Parking control method, computer storage medium, vehicle and cloud server

Abstract

The application discloses a parking control method, a computer storage medium, a vehicle and a cloud server. The parking control method comprises the following steps: receiving a parking request signal, obtaining configuration information of a to-be-parked vehicle according to the parking request signal; judging whether the configuration information meets preset parking conditions for entering a first type of parking area; judging whether there is an effective parking space in the first type of parking area; if the preset parking conditions are met and there is an effective parking space in the first type of parking area, sending a parking permission signal to the to-be-parked vehicle, so that the to-be-parked vehicle completes parking according to the effective parking space. The method can improve the vehicle capacity of a parking lot.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a parking control method, a computer storage medium, a vehicle and a cloud server. BACKGROUND

[0002] With the development of economy, the number of newly registered vehicles has been increasing in recent years, which has aggravated the problem of "difficult parking" in big cities. However, some parking lots, especially outdoor parking lots, do not have fixed parking spaces, and some car owners park randomly, so that the parking spaces are far apart from each other, resulting in a low overall vehicle occupancy rate of the parking lot. SUMMARY

[0003] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, one object of the present application is to provide a parking control method which can improve the vehicle occupancy rate of a parking lot.

[0004] A second object of the present application is to provide a parking control method for a vehicle.

[0005] A third object of the present application is to provide a computer storage medium.

[0006] A fourth object of the present application is to provide a vehicle.

[0007] A fifth object of the present application is to provide a cloud server.

[0008] To solve the above problems, the first aspect of the present application provides a parking control method for a cloud server of a parking lot, wherein the parking lot is provided with a first parking area without fixed parking spaces, and the parking control method comprises the following steps: receiving a parking request signal, obtaining configuration information of a vehicle to be parked according to the parking request signal; determining whether the configuration information meets a preset parking condition for entering the first parking area; determining whether there is an effective parking space in the first parking area; if the preset parking condition is met and there is an effective parking space in the first parking area, sending a parking permission signal to the vehicle to be parked, so that the vehicle to be parked completes parking according to the effective parking space.

[0009] According to the parking control method, based on the first parking area without divided parking spaces in the parking lot, when a vehicle needs to be parked, the configuration information of the vehicle to be parked is judged by the cloud server, and if the vehicle to be parked meets the preset parking condition for entering the first parking area and there is an effective parking space in the first parking area, it is determined that there is a gap in the first parking area that allows other vehicles to be parked. A parking permission signal is sent to the vehicle to be parked, so that the vehicle completes parking according to the effective parking space. Thus, without dividing the parking space interval lines to form parking spaces, all vehicles to be parked entering the parking lot are guided by the effective parking spaces, so as to dynamically divide the distance between the vehicles under the premise of reducing the parking gap between the vehicles, so that the vehicles in the first parking area are parked more compactly and regularly, and the parking capacity of the parking lot is improved.

[0010] In some embodiments, the preset parking condition includes at least radar configuration information and camera configuration information in the configuration information.

[0011] In some embodiments, determining whether there is an effective parking space in the first parking area includes: receiving image information provided by the vehicle to be parked, and obtaining vehicle parking image data of the first parking area; identifying parking posture information of each parked vehicle in the first parking area according to the vehicle parking image data; and determining whether there is an effective parking space in the first parking area according to the image information and the parking posture information.

[0012] In some embodiments, identifying the parking posture information of each parked vehicle in the first parking area according to the vehicle parking image data includes: generating a minimum tracking box of each parked vehicle based on a target detection algorithm according to the vehicle parking image data; and taking the minimum tracking box as the parking posture information of each parked vehicle.

[0013] In some embodiments, determining whether there is an effective parking space in the first parking area according to the image information and the parking posture information includes: identifying lane lines of the first parking area according to the image information; determining an included angle formed by each parked vehicle of two adjacent parked vehicles in the first parking area and the lane line according to the minimum tracking box; calculating an accommodable width between the two adjacent parked vehicles according to the included angle; if the accommodable width is greater than or equal to a minimum allowable parking width of the vehicle to be parked, it is determined that there is an effective parking space between the two adjacent parked vehicles, or if the accommodable width is less than the minimum allowable parking width, it is determined that there is no effective parking space between the two adjacent parked vehicles.

[0014] In some embodiments, further comprising: after determining that there is no valid parking space in the first type of parking area, sending a parking prohibition signal to the vehicle to be parked.

[0015] In some embodiments, further comprising: during parking of the vehicle to be parked according to the valid parking space, tracking a parked vehicle beside the valid parking space based on a target tracking algorithm, and sending a target tracking result to the vehicle to be parked.

[0016] In some embodiments, the parking lot further comprises a second type of parking area in which parking spaces are divided, and the parking control method further comprises: determining that the configuration information does not meet the preset parking condition, then sending an unauthorized signal to the vehicle to be parked, which does not allow the vehicle to be parked to enter the first type of parking area; and sending position information of the second type of parking area to the vehicle to be parked, so that the vehicle to be parked enters the second type of parking area according to the position information and completes parking.

[0017] The second aspect of the present application provides a parking control method for a vehicle, which comprises: sending a parking request signal to a cloud server of a parking lot, wherein the parking lot comprises a first type of parking area in which parking spaces are not divided; sending configuration information of the vehicle to the cloud server; and receiving a parking permission signal fed back by the cloud server, and controlling the vehicle to enter the first type of parking area for parking.

[0018] According to the parking control method of the present application, after entering the parking lot and receiving the parking permission signal, the vehicle can enter the first type of parking area for parking, so that the distance between vehicles can be dynamically divided in the case of no divided parking spaces, the parking gap between vehicles is reduced, the vehicles in the first type of parking area are parked more compactly and regularly, high-density parking is achieved, and the vehicle occupancy rate of the parking lot is effectively improved.

[0019] In some embodiments, controlling the vehicle to enter the first type of parking area for parking comprises: obtaining position information of the first type of parking area and a valid parking space in the first type of parking area; generating a virtual parking space and a parking route for entering the virtual parking space according to the valid parking space; and controlling the vehicle to park in the virtual parking space according to the parking route.

[0020] In some embodiments, obtaining the valid parking space in the first type of parking area comprises: obtaining the valid parking space provided by the cloud server; or obtaining image information around the vehicle; and determining the valid parking space according to the image information.

