Parking lot guiding method and device based on dynamic projection and storage medium

Abstract

The embodiment of the invention provides a parking lot guiding method and device based on dynamic projection and a storage medium, and belongs to the technical field of parking lot management. According to the scheme, the parking lot map of the parking lot is established; acquiring video streams of all cameras of the parking lot; obtaining an idle parking space list and a lane congestion condition according to the video stream; when a vehicle enters the parking lot, performing target detection on a video stream of a camera at an entrance of the parking lot, and determining vehicle characteristics of the target vehicle and positioning information in a parking lot map; based on the positioning information, performing path planning according to an idle parking space list and a lane congestion condition, and determining a target parking space and a parking guide route; determining a guide identifier of the intersection according to the parking guide route; the target vehicle is tracked and positioned by using the vehicle characteristics, and the guide identifier is projected at the next intersection in advance along the parking guide route until the target vehicle arrives at the target parking space, so that the vehicle can be dynamically guided to the target parking space, and the parking efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of parking lot management, and in particular to a parking lot guidance method, device and storage medium based on dynamic projection. Background Art

[0002] With the continuous increase in urban population and the number of vehicles, car owners often need to spend a lot of time and energy looking for vacant parking spaces in parking lots. Due to the opacity of parking space information, manual search for parking spaces can no longer meet the sharply increased parking demand.

[0003] At present, parking lots usually display the total number of free parking spaces on guide signs at intersections to provide guidance for car owners. Although the guide signs provide the number and direction of free parking spaces, car owners still need to find suitable free parking spaces by themselves. The status of parking spaces changes rapidly during peak hours, and the information on the guide signs cannot reflect the status of parking spaces in a timely manner. When car owners look for free parking spaces based on outdated information, they may find that the original free parking spaces have been occupied and have to start looking again, resulting in low parking efficiency. In addition, due to the limited width of parking lot roads, when multiple car owners choose the same direction based on the information on the guide signs, it is easy to cause road congestion, further increasing the time it takes car owners to find parking spaces and reducing parking efficiency. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a parking lot guidance method, device and storage medium based on dynamic projection, aiming to dynamically guide vehicles to target parking spaces and improve parking efficiency.

[0005] To achieve the above-mentioned purpose, one aspect of an embodiment of the present application proposes a parking lot guidance method based on dynamic projection, the method comprising:

[0006] Create a parking lot map for the parking lot;

[0007] Get the video streams from all the cameras in the parking lot;

[0008] Obtaining a list of available parking spaces and lane congestion conditions according to the video stream;

[0009] When a vehicle enters the parking lot, target detection is performed on the video stream of the camera at the entrance of the parking lot to determine the vehicle characteristics of the target vehicle and the positioning information in the parking lot map, wherein the vehicle characteristics include the vehicle head direction, vehicle color and license plate number;

[0010] Based on the positioning information, path planning is performed according to the list of available parking spaces and the lane congestion situation to determine the target parking space and the parking guidance route;

[0011] Determine a guide sign at a fork intersection according to the parking guide route, wherein the guide sign includes going straight, turning left, and turning right;

[0012] The target vehicle is tracked and located using the vehicle features, and the guide mark is projected in advance at the next fork along the parking guide route until the target vehicle arrives at the target parking space.

[0013] In some embodiments, the step of establishing a parking lot map includes the following steps:

[0014] The parking lot is divided into multiple grids by using the grid map method to establish a grid map;

[0015] Determining lane grids in the grid map according to the lane layout of the parking lot, and marking a drivable direction for each lane grid;

[0016] Determine parking space grids in the grid map according to the parking space layout of the parking lot, and mark parking space numbers for each parking space grid;

[0017] A parking lot map of the parking lot is obtained according to the lane grid and the parking space grid.

[0018] In some embodiments, obtaining a list of available parking spaces and lane congestion conditions according to the video stream includes the following steps:

[0019] Determining the parking space status of each parking space according to the video stream, wherein the parking space status includes an idle state and an occupied state;

[0020] Record the positions and parking space numbers of all the parking spaces in the idle state in the parking lot map to obtain an idle parking space list;

[0021] The number of vehicles on each lane and the driving speed are identified according to the video stream to obtain lane congestion conditions.

[0022] In some embodiments, the method of performing path planning based on the positioning information, according to the list of available parking spaces and the lane congestion, and determining a target parking space and a parking guidance route includes the following steps:

[0023] The positioning information is used as the starting point of the path planning, and the list of free parking spaces is used as the list of destinations to be screened;

[0024] Increasing the cost of the lane grid according to the lane congestion situation, and determining the end point with the minimum total path cost as the target parking space through a path planning algorithm;

[0025] The parking guidance route is obtained by tracing back to the starting point according to the target parking space.

[0026] In some embodiments, the tracking and locating of the target vehicle using the vehicle features includes the following steps:

[0027] When the target vehicle moves within the camera range of the same camera, target recognition is performed on the video stream of the same camera according to the vehicle characteristics, and the positioning information is updated to track the target vehicle;

[0028] When the target vehicle moves to the edge of the camera range, the camera is switched to an adjacent camera according to a preset rule, the video stream of the adjacent camera is subjected to target recognition according to the characteristics of the vehicle, and the positioning information is updated to track the target vehicle.

