Parking method and apparatus, and vehicle

Abstract

A parking method, comprising: acquiring data collected by a sensor of a vehicle (S410); on the basis of the data, determining a first vehicle body feature of another vehicle around the vehicle (S420); on the basis of the first vehicle body feature, determining position information and a vehicle body contour of the another vehicle (S430); and on the basis of the position information and the vehicle body contour of the another vehicle, controlling the vehicle to perform auto parking (S440). Also provided are a parking apparatus, a vehicle, a computer readable storage medium, a computer program product and a chip. The parking method can be applied to an intelligent vehicle or an electric vehicle to prevent the vehicle from scraping against another vehicle, thereby facilitating the improvement of the safety of the vehicle during auto parking.

Description

Parking methods, devices and vehicles

[0001] This application claims priority to Chinese Patent Application No. 202410517952.4, filed on April 24, 2024, entitled "Parking Method, Apparatus and Vehicle", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of intelligent driving, and more specifically, to a parking method, apparatus, and vehicle. Background Technology

[0003] Automated parking (AP) refers to the automatic parking of a vehicle, meaning that an autonomous driving system can semi-automatically or fully automatically help the user park the vehicle in a parking space. Automated parking can include automated parking assist (APA), remote parking assist (RPA), and automated valet parking (AVP), among others.

[0004] Currently, vehicles interact with other obstacles during automatic parking. Ensuring vehicle safety during this process has become a pressing issue. Summary of the Invention

[0005] This application provides a parking method, apparatus, and vehicle that helps improve vehicle safety during automatic parking.

[0006] In a first aspect, a parking method is provided, the method comprising: acquiring data collected by sensors of a vehicle; determining first body features of other vehicles around the vehicle based on the data; determining the position information and body outline of the other vehicles based on the first body features; and controlling the vehicle to perform automatic parking based on the position information and body outline of the other vehicles.

[0007] Based on the above technical solution, the position information and body contours of other vehicles are determined by the vehicle's body features. Then, based on the position information and body contours of other vehicles, the vehicle is controlled to perform automatic parking. In this way, collision detection or scratch prevention detection can be achieved during the parking process using the position information and body contours of other vehicles, avoiding collisions or scratches and improving the safety of the vehicle during automatic parking.

[0008] In some possible implementations, the vehicle performs automatic parking via APA or RPA functions. Before determining the first body features of other vehicles around the vehicle based on the data, the method further includes: determining that the target parking space for the vehicle is a narrow parking space.

[0009] In some possible implementations, the vehicle performs automatic parking via AVP (Automatic Parking) function, and the method further includes determining that the vehicle is passing through a narrow passage before determining the first body features of other vehicles around the vehicle based on the data.

[0010] For example, the narrow passage can be the difference between the width of the vehicle and the sum of the widths of the other vehicles and the width of the narrow passage, which is less than or equal to a preset difference.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, determining the first body feature of other vehicles around the vehicle based on the data includes: determining multiple body features based on the data, the multiple body features including the first body feature; clustering the multiple body features to obtain a clustering result, the clustering result including the association between the first body feature and the other vehicles.

[0012] Based on the above technical solution, multiple vehicle body features can be obtained from the data collected by sensors. By clustering these features, the vehicle body features of other vehicles can be obtained. This enables collision detection or scratch prevention between the vehicle and other vehicles, avoiding collisions or scratches and improving vehicle safety during automatic parking.

[0013] In some possible implementations, multiple vehicle body features are determined based on the data, including: inputting the data into a prediction model to obtain the multiple features, wherein the prediction model is trained on a training dataset, which includes sample data collected by sample sensors and the semantics of the vehicle body features in the labeled sample data and the association between feature points (or feature lines).

[0014] In conjunction with the first aspect, in some implementations of the first aspect, the first vehicle body feature includes at least two of the license plate, headlights, rearview mirrors, and wheels of the other vehicle. The step of determining the position information and vehicle body outline of the other vehicle based on the first vehicle body feature includes: splicing the first vehicle body feature to obtain a splicing result; determining the vehicle body outline of the other vehicle based on the splicing result; and determining the position information of the other vehicle based on the relative positional relationship between the first vehicle body feature and the vehicle.

[0015] Based on the above technical solution, after obtaining the body features of each vehicle around the vehicle, the body features of each vehicle can be spliced ​​together to obtain the body outline of each vehicle.

[0016] In some possible implementations, determining the position information of the other vehicle based on the relative positional relationship between the first body feature and the vehicle includes: determining the absolute position of the other vehicle based on the absolute position of the vehicle and the relative positional relationship between the first body feature and the vehicle.

[0017] In some possible implementations, the first vehicle body feature includes a license plate feature, which includes a license plate color. Based on the splicing result, the vehicle body outline of the other vehicle is determined, including: determining the vehicle body outline of the other vehicle based on the splicing result; verifying the vehicle body outline based on the license plate color indicated by the license plate feature; and outputting the vehicle body outline of the other vehicle when the vehicle body outline matches the license plate color.

[0018] In some possible implementations, the first vehicle body feature includes a license plate feature, which includes a license plate color. Determining the vehicle body outline of the other vehicle based on the splicing result includes: determining the vehicle body outline of the other vehicle based on the splicing result; verifying the vehicle body outline based on the license plate color indicated by the license plate feature; acquiring another data collected by the sensor when the vehicle body outline does not match the license plate color; determining a second vehicle body feature of the other vehicle based on the other data; determining another vehicle body outline of the other vehicle based on the second vehicle body feature; verifying the other vehicle body outline based on the license plate color indicated by the license plate feature; and outputting the other vehicle body outline when the other vehicle body outline matches the license plate color.

