Parking scheduling method and device, computer equipment and storage medium thereof

Abstract

The embodiment of the invention provides a parking scheduling method and device, computer equipment and a storage medium thereof, and the parking scheduling method is applied to the current edge cloud of an area where a user is located, and comprises the steps: responding to a parking request sent by a user terminal; determining whether an effective empty parking space exists in the area covered by the current edge cloud based on the obtained size information of the vehicle; sending a scheduling request to a central cloud under the condition that the effective empty parking space does not exist in the area covered by the current edge cloud; the scheduling request carries size information of a vehicle and position information of the vehicle; receiving position information of a target parking space sent by the central cloud and a parking path map planned for arriving at the target parking space; the target parking space is determined by other edge clouds except the current edge cloud; and sending the parking path map to the user terminal to guide the user to drive to the target parking space.

Description

Technical Field

[0001] The present application relates to but is not limited to the field of cloud computing, big data and edge computing, and in particular to a parking scheduling method, device, computer equipment and storage medium thereof. Background Art

[0002] With the rapid increase in the number of motor vehicles in cities, the problem of parking difficulties has become increasingly prominent, especially the congestion, complexity and difficulty of parking spaces on ground roads are constantly increasing. In particular, the existing parking scheduling schemes are generally implemented on the vehicle side, that is, the driver looks for empty parking spaces with the naked eye and then drives over to park, which often takes a long time to find a parking space. In addition, there are also situations where multiple drivers find the same car and compete for parking spaces. Therefore, how to achieve parking scheduling with the help of communication technology without relying on individual drivers has become a key issue that needs to be solved. Summary of the invention

[0003] In view of this, embodiments of the present application provide a parking scheduling method, apparatus, computer equipment and storage medium thereof.

[0004] The technical solution of this application is implemented as follows:

[0005] In a first aspect, an embodiment of the present application provides a parking scheduling method, which is applied to the current edge cloud in the user's area, including: responding to a parking request sent by a user terminal, determining whether there is an effective empty parking space in the area covered by the current edge cloud based on the acquired vehicle size information; if there is no effective empty parking space in the area covered by the current edge cloud, sending a scheduling request to a central cloud; the scheduling request carries the vehicle size information and the vehicle location information; receiving the target parking space location information and a parking path map planned to reach the target parking space sent by the central cloud; the target parking space is determined by other edge clouds other than the current edge cloud; and sending the parking path map to the user terminal to guide the user to drive to the target parking space.

[0006] In a second aspect, an embodiment of the present application provides a parking scheduling method, which is applied to a central cloud and includes: receiving a scheduling request sent by a current edge cloud; the scheduling request carries the size information of a vehicle and the location information of the vehicle; in response to the scheduling request indicating that there are no valid empty parking spaces in the area covered by the current edge cloud, scheduling other edge clouds to find empty parking spaces for the vehicle; determining a target parking space from the empty parking spaces in the area covered by the other edge clouds; and sending the location information of the target parking space and a parking path map planned to reach the target parking space to the current edge cloud.

[0007] In a third aspect, an embodiment of the present application provides a parking scheduling device, which is applied to a current edge cloud in a user's area, including:

[0008] A first determination module is used to respond to a parking request sent by a user terminal and determine whether there is an effective empty parking space in the area covered by the current edge cloud based on the acquired vehicle size information;

[0009] A first sending module is used to send a dispatch request to the central cloud when there is no valid empty parking space in the area covered by the current edge cloud; the dispatch request carries the size information of the vehicle and the location information of the vehicle;

[0010] A first receiving module is used to receive the location information of the target parking space and the parking path map planned to reach the target parking space sent by the central cloud; the target parking space is determined by other edge clouds except the current edge cloud;

[0011] The second sending module is used to send the parking path map to the user terminal to guide the user to drive to the target parking space.

[0012] In a fourth aspect, an embodiment of the present application provides a parking scheduling device, which is applied to a central cloud and includes:

[0013] The third receiving module is used to receive a scheduling request sent by the current edge cloud in the user's area; the scheduling request carries the size information of the vehicle and the location information of the vehicle;

[0014] A scheduling module, configured to schedule other edge clouds to find a valid empty parking space for the vehicle in response to the scheduling request indicating that there is no valid empty parking space in the area covered by the current edge cloud;

[0015] A fourth determination module, configured to determine a target parking space from valid empty parking spaces in the area covered by the other edge clouds;

[0016] The seventh sending module is used to send the location information of the target parking space and the parking path map planned to reach the target parking space to the current edge cloud.

[0017] In a fifth aspect, an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and when the processor executes the program, it implements some or all of the steps in the above method.

[0018] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements part or all of the steps in the above method when executed by a processor.

[0019] In an embodiment of the present application, first, the current edge cloud in the area where the user is located responds to the parking request sent by the user terminal, and determines whether there is a valid empty parking space in the area covered by the current edge cloud based on the acquired vehicle size information. In this way, the accuracy of the current edge cloud in determining whether there is a valid empty parking space is improved; secondly, when there is no valid empty parking space in the area covered by the current edge cloud, the current edge cloud sends a scheduling request to the central cloud, so that the central cloud ensures that the edge cloud uniformly schedules the central cloud to find a valid empty parking space for the vehicle; then, the current edge cloud receives the location information of the target parking space and the parking path map planned to reach the target parking space sent by the central cloud. The target parking space is determined by other edge clouds except the current edge cloud. In this way, other edge clouds across regions dynamically recommend the target parking space to the user; finally, the current edge cloud sends a parking path map to the user terminal to guide the user to the target parking space. In this way, the user's parking time is saved, thereby bringing the user a better parking experience.

[0020] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0022] Figure 1 A schematic diagram of an implementation flow of a parking scheduling method provided in an embodiment of the present application;

[0023] Figure 2 A schematic diagram of the architecture of a computing power network system provided in an embodiment of the present application;

[0024] Figure 3 A schematic diagram of a roadside side parking space scenario provided in an embodiment of the present application;

[0025] Figure 4 A schematic diagram of a vehicle blind spot provided in an embodiment of the present application;

[0026] Figure 5 A schematic diagram of edge-to-edge collaboration for cross-domain scheduling of edge clouds provided in an embodiment of the present application;

[0027] Figure 6 An overall schematic diagram of a vehicle parking method provided in an embodiment of the present application;

[0028] Figure 7 for Figure 6 Schematic diagram of the implementation process of step 607;

[0029] Figure 8 A schematic diagram of the composition structure of a parking scheduling device for an edge cloud in a user's area provided in an embodiment of the present application;

[0030] Fig. 9 A schematic diagram of the composition structure of a parking scheduling device applied to a central cloud provided in an embodiment of the present application;

[0031] Fig.10 A hardware entity diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application are further elaborated in detail below in conjunction with the drawings and embodiments. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0033] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0034] The terms "first / second / third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that "first / second / third" can be interchanged with a specific order or sequence where permitted so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing this application and are not intended to limit this application.

[0036] In order to facilitate understanding of the embodiments of the present application, the technical solutions related to the embodiments of the present application and the shortcomings of the technical solutions are briefly introduced below.