[0021] In some embodiments, controlling the vehicle to park to the virtual parking space according to the parking route comprises: obtaining a distance between the vehicle and a parked vehicle beside the available parking space; sending a parking warning signal when the distance is greater than a preset distance; and adjusting the parking route according to the parking warning signal until the vehicle parks to the virtual parking space.

[0022] In some embodiments, after guiding the vehicle to park to the virtual parking space according to the parking route, the method further comprises: sending a parking completion instruction; obtaining current position information of the vehicle, and sending the current position information to the cloud server.

[0023] A third aspect of the present application provides a computer storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the parking control method for a vehicle according to the above embodiments, or the computer program is executed by a processor to implement the parking control method for a cloud server according to the above embodiments.

[0024] A fourth aspect of the present application provides a vehicle, comprising: at least one processor; a memory in communication connection with the at least one processor; wherein the memory has a computer program stored therein, which can be executed by the at least one processor, and the at least one processor executes the computer program to implement the parking control method according to the above embodiments.

[0025] The vehicle according to the embodiments of the present application can effectively improve the vehicle capacity of a parking lot by executing the parking control method according to the above embodiments by the processor.

[0026] A fifth aspect of the present application provides a cloud server, comprising: a communication module adapted to communicate with a vehicle; and a control module connected with the communication module and used to execute the parking control method according to the above embodiments.

[0027] The cloud server according to the embodiments of the present application can effectively improve the vehicle capacity of a parking lot and effectively avoid the problem of scratching caused by visual judgment errors and improve the success rate of entering the garage by executing the parking control method according to the above embodiments by the control module.

[0028] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0029] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, taken in conjunction with the accompanying drawings, in which:

[0030] Figure 1 is a flowchart of a parking control method for a cloud server according to an embodiment of the present application;

[0031] Figure 2 is a parking lot plan according to an embodiment of the present application;

[0032] Figure 3 is an explanatory diagram at the time of judging an effective parking space according to an embodiment of the present application;

[0033] Figure 4 is an explanatory diagram of recognizing a lane line according to an embodiment of the present application;

[0034] Figure 5 is a diagram of recognizing parking posture information of each of the parked vehicles in the first parking area according to an embodiment of the present application;

[0035] Figure 6 is a flowchart of a parking control method for a vehicle according to an embodiment of the present application;

[0036] Figure 7 is a diagram of vehicle parking according to an embodiment of the present application;

[0037] Figure 8 is a diagram of vehicle parking according to another embodiment of the present application;

[0038] Figure 9 is a structural block diagram of a vehicle according to an embodiment of the present application;

[0039] Figure 10 is a structural block diagram of a cloud server according to an embodiment of the present application.

[0040] Reference numerals:

[0041] vehicle 10; cloud server 20;

[0042] processor 1; memory 2; communication module 3; control module 4. DETAILED DESCRIPTION

[0043] Embodiments of the present application are described in detail below, and the embodiments described with reference to the drawings are exemplary, and embodiments of the present application are described in detail below.

[0044] In related technologies, during parking, users often fail to properly manage the distance to adjacent vehicles, resulting in excessive gaps between cars and a low overall parking lot capacity. To improve parking lot capacity, movable mechanical parking systems are used; however, this method incurs high construction and maintenance costs, and the relocation process is overly cumbersome when the parking lot is full. Alternatively, smart parking systems can be used, but these only display the number of remaining parking spaces and do not increase the overall number of spaces. Therefore, the benefits of improving parking efficiency during peak hours are not significant.

[0045] To address the aforementioned issues, this invention proposes a parking control method. The basic idea is to establish a first-class parking area without designated parking spaces within the parking lot. When a vehicle needs to park, a cloud server determines the vehicle's configuration information. Once the vehicle meets the preset parking conditions for entering the first-class parking area, it can enter and park there. Thus, when parking spaces are not marked with lane lines within the parking lot, all vehicles entering the parking lot can have their spacing dynamically adjusted within the first-class parking area, effectively increasing the parking lot's capacity. Furthermore, dynamically dividing parking spaces based on vehicle spacing allows for more compact and orderly parking, overcoming the limitations of traditional grid-based parking lot layouts. Parking lots can then use parking areas without adjacent lane lines instead.

[0046] The following is for reference. Figure 1 The parking control method of the present invention is described in embodiments such as Figure 1 As shown, the parking control method includes at least steps S1-S4. This parking control method is used in a parking lot's cloud server.

[0047] Step S1: Receive a parking request signal and obtain the configuration information of the vehicle to be parked based on the parking request signal.

[0048] The configuration information of the vehicles to be parked may include license plate number, vehicle type, vehicle size, and vehicle hardware configuration.

[0049] For example, refer to Figure 2As shown, when there is a parking demand, the vehicle to be parked can be connected with the cloud server of the parking lot through the 5G / 4G base station at the entrance of the parking lot, and the registration of the user can be displayed and prompted on the terminal of the vehicle such as PAD (portable Android device). The user needs to input the configuration information required for registration such as the license plate number, and send a parking request signal to the cloud server. For obtaining the configuration information of the vehicle to be parked, the user can actively input the configuration information when registering, and send the configuration information to the cloud server, or after the user completes the first registration, the configuration information of the vehicle to be parked can be automatically identified through various sensors at the entrance of the parking lot when the cloud server receives the parking request signal.

[0050] In step S2, it is judged whether the configuration information meets the preset parking condition for entering the first type of parking area.

[0051] In the embodiment, it is considered that the first type of parking area is a parking area without divided parking spaces, so in order to regulate parking, the vehicle needs to have the configuration requirement for completing parking in the parking area without divided parking spaces, i.e., the preset parking condition, when the vehicle enters the first type of parking area for parking. For the vehicle that does not meet the preset parking condition, it means that the vehicle does not have the above configuration requirement, and the vehicle cannot realize regular parking in the parking area without divided parking spaces. Therefore, the cloud server of the parking lot needs to identify the vehicle to be parked, and specifically, the cloud server identifies the configuration information of the vehicle to be parked to search in the database whether the vehicle to be parked meets the preset parking condition for entering the first type of parking area.

[0052] In some embodiments, the preset parking condition is that the configuration information at least includes radar configuration information and camera configuration information, that is, it is judged whether the vehicle to be parked has ultrasonic radar and camera. If it is determined that the configuration information at least includes radar configuration information and camera configuration information, it means that the vehicle to be parked can meet the requirement for completing parking in the parking area without divided parking spaces; if it is determined that the configuration information does not include radar configuration information and camera configuration information, it means that the vehicle to be parked cannot meet the requirement for completing parking in the parking area without divided parking spaces.