[0019] Based on the above technical solution, the vehicle can verify the body outline determined by data collected from sensors based on the license plate color. For example, if the license plate is yellow and the body outline is approximately rectangular, then the license plate color matches the body outline. Furthermore, collision detection or anti-scratch detection can be performed based on the body outlines of other vehicles, which helps to further improve the safety of the vehicle during automatic parking.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, before acquiring the data collected by the vehicle's sensors, the method further includes: determining that the vehicle and the other vehicle are about to meet on the road.

[0021] Based on the above technical solution, when a vehicle is about to meet another vehicle, it can trigger the detection of the other vehicle's position information and body outline, thereby avoiding collisions or scrapes when the vehicle meets another vehicle.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, before acquiring the data collected by the vehicle's sensors, the method further includes: determining that the other vehicle has entered the vehicle's blind spot.

[0023] Based on the above technical solution, when other vehicles enter the blind spot of the vehicle, the vehicle can detect the position information and body outline of other vehicles, thereby avoiding collisions or scrapes between other vehicles in the blind spot.

[0024] In conjunction with the first aspect, in some implementations of the first aspect, controlling the vehicle to perform automatic parking based on the location information and vehicle body outline of the other vehicle includes: controlling the vehicle to stop automatic parking when it is determined based on the location information and vehicle body outline that the collision risk between the other vehicle and the vehicle meets preset conditions, or replanning the parking trajectory.

[0025] Based on the above technical solution, when the collision risk between a vehicle and other vehicles meets preset conditions based on the location information and vehicle body contours of other vehicles, the vehicle can be controlled to stop automatic parking or replan the parking trajectory. This can prevent collisions or scrapes between the vehicle and other vehicles.

[0026] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: controlling the display device to display the distance between the vehicle and the other vehicle.

[0027] In some possible implementations, the control display device displays the distance between the vehicle and other vehicles, including: when the distance between the vehicle and other vehicles is less than a preset distance, the control display device displays the distance.

[0028] In conjunction with the first aspect, in some implementations of the first aspect, the sensor includes a fisheye camera and / or lidar.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, determining the first body features of other vehicles around the vehicle based on the data includes: inputting the data into a trained model to obtain the first body features.

[0030] In some possible implementations, the trained model is trained on a training dataset that includes sample data collected by sensors and labeled vehicle body features (e.g., feature points or feature lines) in the sample data.

[0031] Secondly, a parking device is provided, comprising: an acquisition unit for acquiring data collected by sensors of a vehicle; a first determination unit for determining first body features of other vehicles around the vehicle based on the data; a second determination unit for determining the position information and body outline of the other vehicles based on the first body features; and a control unit for controlling the vehicle to perform automatic parking based on the position information and body outline of the other vehicles.

[0032] In conjunction with the second aspect, in some implementations of the second aspect, the first determining unit is specifically used for: determining multiple vehicle body features based on the data, the multiple vehicle body features including the first vehicle body feature; clustering the multiple vehicle body features to obtain a clustering result, the clustering result including the association relationship between the first vehicle body feature and the other vehicles.

[0033] In conjunction with the second aspect, in some implementations of the second aspect, the first vehicle body feature includes at least two of the license plate, headlights, rearview mirrors, and wheels of the other vehicle. The second determining unit is specifically used to: splice the first vehicle body feature to obtain a splicing result; determine the vehicle body outline of the other vehicle based on the splicing result and determine the position information of the other vehicle based on the relative positional relationship between the first vehicle body feature and the vehicle.

[0034] In conjunction with the second aspect, in some implementations of the second aspect, the device further includes: a third determining unit for determining that the vehicle and the other vehicle are about to meet on the road.

[0035] In conjunction with the second aspect, in some implementations of the second aspect, the device further includes: a fourth determining unit for determining when the other vehicle enters the blind spot of the vehicle.

[0036] In conjunction with the second aspect, in some implementations of the second aspect, the control unit is specifically used to: control the vehicle to stop automatic parking or replan the parking trajectory when it is determined, based on the location information and the vehicle body outline, that the collision risk between the other vehicle and the vehicle meets preset conditions.

[0037] In conjunction with the second aspect, in some implementations of the second aspect, the control unit is also used to: control the display device to display the distance between the vehicle and the other vehicle.

[0038] In conjunction with the second aspect, in some implementations of the second aspect, the sensor includes a fisheye camera and / or lidar.

[0039] In conjunction with the second aspect, in some implementations of the second aspect, the first determining unit is specifically used to: input the data into the trained model to obtain the first vehicle body feature.

[0040] Thirdly, this application provides a parking device including a processor and a memory, wherein the memory is used to store instructions, and the processor executes the instructions stored in the memory to cause the device to perform any of the possible methods in the first aspect.

[0041] Fourthly, this application provides a vehicle that includes any of the possible devices of the second or third aspect.

[0042] Fifthly, this application provides a computer program product comprising: computer program code, which, when run on a computer, causes the computer to perform any of the possible methods described in the first aspect above.

[0043] It should be noted that the above-mentioned computer program code can be stored in whole or in part on the first storage medium, wherein the first storage medium can be packaged together with the processor or packaged separately from the processor. This application embodiment does not specifically limit this.

[0044] In a sixth aspect, this application provides a computer-readable storage medium storing computer program code that, when executed on a computer, causes the computer to perform any of the possible methods described in the first aspect above.

[0045] In a seventh aspect, this application provides a chip system including a processor for calling a computer program or computer instructions stored in a memory to cause the processor to perform any of the possible methods in the first aspect above.

[0046] In conjunction with the seventh aspect, in one possible implementation, the processor is coupled to the memory via an interface.

[0047] In conjunction with the seventh aspect, in one possible implementation, the chip system further includes a memory in which computer programs or computer instructions are stored.

