the safe parking conditions, it is ensured that the vehicle can be parked and driven out safely, thereby improving the safety of parking. Recommending suitable parking spaces can reduce the time and effort of users in finding parking spaces and improve the convenience of parking.

[0032] In some embodiments, Figure 2 As shown, the step of determining a recommended parking space whose available area satisfies the safe parking condition among the plurality of candidate parking spaces and displaying the recommended parking space includes:

[0033] S201, in response to determining that an available area of ​​a candidate parking space includes a target area of ​​the candidate parking space and the area of ​​the available area is greater than or equal to a preset area, determining that the candidate parking space is a recommended parking space whose available area satisfies a safe parking condition, wherein the target area is an area covered by a maximum inscribed ellipse in the candidate parking space;

[0034] In a specific implementation, firstly, the outlines of all obstacles are determined according to the geometric information of all obstacles around the candidate parking space, and the projections of the outlines of all obstacles on the ground are determined; when it is determined that the projections invade the candidate parking space, the other areas of the candidate parking space except the invaded area are determined as the available areas of the candidate parking space; when it is determined that the projections do not invade the candidate parking space, the candidate parking space and the area covered by the parking space line of the candidate parking space to the projections are determined as the available areas of the candidate parking space. The target area refers to the area covered by the largest inscribed ellipse in the candidate parking space, that is, the effective parking space in the candidate parking space. If the available area includes the target area of ​​the candidate parking space, it indicates that there are no obstacles that affect the parking of the vehicle in the effective parking space of the candidate parking space. At this time, it is also necessary to determine the area of ​​the available area. If the area of ​​the available area is greater than or equal to the preset area (exemplarily, the preset area can be set to 90% of the area of ​​the candidate parking space), it indicates that not only there are no obstacles that affect the parking of the vehicle in the effective parking space of the candidate parking space, but also there are no obstacles that invade the candidate parking space with a large area in the corners of the candidate parking space. The vehicle can be parked safely, and the candidate parking space is determined to be a recommended parking space whose available area meets the safe parking conditions.

[0035] S202: Determine at least one recommended parking space obtained, and display the recommended parking space.

[0036] In specific implementation, when one or more recommended parking spaces are determined, the recommended parking spaces are displayed, for example, information about the recommended parking spaces, including the location of the parking spaces, path guidance, etc., is displayed on the central control display screen of the vehicle. Information about recommended parking spaces and navigation guidance are provided to users through a voice assistant. If a user sends a parking request through a smartphone application, information about recommended parking spaces can be displayed in the application. Users can select a parking space based on the recommended parking spaces for parking. After the user selects a parking space, navigation and parking assistance continue to be provided, or automatic parking is performed directly to help the user successfully complete the parking operation.

[0037] In this embodiment, by determining the outline of the obstacle and its ground projection, the available area in the parking space can be accurately identified to avoid selecting a parking space that is partially occupied by an obstacle. The target area of ​​the parking space is defined by using the largest inscribed ellipse to ensure that there is enough barrier-free space in the parking space for parking operations, and the parking space suitable for safe parking can be effectively screened out. By judging whether the area of ​​the available area is greater than or equal to the preset area, it can be ensured that the recommended parking space not only has no obstacles in the target area, but also has no significant obstacle encroachment in the entire parking space, thereby improving parking safety.

[0038] In some embodiments, determining available areas of a plurality of candidate parking spaces according to the geometric information includes:

[0039] For each candidate parking space among the plurality of candidate parking spaces,

[0040] Determine the outlines of all obstacles based on the geometric information of all obstacles around the candidate parking space, and determine the projections of the outlines of all obstacles on the ground.

[0041] In specific implementation, the outline of each obstacle is determined based on the acquired geometric information. The outline refers to the boundary line or boundary surface of the obstacle in three-dimensional space. For example, for a rectangular column, the outline may be four sides; for a cylindrical obstacle, the outline may be a circular boundary; the outline of the obstacle is projected onto the ground to determine the actual area occupied by the obstacle on the ground. The projection on the ground usually refers to the projection of the outline of the obstacle on the horizontal plane. For example, for a vertical column, its ground projection is the bottom area of ​​the column; for an inclined obstacle, its ground projection may be an irregular shape. The purpose of calculating the projection on the ground is to understand the space occupied by the obstacle on the ground, so as to evaluate its impact on the candidate parking space. In a real environment, there may be multiple obstacles around the candidate parking space. It is necessary to comprehensively consider the projections of all obstacles to determine the final available area.