[0037] The existing parking assistance systems are reversing radar systems and systems containing sonar sensors. Their function is to help the driver detect the distance of surrounding objects when reversing and remind the driver that there are objects behind. When the vehicle gear lever is put into reverse gear, the reversing radar automatically starts working. When the probe detects that the distance between the vehicle and the rear object is less than the preset value, the buzzer sounds an alarm. When the vehicle continues to reverse and approach the object, the frequency of the alarm sound will gradually increase and finally become a long beep. Some high-end vehicles have forward vision functions, but they are not popular. However, the reversing radar system has the following disadvantages: due to the problem of inaccurate measurement accuracy of millimeter-wave radar in rainy and foggy days, errors are inevitable in practical applications. For example, even if the constant beep prompts during the warehousing action, the actual collision object or obstruction may not interfere with parking. For example, weeds on the flower bed and raincoats on electric vehicles will interfere with the driver's judgment of the parking space to a certain extent; the auxiliary detection range of the reversing radar is limited to 4 to 6 corners of the vehicle, and there is still a visual blind spot for the driver at a 45-degree oblique angle to the front of the vehicle, which is easy to cause misjudgment and collision.

[0038] The panoramic surround view system is deployed in high-end cars, including multiple cameras installed around the car, image acquisition components, video synthesis / processing components, digital image processing components and on-board displays; the cameras take images of the front, back, left and right sides of the car respectively, and the images are converted into digital information by the image acquisition components and sent to the video synthesis / processing components. The images processed by the video synthesis / processing components are converted into analog signals for output by the digital image processing components, and the panoramic image information of the car and its surrounding environment is generated on the on-board display installed inside the car. The panoramic surround view system sets up 4 to 8 wide-angle cameras around the vehicle that can cover all the fields of view around the vehicle, and processes the multi-channel video images collected at the same time into a 360-degree overhead view of the vehicle's surroundings, and finally displays it on the screen of the center console, so that the driver can clearly check whether there are obstacles around the vehicle and understand the relative position and distance of the obstacles, helping the driver to park the vehicle easily. Not only is it very intuitive, but there are no blind spots, which can improve the driver's ability to calmly control the vehicle to park or pass through complex roads, effectively reducing the occurrence of scratches, collisions, sinking and other accidents. However, the panoramic surround view system has the following shortcomings: it is limited by the computing power limit and cache of the vehicle computer. Since the vehicle computer is also an electronic system, there is a tendency for electronic components to age, which will increase the delay in software operation and image processing. For the user side, it will cause imaging jams and virtual positions, indirectly leading to misjudgment by the driver. The market share of the panoramic surround view system is relatively low and is limited to high-end luxury vehicle configurations, because a large number of expensive cameras and radar devices need to be configured on the vehicle side, which increases consumer costs.

[0039] Based on this, the embodiment of the present application provides a parking scheduling method, such as Figure 1As shown, the method may include the following steps S101 to S108, wherein:

[0040] Step S101, the current edge cloud in the area where the user is located responds to the parking request sent by the user terminal, and determines whether there is an effective empty parking space in the area covered by the current edge cloud based on the acquired vehicle size information;

[0041] Here, the user terminal includes at least one of a mobile terminal and a vehicle-mounted terminal. The mobile terminal can be a mobile phone application (Application, App); the parking request is sent by the user terminal to the central cloud, and then sent by the central cloud to the edge cloud. For example, in the case where the vehicle is a non-intelligent vehicle, the user terminal can be a mobile terminal; in the case where the vehicle is a smart vehicle, the user terminal can be a mobile terminal or a vehicle-mounted terminal. The size information of the vehicle can be sent by the user terminal together with the parking request. In some embodiments, in the case where the user terminal does not send the size information of the vehicle, the size information of the vehicle can also be obtained by processing the vehicle data collected by the sensing device.

[0042] In some implementations, the implementation of “obtaining vehicle size information” in step S101 may include the following steps S1011 to S1014, wherein:

[0043] Step S1011, the current edge cloud dispatches sensing devices within a preset range around the vehicle to collect vehicle data based on the location information of the vehicle;

[0044] Here, the sensing devices include cameras and lidars, and the vehicle's location information may be uploaded by the user after the user terminal sends a parking request and the fifth generation mobile communication technology (5G) network verifies the user's identity and connects to the central cloud service.

[0045] During implementation, if the current position of the vehicle is within the area of ​​edge cloud A, it is only necessary to dispatch cameras and lidars in the area covered by edge cloud A within a preset range around the vehicle to collect vehicle data. For example, the preset range around the vehicle can be 1 kilometer (km) around the vehicle.

[0046] Step S1012, the current edge cloud obtains the image sequence of the vehicle captured by the camera and the scanning data of the vehicle by the laser radar;

[0047] Here, the image sequence of the vehicle captured by the camera refers to: the continuous images of the vehicle captured by the camera installed in the vehicle detection area; the scanning data of the vehicle by the laser radar refers to: the scanning data of the vehicle obtained after the laser radar scans the vehicle.

[0048] Step S1013, the current edge cloud generates three-dimensional point cloud data of the vehicle based on the image sequence of the vehicle and the scan data of the vehicle;

[0049] During implementation, the image sequence of the vehicle and the scanning data of the vehicle are fused to generate three-dimensional point cloud data of the vehicle.

[0050] Step S1014: the current edge cloud determines the size information of the vehicle based on the three-dimensional point cloud data of the vehicle.

[0051] During implementation, the vehicle size information is obtained by fitting the bounding box or minimum bounding sphere of the three-dimensional point cloud data of the vehicle through the least square method, thus improving the accuracy of the vehicle size information.

[0052] Step S102, when there is no valid empty parking space in the area covered by the current edge cloud, the current edge cloud sends a scheduling request to the central cloud; the scheduling request carries the size information of the vehicle and the location information of the vehicle;

[0053] Here, the fact that there is no valid empty parking space in the area covered by the current edge cloud means that the current edge cloud determines that the size information of the vehicle is larger than the size information of the empty parking space, or there is an obstacle on the empty parking space.

[0054] During implementation, if there are no valid empty parking spaces in the area covered by the current edge cloud, the current edge cloud sends a scheduling request carrying the vehicle's size information and location information to the central cloud, so that the central cloud can dispatch other edge clouds close to the vehicle's location to find valid empty parking spaces for the vehicle.

[0055] In some embodiments, the current edge cloud determines that there is no valid empty parking space, which may include the following steps S1021 and S1022, wherein:

[0056] Step S1021, the current edge cloud determines the size information of the empty parking space;

[0057] In implementation, the current edge cloud can determine the size information of the empty parking space in the following two ways.

[0058] Method 1: Determine the size information of the empty parking space based on the image frame containing the empty parking space captured by the camera. In some embodiments, the implementation of step S1021 "determine the size information of the empty parking space" may include the following steps S111 to S113, wherein:

[0059] Step S111, the current edge cloud determines an empty parking space from an image frame containing an empty parking space collected by the camera;

[0060] In implementation, since the image frame containing the empty parking space captured by the camera may also contain other obstacles (eg, trees), the empty parking space needs to be segmented from the image frame first to facilitate determination of the geometric shape of the empty parking space.

[0061] Step S112, in the absence of a traffic stop line, the current edge cloud determines the geometric shape of the empty parking space based on the edge point set of the front vehicle and the edge point set of the rear vehicle of the empty parking space;

[0062] During implementation, if there is no traffic stop line at the location of the empty parking space, the current edge cloud uses the least squares method or random sample consensus (RanSaC) algorithm to fit the boundary polygon of the empty parking space based on the edge point set of the front vehicle and the edge point set of the rear vehicle of the empty parking space, thereby determining the geometric shape of the empty parking space.

[0063] Step S113: The current edge cloud determines the size information of the empty parking space based on the diagonal length in the geometric shape of the empty parking space and the distance between the two farthest boundary points.