[0048] Eighthly, this application provides a chip system including circuitry for performing any of the possible methods described in the first aspect above. Attached Figure Description

[0049] Figure 1 is a functional block diagram of the vehicle provided in an embodiment of this application;

[0050] Figure 2 is a schematic diagram of the system architecture provided in an embodiment of this application;

[0051] Figure 3 is a schematic flowchart of the parking method provided in an embodiment of this application;

[0052] Figure 4 is another schematic flowchart of the parking method provided in the embodiments of this application;

[0053] Figure 5 is a schematic diagram of the application scenario provided in the embodiments of this application;

[0054] Figure 6 is a schematic diagram of a narrow parking space provided in an embodiment of this application;

[0055] Figure 7 is a graphical user interface provided in an embodiment of this application;

[0056] Figure 8 is a schematic block diagram of a parking device provided in an embodiment of this application. Detailed Implementation

[0057] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B; "and / or" in this document is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. "At least one" refers to one or more. For example, "at least one of A and B," similar to "A and / or B," describes the association relationship between related objects, indicating that three relationships can exist. For example, at least one of A and B can represent: A existing alone, A and B existing simultaneously, and B existing alone.

[0058] The prefixes such as "first" and "second" used in this application embodiment are merely for distinguishing different descriptive objects and do not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes used to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. The description of the described objects is given in the claims or the context of the embodiments, and should not constitute unnecessary restrictions due to the use of such prefixes. Furthermore, in the description of this embodiment, unless otherwise stated, "multiple" means two or more.

[0059] Figure 1 is a functional block diagram of a vehicle 100 provided in an embodiment of this application. The vehicle 100 may include a sensing system 110, a computing platform 120, and a display device 130. The sensing system 110 may include one or more sensors for sensing information about the environment surrounding the vehicle 100. For example, the sensing system 110 may include a positioning system, which may be a Global Positioning System (GPS), a BeiDou Navigation Satellite System, or another positioning system. As another example, the sensing system 110 may include one or more of the following: an inertial measurement unit (IMU), an accelerometer, a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0060] Some or all of the functions of vehicle 100 can be controlled by computing platform 120. Computing platform 120 may include one or more processors, such as processors 121 to 12n (n being a positive integer). A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In reconfigurable hardware circuits, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement some or all of the functions of the aforementioned units. Furthermore, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. In addition, the computing platform 120 may also include a memory for storing instructions. Some or all of the processors 121 to 12n can call the instructions in the memory to implement the corresponding functions.

[0061] The in-cabin display devices 130 are mainly divided into two categories: the first is the in-vehicle display screen; the second is the projection display screen, such as the head-up display (HUD). An in-vehicle display screen is a physical display screen and an important component of the in-vehicle infotainment system. Multiple displays can be installed in the cabin, such as the digital instrument cluster display, the central control screen, the display screen in front of the front passenger (also known as the front-seat passenger), the display screen in front of the left rear passenger, the display screen in front of the right rear passenger, and even the car window can be used as a display screen. A head-up display, also known as a head-up display system, is mainly used to display driving information such as speed and navigation on a display device in front of the driver (such as the windshield). This reduces the driver's eye-shift time, avoids pupil changes caused by eye-shifting, and improves driving safety and comfort. Examples of HUDs include combiner-HUD (C-HUD) systems, windshield-HUD (W-HUD) systems, and augmented reality HUD (AR-HUD) systems. It should be understood that HUDs can also evolve into other types of systems as technology progresses, and this application does not limit them.

[0062] The above description of the display device 130 uses an in-vehicle display screen and a projection display screen as examples, but the embodiments of this application are not limited thereto. For example, the display device 130 can also be a light display screen or a projection screen.

[0063] Vehicle 100 may include an Advanced Driving Assistant System (ADAS). ADAS utilizes various sensors on the vehicle (including but not limited to: LiDAR, millimeter-wave radar, cameras, ultrasonic sensors, GPS, and inertial measurement units) to acquire information from the vehicle's surroundings, analyzes and processes this information, and performs functions such as obstacle perception, target recognition, vehicle localization, path planning, and driver monitoring / alerts, thereby improving vehicle driving safety, automation, and comfort. At different levels of autonomous driving (L0-L5), based on artificial intelligence algorithms and information acquired from multiple sensors, ADAS can achieve different levels of autonomous driving assistance. The aforementioned autonomous driving levels (L0-L5) are based on the classification standards of the Society of Automotive Engineers (SAE). Level L0 is no automation; Level L1 is driver assistance; Level L2 is partial automation; Level L3 is conditional automation; Level L4 is high automation; and Level L5 is full automation. At levels L1 to L3, the task of monitoring road conditions and reacting is jointly performed by the driver and the system, but the driver needs to take over dynamic driving tasks. Levels 4 and 5 allow the driver to completely transition into a passenger role. For example, automated parking can include APA, RPA, and AVP. With APA, the driver doesn't need to operate the steering wheel, but still needs to control the accelerator and brake from outside the vehicle; with RPA, the driver can remotely park the vehicle from outside using a terminal (such as a mobile phone); with AVP, the vehicle can park without a driver. In terms of corresponding autonomous driving levels, APA is roughly equivalent to Level 1, RPA is roughly equivalent to Level 2-3, and AVP is roughly equivalent to Level 4.