[0042] In response to determining that the projection intrudes into the candidate parking space, determining other areas of the candidate parking space except the intruded area as available areas of the candidate parking space,

[0043] In the specific implementation, first detect and confirm whether the projection of the obstacle invades the range of the candidate parking space. Once the projection is detected to invade the candidate parking space, determine the specific area covered by the projection. The intrusion area refers to the part of the obstacle projection within the candidate parking space. The intrusion area cannot be used for parking because it may cause a vehicle collision or fail to park smoothly due to being occupied by an obstacle. The intrusion area in the candidate parking space is excluded, and the remaining part is used as the available area. If the position of the obstacle changes or a new obstacle appears, the evaluation result of the available area needs to be dynamically adjusted.

[0044] In response to determining that the projection does not intrude into the candidate parking space, the candidate parking space and an area covered between a parking space line of the candidate parking space and the projection are determined as an available area of ​​the candidate parking space.

[0045] In specific implementation, the non-invasion state means that the ground projection of the obstacle is completely outside the candidate parking space and does not cover any part of the parking space. If it is detected that the projection does not intrude the parking space, the area between the parking space line of the candidate parking space and the obstacle projection is confirmed. This area is usually a buffer zone around the candidate parking space, which can provide additional space to ensure that the vehicle has enough room for maneuver when parking and exiting. The available area includes the entire candidate parking space and the area between the parking space line and the projection, indicating that the vehicle can not only be safely parked in the parking space, but also use the buffer zone around the parking space for parking operations, while avoiding the risk of collision with the vehicle next to it.

[0046] In this embodiment, by determining the outline of the obstacle and its projection on the ground, the actual impact of each obstacle on the candidate parking space can be accurately identified to avoid misjudgment and misrecommendation. By identifying and excluding the area occupied by the obstacle, it can be ensured that the recommended parking space is not occupied by the obstacle, reducing the risk of collision during parking. In the case where the obstacle projection does not invade the parking space, the area between the parking space line and the projection is also used as an available area to provide additional operating space, ensuring that the vehicle has enough room when parking and exiting, further improving the safety of parking.

[0047] In some embodiments, displaying the recommended parking space includes:

[0048] In response to determining that there are a plurality of recommended parking spaces, determining areas of available areas of the plurality of recommended parking spaces;

[0049] The multiple recommended parking spaces are sorted and displayed in descending order according to the area of ​​the available areas.

[0050] In the specific implementation, because multiple recommended parking spaces that meet the safe parking conditions have been screened out, it is necessary to calculate the area of ​​the available area of ​​each recommended parking space. Obtain the boundary information of the available area and use a geometric algorithm to calculate the area of ​​the available area. For areas with complex shapes, a polygonal area calculation method can be used. Sort according to the available area of ​​each recommended parking space. The sorting standard is from large to small, that is, the parking spaces with larger areas are ranked in front, that is, a list containing parking space identification and available area is generated for each recommended parking space, and the list is sorted using a sorting algorithm (such as quick sort, merge sort, etc.) and arranged in order from large to small. When the sorting is completed, the sorted recommended parking space information needs to be displayed to the user. The user can select a parking space for parking based on the sorted recommended parking space information, such as giving priority to the recommended parking space with the largest available area. The larger the area of ​​the available area, the easier it is for the vehicle to park in the recommended parking space, and the lower the risk of being hit by other vehicles. The available area of ​​each recommended parking space is comprehensively considered to provide more accurate and safe parking space recommendations. Not only the accuracy and safety of parking space selection are improved, but also the user's parking experience and convenience are improved.

[0051] In this embodiment, by calculating and sorting the available area of ​​the recommended parking spaces, those parking spaces with larger available area can be displayed first. This ensures that users can first see and select parking spaces with lower parking difficulty and more space, thereby improving the accuracy of parking space selection. Parking spaces with larger available area usually mean fewer obstacles and more operating space. Displaying these parking spaces first can help users quickly find the best parking location.