[0053] If the preset parking condition is met, an authorization signal for entering the first type of parking area is sent to the vehicle to be parked. Specifically, when the cloud server receives the configuration information, the vehicle to be parked can be searched in the database according to the vehicle model in the configuration information whether the vehicle to be parked meets the preset parking condition for entering the first type of parking area. Only the vehicle that meets the preset parking condition can obtain the access permission, i.e., the authorization signal for entering the first type of parking area fed back by the cloud server.

[0054] For example, referring to FIG. 1, Figure 2A parking space division scheme in a parking lot is shown. A plurality of first parking areas without divided parking spaces are provided on the right side of the parking lot, numbered A1-A8 in sequence. The vehicles parked in each parking area are of the type that obtains the authorization signal of the first parking area. Among them, the existing divided parking spaces basically adopt fixed parking spaces with a length of 5.3 m and a width of 2.5 m. However, for small vehicles, the width of the parking space has exceeded their use requirements, affecting the vehicle occupancy rate. Therefore, in order to meet the parking needs of different vehicle types, the plurality of first parking areas can be further classified according to the size of the vehicle. For example, the parking areas numbered A1-A3 can be set as microcar parking areas; the parking areas numbered A4-A6 can be set as small car parking areas; the parking area numbered A7 can be set as medium car parking area; and the parking area numbered A8 can be set as large car parking area. Thus, based on the above parking lot design, when the cloud server receives the configuration information, it can search in the database whether the vehicle type in the configuration information is equipped with ultrasonic radar and camera. Only the vehicles equipped with both can obtain the access permission, i.e. the authorization signal feedback by the cloud server. At the same time, the cloud server can mark the appropriate first parking area according to the vehicle size in the configuration information and push it to the PAD end of the vehicle to be parked.

[0055] In addition, when the vehicle to be parked enters the parking lot, the cloud server can send the plan data of the parking lot to the vehicle to be parked, so that the PAD end of the vehicle to be parked displays the plan of the parking lot to the owner based on the plan data of the parking lot, so as to facilitate the user to drive to the first parking area according to the plan.

[0056] Step S3, judging whether there is an effective parking space in the first parking area. The effective parking space can be understood as a parking space that can meet the parking needs of the current vehicle to be parked.

[0057] Step S4, if the preset parking condition is met and there is an effective parking space in the first parking area, it means that there is a gap in the first parking area that allows other vehicles to be parked. Therefore, a parking permission signal is sent to the vehicle to be parked, so that the vehicle to be parked completes parking in the first parking area according to the effective parking space. Thus, without dividing the parking spaces to form the parking spaces, all the vehicles to be parked entering the parking lot are guided by the effective parking spaces, so as to dynamically divide the distance between the vehicles under the premise of reducing the parking gap between the vehicles, making the parking of the vehicles in the first parking area more compact and regular, and effectively improving the vehicle occupancy rate of the parking lot. At the same time, based on the effective parking space provided by the cloud server, the user does not need to visually observe the gap between the parked vehicles in the parking lot, so as to effectively avoid the problem of scratching caused by visual judgment error, and improve the success rate of entering the garage.

[0058] For example, refer to Figure 2As shown, no parking space is divided in the first type of parking area, but due to the use of the above-mentioned parking control method, the vehicle density is large, the vehicle spacing is small, and because the vehicle obtaining the authorization signal no longer relies on the naked eye observation of the vehicle owner, but can accurately perceive the surrounding environment of the vehicle body with the help of the perception device, i.e. the ultrasonic radar or camera of the vehicle, it can park at a low interval according to the indication of the PAD end of the vehicle.

[0059] According to the parking control method of the embodiment of the application, based on the first type of parking area without divided parking spaces in the parking lot, when a vehicle needs to be parked, the configuration information of the vehicle to be parked is judged by the cloud server end. If the vehicle to be parked meets the preset parking condition for entering the first type of parking area and there is an effective parking space in the first type of parking area, it means that there is a gap in the first type of parking area that allows other vehicles to be parked. Therefore, a parking permission signal is sent to the vehicle to be parked, so that the vehicle completes parking according to the effective parking space. Thus, without dividing the vehicle spacing lines to form parking spaces, all vehicles to be parked entering the parking lot are guided by the effective parking spaces, thereby facilitating the dynamic division of the distance between vehicles under the premise of reducing the parking gap between vehicles, making the parking of vehicles in the first type of parking area more compact and more regular, and effectively improving the vehicle capacity of the parking lot.

[0060] In some embodiments, the step of judging whether there is an effective parking space in the first type of parking area specifically includes steps S5-S7.

[0061] In step S5, the image information provided by the vehicle to be parked is received, and the vehicle parking image data of the first type of parking area is obtained.

[0062] Specifically, during the process of the vehicle to be parked driving to the first type of parking area, the vehicle to be parked will collect image information around the vehicle in real time, and transmit the image information to the cloud server in real time, so that the cloud server can know the driving position and driving environment of the vehicle to be parked in the parking lot in real time. In addition, a camera can be arranged at each first type of parking area in the parking lot to collect the vehicle parking image data of the first type of parking area and upload it to the cloud server.

[0063] For example, referring to FIG. 1, Figure 2 As shown, a camera is arranged above each first type of parking area, such as the A1 parking area and the A2 parking area, in the parking lot. When the vehicle to be parked drives to the first type of parking area, the cloud server can retrieve the vehicle parking image data collected by the camera above the nearest first type of parking area of the vehicle to be parked.

[0064] In step S6, the parking posture information of each parked vehicle in the first type of parking area is identified according to the vehicle parking image data.

[0065] Specifically, the parking states of each parked vehicle in the first type of parking area are different, and the parking state of each parked vehicle will affect the parking of the subsequent to-be-parked vehicle. Therefore, in order to understand the parking situation of the vehicles in the first type of parking area, the cloud server identifies the parking posture information of each parked vehicle in the first type of parking area according to the collected vehicle parking image data, so as to subsequently judge whether there is a gap in the first type of parking area that allows parking of other vehicles.

[0066] In step S7, it is judged whether there is an effective parking space in the first type of parking area according to the image information and the parking posture information.

[0067] In some embodiments, based on a target detection algorithm such as a YOLOv5 algorithm or a YOLOv4 algorithm, the minimum tracking box of each parked vehicle is generated according to the vehicle parking image data; and the minimum tracking box is taken as the parking posture information of each parked vehicle.