[0064] For example, Figure 2 shows a schematic diagram of the system architecture provided in an embodiment of this application. This system architecture includes ADAS and vehicle hardware. Logically, ADAS can include three main functional modules: a perception system 110, a planning system 220, and a control system 230. The perception system 110 senses the environment around the vehicle through sensors and inputs corresponding real-time data to the planning system 220. The planning system 220 plans a parking trajectory based on the information obtained by the perception module 210 and sends the planned parking trajectory to the control system 230. The control system 230 receives the parking trajectory information from the planning system 220 and controls the vehicle based on the parking trajectory. For example, the control system 230 can control the vehicle's hardware, thereby enabling the vehicle to change lanes, steer, brake, etc. In this embodiment, the planning system 220 can determine whether a collision or scrape will occur between the vehicle and other vehicles based on the data collected by the perception system 110. For example, when the planning system 220 determines that a collision or scrape will occur between the vehicle and other vehicles, it can instruct the control system 230 to control the vehicle 100 to brake in time or to control the vehicle 100 to stop automatic parking.

[0065] The planning system 220 and control system 230 can be located in the computing platform 120.

[0066] In one embodiment, vehicle 100 can also interact with electronic devices (e.g., mobile phones) via a network. For example, in an unmanned parking scenario, vehicle 100 can send information about the planned parking trajectory to a mobile phone, allowing the user to view the parking process of vehicle 100 via their mobile phone.

[0067] The vehicle 100 in this application may include: road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment, etc. For example, vehicle 100 may be a means of transportation (such as commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), agricultural equipment (such as lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, etc. The embodiments of this application do not specifically limit the type of vehicle.

[0068] To improve parking safety, especially in scenarios with dense traffic such as narrow passages and road parking, this embodiment of the application can achieve real-time collision avoidance for other vehicles by accurately calculating their positions, which helps to improve vehicle safety during parking.

[0069] Figure 3 shows a schematic flowchart of a parking method 300 provided in an embodiment of this application. The method 300 includes:

[0070] S310, acquire image information.

[0071] Optionally, acquiring image information includes: acquiring image information during the process of automatic parking of the vehicle.

[0072] For example, during the automatic parking process of a vehicle, image information is acquired, including when it is detected that the user has activated the AVP, APA, or RPA function.

[0073] For example, the image information could be image information captured by a fisheye camera.

[0074] For example, the acquisition of image information includes: acquiring the image information when it is detected that the vehicle is meeting another vehicle, or when another vehicle enters the vehicle's blind spot.

[0075] S320, based on the image information, identifies multiple vehicle body features.

[0076] Optionally, multiple vehicle body features can be determined based on the image information, including: determining multiple vehicle body features based on the real-time detection results of a single frame image and the multi-view detection results of multiple frames images.

[0077] For example, a vehicle can determine real-time features, such as the tires of other vehicles, based on the real-time detection results of a single frame image. Since the real-time detection results of a single frame image can yield feature points with relatively high accuracy, this can improve the accuracy of the detection results for real-time features.

[0078] For example, a vehicle can determine static features based on the multi-view detection results of multiple frames of images, such as one or more of the license plates, rearview mirrors, body, front of the vehicle, and headlights of other vehicles.

[0079] Optionally, based on the image information, multiple vehicle body features are determined, including: inputting the image information into a prediction model to obtain multiple vehicle body features.

[0080] For example, the prediction model can be a residual neural network (ResNet), a recurrent neural network (RNN), or a multilayer perceptron (MLP).

[0081] For example, the prediction model can also be a machine learning model, such as a support vector machine (SVM).

[0082] For example, a training dataset can be used to train the prediction model. This training dataset can include images captured by a fisheye camera and the relationships between labeled feature points or feature segments in the images and their corresponding vehicle body features. For instance, the training dataset could include multiple frames of images captured by a fisheye camera and feature points and feature segments of the wheels, license plates, side mirrors, and key points and feature segments of the vehicle body in each frame. Based on this training dataset, the prediction model can be trained.

[0083] The feature points and feature line segments for the different features mentioned above can be different. For example, the feature point for a rearview mirror can be the feature point at the root of the rearview mirror; another example is that the feature point for a wheel can be the feature point where the wheel contacts the ground, and the feature line segment for the wheel can be the hub line.

[0084] During the prediction phase, the vehicle can input image information captured by a fisheye camera into the trained prediction model, thereby obtaining multiple feature points and feature line segments, as well as the semantic information corresponding to each feature point and feature line segment. Based on the semantic information output by the prediction model for each feature point and feature line segment, the vehicle can determine the corresponding vehicle body features.

[0085] The above training process uses image data acquired by a fisheye camera as an example, but the embodiments of this application are not limited to this. For example, point cloud data acquired by LiDAR or millimeter-wave radar can also be used when training the prediction model. In this way, during the prediction stage, the vehicle can input the point cloud data acquired by LiDAR or millimeter-wave radar into the prediction model, thereby obtaining multiple feature points and multiple feature line segments, as well as the semantic information corresponding to each feature point and feature line segment.

[0086] S330 performs clustering on multiple vehicle body features to obtain clustering results.

[0087] Optionally, clustering multiple vehicle body features to obtain clustering results includes: using the K-means clustering algorithm or the density-based spatial clustering of applications with noise (DBSCAN) algorithm to cluster the multiple vehicle body features and obtain the clustering results.

[0088] For example, obtaining clustering results includes: obtaining the body features of vehicles belonging to the same vehicle.

[0089] For example, using the same prediction model as described above, feature points 1-N and feature line segments 1-M can be obtained, where N and M are integers greater than 1. The vehicle can determine multiple body features based on the semantic information corresponding to feature points 1-N and 1-M, such as body 1, body 2, body 3, wheel 1, wheel 2, rearview mirror 1, rearview mirror 2, license plate 1, license plate 2, and license plate 3. The vehicle can cluster these multiple body features. For example, the vehicle can cluster these multiple body features based on the relative distance and relative orientation between them, thus obtaining the clustering results shown in Table 1.

[0090] Table 1

[0091] Through the above clustering process, the vehicle can obtain the body features of each surrounding vehicle.