[0064] During implementation, the current edge cloud uses the length of the diagonal in the geometry of the empty parking space and the distance between the two farthest boundary points to fit the length, width and height of the empty parking space, thereby determining the size information of the empty parking space.

[0065] Method 2: Determine the size information of the empty parking space based on the environmental point cloud data scanned by the laser radar. In some embodiments, the implementation of step S1021 "determine the size information of the empty parking space" may include the following steps S121 to S123, wherein:

[0066] Step S121, the current edge cloud obtains environmental point cloud data scanned by the laser radar;

[0067] Here, the environmental point cloud data includes vehicle point cloud data and vacant parking lot point cloud data.

[0068] Step S122, the current edge cloud segments the environment point cloud data to obtain the vehicle point cloud data and the vacant parking lot point cloud data;

[0069] During implementation, the current edge cloud segments the environmental point cloud data to obtain vehicle point cloud data and empty parking space point cloud data, so as to determine the size information of the empty parking space based on the empty parking space point cloud data.

[0070] Step S123: the current edge cloud determines the size information of the empty parking space based on the empty parking space cloud data.

[0071] During implementation, the current edge cloud determines the boundary polygon of the empty parking space based on the empty parking space point cloud data, thereby determining the geometric shape of the empty parking space. Then, the length of the diagonal in the geometric shape of the empty parking space and the distance between the two farthest boundary points are used to fit the length, width and height of the empty parking space, thereby determining the size information of the empty parking space.

[0072] Step S1022: When there is a mismatch between the size information of the vehicle and the size information of the empty parking space, the current edge cloud determines that there is no valid empty parking space.

[0073] Here, the mismatch between the size information of the vehicle and the size information of the empty parking space means that the size information of the vehicle is larger than the size information of the empty parking space.

[0074] During implementation, if the size information of the vehicle is larger than the size information of the empty parking space, the current edge cloud determines that there is no valid empty parking space, and sends the information of the non-existence of the valid parking space and the scheduling request to the central cloud, so that the central cloud can schedule other edge clouds to determine the validity of the empty parking space.

[0075] Step S103, the central cloud receives a dispatch request sent by the current edge cloud in the area where the user is located; the dispatch request carries the size information of the vehicle and the location information of the vehicle;

[0076] During implementation, the central cloud receives a scheduling request carrying the vehicle's size information and location information sent by the current edge cloud to find an effective empty parking space for the vehicle through other edge clouds.

[0077] Step S104: In response to the scheduling request, the central cloud indicates that there is no valid empty parking space in the area covered by the current edge cloud, and schedules other edge clouds to find a valid empty parking space for the vehicle;

[0078] During implementation, if there are no valid empty parking spaces in the area covered by the current edge cloud, the central cloud will respond to the scheduling request sent by the current edge cloud and schedule other edge clouds to find valid empty parking spaces for the vehicle.

[0079] In some embodiments, the implementation of step S104 “dispatching other edge clouds to find an effective empty parking space for the vehicle” may include the following steps S1041 and S1042, wherein:

[0080] Step S1041: the central cloud sends a parking space request to the other edge cloud; the parking space request carries the size information of the vehicle;

[0081] Here, when there are no valid empty parking spaces in the area covered by the current edge cloud in the user's area, the central cloud sends a parking space request carrying the vehicle's size information to other edge clouds, so that other edge clouds can determine the validity of the empty parking spaces based on the vehicle's size information.

[0082] Step S1042, the central cloud receives the judgment result sent by the other edge cloud; the judgment result is used to indicate whether there is a valid empty parking space in the area covered by the other edge cloud;

[0083] Here, the central cloud receives the judgment results of whether there are valid empty parking spaces or not in the areas covered by other edge clouds, which are sent by other edge clouds.

[0084] Step S105, the central cloud determines the target parking space from the valid empty parking spaces in the area covered by the other edge clouds;

[0085] Here, the target parking space refers to: there are valid empty parking spaces in the areas covered by other edge clouds and the valid empty parking spaces closest to the location of the vehicle.

[0086] In some embodiments, the implementation of step S105 "determining the target parking space from the valid empty parking spaces in the area covered by the other edge clouds" may include the following steps S1051 to S1053, wherein:

[0087] Step S1051, the central cloud receives the size information of the empty parking spaces sent by the edge clouds in other areas;

[0088] During implementation, the central cloud receives the size information of empty parking spaces periodically sent by the edge clouds in other regions, ensuring that the central cloud can periodically grasp the update status of empty parking spaces and the updated size information of empty parking spaces of the edge clouds in other regions.

[0089] Step S1052, the central cloud determines whether there is a valid empty parking space in the edge cloud of the other area based on the size information of the vehicle and the size information of the empty parking space;

[0090] During implementation, the central cloud determines whether there are valid empty parking spaces in the edge clouds of other areas based on the vehicle's size information and the size information of the empty parking spaces. If the vehicle's size information is larger than the size information of the empty parking spaces, there are no valid empty parking spaces; if the vehicle's size information is smaller than the size information of the empty parking spaces, there are valid empty parking spaces.

[0091] Step S1053: When there are at least two valid empty parking spaces in the area covered by the other edge clouds, the central cloud determines the valid empty parking space closest to the vehicle as the target parking space.

[0092] During implementation, when there are at least two valid empty parking spaces in the area covered by other edge clouds, the central cloud will determine the valid empty parking space in the area covered by other edge clouds closest to the vehicle as the target parking space to reduce the time it takes for the user to travel to the target parking space.

[0093] Step S106, the central cloud sends the location information of the target parking space and the parking path map planned to reach the target parking space to the current edge cloud;

[0094] During implementation, the central cloud sends the location information of the target parking space and the parking path map planned to reach the target parking space to the current edge cloud, so as to facilitate the user to drive to the target parking space according to the planned parking path map.

[0095] Step S107, the current edge cloud receives the location information of the target parking space and the parking path map planned to reach the target parking space sent by the central cloud; the target parking space is determined by other edge clouds except the current edge cloud;

[0096] During implementation, the current edge cloud receives the location information of the target parking space and the parking path map planned to reach the target parking space sent by the central cloud, enabling other edge clouds across regions to dynamically recommend target parking spaces to users.

[0097] Step S108: The current edge cloud sends the parking path map to the user terminal to guide the user to drive to the target parking space.

[0098] Correspondingly, the user terminal receives the parking path map sent by the current edge cloud, and uses the parking path map to drive to the target parking space, thereby saving the user's parking time and bringing the user a better parking experience.

[0099] In an embodiment of the present application, first, the current edge cloud in the area where the user is located responds to the parking request sent by the user terminal, and determines whether there is a valid empty parking space in the area covered by the current edge cloud based on the acquired vehicle size information. In this way, the accuracy of the current edge cloud in determining whether there is a valid empty parking space is improved; secondly, when there is no valid empty parking space in the area covered by the current edge cloud, the current edge cloud sends a scheduling request to the central cloud, so that the central cloud ensures that the edge cloud uniformly schedules the central cloud to find a valid empty parking space for the vehicle; then, the current edge cloud receives the location information of the target parking space and the parking path map planned to reach the target parking space sent by the central cloud. The target parking space is determined by other edge clouds except the current edge cloud. In this way, other edge clouds across regions dynamically recommend the target parking space to the user; finally, the current edge cloud sends a parking path map to the user terminal to guide the user to the target parking space. In this way, the user's parking time is saved, thereby bringing the user a better parking experience.