[0068] It can be understood that, for the YOLOv5 algorithm, the input end adopts mosaic data enhancement, can adaptively calculate anchor boxes, and can adaptively scale pictures, and the benchmark network integrates Focus structure and CSP structure, so that the processing speed can be faster by using the YOLOv5 algorithm.

[0069] Taking the YOLOv5 algorithm as an example, after the vehicle parking image data is detected by the YOLOv5 algorithm, a bounding box, i.e. a minimum tracking box, is generated around the vehicle body in the data, as shown in FIG. 5. Figure 3 As shown in FIG. 5, the minimum tracking boxes are generated around the two parked vehicles parked in the first type of parking area, and the minimum tracking boxes are taken as the parking posture information of each parked vehicle.

[0070] In some embodiments, for part of the owners, there is a problem of difficulty in reversing during parking, especially in parking lots without divided parking spaces. The owner relies on the naked eye to determine whether the space between two cars is too narrow, which can easily lead to collision and scratching with the adjacent car during reversing. Therefore, when judging whether there is an effective parking space in the first type of parking area according to image information and parking posture information, the application identifies the lane line of the first type of parking area according to the image information; determines the included angle formed by each of the two adjacent parked vehicles in the first type of parking area and the lane line according to the minimum tracking frame; calculates the accommodable width between the two adjacent parked vehicles according to the included angle; if the accommodable width is greater than the minimum allowable parking width of the to-be-parked vehicle, it is determined that there is an effective parking space between the two adjacent parked vehicles, or if the accommodable width is less than the minimum allowable parking width, it is determined that there is no effective parking space between the two adjacent parked vehicles. Thus, by judging the effective parking space in the above manner, the size of the vacant area between the two adjacent parked vehicles can be predicted in advance before parking, and it can be determined in advance whether the parking can be successfully carried out, so that the to-be-parked vehicle can be accurately pushed to the parking space that allows the to-be-parked vehicle to park in the first type of parking area, reducing the scratching caused by the judgment error of the human eye, and improving the success rate of vehicle storage.

[0071] wherein the minimum allowable parking width is a value preset based on the actual width of the to-be-parked vehicle and the actual situation such as the space to be reserved for getting off the vehicle when the door of the to-be-parked vehicle is opened.

[0072] Specifically, after the to-be-parked vehicle enters the parking lot, the to-be-parked vehicle is controlled to move forward along the indicated line according to the parking lot plan displayed on the PAD, and at the same time, the camera and ultrasonic radar of the to-be-parked vehicle are turned on and generate real-time image information, which can be displayed on the PAD and uploaded to the cloud server in real time at a certain sampling frequency for further processing by the cloud server. Figure 4 The image information sent by the vehicle to the cloud server during the storage searching process is shown, and the cloud server identifies the lane line of the first type of parking area according to the image information.

[0073] For example, in the lane line detection process, the image information is first subjected to grayscale processing, and the RGB of each pixel point is unified to the same value. Assuming that the pixel point coordinates are (x, y), the grayscale point calculation formula is as follows.

[0074] Gray(x, y) = 0.299 * Red(x, y) + 0.587 * Green(x, y) + 0.114 * Blue(x, y)

[0075] Wherein, Red(x, y), Green(x, y), Blue(x, y) are RGB three channel values.

[0076] Further, after the gray processing is completed, since the lane line is white or yellow, and the ground is gray or black, there will be obvious dark alternation at the edge of the lane line, so the next step is to use the Canny algorithm to process the result after the gray processing, specifically, first, the Gaussian filter is used to smooth the image information after the gray processing, and the first-order partial derivative finite difference is used to calculate the gradient amplitude and direction of the image information after the filtering and smoothing.

[0077] Further, the gradient amplitude is subjected to non-maximum suppression, that is, the gradient intensity of the current pixel point is compared with the gradient intensity of the two pixel points in the positive and negative directions, if the gradient intensity of the current pixel point is greater than the other two pixel points, it is retained as an edge point, otherwise it is suppressed. Finally, the image information after the non-maximum suppression is processed by using a double-threshold algorithm for edge connection, specifically, two thresholds are first set: a first threshold and a second threshold, wherein the first threshold is greater than the second threshold, if the gradient of a pixel point is higher than the first threshold, it is considered to be a strong edge point; if the gradient of the pixel point is lower than the second threshold, it is suppressed; if the gradient of the pixel point is between the first threshold and the second threshold, it is checked whether there is a pixel point higher than the first threshold in its eight neighborhood points, if there is, it is considered to be a strong edge point, otherwise it is suppressed.

[0078] Thus, through the above processing, the edge of the lane line can be extracted, so as to highlight the lane line to be detected. Finally, the Hough transform is used to extract the straight line in the edge recognition result, the main principle of which is to find imperfect instances of objects within a specific type of shape through a voting program, and the most basic Hough transform is to detect straight lines from black and white images, that is, to identify and obtain the lane line of the parking area.

[0079] Further, according to the minimum tracking frame, the included angle formed by each parked vehicle of the two adjacent parked vehicles and the lane line is determined, for example, as shown in reference 5, the minimum tracking frame generated by the YOLOv5 algorithm around the body of the parked vehicle is taken as the parking posture information of the parked vehicle, at this time, the included angles formed by the minimum tracking frames of the two adjacent parked vehicles and the lane line can be calculated. Assuming that the two adjacent parked vehicles are denoted as car A and car B, as shown in reference 6, the minimum tracking frames of the two parked vehicles A and B detected are shown, and the included angles formed by the minimum tracking frames and the lane line are denoted as θ1 and θ2 respectively. Figure 3

[0080] ​Furthermore, based on the aforementioned included angle, the acceptable width between two adjacent parked vehicles is calculated. Specifically, based on the angle formed by each parked vehicle and the lane line, a parallelogram can be constructed between two adjacent parked vehicles within the parking area using deep learning. The size of this parallelogram region is then used to infer the acceptable width. For example, assuming θ1 > θ2, to calculate whether the distance between two parked vehicles (A and B) constitutes a valid parking space, refer to... Figure 3 As shown, first, shift the left line segment AC of the minimum tracking frame of car A to the left until it intersects with the minimum tracking frame of car B at point C'. At this point, AA' = x. Figure 3 As shown, draw a perpendicular line CD from point C to A'C', intersecting A'C' at point D. Based on the principle of parallelogram ACC'A', the accommodating width CD = xsin(θ1) can be deduced. Furthermore, if the accommodating width CD is greater than or equal to the minimum allowable parking width of the vehicle to be parked, it indicates that there is a valid parking space between the two parked vehicles, A and B. The cloud server will send a parking permission signal to the vehicle to be parked, thus constructing a virtual parking space and parking route on the vehicle's PAD. If the accommodating width CD is less than the minimum allowable parking width, it is determined that there is no valid parking space between the two adjacent parked vehicles. In this case, the cloud server will send a parking prohibition signal to the vehicle to be parked, and the PAD of the vehicle to be parked will prompt the driver to continue moving to find a valid parking space.