[0092] S340: Based on the clustering results, the features of each vehicle are pieced together.

[0093] For example, after obtaining the clustering results shown in Table 1 above, vehicle 100 can stitch together the body features of each surrounding vehicle. For example, it can stitch together body 1, wheel 1, rearview mirror 1, and license plate 1; it can stitch together body 2, wheel 2, rearview mirror 2, and license plate 2; and it can stitch together body 3 and license plate 3.

[0094] S350 determines the position and outline information of each vehicle based on the spliced ​​features.

[0095] For example, after stitching together the vehicle body 1, wheel 1, rearview mirror 1, and license plate 1, the outline information of the vehicle identified as 1 can be obtained. After stitching together the vehicle body 2, wheel 2, rearview mirror 2, and license plate 2, the outline information of the vehicle identified as 2 can be obtained. After stitching together the vehicle body 3 and license plate 3, the outline information of the vehicle identified as 3 can be obtained.

[0096] Optionally, the position of each vehicle includes the absolute position of each vehicle, or the relative positional relationship between each vehicle and vehicle 100.

[0097] For example, after clustering and stitching the body features of the vehicle identified as 1, the outline information of the vehicle identified as 1 can be obtained. Vehicle 100 can first determine the relative position between each feature point on the outline information and vehicle 100. Then, based on the absolute position of vehicle 100 and the relative positions between each feature point and vehicle 100, the absolute position of the vehicle identified as 1 can be determined.

[0098] Optionally, the position and outline information of each vehicle can be used by vehicle 100 for parking environment detection and collision avoidance detection.

[0099] S360 controls vehicles to park based on their position and outline information.

[0100] For example, vehicle 100 can determine whether its parking safety is affected based on the location and outline information of each vehicle. If the parking safety is affected, vehicle 100 can exit the parking area and prompt the user to take over the vehicle, or replan the parking route; otherwise, it can return to continue executing S310-S360.

[0101] Figure 4 shows a schematic flowchart of a parking method 400 provided in an embodiment of this application. The method 400 includes:

[0102] S410 acquires data collected by the vehicle's sensors.

[0103] Optionally, the sensor may include a fisheye camera and / or a lidar.

[0104] Optionally, before acquiring the data collected by the vehicle's sensors, the method further includes: determining that the vehicle is about to meet another vehicle on the road.

[0105] For example, Figure 5 illustrates a schematic diagram of an application scenario provided by an embodiment of this application. During the process of parking a vehicle 100 into a target parking space using the AVP function, it will pass through a narrow intersection while driving on the road. When the vehicle 100 is about to meet an oncoming vehicle 200 at this narrow intersection, it can acquire data collected by sensors and execute the following steps S420-S440.

[0106] Optionally, before acquiring the data collected by the vehicle's sensors, the method further includes: determining that the other vehicle has entered the vehicle's blind spot.

[0107] Optionally, before acquiring the data collected by the vehicle's sensors, the method 400 further includes: when the vehicle performs automatic parking via APA or RPA function, determining that the target parking space for the vehicle is a narrow parking space.

[0108] Optionally, before acquiring the data collected by the vehicle's sensors, the method 400 further includes: when the vehicle performs automatic parking via the AVP function, determining the target parking space as a narrow parking space during the parking phase.

[0109] The automatic parking process using the AVP function can be divided into two phases: the cruise phase and the parking phase. The cruise phase refers to the process of the vehicle moving from its current position to the vicinity of the target parking space, while the parking phase refers to the process of the vehicle moving from the vicinity of the target parking space into the target parking space.

[0110] Figure 6 shows a schematic diagram of a narrow parking space provided in an embodiment of this application.

[0111] Exemplarily, during the process of a vehicle driving and searching for a target parking space to park in, the ground parking space image is recognized by a camera. The type of the parking space is determined according to the parking space image, and the size of the parking space image is compared with the size of a standard parking space and the outer contour size of the vehicle itself. Combining the type of the parking space, it is judged whether each recognized parking space is a narrow parking space. In FIG. 6(a), a1 and b1 respectively represent the width and length of the target parking space, and a2 and b2 respectively represent the width and length of the vehicle. Among them, a1 and b1 are respectively the distances between the central axes of two parking space lines. The width of the vehicle refers to the distance between two planes that are parallel to the longitudinal symmetry plane of the vehicle and respectively abut against the protruding parts on both sides of the vehicle (including the outside of the rearview mirror, measuring marker lamp, steering indicator lamp, flexible fender, and the deformed part of the tire in contact with the ground). The length of the vehicle refers to the distance between two planes that are perpendicular to the longitudinal symmetry plane of the vehicle and respectively abut against the protruding parts on both sides of the vehicle (including the outside of the rearview mirror, measuring marker lamp, steering indicator lamp, flexible fender, and the deformed part of the tire in contact with the ground), that is, they are respectively the sizes of the widest part and the longest part of the vehicle. When a1–a2≥A1 and a1<A, and / or b1–b2≥B1 and b1<B, it is determined that the target parking space is a narrow parking space. Among them, A1 and B1 are the minimum safety distances to ensure that the vehicle itself will not rub against surrounding obstacles during the parking process, and can be set according to the vehicle model and the type of the target parking space; A and B are respectively the width and length of the standard parking space.