[0100] In some embodiments, the method further includes the following steps S131 to S133, wherein:

[0101] Step S131, the current edge cloud receives the parking space request sent by the central cloud; the parking space request carries the size information of the vehicle;

[0102] During implementation, the current edge cloud receives a parking space request carrying the vehicle size information sent by the central cloud, so as to determine whether there is an effective empty parking space in the area covered by the current edge cloud according to the vehicle size information through the current edge cloud.

[0103] Step S132, the current edge cloud responds to the parking space request and determines whether there is an effective empty parking space in the area covered by the current edge cloud based on the size information of the vehicle, and obtains a determination result;

[0104] Here, the judgment result includes whether there are valid empty parking spaces in the area covered by the current edge cloud and whether there are no valid empty parking spaces in the area covered by the current edge cloud.

[0105] Step S133: the current edge cloud sends the judgment result to the central cloud.

[0106] In some embodiments, when the vehicle has reached a preset range of the target parking space, the method further includes the following steps S141 to S144, wherein:

[0107] Step S141, the current edge cloud obtains the blind spot image of the vehicle entering the warehouse collected by the camera;

[0108] Here, the blind spot image of the vehicle includes the image when the front wheels of the vehicle enter the garage and the image when the rear wheels enter the garage. For example, the image when the front wheels enter the garage can be a 45-degree oblique view image of the front of the vehicle, and the image when the rear wheels enter the garage can be a 90-degree image of the rear of the vehicle.

[0109] During implementation, the camera corresponding to the current edge cloud collects a 45-degree oblique image of the front of the vehicle and a 90-degree image of the rear of the vehicle, and combines it with the outline of the vehicle to generate a video to guide users to park.

[0110] Step S142, the current edge cloud determines the outline of the vehicle based on the size information of the vehicle;

[0111] Step S143, the current edge cloud responds to the entry request sent by the user terminal, and determines the entry video of the vehicle based on the blind spot image of the vehicle and the outline of the vehicle;

[0112] During implementation, when a user has a request to park in a garage, the current edge cloud responds to the parking request sent by the user terminal, and determines the parking video of the vehicle based on the blind spot image of the vehicle and the outline of the vehicle.

[0113] Step S144, the current edge cloud sends the vehicle entry video to the user terminal to guide the user to park the vehicle.

[0114] Correspondingly, the mobile terminal or the vehicle-mounted terminal receives the vehicle entry video sent by the current edge cloud to guide the user to park the vehicle through the vehicle entry video.

[0115] In some embodiments, when the vehicle is a smart car, the current edge cloud sends the parking path map and the vehicle's entry video to the user terminal; the user terminal includes at least one of a mobile terminal and a vehicle-mounted terminal; when the vehicle is a non-smart car, the current edge cloud sends the parking path map and the vehicle's entry video to the mobile terminal.

[0116] With the development of vehicle-road collaboration technology, edge cloud computing network services that meet the application needs of vehicle terminals have gradually become available. Changes in the way edge cloud computing network is absorbed and the sinking of edge cloud computing power has enabled vehicle terminal computing power to be unloaded or lightweight. Similarly, when existing vehicles that do not have intelligence and vehicle terminal computing power participate in traffic activities, they can also use vehicle-road collaboration technology to solve different parking scheduling needs. The embodiment of the present application provides another parking scheduling method, which uses vehicle-road collaboration technology, that is, an edge cloud with edge computing capabilities to analyze traffic information data such as vehicles and parking spaces collected by road-side sensing equipment, and sends the analyzed information to the user terminal through the mobile operator network.

[0117] In addition, with the enhancement of edge computing capabilities of edge cloud, the edge cloud computing network has met the conditions for realizing real-time interaction between central cloud, edge cloud and user terminal. For example, the development of road-side sensing devices such as high-definition cameras, night vision cameras, and lidar has achieved millisecond-level big data collection. These road-side sensing devices can perform structured processing on the collected data on the terminal side. The accuracy of data collected by road-side sensing devices has also improved accordingly. For example, the clarity of images or videos in rainy, snowy and foggy weather has been enhanced, and the accuracy of night vision imaging and point cloud imaging has been improved. At the same time, these road-side sensing devices are connected to the edge cloud, which has the ability to analyze real-time data. The edge computing unit in the edge cloud is integrated with cloud computing to generate an edge cloud computing network. The central cloud gathers data processed and analyzed by the edge cloud and uniformly dispatches edge clouds in different regions.

[0118] The embodiment of the present application provides another parking scheduling method, in which the road-side sensing device uploads the collected traffic information data such as vehicles and parking spaces to the edge cloud, so as to perform real-time data analysis and auxiliary information output through the edge cloud, and provide users with effective parking guidance and in-and-out assistance functions. In addition, the computing power sinking structure of the edge cloud ensures the latency requirements of the business and improves the user's service experience. The edge clouds in multiple regions are connected to the central cloud through the 5G network. The central cloud determines the available parking spaces according to the user's location allocation to the nearest edge cloud, realizing the precise scheduling of the central cloud to the edge cloud and the coordination of edge clouds in different regions, so as to realize dynamic cross-domain parking space recommendations for users. The embodiment of the present application does not rely on vehicle computing power, but is completely based on road-side sensing devices and edge clouds to assist users in parking. It is a typical vehicle-road collaborative application scenario.

[0119] Figure 2 A schematic diagram of the architecture of a computing power network system provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the central cloud 20 serves as a central control platform, connecting edge cloud A 21, edge cloud B 22 and edge cloud C 23 through a bearer network, and performs multi-region edge cloud management, data aggregation, big data computing and analysis, edge cloud scheduling and optimization of non-real-time services, etc.

[0120] The edge cloud is responsible for the analysis of local data, the issuance of conclusions, and the management of computing power equipment (operator management end and supplier computing power module), such as Figure 2 As shown in the figure, the edge cloud and the edge computing unit are connected in an edge-controlled interface to achieve the management of the edge computing unit by the edge cloud. The edge cloud sends the analysis conclusions of local data (for example, real-time video, path planning, digital twin map, and voice navigation prompts, etc.) to the user side in real time through the 5G base station. The user side must have at least a 4 / 5G mobile terminal to interact through the application or the vehicle side must have a car system with a display (supporting 4 / 5G modules) to receive the analysis conclusions.

[0121] The edge computing unit is deployed downward, as close to the road as possible. The edge computing unit must be deployed near the random parking spaces involved in the application embodiment. The edge computing unit can be co-located with the 5G base station, or it can be directly connected to the road-side sensing device. The road-side sensing device transmits the collected data to the edge computing unit through the Uu interface. For example, the sensing device inserts a phone card and transmits data through the wireless Uu interface. The edge computing unit and the edge cloud are logically a network element, and the hardware is separable.

[0122] The sensing device 24 includes an intelligent high-definition camera and a laser radar, wherein the intelligent high-definition camera needs to meet the requirements of 4K high-definition, rainy and foggy climates, and nighttime coping capabilities. The random parking spaces involved in the embodiments of this application must be within the coverage of the sensing device. The sensing device should at least be able to transmit the collected data to the edge computing unit through the Uu interface.

[0123] The present application embodiment provides another parking scheduling method comprising the following steps:

[0124] Step 1: Collect the spatial data of parking spaces;

[0125] The parking spaces marked in parking lots and on roads are relatively easy to calibrate and calculate. For random parking spaces that are not marked, calculation and simulation are required based on the collected valid data. Figure 3 A schematic diagram of a roadside side parking space scenario provided in an embodiment of the present application, such as Figure 3 As shown, the embodiment of the present application collects spatial data of parking spaces through a road-side sensing device 24, for example, a camera or a laser radar collects spatial data of parking spaces.