[0081] In some embodiments, since there may be missed detections when the camera collects data, meaning that it may not be possible to detect two adjacent parked vehicles during the parking process, this application uses a target tracking algorithm to track parked vehicles next to valid parking spaces during the parking process of the vehicle to be parked according to the valid parking space. That is, when the parking route is displayed on the vehicle's PAD, the user can start parking. At the same time, the cloud server will detect the data transmitted back by the cameras in the parking lot in real time, i.e., the vehicle parking image data, and draw the minimum tracking box of the parked vehicles next to the valid parking space. The cloud server will then perform target tracking on the minimum tracking box of the detected parked vehicles next to the valid parking space, and feed the target tracking results back to the vehicle to be parked in real time so that the vehicle to be parked is aware that there are parked vehicles next to the valid parking space. Therefore, based on the target tracking algorithm, the minimum tracking box of the currently missed vehicle can be predicted by using prior information, which can effectively solve the problem of discontinuous detection results in time sequence. In addition, during the parking process, it can also effectively ensure that the minimum tracking box between different frames captured by the camera belongs to the same vehicle. Thus, by tracking the parked vehicles next to the valid parking space in real time, it can further ensure that the vehicles waiting to park can park with a shorter interval.

[0082] Exemplarily, taking the SORT multi-target tracking algorithm as an example, based on the SORT multi-target tracking algorithm, a Kalman tracker for the minimum tracking box and a Hungarian matching algorithm are used to realize target tracking. The core idea of the Kalman tracker is to calculate the optimal quantity of the current Kalman tracker state according to the measurement value of the instrument at the current time, that is, the minimum tracking box detected in the current frame, the minimum tracking box predicted by the Kalman tracker at the last time, and the error, and to predict the next time. The Hungarian matching is mainly to solve the assignment problem, that is, assuming that there are n agents and n tasks, any agent can be assigned to perform any task, and the process will generate a certain cost, and the cost will vary with the agent task assignment, wherein when all tasks are required to be executed, each task can be assigned to one agent to minimize the assignment cost.

[0083] Exemplarily, if it is judged whether the minimum tracking boxes of the same object in the adjacent two frames constitute a pair, assuming that the current frame number is a, the minimum tracking boxes of all vehicles in the frame are matched with the minimum tracking boxes of all vehicles in the a+1 frame using the Hungarian matching algorithm, and the corresponding assignment problem is that the minimum tracking boxes (agents) of n vehicles in the a frame correspond to the minimum tracking boxes (tasks) of n vehicles in the a+1 frame, and the cost of each two minimum tracking boxes is (1-IOU), wherein IOU (Intersection of Union) is the intersection rate of the predicted tracking box and the true tracking box, which is 1 in the most ideal case that the two are completely overlapped.

[0084] The purpose of using the Hungarian pairing algorithm in this application is to find the n pairs of minimum tracking boxes with the minimum total cost between frame a and frame a+1, that is, to identify the minimum tracking box pairings most likely to have a one-to-one mapping relationship between adjacent frames. Based on this, in order to track the minimum tracking boxes of two parked vehicles on the left and right sides of an effective parking space, it can be transformed into pairing the minimum tracking box predicted by the Kalman tracker in frame a with the minimum tracking box detected in frame a+1. During the tracking process, a Kalman tracker needs to be constructed first, with the hidden state as: (x, y, m, r, x', y', m'), where x, y, area, aspect ratio, x-coordinate rate, y-coordinate rate, and area change rate of the minimum tracking box, respectively. After the Kalman tracker is initialized, once one of the parked vehicles is detected, the detection result is used to update and predict the Kalman tracker. Assuming the minimum tracking box of the parked vehicle is not missed in the next frame, and the prediction result of the current frame can be successfully paired with the detection result of the next frame using the Hungarian pairing algorithm, then the Kalman tracker of the next frame can be assigned the same ID, and the Kalman tracker can continue to be updated and predicted. After multiple iterations, the hidden state of the vehicle will gradually converge to a value close to the truth. When a missed detection occurs, the Kalman tracker will predict the minimum tracking box of the missed vehicle in the current frame based on the position information and movement speed of the minimum tracking box in the previous frame. If the Kalman filter is not updated for 5 consecutive frames, the target is considered lost, and its corresponding Kalman tracker will be destroyed. Thus, during the parking process, the cloud server achieves real-time tracking of two adjacent parked vehicles in the above manner to further ensure that vehicles can park with shorter intervals.

[0085] In some embodiments, the parking lot also includes a second type of parking area with designated parking spaces, for example, see reference. Figure 2 As shown, the left side of the parking lot has several secondary parking zones, numbered B1-B8, designated for conventional vehicles and vehicles without authorized parking. To accommodate different vehicle types, these zones can be further categorized by size. For example, zones B1-B3 could be designated for microcars; B4-B6 for small cars; B7 for medium-sized cars; and B8 for large cars. Figure 2 As can be seen, the second type of parking area uses rectangles to divide fixed parking spaces, and the gaps between parked vehicles are relatively large.

[0086] Based on the above, the parking control method of this application further includes, if it is determined that the configuration information does not meet the preset parking conditions, sending an unauthorized signal that does not allow entry into the first type of parking area to the vehicle to be parked, and sending the location information of the second type of parking area to the vehicle to be parked, so that the vehicle to be parked can enter the second type of parking area according to the location information and complete parking. That is to say, when the configuration information of the vehicle to be parked does not meet the preset parking conditions, such as when the vehicle to be parked does not have the radar configuration information and camera configuration information used for sensing the environment, it means that the vehicle to be parked cannot meet the requirement of parking in an unmarked parking space, and therefore can only park in the first type of parking area with fixed parking spaces.