[0052] In some embodiments, identifying an available parking space includes:

[0053] Acquire an environmental image of the vehicle, and perform target detection on the environmental image;

[0054] In the specific implementation, the vehicle's environmental image is obtained. The environmental image can be obtained by a camera installed on the vehicle. The vehicle is usually equipped with multiple cameras, covering the front, back, left and right perspectives to provide comprehensive environmental information. The environmental image includes the actual scene of the parking lot or roadside. The environmental image is the basic data for target detection and parking space recognition. Target detection is performed on the acquired environmental image to identify the parking space and other related targets (such as vehicles, pedestrians, obstacles, etc.) in the environmental image; target detection usually uses computer vision and deep learning algorithms, such as convolutional neural network (CNN), regional convolutional neural network (R-CNN), YOLO (You Only Look Once), etc. The specific steps include preprocessing the environmental image, such as denoising, normalization, etc., to improve image quality and detection accuracy, extracting features from the image using a deep learning model, identifying the bounding boxes of parking spaces and other targets, classifying the extracted features, and determining the target type (such as parking spaces, vehicles, pedestrians, etc.) in each bounding box. Detecting parking spaces in the environmental image includes identifying the boundary lines and parking space markings (such as parking lines, parking signs, etc.) of the parking space. After detecting the parking space, it is necessary to further detect whether there is a vehicle in the parking space and determine the vehicle's bounding box in order to further determine the vehicle's location and occupancy status.

[0055] In response to detecting a parking space and no vehicle being present in the parking space, determining the parking space as a vacant parking space.

[0056] In specific implementation, if no vehicle is detected in the parking area, the parking space will be marked as a vacant parking space, and the location, boundary and other relevant information of the vacant parking space will be recorded for subsequent recommendation and display. It is also necessary to update the detection results of vacant parking spaces in real time to cope with the dynamic changes in the parking environment. By accurately identifying and detecting vacant parking spaces, the environmental image and target detection results are comprehensively considered to provide more accurate and timely parking space recommendations. Improve the adaptability and user experience in complex parking environments.

[0057] In this embodiment, by accurately detecting whether a parking space is occupied, it is ensured that the recommended parking space is a real vacant parking space, reducing the risk of collision or scratch during parking. Other relevant targets (such as vehicles, pedestrians, obstacles, etc.) in the environmental image are identified, and environmental factors are comprehensively considered to ensure the safety of parking.

[0058] In some embodiments, the recognition information includes a confidence score of the target detection identifying the vacant parking space; and determining a plurality of candidate parking spaces from the plurality of vacant parking spaces according to the recognition information includes:

[0059] In response to determining that a confidence score of identifying an empty parking space is greater than or equal to a first preset confidence score, determining the empty parking space as a candidate parking space;

[0060] In specific implementation, the confidence score refers to the credibility score of the detection result given by the target detection algorithm, which is usually between 0 and 1. The higher the score, the greater the confidence in the detection result. In parking space detection, the confidence score is used to evaluate the accuracy of the judgment on whether a parking space is vacant. Two confidence thresholds are preset: a first preset confidence score and a second preset confidence score. The first preset confidence score (higher) is used to determine vacant parking spaces with high confidence, and the second preset confidence score (lower) is used to determine parking spaces that need further evaluation. For example, the first preset confidence score can be set to 0.9, and the second preset confidence score can be set to 0.7. After detecting the vacant parking space, the target detection algorithm will output the confidence score of each detection result, and the confidence score is based on the algorithm's analysis of the image features and the prediction results of the model. If the confidence score of a vacant parking space is greater than or equal to the first preset confidence score, the vacant parking space is considered to be a highly credible vacant parking space and is determined as a candidate parking space.

[0061] In response to determining that the confidence score of identifying an empty parking space is greater than or equal to a second preset confidence score and less than the first preset confidence score, determining the empty parking space as a parking space to be evaluated; wherein the first preset confidence score is greater than the second preset confidence score;

[0062] In specific implementation, if the confidence score of a vacant parking space is greater than or equal to the second preset confidence score but less than the first preset confidence score, it indicates that the vacant parking space may be obscured or the parking space line is not obvious, but its confidence score is still high. In this case, the vacant parking space needs further evaluation to confirm whether it is truly suitable for parking, and the vacant parking space is determined to be a parking space to be evaluated.

[0063] In response to determining that there are a plurality of parking spaces to be evaluated, a plurality of candidate parking spaces are determined from the plurality of parking spaces to be evaluated.

[0064] In specific implementation, when it is determined that there are multiple parking spaces to be evaluated, the parking spaces to be evaluated are further evaluated to determine whether they can be used as candidate parking spaces. A comprehensive evaluation can be conducted in combination with data from other sensors (such as ultrasonic sensors, lidar, etc.), or historical parking data and parking space usage can be used for analysis. In some cases, manual confirmation or user feedback may be required to assist in the evaluation. After further evaluation, eligible parking spaces to be evaluated will also be identified as candidate parking spaces. Through the confidence score based on target detection, vacant parking spaces are accurately identified and evaluated, thereby providing more accurate and safe parking space recommendations. This process not only improves the accuracy and safety of parking space selection, but also improves the user's parking experience and convenience.