[0126] 1. Cameras collect spatial data of parking spaces: Use multiple high-definition cameras with different viewing angles around the parking spaces to capture images of empty parking spaces as much as possible, and upload the images to the edge computing unit. In the process of capturing images of empty parking spaces, multiple requirements must be met, including acquisition frequency, sampling frequency, resolution, and environmental conditions.

[0127] The starting conditions for the camera to collect spatial data of parking spaces are: 1. There is a parking request within the computing network service range, and the empty parking space detection is started. 2. There is object movement in the empty parking space shooting area, and the dynamic information frame of the empty parking space needs to be re-collected for update. 3. Set periodic parking space vacancy detection. The spatial outline of the detected area can be delineated by electronic fences. Condition 1 is a necessary condition for 2. 3. When the user initiates an outbound application, also within the computing network service area, the user initiates an outbound application through the network, and the central cloud assigns the corresponding sensing device of the nearest edge cloud to start the collection. The overall process is consistent with the inbound application.

[0128] 2. LiDAR collects spatial data of parking spaces:

[0129] The environment is scanned by the laser radar configured at the road end, and the collected point cloud data is uploaded to the edge computing unit. The laser radar rotates one circle, that is, the number of points scanned in one scanning cycle is 1800*64=115200 points, the sampling frequency is about 10 Hz, and generally generates a code stream of 40 megabits per second (Mbps), which can solve the data coverage of the circular area with a radius of 100 meters. In the parking scene, since the sensing equipment is deployed on the roadside and in a fixed position, it can collect the spatial data of random parking spaces more accurately.

[0130] The conditions for starting the laser radar to collect parking space spatial data are: 1. There is a parking request within the computing network service range, and the collection of parking space spatial data is started. 2. Set periodic parking space vacancy detection.

[0131] 3. Collecting users’ vehicle data:

[0132] After the user initiates a parking request, the 5G network verifies the user's identity and connects to the central cloud service, and requires the user to report the user's location information. The central cloud dispatches the corresponding sensing device of the edge cloud closest to the user's location to collect the user's vehicle data based on the user's location information. The collection of the user's vehicle data mainly includes vehicle calibration, vehicle volume estimation, and important real-time video frame shooting (small-scale high-definition follow-up shooting). Figure 4 As shown, the images in the real-time video may include a dynamic image 41 of a 90-degree blind spot at the rear of the vehicle, and a dynamic image 42 of a 45-degree oblique blind spot of the driver at the front of the vehicle; the remaining angles depend on the shooting angle and quantity conditions of the perception device, and the user's vehicle data is collected by shooting at as many angles as possible, and the collected user's vehicle data is uploaded to the edge cloud for calculation.

[0133] Step 2: Analyze the collected spatial data of parking spaces;

[0134] The following analysis is performed on the spatial data of the parking space collected by the camera in step 1 and the spatial data of the parking space collected by the lidar:

[0135] 1. Upload the spatial data of the parking space collected by the camera or the spatial data of the parking space collected by the lidar to the edge computing unit for data structuring processing to obtain regulated structured data; upload the regulated structured data to the edge cloud through the Uu interface for digital twin rendering to obtain a dynamic image of the spatial structure of the parking space.

[0136] The spatial dimensions of the parking spaces are calculated based on the collected spatial data of the parking spaces, and the spatial dimensions of the parking spaces are compared with the spatial dimensions of the vehicles as follows:

[0137] For the image frames containing parking spaces captured by the camera, it is necessary to first use a deep learning-based object detection algorithm to perform object detection on the image frames containing parking spaces in order to segment the parking spaces from the image frames. For each detected parking space, the following steps can be used to calculate the spatial dimensions of the parking space:

[0138] (1) In the absence of traffic stop lines, the edge point set of the front or rear vehicle of the parking space can be selected for offset calculation. If no vehicle is parked in advance, the first parking position is determined according to the traffic markings. The edge point set must be determined in consideration of retaining a safe distance. The boundary polygon of the parking space is fitted using the least squares method or random sampling consensus algorithm to obtain the geometric shape of the parking space.

[0139] (2) The length and width of the parking space are calculated by fitting the diagonal length of the geometric shape of the parking space and the distance between the two farthest boundary points, and presented on the front end in the form of an electronic fence.

[0140] (3) The edge cloud determines whether the parking space is suitable for the vehicle based on the vehicle's reported space dimensions and the parking space dimensions. It can also make decisions based on the set parking space size threshold. For example, the length and width of the parking space need to be greater than a certain value, while the length and width of the parking space cannot exceed a certain value. If the size of the parking space is within the threshold range, the parking space is considered valid.

[0141] For the point cloud data scanned by LiDAR, the following steps can be used to calculate the spatial dimensions of the parking space:

[0142] (1) Segment the point cloud data of the vehicle and the parking space to obtain the point cloud data of the vehicle and the point cloud data of the parking space.

[0143] (2) For the point cloud data of each parking space, a method similar to that of the image frame can be used to calculate the length and width of the parking space.

[0144] (3) The edge cloud determines whether the parking space is suitable for parking the vehicle based on the space size of the vehicle reported by the vehicle and the space size of the parking space. It can also use a method similar to the image frame to set a parking space size threshold to make a decision. If the size of the parking space is within the threshold range, the parking space is considered valid.

[0145] 2. The edge cloud collects high-definition image frames of users entering and leaving the warehouse, processes them, and sends them to the user side to guide the user to enter and exit the warehouse. This method is mainly used for live video assistance of in-and-out actions, and supports mobile app playback.

[0146] 3. Smart cars report vehicle information through the 5G network. The edge cloud determines the vehicle's spatial dimensions in advance based on the vehicle model and type, and then allocates cameras or lidars to collect vehicle data based on the vehicle's location information and calculates the vehicle's spatial dimensions. Non-smart cars can only estimate the size of the vehicle based on the vehicle data collected by cameras or lidars. The following steps can be used to calculate the vehicle's spatial dimensions:

[0147] (1) Collect vehicle data: Install a camera in the detection area to obtain the image sequence of the vehicle passing through the detection area and the laser radar scanning data of the vehicle.

[0148] (2) Preprocessing vehicle data: Preprocess the acquired image sequence, including image correction, distortion correction, and image segmentation operations, to improve image quality. At the same time, the laser radar scanning data of the vehicle is fused with the vehicle's image sequence to generate the vehicle's three-dimensional point cloud data.

[0149] (3) Labeling vehicle information in the vehicle image sequence: labeling the vehicle position, size, and direction information in the vehicle image sequence.

[0150] (4) Training on labeled vehicle image sequences: Use a deep learning model to train on labeled vehicle image sequences to identify and locate vehicles.

[0151] (5) Calculating the spatial dimensions of the vehicle: Based on the three-dimensional point cloud data of the vehicle and the vehicle identification and positioning results, the spatial dimensions of the vehicle are calculated by using the least squares method to fit the bounding box of the three-dimensional point cloud data or the minimum bounding sphere method.

[0152] (6) If LiDAR is not configured, the image sequence collected by the camera is used to determine the spatial dimensions of the vehicle.

[0153] 4. If the edge cloud determines that there is no valid parking space based on the spatial dimensions of the parking space and the spatial dimensions of the vehicle, the central cloud will query the nearest random parking space that can accommodate the vehicle for recommendation and path planning. If there is a valid parking space, the path planning will be carried out and the user will be guided to the vicinity of the parking space.