[0112] It should be understood that for an inclined parking space, its width b2 is calculated according to the vertical distance of the diagonal line, as shown in FIG. 6(b). Taking a small car with a total length of 5000 mm and a total width of 2000 mm as an example, the specific setting rules of A1 and B1 are as follows: ① When the type of the target parking space is a vertical parking space or an inclined parking space, A1 can be set to 300 mm respectively, and B1 can be set to any value greater than 1000 mm; ② When the type of the target parking space is a parallel parking space, A1 can be set to any value greater than 500 mm respectively, and B1 can be set to 1000 mm; ③ Or, regardless of the type of the target parking space, A1 is set to 300 mm and B1 is set to 1000 mm. It should be understood that the purpose of the above setting ① is that for a vertical parking space or an inclined parking space, since the size in the length direction of the parking space has a relatively small impact on the safety of parking during the parking process, only the size in the width direction of the parking space needs to be concerned; the purpose of the above setting ② is that for a parallel parking space, since the size in the width direction of the parking space has a relatively small impact on the safety of parking during the parking process, only the size in the length direction of the parking space needs to be concerned. For vehicles with larger outer contour sizes, A1 and B1 can be set to other sizes according to different vehicle models, and the embodiments of the present application do not limit this.

[0113] Optionally, the vehicle performs automatic parking via AVP function. Before determining the first body features of other vehicles around the vehicle based on the data, the method further includes: determining that the vehicle is passing through a narrow passage.

[0114] For example, the narrow passage can be the difference between the width of the vehicle and the sum of the widths of the other vehicles and the width of the narrow passage, which is less than or equal to a preset difference.

[0115] For example, the preset difference is 5cm-50cm.

[0116] S420, based on this data, determines the first body features of other vehicles around the vehicle.

[0117] Optionally, based on the data, determining the first body feature of other vehicles around the vehicle includes: determining multiple body features based on the data, the multiple body features including the first body feature; clustering the multiple body features to obtain a clustering result, the clustering result including the association between the first body feature and the other vehicles.

[0118] Optionally, based on the data, multiple vehicle body features are determined, including: inputting the data into a prediction model to obtain the multiple features, wherein the prediction model is trained on a training dataset, which includes sample data collected by sample sensors and the semantic and feature point (or feature line segment) association relationships of the vehicle body features in the labeled sample data.

[0119] The process of obtaining multiple features based on the prediction model described above can be referred to the description in the above embodiments, and will not be repeated here.

[0120] S430, based on the first vehicle body feature, determines the location information and body outline of the other vehicle.

[0121] Optionally, the first vehicle body feature includes at least two of the license plate, headlights, rearview mirrors, and wheels of the other vehicle. The step of determining the position information and vehicle body outline of the other vehicle based on the first vehicle body feature includes: splicing the first vehicle body feature to obtain a splicing result; determining the vehicle body outline of the other vehicle based on the splicing result; and determining the position information of the other vehicle based on the relative positional relationship between the first vehicle body feature and the vehicle.

[0122] Optionally, the first vehicle body feature includes a license plate feature, which includes a license plate color. Determining the vehicle body outline of the other vehicle based on the splicing result includes: determining the vehicle body outline of the other vehicle based on the splicing result; verifying the vehicle body outline based on the license plate color indicated by the license plate feature; and outputting the vehicle body outline of the other vehicle when the vehicle body outline matches the license plate color.

[0123] For example, if the license plate color indicates that the background color of the license plate is blue and the license plate numbers are white, then the corresponding vehicle is generally a small car (e.g., a sedan or SUV). The front of this type of vehicle is generally curved in its body outline.

[0124] For example, if the license plate color indicates that the background color of the license plate is green and the license plate numbers are black, then the corresponding vehicle is generally a new energy vehicle. The front of this type of vehicle is generally curved in its body outline.

[0125] For example, if the license plate color indicates that the background color of the license plate is yellow, then the corresponding vehicle is generally a large vehicle, such as a large bus, a large truck, or a construction vehicle. The front of this type of vehicle is generally rectangular in its body outline.

[0126] The color of the license plate can be used to verify the vehicle body outline, which helps to further improve the accuracy of the vehicle body outline detection results of other vehicles, and also helps to improve the accuracy of vehicle collision detection or anti-scratch detection.

[0127] In some possible implementations, the first vehicle body feature includes a license plate feature, which includes a license plate color. Determining the vehicle body outline of the other vehicle based on the splicing result includes: determining the vehicle body outline of the other vehicle based on the splicing result; verifying the vehicle body outline based on the license plate color indicated by the license plate feature; if the vehicle body outline does not match the license plate color, acquiring another data collected by the sensor; determining a second vehicle body feature of the other vehicle based on the other data; determining another vehicle body outline of the other vehicle based on the second vehicle body feature; verifying the other vehicle body outline based on the license plate color indicated by the license plate feature; and outputting the other vehicle body outline when the other vehicle body outline matches the license plate color.

[0128] S440 controls the vehicle to perform automatic parking based on the location information and body outline of the other vehicle.

[0129] Optionally, the planned parking trajectory of the vehicle is a first parking trajectory, which includes multiple waypoints. Based on the position information and vehicle body contour of the other vehicles, the vehicle is controlled to perform automatic parking, including: at each waypoint on the first parking trajectory, the vehicle is controlled to perform automatic parking based on the position information and vehicle body contour of the vehicle and the position information and vehicle body contour of the other vehicles.

[0130] For example, the vehicle's body outline can be a polygonal outline of the vehicle or a rectangular or cubic bounding box (bbox) in which the vehicle is located.

[0131] Optionally, based on the location information and vehicle outline of the other vehicle, the vehicle is controlled to perform automatic parking, including: when it is determined based on the location information and vehicle outline that the collision risk between the other vehicle and the vehicle meets preset conditions, the vehicle is controlled to stop automatic parking, or the parking trajectory is replanned.

[0132] For example, the preset condition could be that the time to collision (TTC) between the vehicle and other vehicles is less than a preset TTC, or that the distance between the vehicle and other vehicles is less than or equal to a preset distance. For example, the preset distance could be 20cm.