[0065] In this embodiment, by using the confidence score of the target detection algorithm, the credibility of each vacant parking space can be evaluated to ensure that only parking spaces with high confidence are recommended, reducing the possibility of misjudgment and wrong recommendation. The first preset confidence score and the second preset confidence score are set to distinguish between highly reliable vacant parking spaces and parking spaces that need further evaluation, providing a multi-level screening mechanism to ensure the accuracy of parking space selection. For parking spaces with high confidence scores but not reaching the highest threshold, further evaluation is performed to ensure that these parking spaces are fully verified before recommendation, thereby improving parking safety.

[0066] In some embodiments, determining a plurality of candidate parking spaces from the plurality of parking spaces to be evaluated includes:

[0067] Determine the distances between the multiple parking spaces to be evaluated and the entrance and exit of the parking lot,

[0068] In specific implementation, the location information of the parking lot entrance and exit can be obtained by determining the location information of the parking lot entrance and exit through map data, or by obtaining the location information of the parking lot entrance and exit through vehicle sensors; the location information of the entrance and exit can include specific coordinate points, indicating the entrance and exit positions of the parking lot, and calculating the distance between each parking space to be evaluated and the parking lot entrance and exit. Distance calculation can be based on geometric algorithms, such as using the Euclidean distance formula to calculate the straight-line distance, or using a path planning algorithm to calculate the driving distance in a complex parking lot environment.

[0069] In response to determining that a distance between a parking space to be evaluated and an entrance or exit of the parking lot is greater than or equal to a preset distance, the parking space to be evaluated is determined to be a candidate parking space.

[0070] In specific implementation, if it is determined that the distance between a parking space to be evaluated and the entrance and exit of the parking lot is greater than or equal to the preset distance (for example, the preset distance can be set to 20 meters), it indicates that the parking space to be evaluated is far from the entrance and exit of the parking lot. Since the traffic volume at the entrance and exit of the parking lot is large, there is a risk of vehicle collision. Therefore, when the parking space to be evaluated is far from the entrance and exit of the parking lot, it indicates that the parking space to be evaluated is more suitable for parking, and the parking space to be evaluated is determined as a candidate parking space. By further screening and determining the candidate parking spaces based on the distance between the parking space to be evaluated and the entrance and exit of the parking lot, a more accurate and safe parking space recommendation is provided. Not only the accuracy and safety of parking space selection are improved, but also the parking experience and convenience of users are improved.

[0071] In this embodiment, by calculating the distance between each parking space to be evaluated and the parking lot entrance and exit, parking spaces that are farther away from the entrance and exit can be screened out. The parking lot entrance and exit usually have a large volume of traffic. Selecting a parking space that is farther away from the entrance and exit can reduce the risk of collision when vehicles enter and exit, thereby improving parking safety.

[0072] In some embodiments, determining a plurality of candidate parking spaces from the plurality of parking spaces to be evaluated includes:

[0073] Determine the width of the lanes next to the plurality of parking spaces to be evaluated,

[0074] In specific implementation, the width information of the lane next to the parking space to be evaluated can be obtained through sensor data or map data. Lane width refers to the width of the lane or passage next to the parking space. The width of the lane affects the convenience and safety of vehicles entering and exiting the parking space. The lane width can be measured through sensor data (such as lidar, ultrasonic sensor, etc.) or queried through map data.

[0075] In response to determining that a width of a lane adjacent to a parking space to be evaluated is greater than or equal to a preset width, the parking space to be evaluated is determined to be a candidate parking space.

[0076] In specific implementation, if it is determined that the width of the lane next to a parking space to be evaluated is greater than or equal to the preset width (the preset width can be set based on factors such as the specific layout of the parking lot, the type of vehicle, and the user's parking preference. For example, the preset width can be set to 3 meters to ensure that the lane is wide enough for vehicles to enter and exit the parking space), it indicates that the lane is spacious, easy to enter and exit, and safe. Therefore, the parking space to be evaluated is determined as a candidate parking space. Based on the width of the lane next to the parking space to be evaluated, the candidate parking space is further screened and determined, thereby providing a more accurate and safe parking space recommendation. Not only does it improve the accuracy and safety of parking space selection, but it also improves the user's parking experience and convenience.