[0154] Step 3: Send analysis results;

[0155] When a user applies for parking, the sensing device collects data on random parking spaces and uploads the collected data on random parking spaces to the edge cloud. The edge cloud calculates the spatial dimensions of random parking spaces, integrates maps, plans paths, and integrates user dynamic real-time videos, and sends the real-time dynamic images of the parking space outline and the vehicle's entry scene to the user side to assist the user in finding a parking space and parking. When a user applies for exiting the warehouse, through the interaction of the mobile network, the 5G network obtains the user's location and notifies the central cloud to dispatch the sensing device corresponding to the edge cloud to collect data on random parking spaces, and sends the real-time exit reference video of the vehicle to the user side to assist the user in exiting the warehouse. Before the vehicle enters the warehouse, if the edge cloud determines that the spatial dimensions of the parking space do not match the spatial dimensions of the vehicle, the edge cloud sends information to the applying vehicle through Uu. The information includes periodically detected vacant parking space information, recommended point map path planning, and prompt messages.

[0156] Step 4: Cross-domain scheduling of edge cloud edge collaboration.

[0157] Figure 5 A schematic diagram of edge-to-edge collaboration for cross-domain scheduling of edge clouds provided in an embodiment of the present application is shown in FIG. Figure 5As shown, edge cloud A 21, edge cloud B 22, and edge cloud C 23 cover three different parking areas respectively, and send and receive user-side information through the 5G network. The edge cloud sends the detection results of the parking space to the central cloud through periodic parking space detection. When the user terminal (UE) 25 located in the edge cloud A area applies for parking, the edge cloud determines whether there is a valid parking space based on the spatial dimensions of the random parking space and the spatial dimensions of the vehicle. When there is no valid parking space in the edge cloud A area, edge cloud A sends a scheduling request carrying the size information and location information of the vehicle to the central cloud. After receiving the scheduling request, the central cloud starts the scheduling process, calculates the nearest edge cloud B and edge cloud C (the edge cloud is not limited to 2, and it needs to be judged nearby based on the location information of the vehicle), and sends the spatial dimensions of the vehicle to edge cloud B and edge cloud C. After receiving the spatial dimensions of the vehicle, edge cloud B and edge cloud C start a round of random parking space scanning, and compare the spatial dimensions of the random parking spaces with the spatial dimensions of the vehicle to determine whether there is a valid parking space. If there is a valid parking space, the location of the parking space is sent to the central cloud, and the central cloud sends the location of the parking space to edge cloud A. Edge cloud A sends the planned parking path map to UE to guide the user to drive near the recommended parking space. Edge cloud B calls the roadside sensing device to guide the user to park in the garage. It should be noted that if the vehicle's location information is obtained from the UE, the central cloud sends the vehicle's location information to the scheduled edge cloud. If the vehicle's location information is obtained from the base station, the central cloud needs to obtain the vehicle's location information through the 5G network and send the vehicle's location information to the edge cloud.

[0158] Figure 6 An overall schematic diagram of a vehicle parking method provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, vehicle parking includes the following steps:

[0159] Step 601: The user terminal randomly initiates a parking request;

[0160] Here, the parking request is sent from the user terminal to the central cloud, and then from the central cloud to the edge cloud.

[0161] Step 602: For the smart car, the vehicle terminal reports the vehicle information and the location of the vehicle located by the 5G base station;

[0162] Here, the vehicle information includes the make and model of the vehicle, etc.

[0163] Step 603, for non-intelligent vehicles, the 5G base station locates the position of the vehicle;

[0164] Step 604, the central cloud dispatches the sensing device corresponding to the edge cloud closest to the vehicle to collect vehicle data;

[0165] Step 605, based on the vehicle information reported by the vehicle terminal, the spatial dimensions of the vehicle are calculated by edge cloud computing;

[0166] Step 606, collecting vehicle data based on the sensing device, and calculating the spatial dimensions of the vehicle through edge cloud computing;

[0167] Step 607, the edge cloud compares the spatial dimensions of the vehicle with the spatial dimensions of the random parking space;

[0168] Step 608, the edge cloud determines whether the vehicle can enter the warehouse;

[0169] Here, if yes, that is, the vehicle can enter the warehouse, then step 610 is executed; if no, that is, the vehicle cannot enter the warehouse, then step 609 is executed.

[0170] Step 609, the central cloud recommends an effective parking space;

[0171] Here, the central cloud compares the spatial dimensions of the vehicle with the spatial dimensions of random parking spaces based on the edge cloud, and recommends the valid parking space closest to the vehicle to the user based on the distance between the valid parking space and the vehicle.

[0172] Step 610, the central cloud generates a video of the vehicle entering the warehouse;

[0173] Step 611, the camera captures the blind spot image of the vehicle in real time;

[0174] Step 612, the edge cloud generates a real-time video of the vehicle blind spot; to execute step 610;

[0175] Step 613: for the smart car, the user terminal receives the vehicle entry video and guides the vehicle to enter the warehouse;

[0176] Step 614: For non-intelligent vehicles, the mobile terminal receives the vehicle entry video and guides the vehicle into the warehouse.

[0177] Figure 7 for Figure 6 The implementation flow diagram of step 607 is as follows: Figure 7 As shown, step 607 includes the following steps:

[0178] Step 701: a parking request is detected within the coverage area of ​​the edge cloud;

[0179] Step 702, the central cloud dispatches the spatial size of the edge cloud computing random parking space closest to the vehicle;

[0180] Step 703, the edge cloud compares the spatial size of the last random parking space;

[0181] Step 704, the edge cloud determines whether the number and space size of the random parking spaces need to be updated;

[0182] Here, if yes, that is, the number and space size of the random parking spaces need to be updated, then step 705 is executed; if no, that is, the number and space size of the random parking spaces do not need to be updated, then step 607 is executed.

[0183] Step 705, the sensing device collects data of random parking spaces;

[0184] In step 607 , the edge cloud compares the spatial dimensions of the vehicle with the spatial dimensions of the random parking space.

[0185] For general vehicles within the coverage of the 5G computing network, users randomly initiate parking requests. The authentication method (IoT core layer authentication for smart cars and ToC public network core layer authentication for non-smart cars) complies with the general 5G network standard. Smart cars can report vehicle information and initiate parking applications through the car machine, while non-smart cars mainly initiate parking applications by the driver carrying a smart mobile terminal. After the user successfully subscribes to the mobile cloud service, the sensor device corresponding to the nearest edge cloud is dispatched to collect the user's vehicle data based on the user's location information. The edge cloud calibrates and calculates the size of the collected user's vehicle data, and compares the calculated vehicle space size with the space size of the random parking space collected periodically in advance. If the comparison result shows that the vehicle can be stored, the nearest parking space that can be stored is recommended, and the planned parking path map is sent to the user side through 5G-Uu. If the smart car itself has functions such as 360-degree surround view and smart parking, the secondary parking assistance service can be displayed on the car machine as auxiliary information; non-smart cars receive the result information through the mobile phone for parking assistance. When the sensing device detects that the car is entering the warehouse, the edge cloud sends real-time video of key locations through 5G-Uu for assistance (the random parking space detection step is omitted when leaving the warehouse). If the user does not enter the warehouse according to the recommended parking space, the service is terminated and the application must be re-initiated. When the completion of the entry into the warehouse is detected through the perception collection data analysis, the edge cloud sends the end of business and service evaluation message through 5G-Uu. Regarding the judgment of leaving the warehouse: when the next parking application exists within the coverage area of ​​the specified edge cloud, the periodic empty parking space detection results are queried first. If no empty parking space is found, the assigned road-side sensing device starts a new round of random parking space detection actions, so when the vehicle leaves the warehouse this time, the status change of the parking space will be updated before the next service is provided.