[0087] Specifically, for the location information of the second type of parking area, the cloud server can include this location information in the floor plan data of the parking lot and provide it to the vehicle waiting to park. As a result, the PAD terminal of the vehicle waiting to park will display the parking lot floor plan to the car owner based on the floor plan data, so that the user can drive to the second type of parking area according to the floor plan.

[0088] A second aspect of the present invention provides a parking control method for vehicles, such as... Figure 6 As shown, the parking control method includes at least steps S8-S10.

[0089] Step S8: When entering the parking lot, a parking request signal is sent to the parking lot's cloud server. The parking lot has a first-class parking area with no designated parking spaces.

[0090] For example, refer to Figure 2 As shown, when there is a parking need, the vehicle can connect to the parking lot's cloud server through a 5G / 4G base station at the parking lot entrance. The information can be displayed on the vehicle's terminal, such as a PAD (portable Android device), and the user will be prompted to register. The user needs to enter registration information such as the license plate number and send a parking request signal to the cloud server.

[0091] Step S9: Send the vehicle configuration information to the cloud server.

[0092] Step S10: Upon receiving the parking permission signal from the cloud server, control the vehicle to drive into the first type of parking area for parking.

[0093] Specifically, when entering the first type of parking area for parking, the cloud server first judges whether the configuration information of the vehicle meets the preset parking condition for entering the first type of parking area. After meeting the preset parking condition, the cloud server sends an authorization signal allowing entering the first type of parking area to the vehicle to be parked. In response to the authorization signal, when the vehicle to be parked enters the parking lot, the cloud server can send the plan data of the parking lot to the vehicle, so that the PAD end of the vehicle displays the plan of the parking lot to the owner, so that the user controls the vehicle to drive along the indicated line to the first type of parking area according to the plan, and when the parking permission signal is received, it means that the vehicle has arrived at the position capable of parking in the first type of parking area, so as to park the vehicle in the first type of parking area. Since the first type of parking area is not divided into parking spaces, the user can dynamically adjust the distance between the vehicle and other parked vehicles when parking the vehicle under the premise of reducing the parking gap between vehicles, thereby making the vehicle parking in the first type of parking area more compact and regular, achieving high-density parking, and effectively improving the vehicle occupancy rate of the parking lot.

[0094] According to the parking control method, after entering the parking lot and receiving the parking permission signal, the vehicle can enter the first type of parking area for parking, so that the distance between vehicles can be dynamically divided without dividing parking spaces, the parking gap between vehicles is reduced, the vehicle parking in the first type of parking area is more compact and regular, high-density parking is achieved, and the vehicle occupancy rate of the parking lot is effectively improved.

[0095] In some embodiments, during the process of controlling the vehicle to enter the first type of parking area for parking, the position information of the first type of parking area and the effective parking spaces in the first type of parking area are obtained; a virtual parking space and a parking route for entering the virtual parking space are generated according to the effective parking spaces; and the vehicle is controlled to park in the virtual parking space according to the parking route. Thus, the virtual parking space and the parking route are used as references to achieve parking, meet the requirements of standard parking, and achieve the effect of making the vehicle parking in the parking lot more compact and regular.

[0096] In the process of obtaining the position information of the first type of parking area, the cloud server can send the authorization signal allowing entering the first type of parking area to the vehicle; or the position information of the first type of parking area in the parking lot where the user is used to park for a long time can be pre-stored in the vehicle, for example, so as to be called and used every time the vehicle enters the parking lot.

[0097] In the process of obtaining the effective parking spaces in the first type of parking area, the vehicle side can automatically identify the effective parking spaces in the first type of parking area, which includes obtaining image information around the vehicle and determining the effective parking spaces according to the image information.

[0098] Specifically, by acquiring image information around the vehicle; according to the image information to determine the current driving environment of the vehicle and the parking posture information of each parked vehicle in the first type of parking area, and then combine the above parking posture information to determine whether there is an effective parking space in the first type of parking area, such as can be based on image information to know the angle formed by each parked vehicle and the lane line, and through the way of deep learning to construct a parallelogram between the two adjacent parked vehicles in the parking area, to infer the effective parking space by the size of the parallelogram area, so as to generate a virtual parking space and a parking route into the virtual parking space according to the effective parking space after identifying the effective parking space in the first type of parking area, and guide the vehicle to park to the virtual parking space according to the parking route. At this point, the virtual parking space with appropriate interval and the parking route into the virtual parking space are generated based on the identified effective parking space, so that the user can refer to the parking route to guide the vehicle to park until the vehicle is parked to the virtual parking space, thereby guiding the user to park the vehicle through the virtual parking space without the need to divide the parking space interval line, thereby facilitating the dynamic division of the distance between the vehicles under the premise of reducing the parking gap between the vehicles, so that the vehicle parking in the first type of parking area is more compact and more regular, realizing high-density parking and effectively improving the parking capacity of the parking lot

[0099] Alternatively, the cloud server can also push the effective parking space in the first type of parking area for the vehicle, thereby reducing the computational load of the vehicle side, which can be implemented through the following steps S11-S12.

[0100] Step S11, after receiving the parking permission signal feedback by the cloud server, a virtual parking space and a parking route into the virtual parking space are generated according to the effective parking space provided by the cloud server.

[0101] For example, after a vehicle enters the parking lot, the cloud server will push available parking spaces to the user based on the parking situation within the parking area. Specifically, the cloud server uses the parking image data of the first type of parking area in the parking lot to identify the parking posture information of each parked vehicle, and determines whether there are available parking spaces in the first type of parking area based on the parking posture information. This determination process can be referred to the previous description and will not be repeated here. If there are available parking spaces, it means that there is a certain gap in the first type of parking area that allows other vehicles to park. Therefore, a parking permission signal is sent to the vehicle waiting to park. After receiving the parking permission signal, the vehicle can generate a virtual parking space and a parking route to enter the virtual parking space based on the available parking spaces provided by the cloud server, and can display it on the vehicle's terminal such as a PAD for user use. Moreover, by generating virtual parking spaces and parking routes based on available parking spaces provided by cloud servers to guide vehicles to park, it can predict in advance whether two adjacent parked vehicles can park smoothly. Users do not need to rely on their naked eyes to identify the gap between parked vehicles next to available parking spaces during the parking process, thus effectively avoiding the problem of scratches caused by visual judgment errors and improving the success rate of parking.