[0133] Optionally, the method 400 further includes: controlling a display device to display the distance between the vehicle and the other vehicle.

[0134] For example, Figure 7 illustrates a graphical user interface (GUI) provided in an embodiment of this application.

[0135] As shown in Figure 7, if the distance between vehicle 100 and vehicle 200 in the adjacent parking space is less than 30cm during the process of vehicle 100 parking into the target parking space, vehicle 100 can be triggered to control the display screen to show the distance between vehicle 100 and vehicle 200. For example, vehicle 100 can display on the screen that the distance between vehicle 100 and vehicle 200 is 7cm.

[0136] The above method can be executed by the vehicle 100, or by the computing platform 120, or by a system consisting of the computing platform 120 and the sensing system 110, or by a system-on-a-chip (SoC) in the computing platform 120, or by a processor, chip, or circuit in the computing platform 120, or by the planning system 220.

[0137] Figure 8 shows a schematic block diagram of a parking device 800 provided in an embodiment of this application. The device 800 includes: an acquisition unit 810 for acquiring data collected by the vehicle's sensors; a first determination unit 820 for determining first body features of other vehicles around the vehicle based on the data; a second determination unit 830 for determining the position information and body outline of the other vehicles based on the first body features; and a control unit 840 for controlling the vehicle to perform automatic parking based on the position information and body outline of the other vehicles.

[0138] Optionally, the first determining unit 820 is specifically used to: determine multiple vehicle body features based on the data, the multiple vehicle body features including the first vehicle body feature; cluster the multiple vehicle body features to obtain a clustering result, the clustering result including the association between the first vehicle body feature and the other vehicles.

[0139] Optionally, the first vehicle body feature includes at least two of the license plate, headlights, rearview mirrors, and wheels of the other vehicle. The second determining unit 830 is specifically used to: splice the first vehicle body feature to obtain a splicing result; determine the vehicle body outline of the other vehicle based on the splicing result; and determine the position information of the other vehicle based on the relative positional relationship between the first vehicle body feature and the vehicle.

[0140] Optionally, the device 800 further includes a third determining unit for determining that the vehicle and the other vehicle are about to meet on the road.

[0141] Optionally, the device 800 further includes a fourth determining unit for determining when the other vehicle enters the blind spot of the vehicle.

[0142] Optionally, the control unit 840 is specifically used to: control the vehicle to stop automatic parking when it is determined, based on the location information and the vehicle body profile, that the collision risk between the other vehicle and the vehicle meets preset conditions, or to replan the parking trajectory.

[0143] Optionally, the control unit 840 is also configured to: control the display device to display the distance between the vehicle and the other vehicle.

[0144] For example, the acquisition unit 810 can be the computing platform in Figure 1, or the processing circuit, processor, or controller in the computing platform. Taking the processor 121 in the computing platform as an example, the acquisition unit 810 can acquire the data collected by the perception system 110 of the vehicle 100.

[0145] For example, the first determining unit 820 may be the computing platform in Figure 1 or the processing circuit, processor, or controller in the computing platform. Taking the processor 122 in the computing platform as an example, the processor 122 may determine the body features of other vehicles (e.g., vehicle 200) around vehicle 100 based on the data obtained by the processor 121. For example, one or more of the wheels, rearview mirrors, license plates, and front of vehicle 200 may be present.

[0146] For example, the second determining unit 830 may be the computing platform in Figure 1, or the processing circuit, processor, or controller in the computing platform. Taking the second determining unit 830 as the processor 123 in the computing platform as an example, the processor 123 may determine the position information and body outline of the vehicle 200 based on the body features determined by the processor 122.

[0147] For example, the control unit 840 can be the computing platform in Figure 1, or the processing circuit, processor, or controller in the computing platform. Taking the control unit 840 as the processor 124 in the computing platform as an example, the processor 124 can control the vehicle 100 to park in the target parking space based on the position information and body outline of the vehicle 200 determined by the processor 123.

[0148] The functions implemented by the acquisition unit 810, the first determination unit 820, the second determination unit 830, and the control unit 840 can be implemented by different processors, or by the same processor, or some functions can be implemented by the same processor. This application embodiment does not limit this.

[0149] It should be understood that the division of units in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units in the device can be implemented by a processor calling software; for example, the device includes a processor connected to memory, which stores instructions. The processor calls the instructions stored in memory to implement any of the above methods or to implement the functions of each unit in the device. The processor can be, for example, a general-purpose processor, such as a CPU or microprocessor, and the memory can be internal or external to the device. Alternatively, the units in the device can be implemented as hardware circuits. The functions of some or all units can be implemented through the design of the hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all units are implemented through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a PLD, such as an FPGA, which can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby implementing the functions of some or all units. All units of the above devices can be implemented entirely through processor calling software, or entirely through hardware circuits, or partially through processor calling software with the remaining parts implemented through hardware circuits.

[0150] In this application embodiment, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a CPU, microprocessor, GPU, or DSP. In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented as an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the processor loading instructions to implement the functions of some or all of the above units. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, or DPU.

[0151] As can be seen, each unit in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0152] Furthermore, the units in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these units are integrated together as a System-on-a-Chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the units in the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and AI processor, CPU and GPU, etc.

[0153] This application also provides an apparatus comprising a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit to cause the apparatus to perform the methods or steps described in the above embodiments.

[0154] Alternatively, if the device is located in a vehicle, the aforementioned processing unit may be the processor 121-12n shown in FIG1.

[0155] This application also provides a parking system, which may include a computing platform and a perception system. The computing platform may include the parking device 800 described above.

[0156] This application also provides a vehicle that may include the parking device 800 or the parking system described above.