[0186] Compared with the prior art, the embodiments of the present application have the following advantages:

[0187] The computing power of the parking service is migrated to the road side, and the driver is helped to park safely through the collection, analysis, and decision-making of sensory data. The auxiliary function of three-party vision is supplemented for vehicles that already have parking assistance functions, and auxiliary functions are provided for vehicles that do not have auxiliary functions, which improves the versatility of vehicle-road collaborative services. Secondly, the business process of the embodiment of the present application can be adapted to both the vehicle computer and the mobile terminal at the same time, smoothly adapt to the authentication of the 5G network, and seamlessly connect the mobile App service.

[0188] The embodiment of the present application provides a parking scheduling device for the current edge cloud in the area where the user is located, such as Figure 8 As shown, the parking scheduling device 800 includes: a first determination module 810, which is used to respond to the parking request sent by the user terminal, and determine whether there is a valid empty parking space in the area covered by the current edge cloud based on the acquired vehicle size information; a first sending module 820, which is used to send a scheduling request to the central cloud when there is no valid empty parking space in the area covered by the current edge cloud; the scheduling request carries the vehicle size information and the vehicle position information; a first receiving module 830, which is used to receive the location information of the target parking space and the parking path map planned to reach the target parking space sent by the central cloud; the target parking space is determined by other edge clouds except the current edge cloud; a second sending module 840, which is used to send the parking path map to the user terminal to guide the user to drive to the target parking space.

[0189] In some embodiments, the first determination module includes: a scheduling submodule, which is used to schedule perception devices within a preset range around the vehicle to collect vehicle data based on the location information of the vehicle; the perception devices include cameras and lidars; an acquisition submodule, which is used to acquire the image sequence of the vehicle captured by the camera and the scanning data of the vehicle by the lidar; a generation submodule, which is used to generate three-dimensional point cloud data of the vehicle based on the image sequence of the vehicle and the scanning data of the vehicle; the first determination submodule is used to determine the size information of the vehicle based on the three-dimensional point cloud data of the vehicle.

[0190] In some embodiments, the first sending module includes: a second determination submodule, used to determine the size information of the empty parking space; and a third determination submodule, used to determine that there is no valid empty parking space when there is a mismatch between the size information of the vehicle and the size information of the empty parking space.

[0191] In some embodiments, the second determination submodule includes: a first determination unit, used to determine an empty parking space from an image frame captured by a camera and containing the empty parking space; a second determination unit, used to determine the geometric shape of the empty parking space based on a set of edge points of a front vehicle and a set of edge points of a rear vehicle of the empty parking space in the absence of a traffic stop line; and a third determination unit, used to determine the size information of the empty parking space based on the length of a diagonal line in the geometric shape of the empty parking space and the distance between two farthest boundary points.

[0192] In some embodiments, the second determination submodule includes: an acquisition unit, used to acquire the environmental point cloud data scanned by the laser radar; the environmental point cloud data includes vehicle point cloud data and empty parking space point cloud data; a segmentation unit, used to segment the environmental point cloud data to obtain the vehicle point cloud data and the empty parking space point cloud data; a fourth determination unit, used to determine the size information of the empty parking space based on the empty parking space point cloud data.

[0193] In some embodiments, when the vehicle has reached a preset range of the target parking space, the parking scheduling device further includes: an acquisition module, used to acquire a blind spot image of the vehicle entering the garage captured by a camera; the blind spot image of the vehicle includes an image of the front wheels of the vehicle entering the garage and an image of the rear wheels of the vehicle entering the garage; a second determination module, used to determine the outline of the vehicle based on the size information of the vehicle; a third determination module, used to respond to a garage entry request sent by a user terminal, and determine the garage entry video of the vehicle based on the blind spot image of the vehicle and the outline of the vehicle; a third sending module, used to send the garage entry video to the user terminal to guide the user to park into the garage.

[0194] In some embodiments, the parking scheduling device also includes: a fourth sending module, which is used to send the parking path map and the vehicle's entry video to the user terminal when the vehicle is a smart car; the user terminal includes at least one of a mobile terminal and a vehicle-mounted terminal; a fifth sending module, which is used to send the parking path map and the vehicle's entry video to the mobile terminal when the vehicle is a non-smart car.

[0195] In some embodiments, the parking scheduling device also includes: a second receiving module, used to receive a parking space request sent by the central cloud; the parking space request carries the size information of the vehicle; a judgment module, used to respond to the parking space request, based on the size information of the vehicle, to judge whether there is a valid empty parking space in the area covered by the current edge cloud, and obtain a judgment result; a sixth sending module, used to send the judgment result to the central cloud.

[0196] The present application embodiment provides a parking scheduling device applied to a central cloud, such as Fig. 9As shown, the parking scheduling device 900 includes: a third receiving module 910, used to receive a scheduling request sent by the current edge cloud; the scheduling request carries the size information of the vehicle and the location information of the vehicle; a scheduling module 920, used to respond to the scheduling request indicating that there are no valid empty parking spaces in the area covered by the current edge cloud, and schedule other edge clouds to find valid empty parking spaces for the vehicle; a fourth determination module 930, used to determine the target parking space from the valid empty parking spaces in the area covered by the other edge clouds; a seventh sending module 940, used to send the location information of the target parking space and the parking path map planned to reach the target parking space to the current edge cloud.

[0197] In some embodiments, the scheduling module includes: a sending submodule, used to send a parking space request to the other edge cloud; the parking space request carries the size information of the vehicle; a receiving submodule, used to receive the judgment result sent by the other edge cloud; the judgment result is used to characterize whether there is a valid empty parking space in the area covered by the other edge cloud.

[0198] In some embodiments, the fourth determination module includes: a receiving submodule, used to receive the size information of the empty parking spaces sent by the edge cloud of the other area; a judging submodule, used to judge whether there are valid empty parking spaces in the edge cloud of the other area based on the size information of the vehicle and the size information of the empty parking spaces; the fourth determination submodule is used to determine the valid empty parking space closest to the vehicle as the target parking space when there are at least two valid empty parking spaces in the area covered by the other edge cloud.

[0199] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. In some embodiments, the functions or modules included in the device provided in the embodiment of the present application can be used to execute the method described in the above method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0200] It should be noted that in the embodiments of the present application, if the above-mentioned parking scheduling method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can be essentially or partly reflected in the form of a software product that contributes to the relevant technology. The software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiments of the present application are not limited to any specific hardware, software or firmware, or any combination of hardware, software, and firmware.

[0201] An embodiment of the present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and when the processor executes the program, some or all of the steps in the above method are implemented.

[0202] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, some or all of the steps in the above method are implemented. The computer-readable storage medium can be transient or non-transient.

[0203] An embodiment of the present application also provides a computer program, including a computer-readable code. When the computer-readable code is run in a computing device, a processor in the computing device executes some or all of the steps for implementing the above method.

[0204] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, some or all of the steps in the above method are implemented. The computer program product can be implemented specifically by hardware, software, or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium, and in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc.

[0205] It should be noted here that the description of the various embodiments above tends to emphasize the differences between the various embodiments, and the same or similar aspects can be referenced to each other. The description of the above device, storage medium, computer program and computer program product embodiments is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the embodiments of the device, storage medium, computer program and computer program product of this application, please refer to the description of the method embodiment of this application for understanding.