[0102] For example, refer to Figure 2 As shown, the parking lot has multiple Class I parking areas. Cameras can be installed above these areas to collect images of parked vehicles. The cloud server can then use this data to determine the parking situation within the Class I areas and recommend suitable parking spaces to users. (Refer to...) Figure 2 and Figure 7 The cloud server, based on parking posture information, can identify whether there is a gap between two adjacent parked vehicles (let's call them Car A and Car B) in parking area A2 (Category 1). It then determines whether this gap constitutes a valid parking space, specifically whether it allows the vehicle waiting to park to do so. If a valid parking space is formed between Car A and Car B, a parking permission signal is sent to the waiting vehicle. In response, the vehicle's terminal constructs a virtual parking space and can use a dashed arrow to indicate the parking route for the user to view. If a valid parking space is not formed between Car A and Car B, the cloud server sends a parking prohibition signal to the vehicle, and the vehicle's terminal prompts the user to continue searching for other parking spaces.

[0103] Step S12: Guide the vehicle to park according to the parking route, that is, the user refers to the parking route displayed on the vehicle terminal such as the PAD and controls the vehicle to gradually drive into the virtual parking space.

[0104] According to the parking control method, when entering a parking lot and receiving an authorization signal allowing to enter the first type of parking area, a virtual parking space with proper interval and a parking route to the virtual parking space are generated based on the effective parking space provided by the cloud server, so that the user can guide the vehicle to park according to the parking route until the vehicle is parked in the virtual parking space. Thus, the user can be guided to park the vehicle by the virtual parking space without dividing the interval line between the vehicles to form the parking space, so as to dynamically divide the interval between the vehicles under the premise of reducing the parking interval between the vehicles, so that the vehicles in the first type of parking area are parked more compactly and regularly, high-density parking is achieved, and the vehicle capacity of the parking lot is effectively improved.

[0105] In some embodiments, when guiding the vehicle to park in the virtual parking space according to the parking route, the interval distance between the vehicle and the parked vehicle beside the effective parking space is obtained, and when the interval distance is greater than a preset distance, a parking warning signal is sent to remind the user that the current parking position has a large interval distance with the adjacent vehicle, so as to prompt the user to adjust the parking route according to the parking warning signal until the vehicle is parked in the virtual parking space. Thus, while guiding the vehicle to park, the user's non-standard parking behavior is reminded, so as to shorten the parking interval between the vehicles and improve the vehicle capacity of the parking lot.

[0106] The preset distance is a value preset according to actual conditions such as vehicle model, space required for opening the vehicle door, or range of the parking area, and is not limited.

[0107] For example, the interval distance between the vehicle and the parked vehicle beside the effective parking space can be collected in real time by the ultrasonic radar arranged on the vehicle, and the collected interval distance between the vehicle and the parked vehicle beside the effective parking space can be displayed on the vehicle terminal such as a PAD terminal, so that the user can check at any time. Thus, during the process of gradually driving the vehicle into the virtual parking space, the user can dynamically adjust the parking route according to the interval distance between the vehicle and the parked vehicle beside the effective parking space, so that the vehicle can be parked with a shorter interval distance between the vehicles, thereby greatly reducing the interval distance between all the vehicles in the parking lot, making the parking of the vehicles in the parking lot more compact and regular, achieving high-density parking, and effectively improving the vehicle capacity of the parking lot. Figure 8 As shown in the figure, the vehicle end can monitor the interval distance between the vehicle and the parked vehicle beside the effective parking space in real time. If the interval distance is greater than the preset distance during parking, it indicates that the current parking position of the vehicle has a large interval distance with the parked vehicle beside it, and thus a parking warning signal is sent to remind the user that the current parking behavior is not standard. Then, the user can dynamically adjust the parking route after knowing that the parking is not standard, so that the interval distance between the vehicle and the parked vehicle beside it meets the standard parking distance, and the vehicle can be parked with a shorter interval distance between the vehicles. Thus, the interval distance between all the vehicles in the parking lot is greatly reduced, the parking of the vehicles in the parking lot is more compact and regular, high-density parking is achieved, and the vehicle capacity of the parking lot is effectively improved.

[0108] In some embodiments, after the vehicle is parked to the virtual parking space, the vehicle sends a parking completion instruction to remind the user of the successful parking; the current position information of the vehicle is acquired and sent to the cloud server, the connection with the cloud server is disconnected, and thus the parking of the vehicle is completed.

[0109] The third aspect of the present application provides a computer storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the parking control method for a vehicle of the above-mentioned embodiments, or the computer program is executed by a processor to implement the parking control method for a cloud server of the above-mentioned embodiments.

[0110] The fourth aspect of the present application provides a vehicle, as shown in the figure, the vehicle 10 comprises at least one processor 1 and a memory 2 connected with the at least one processor 1. Figure 9

[0111] The memory 2 stores a computer program executable by the at least one processor 1, and the at least one processor 1 executes the computer program to implement the parking control method for a vehicle of the above-mentioned embodiments.

[0112] It should be noted that the specific implementation of the vehicle 10 of the embodiments of the present application is similar to the specific implementation of the parking control method for a vehicle of any of the above-mentioned embodiments of the present application, and specific reference is made to the description of the method part, and here is not repeated in order to reduce redundancy.

[0113] According to the vehicle 10 of the embodiments of the present application, by executing the parking control method provided by the above-mentioned embodiments by the processor 1, the vehicle capacity of the parking lot can be effectively improved.

[0114] The fifth aspect of the present application provides a cloud server, as shown in the figure, the cloud server 20 comprises a communication module 3 and a control module 4. Figure 10

[0115] The communication module 3 is adapted to communicate with the vehicle 10; the control module 4 is connected with the communication module 3 and is used to execute the parking control method for a cloud server of the above-mentioned embodiments.

[0116] It should be noted that the specific implementation of the cloud server 20 of the embodiments of the present application is similar to the specific implementation of the parking control method for a cloud server of any of the above-mentioned embodiments of the present application, and specific reference is made to the description of the method part, and here is not repeated in order to reduce redundancy.

[0117] According to the cloud server 20 of the embodiments of the present application, by executing the parking control method of the above-mentioned embodiments by the control module 4, the vehicle capacity of the parking lot can be effectively improved, and the problem of scratching caused by visual judgment error can be effectively avoided, and the success rate of entering the garage can be improved.​​

[0118] In the description of the present specification, any process or method described in the flowchart or otherwise described herein can be understood as representing a module, segment, or portion of code that includes one or more executable instructions for implementing the specified logical functions or steps, and the scope of the preferred embodiments of the present application includes alternatives where the functions can be carried out in the order shown or discussed, including in an essentially simultaneous manner or in the reverse order, according to the functionality involved, as would be understood by those skilled in the art of the embodiments of the present application.