[0077] In this embodiment, by measuring and evaluating the width of the lanes next to the parking spaces to be evaluated, parking spaces with spacious lanes can be screened out, ensuring that the recommended parking spaces are convenient for vehicles to enter and exit, thereby improving the accuracy of parking space selection. Parking spaces with spacious lanes provide more operating space, and vehicles have more room to enter and exit the parking spaces, reducing the risk of collision with surrounding vehicles or obstacles, and improving parking safety.

[0078] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0079] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a parking space recommendation device.

[0081] refer to Figure 3 , the parking space recommendation device comprises:

[0082] an identification module 701 configured to identify an available parking space in response to receiving a parking request;

[0083] A first determination module 702 is configured to, in response to determining that there are a plurality of vacant parking spaces, determine identification information of the plurality of vacant parking spaces, and determine a plurality of candidate parking spaces from the plurality of vacant parking spaces according to the identification information;

[0084] A second determination module 703 is configured to obtain geometric information of all obstacles around the plurality of candidate parking spaces, and determine available areas of the plurality of candidate parking spaces according to the geometric information;

[0085] The recommendation module 704 is configured to determine a recommended parking space whose available area meets the safe parking condition among the plurality of candidate parking spaces, and display the recommended parking space.

[0086] Furthermore, the recommendation module 704 is specifically used for:

[0087] In response to determining that an available area of ​​a candidate parking space includes a target area of ​​the candidate parking space and the area of ​​the available area is greater than or equal to a preset area, determining the candidate parking space as a recommended parking space whose available area satisfies a safe parking condition, wherein the target area is an area covered by a maximum inscribed ellipse in the candidate parking space;

[0088] The at least one recommended parking space obtained is determined, and the recommended parking space is displayed.

[0089] Further, the second determining module 703 is specifically used for:

[0090] For each candidate parking space among the plurality of candidate parking spaces,

[0091] Determine the outlines of all obstacles based on the geometric information of all obstacles around the candidate parking space, and determine the projections of the outlines of all obstacles on the ground.

[0092] In response to determining that the projection intrudes into the candidate parking space, determining other areas of the candidate parking space except the intruded area as available areas of the candidate parking space,

[0093] In response to determining that the projection does not intrude into the candidate parking space, the candidate parking space and an area covered between a parking space line of the candidate parking space and the projection are determined as an available area of ​​the candidate parking space.

[0094] Furthermore, the recommendation module 704 is further configured to:

[0095] In response to determining that there are a plurality of recommended parking spaces, determining areas of available areas of the plurality of recommended parking spaces;

[0096] The multiple recommended parking spaces are sorted and displayed in descending order according to the area of ​​the available areas.

[0097] Further, the identification module 701 is specifically used for:

[0098] Acquire an environmental image of the vehicle, and perform target detection on the environmental image;

[0099] In response to detecting a parking space and no vehicle being present in the parking space, determining the parking space as a vacant parking space.

[0100] Further, the first determining module 702 is specifically configured to:

[0101] In response to determining that a confidence score of identifying an empty parking space is greater than or equal to a first preset confidence score, determining the empty parking space as a candidate parking space;

[0102] In response to determining that the confidence score of identifying an empty parking space is greater than or equal to a second preset confidence score and less than the first preset confidence score, determining the empty parking space as a parking space to be evaluated; wherein the first preset confidence score is greater than the second preset confidence score;

[0103] In response to determining that there are a plurality of parking spaces to be evaluated, a plurality of candidate parking spaces are determined from the plurality of parking spaces to be evaluated.

[0104] Furthermore, the first determining module 702 is further configured to:

[0105] Determine the distances between the multiple parking spaces to be evaluated and the entrance and exit of the parking lot,

[0106] In response to determining that a distance between a parking space to be evaluated and an entrance or exit of the parking lot is greater than or equal to a preset distance, the parking space to be evaluated is determined to be a candidate parking space.

[0107] Furthermore, the first determining module 702 is further configured to:

[0108] Determine the width of the lanes next to the plurality of parking spaces to be evaluated,

[0109] In response to determining that a width of a lane adjacent to a parking space to be evaluated is greater than or equal to a preset width, the parking space to be evaluated is determined to be a candidate parking space.

[0110] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0111] The device of the above embodiment is used to implement the corresponding parking space recommendation method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0112] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the parking space recommendation method described in any of the above embodiments is implemented.