[0206] It should be noted that Fig.10 A schematic diagram of a hardware entity of a computer device in an embodiment of the present application is shown in FIG. Fig.10 As shown, the hardware entity of the computer device 1000 includes: a processor 1001, a communication interface 1002 and a memory 1003, wherein: the processor 1001 generally controls the overall operation of the computer device 1000. The communication interface 1002 can enable the computer device to communicate with other terminals or servers through a network. The memory 1003 is configured to store instructions and applications executable by the processor 1001, and can also cache data to be processed or processed by the processor 901 and each module in the computer device 1000 (for example, image data, audio data, voice communication data and video communication data), which can be implemented by flash memory (FLASH) or random access memory (Random Access Memory, RAM). Data transmission can be carried out between the processor 1001, the communication interface 1002 and the memory 1003 through the bus 1004.

[0207] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial numbers of the above-mentioned steps / processes does not mean the order of execution, and the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

[0208] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0209] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0210] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0211] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0212] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0213] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0214] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A parking scheduling method, characterized in that: Applied to the current edge cloud in the area where the user is located, the method includes: In response to a parking request sent by a user terminal, determining whether there is an effective empty parking space in the area covered by the current edge cloud based on the acquired vehicle size information; When there is no valid empty parking space in the area covered by the current edge cloud, a dispatch request is sent to the central cloud; the dispatch request carries the size information and the location information of the vehicle; Receiving the location information of the target parking space and the parking path map planned to reach the target parking space sent by the central cloud; the target parking space is determined by other edge clouds except the current edge cloud; The parking path map is sent to the user terminal to guide the user to drive to the target parking space.

2. The parking scheduling method according to claim 1, characterized in that: The obtained vehicle size information includes: Based on the location information of the vehicle, dispatching sensing devices within a preset range around the vehicle to collect vehicle data; the sensing devices include cameras and laser radars; Acquire the image sequence of the vehicle captured by the camera and the scanning data of the vehicle by the laser radar; Generating three-dimensional point cloud data of the vehicle based on the image sequence of the vehicle and the scan data of the vehicle; Based on the three-dimensional point cloud data of the vehicle, size information of the vehicle is determined.

3. The parking scheduling method according to claim 1 or 2, characterized in that: Determine that there are no valid empty parking spaces, including: Determine the size information of the empty parking space; When the size information of the vehicle does not match the size information of the empty parking space, it is determined that there is no valid empty parking space.

4. The parking scheduling method according to claim 3, characterized in that: The step of determining the size information of the empty parking space includes: Determine an empty parking space from an image frame containing an empty parking space captured by a camera; In the absence of a traffic stop line, determining a geometric shape of the empty parking space based on an edge point set of a front vehicle and an edge point set of a rear vehicle of the empty parking space; The size information of the empty parking space is determined based on the length of a diagonal line in the geometric shape of the empty parking space and the distance between two farthest boundary points.

5. The parking scheduling method according to claim 3, characterized in that: The step of determining the size information of the empty parking space includes: Acquire environmental point cloud data scanned by a laser radar; the environmental point cloud data includes vehicle point cloud data and vacant parking lot point cloud data; Segmenting the environment point cloud data to obtain the vehicle point cloud data and the vacant parking lot point cloud data; Based on the empty parking space cloud data, size information of the empty parking space is determined.

6. The parking scheduling method according to claim 5, characterized in that: When the vehicle has reached a preset range of the target parking space, the method further includes: Obtaining a blind spot image of the vehicle entering the garage captured by a camera; the blind spot image includes an image of the front wheels of the vehicle entering the garage and an image of the rear wheels of the vehicle entering the garage; Determining a contour of the vehicle based on the size information of the vehicle; In response to a storage entry request sent by a user terminal, determining a storage entry video of the vehicle based on a blind spot image of the vehicle and a contour of the vehicle; The video of the vehicle entering the garage is sent to the user terminal to guide the user to park the vehicle.

7. The parking scheduling method according to claim 6, characterized in that: The method further comprises: In the case where the vehicle is a smart car, the parking path map and the parking video of the vehicle are sent to the user terminal; the user terminal includes at least one of a mobile terminal and a vehicle-mounted terminal; In the case where the vehicle is a non-intelligent vehicle, the parking path map and the parking video of the vehicle are sent to the mobile terminal.

8. The parking scheduling method according to claim 7, characterized in that: The method further comprises: Receiving a parking space request sent by the central cloud; the parking space request carries the size information of the vehicle; In response to the parking space request, based on the size information of the vehicle, determining whether there is an effective empty parking space in the area currently covered by the edge cloud, and obtaining a determination result; The judgment result is sent to the central cloud.

9. A parking scheduling method, characterized in that: Applied to the central cloud, the method includes: Receive a scheduling request sent by the current edge cloud in the area where the user is located; the scheduling request carries the size information of the vehicle and the location information of the vehicle; In response to the dispatch request indicating that there is no valid empty parking space in the area covered by the current edge cloud, dispatching other edge clouds to find a valid empty parking space for the vehicle; Determine a target parking space from valid empty parking spaces in the area covered by the other edge clouds; The location information of the target parking space and a parking path map planned to reach the target parking space are sent to the current edge cloud.

10. The parking scheduling method according to claim 9, characterized in that: The dispatching of other edge clouds to find an effective empty parking space for the vehicle includes: Sending a parking space request to the other edge cloud; the parking space request carries the size information of the vehicle; Receive the judgment result sent by the other edge cloud; the judgment result is used to indicate whether there is a valid empty parking space in the area covered by the other edge cloud.

11. The parking dispatching method according to claim 9 or 10, characterized in that: The determining of the target parking space from the empty parking spaces in the area covered by the other edge clouds includes: Receiving size information of empty parking spaces sent by the edge cloud of the other area; Based on the size information of the vehicle and the size information of the empty parking space, determining whether there is an effective empty parking space in the edge cloud of the other area; When there are at least two valid empty parking spaces in the area covered by the other edge clouds, the valid empty parking space closest to the vehicle is determined as the target parking space.

12. A parking dispatching device, characterized in that: Applied to the current edge cloud in the area where the user is located, the device includes: A first determination module is used to respond to a parking request sent by a user terminal and determine whether there is an effective empty parking space in the area covered by the current edge cloud based on the acquired vehicle size information; A first sending module is used to send a dispatch request to the central cloud when there is no valid empty parking space in the area covered by the current edge cloud; the dispatch request carries the size information of the vehicle and the location information of the vehicle; A first receiving module is used to receive the location information of the target parking space and the parking path map planned to reach the target parking space sent by the central cloud; the target parking space is determined by other edge clouds except the current edge cloud; The second sending module is used to send the parking path map to the user terminal to guide the user to drive to the target parking space.

13. A parking dispatching device, characterized in that: Applied to the central cloud, the device comprises: The third receiving module is used to receive a scheduling request sent by the current edge cloud in the user's area; the scheduling request carries the size information of the vehicle and the location information of the vehicle; A scheduling module, configured to schedule other edge clouds to find a valid empty parking space for the vehicle in response to the scheduling request indicating that there is no valid empty parking space in the area covered by the current edge cloud; A fourth determination module, configured to determine a target parking space from valid empty parking spaces in the area covered by the other edge clouds; The seventh sending module is used to send the location information of the target parking space and the parking path map planned to reach the target parking space to the current edge cloud.

14. A computer device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, wherein: When the processor executes the program, the steps of the method described in any one of claims 1 to 8 are implemented; or, the steps of the method described in claims 9 to 11 are implemented.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 8; or, the computer program implements the steps of the method according to claims 9 to 11.

Images