[0119] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a list of executable instructions for implementing the logic function, and can be specifically embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor- based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or in conjunction with such an instruction execution system, apparatus, or device. For the purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electrical apparatus), a portable computer diskette (magnetic apparatus), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber (optical apparatus), and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, by optically scanning the paper or other suitable medium, then electronically converted into a form that is suitable for use by the instruction execution system, apparatus, or device, and then stored in computer memory.

[0120] It should be understood that portions of the present application can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, a number of steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As such, if implemented in hardware, as in another embodiment, any of the following technologies, or a combination thereof, can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like, as are known in the art.

[0121] Those skilled in the art can understand that all or part of the steps of the method carried out by the above-mentioned embodiments can be instructed by a program to relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0122] In addition, each functional unit in each embodiment of the present application can be integrated into one processing module, or each unit can exist physically independently, or two or more units can be integrated into one module. The integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0123] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application. Those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

[0124] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "exemplary embodiment", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the exemplary description of the above terms does not necessarily mean the same embodiment or example.

[0125] Although the embodiments of the present application have been shown and described, those skilled in the art can understand that various changes, modifications, replacements and variations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the claims and their equivalents.

Claims

1. A parking control method for a cloud server in a parking lot, characterized in that, The parking lot has a first-class parking area without designated parking spaces, and the parking control method includes: Receive a parking request signal and obtain the configuration information of the vehicle to be parked based on the parking request signal; Determine whether the configuration information meets the preset parking conditions for entering the first type of parking area, wherein the preset parking conditions include at least radar configuration information and camera configuration information in the configuration information; Determining whether there are valid parking spaces within the first type of parking area based on image information and parking posture information includes: Identify the lane lines of the first type of parking area based on the image information; The angle between each of the two adjacent parked vehicles in the first type of parking area and the lane line is determined based on the minimum tracking frame. Calculate the acceptable width between two adjacent parked vehicles based on the included angle; If the accommodating width is greater than or equal to the minimum allowable parking width of the vehicle to be parked, then it is determined that there is a valid parking space between two adjacent parked vehicles; or, if the accommodating width is less than the minimum allowable parking width, then it is determined that there is no valid parking space between two adjacent parked vehicles. If the preset parking conditions are met and there is a valid parking space in the first type of parking area, a parking permission signal is sent to the vehicle to be parked, so that the vehicle to be parked can complete parking according to the valid parking space.

2. The parking control method according to claim 1, characterized in that, Determining whether there are valid parking spaces within the first type of parking area includes: Receive image information provided by the vehicle to be parked, and acquire vehicle parking image data of the first type of parking area; The parking posture information of each parked vehicle in the first type of parking area is identified based on the vehicle parking image data. Based on the image information and the parking posture information, it is determined whether there is a valid parking space in the first type of parking area.

3. The parking control method according to claim 2, characterized in that, Based on the vehicle parking image data, the parking posture information of each parked vehicle in the first type of parking area is identified, including: Based on the target detection algorithm, a minimum tracking box is generated for each parked vehicle according to the vehicle parking image data; The minimum tracking box is used as the parking posture information for each parked vehicle.

4. The parking control method according to any one of claims 1-3, characterized in that, Also includes: After determining that there are no valid parking spaces in the first type of parking area, a no-parking signal is sent to the vehicle to be parked.

5. The parking control method according to claim 4, characterized in that, Also includes: During the parking process of the vehicle waiting to be parked in the valid parking space, the target tracking algorithm is used to track the parked vehicles next to the valid parking space and the target tracking results are sent to the vehicle waiting to be parked.

6. The parking control method according to claim 1, characterized in that, The parking lot also includes a second type of parking area with designated parking spaces, and the parking control method further includes: If it is determined that the configuration information does not meet the preset parking conditions, an unauthorized signal prohibiting entry into the first type of parking area is sent to the vehicle to be parked. The location information of the second type of parking area is sent to the vehicle to be parked, so that the vehicle to be parked can drive into the second type of parking area and complete parking according to the location information.

7. A cloud server, characterized in that, include: A communication module, the communication module being adapted to communicate with a vehicle; A control module, which is connected to the communication module, is used to execute the parking control method according to any one of claims 1-6.

8. A parking control method, characterized in that, For a vehicle used to communicate with the cloud server of claim 7, the parking control method includes: Send a parking request signal to the cloud server of the parking lot, wherein the parking lot has a first-class parking area without designated parking spaces; Send the vehicle's configuration information to the cloud server; Upon receiving a parking permission signal from the cloud server, the system controls the vehicle to enter the first type of parking area for parking.

9. The parking control method according to claim 8, characterized in that, Controlling the vehicle to enter the first type of parking area for parking includes: Obtain the location information of the first type of parking area and the available parking spaces within the first type of parking area; Based on the available parking spaces, generate virtual parking spaces and parking routes to enter the virtual parking spaces; The vehicle is controlled to park in the virtual parking space according to the parking route.

10. The parking control method according to claim 9, characterized in that, Obtaining valid parking spaces within the first type of parking area includes: Obtain the available parking spaces provided by the cloud server; Alternatively, acquire image information about the area surrounding the vehicle; The valid parking space is determined based on the image information.

11. The parking control method according to claim 9 or 10, characterized in that, Controlling the vehicle to park in the virtual parking space according to the parking route includes: Obtain the distance between the vehicle and the parked vehicle next to the valid parking space; When the interval distance is greater than a preset distance, a parking warning signal is sent; The parking route is adjusted according to the parking warning signal until the vehicle is parked in the virtual parking space.

12. The parking control method according to claim 9 or 10, characterized in that, After guiding the vehicle to park in the virtual parking space according to the parking route, the process also includes: Send parking completion command; Obtain the current location information of the vehicle and send the current location information to the cloud server.

13. A computer storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the parking control method according to any one of claims 1-6, or when the computer program is executed by the processor, it implements the parking control method according to any one of claims 8-12.

14. A vehicle, characterized in that, include: At least one processor; A memory that is communicatively connected to at least one of the processors; The memory stores a computer program that can be executed by at least one of the processors, and when the at least one processor executes the computer program, it implements the parking control method according to any one of claims 8-12.

Images