[0113] Figure 4 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0114] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0115] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0116] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0117] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0118] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0119] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0120] The electronic device of the above embodiment is used to implement the corresponding parking space recommendation method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0121] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the parking space recommendation method described in any of the above embodiments.

[0122] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0123] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the parking space recommendation method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0124] Based on the same concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the method described in any of the above embodiments, which has the beneficial effects of the corresponding method embodiments and will not be repeated here.

[0125] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0126] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0127] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0128] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0129] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0130] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0131] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0132] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A parking space recommendation method, characterized in that: include: In response to receiving the parking request, identifying an available parking space; In response to determining that there are a plurality of vacant parking spaces, determining identification information of the plurality of vacant parking spaces, and determining a plurality of candidate parking spaces from the plurality of vacant parking spaces according to the identification information; Acquire geometric information of all obstacles around the multiple candidate parking spaces, and determine available areas of the multiple candidate parking spaces according to the geometric information; A recommended parking space whose available area satisfies a safe parking condition is determined among the plurality of candidate parking spaces, and the recommended parking space is displayed.

2. The parking space recommendation method according to claim 1, characterized in that: The step of determining a recommended parking space whose available area satisfies the safe parking condition among the plurality of candidate parking spaces, and displaying the recommended parking space, comprises: In response to determining that an available area of ​​a candidate parking space includes a target area of ​​the candidate parking space and the area of ​​the available area is greater than or equal to a preset area, determining the candidate parking space as a recommended parking space whose available area satisfies a safe parking condition, wherein the target area is an area covered by a maximum inscribed ellipse in the candidate parking space; The at least one recommended parking space obtained is determined, and the recommended parking space is displayed.

3. The parking space recommendation method according to claim 1, characterized in that: The step of determining available areas of a plurality of candidate parking spaces according to the geometric information includes: For each candidate parking space among the plurality of candidate parking spaces, Determine the outlines of all obstacles based on the geometric information of all obstacles around the candidate parking space, and determine the projections of the outlines of all obstacles on the ground. In response to determining that the projection intrudes into the candidate parking space, determining other areas of the candidate parking space except the intruded area as available areas of the candidate parking space, In response to determining that the projection does not intrude into the candidate parking space, the candidate parking space and an area covered between a parking space line of the candidate parking space and the projection are determined as an available area of ​​the candidate parking space.

4. The parking space recommendation method according to claim 1, characterized in that: The displaying of the recommended parking space includes: In response to determining that there are a plurality of recommended parking spaces, determining areas of available areas of the plurality of recommended parking spaces; The multiple recommended parking spaces are sorted and displayed in descending order according to the area of ​​the available areas.

5. The parking space recommendation method according to claim 1, characterized in that: The identifying of vacant parking spaces includes: Acquire an environmental image of the vehicle, and perform target detection on the environmental image; In response to detecting a parking space and no vehicle being present in the parking space, determining the parking space as a vacant parking space.

6. The parking space recommendation method according to claim 5, characterized in that: The identification information includes a confidence score of the target detection identifying an empty parking space; The determining a plurality of candidate parking spaces from the plurality of vacant parking spaces according to the identification information comprises: In response to determining that a confidence score of identifying an empty parking space is greater than or equal to a first preset confidence score, determining the empty parking space as a candidate parking space; In response to determining that the confidence score of identifying an empty parking space is greater than or equal to a second preset confidence score and less than the first preset confidence score, determining the empty parking space as a parking space to be evaluated; wherein the first preset confidence score is greater than the second preset confidence score; In response to determining that there are a plurality of parking spaces to be evaluated, a plurality of candidate parking spaces are determined from the plurality of parking spaces to be evaluated.

7. The parking space recommendation method according to claim 6, characterized in that: The determining of a plurality of candidate parking spaces from the plurality of parking spaces to be evaluated comprises: Determine the distances between the multiple parking spaces to be evaluated and the entrance and exit of the parking lot, In response to determining that a distance between a parking space to be evaluated and an entrance or exit of the parking lot is greater than or equal to a preset distance, the parking space to be evaluated is determined to be a candidate parking space.

8. The parking space recommendation method according to claim 6, characterized in that: The determining of a plurality of candidate parking spaces from the plurality of parking spaces to be evaluated comprises: Determine the width of the lanes next to the plurality of parking spaces to be evaluated, In response to determining that a width of a lane adjacent to a parking space to be evaluated is greater than or equal to a preset width, the parking space to be evaluated is determined to be a candidate parking space.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

10. A vehicle, characterized in that: The vehicle comprises the electronic device as claimed in claim 9.

Images