[0157] This application also provides a computer program product, which includes computer program code that, when run on a computer, causes the computer to perform the methods described in the above embodiments.

[0158] This application also provides a computer-readable medium storing program code that, when run on a computer, causes the computer to perform the methods described in the above embodiments.

[0159] This application also provides a chip, which includes a circuit for performing the methods described in the above embodiments.

[0160] In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software. The method disclosed in the embodiments of this application can be directly implemented by a hardware processor, or by a combination of hardware and software modules within the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, power-on erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are omitted here.

[0161] It should be understood that in the embodiments of this application, the memory may include read-only memory and random access memory, and provides instructions and data to the processor.

[0162] It should also be understood that, in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0163] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0164] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0165] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0166] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0167] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0168] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0169] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be covered. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A parking method, characterized in that, include: Acquire data collected by the vehicle's sensors; Based on the data, determine the first body features of other vehicles around the vehicle; Based on the first vehicle body feature, determine the location information and vehicle body outline of the other vehicles; Based on the location information and vehicle outline of the other vehicles, the vehicle is controlled to perform automatic parking.

2. The method according to claim 1, characterized in that, The step of determining the first body features of other vehicles around the vehicle based on the data includes: Based on the data, multiple vehicle body features are determined, including the first vehicle body feature; Clustering is performed on the multiple vehicle body features to obtain clustering results, which include the association between the first vehicle body feature and the other vehicles.

3. The method according to claim 1 or 2, characterized in that, The first vehicle body feature includes at least two of the following: license plate, headlights, rearview mirrors, and wheels of the other vehicles. The step of determining the location information and body outline of the other vehicles based on the first vehicle body feature includes: The first vehicle body features are spliced ​​together to obtain the splicing result; Based on the splicing result, the body outline of the other vehicles is determined, and the position information of the other vehicles is determined based on the relative positional relationship between the first body feature and the vehicle.

4. The method according to any one of claims 1 to 3, characterized in that, Before acquiring the data collected by the vehicle's sensors, the method further includes: It is determined that the vehicle is about to meet the other vehicles on the road.

5. The method according to any one of claims 1 to 3, characterized in that, Before acquiring the data collected by the vehicle's sensors, the method further includes: Determine if the other vehicles enter the blind spot of the vehicle.

6. The method according to any one of claims 1 to 5, characterized in that, The step of controlling the vehicle to perform automatic parking based on the location information and vehicle outline of the other vehicles includes: When the collision risk between the vehicle and other vehicles is determined to meet preset conditions based on the location information and the vehicle body outline, the vehicle is controlled to stop automatic parking, or the parking trajectory is replanned.

7. The method according to claim 6, characterized in that, The method further includes: The control display device displays the distance between the vehicle and the other vehicles.

8. The method according to any one of claims 1 to 7, characterized in that, The sensors include fisheye cameras and / or lidar.

9. The method according to any one of claims 1 to 8, characterized in that, The step of determining the first body features of other vehicles around the vehicle based on the data includes: The data is input into the trained model to obtain the first vehicle body feature.

10. A parking device, characterized in that, include: Acquisition unit, used to acquire data collected by the vehicle's sensors; The first determining unit is configured to determine, based on the data, the first body features of other vehicles surrounding the vehicle; The second determining unit is used to determine the position information and body outline of the other vehicles based on the first body features; The control unit is used to control the vehicle to perform automatic parking based on the location information and body outline of the other vehicles.

11. The apparatus according to claim 10, characterized in that, The first determining unit is specifically used for: Based on the data, multiple vehicle body features are determined, including the first vehicle body feature; Clustering is performed on the multiple vehicle body features to obtain clustering results, which include the association between the first vehicle body feature and the other vehicles.

12. The apparatus according to claim 10 or 11, characterized in that, The first vehicle body feature includes at least two of the following from the other vehicles: license plate, headlights, rearview mirrors, and wheels. The second determining unit is specifically used for: The first vehicle body features are spliced ​​together to obtain the splicing result; Based on the splicing result, the body outline of the other vehicles is determined, and the position information of the other vehicles is determined based on the relative positional relationship between the first body feature and the vehicle.

13. The apparatus according to any one of claims 10 to 12, characterized in that, The device further includes: The third determining unit is used to determine that the vehicle and the other vehicles are about to meet on the road.

14. The apparatus according to any one of claims 10 to 12, characterized in that, The device further includes: The fourth determining unit is used to determine when the other vehicles enter the blind spot of the vehicle.

15. The apparatus according to any one of claims 10 to 14, characterized in that, The control unit is specifically used for: When the collision risk between the vehicle and other vehicles is determined to meet preset conditions based on the location information and the vehicle body outline, the vehicle is controlled to stop automatic parking, or the parking trajectory is replanned.

16. The apparatus according to claim 15, characterized in that, The control unit is also used for: The control display device displays the distance between the vehicle and the other vehicles.

17. The apparatus according to any one of claims 10 to 16, characterized in that, The sensors include fisheye cameras and / or lidar.

18. The apparatus according to any one of claims 10 to 17, characterized in that, The first determining unit is specifically used for: The data is input into the trained model to obtain the first vehicle body feature.

19. A parking device, characterized in that, include: Memory, used to store computer programs; A processor for executing a computer program stored in the memory to cause the apparatus to perform the method as described in any one of claims 1 to 9.

20. A vehicle, characterized in that, Includes the apparatus as described in any one of claims 10 to 19.

21. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by a processor, cause the processor to implement the method as described in any one of claims 1 to 9.

22. A computer program product, characterized in that, The computer program product includes computer program code that, when run on a computer, causes the computer to perform the method as described in any one of claims 1 to 9.

23. A chip, characterized in that, The chip includes circuitry for performing the method as described in any one of claims 1 to 9.

Images