[0029] In some embodiments, projecting the guide mark at the next fork in the road along the parking guide route until the target vehicle reaches the target parking space comprises the following steps:

[0030] Projecting the guide sign at the next fork in the road in advance along the parking guide route, and projecting the parking space number of the target parking space and the license plate number of the target vehicle next to the guide sign until the target vehicle arrives at the target parking space;

[0031] The step of projecting the guide sign at the next fork in the road along the parking guide route in advance, and projecting the parking space number of the target parking space and the license plate number of the target vehicle next to the guide sign, comprises the following steps:

[0032] When there are multiple target vehicles, a different guide color is assigned to each target vehicle, and the guide signs are projected according to the guide colors at the next fork along the parking guide route in advance, and the parking space number of the target parking space and the license plate number of the target vehicle are projected next to the guide sign according to the guide color.

[0033] In some embodiments, the parking lot guidance method based on dynamic projection further includes the following steps:

[0034] When the parking space state of the target parking space changes from an idle state to an occupied state, updating the target parking space and the parking guidance route according to the idle parking space list;

[0035] When the target vehicle deviates from the parking guidance route, the target parking space and the parking guidance route are updated according to the vehicle head direction;

[0036] When the lane congestion exceeds a preset threshold range, the target parking space and the parking guidance route are updated according to the lane congestion.

[0037] In some embodiments, the parking lot guidance method based on dynamic projection further includes the following steps:

[0038] Recording the positions, parking space numbers and corresponding occupied vehicle license plate numbers of all the occupied parking spaces in the parking lot map to obtain an occupied parking space list, wherein the occupied vehicle license plate numbers are the license plate numbers of vehicles parked in the occupied parking spaces;

[0039] Obtaining the vehicle owner's vehicle search request information, wherein the vehicle search request information includes the requested location and the vehicle license plate number;

[0040] Matching the occupied license plate number in the occupied parking space list according to the sought-for vehicle license plate number, and determining the parking space corresponding to the matched occupied license plate number as the sought-for vehicle parking space;

[0041] The requested location is used as the starting point of the car search, and the parking space is used as the end point of the car search. A path is planned according to the starting point and the end point of the car search to determine the car search guidance route;

[0042] Determine the guidance sign of the fork in the road according to the vehicle-finding guidance route;

[0043] The guide mark is projected in advance at the next fork in the road along the vehicle-finding guide route.

[0044] To achieve the above-mentioned purpose, another aspect of the embodiment of the present application provides a parking lot guidance device based on dynamic projection, the device comprising:

[0045] The first module is used to establish a parking lot map;

[0046] The second module is used to obtain the video streams of all cameras in the parking lot;

[0047] The third module is used to obtain a list of free parking spaces and lane congestion conditions according to the video stream;

[0048] The fourth module is used to detect the target on the video stream of the camera at the entrance of the parking lot when a vehicle enters the parking lot, and determine the vehicle characteristics of the target vehicle and the positioning information in the parking lot map, wherein the vehicle characteristics include the vehicle head direction, vehicle color and license plate number;

[0049] A fifth module is used to perform path planning based on the positioning information, the list of available parking spaces and the lane congestion, and determine a target parking space and a parking guidance route;

[0050] A sixth module is used to determine a guide sign at a fork intersection according to the parking guide route, wherein the guide sign includes going straight, turning left, and turning right;

[0051] The seventh module is used to track and locate the target vehicle using the vehicle features, and to project the guide sign at the next fork in the road along the parking guide route until the target vehicle arrives at the target parking space.

[0052] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0053] The embodiments of the present application include at least the following beneficial effects: the present application provides a parking lot guidance method, device and storage medium based on dynamic projection, the scheme establishes a parking lot map of the parking lot; obtains the video streams of all cameras in the parking lot; obtains a list of free parking spaces and lane congestion conditions based on the video streams; when a vehicle enters the parking lot, performs target detection on the video stream of the camera at the entrance of the parking lot to determine the vehicle characteristics of the target vehicle and the positioning information in the parking lot map; based on the positioning information, performs path planning according to the list of free parking spaces and lane congestion conditions to determine the target parking space and the parking guidance route; determines the guidance signs at the fork in the road according to the parking guidance route; tracks and locates the target vehicle using the vehicle characteristics, and pre-projects the guidance signs at the next fork in the road along the parking guidance route until the target vehicle reaches the target parking space, which can dynamically guide the vehicle to the target parking space and improve parking efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a flow chart of a parking lot guidance method based on dynamic projection provided in an embodiment of the present application;

[0055] Figure 2 It is a schematic diagram of the effect of the layout map provided in the embodiment of the present application;

[0056] Figure 3 It is a schematic diagram of the effect of the parking lot map provided in the embodiment of the present application;

[0057] Figure 4 This is a schematic diagram of the effect of the dynamic projection guide sign provided in the embodiment of the present application;

[0058] Figure 5 is a schematic diagram of a scene of parking guidance for multiple vehicles provided in an embodiment of the present application;

[0059] Figure 6 is a structural schematic diagram of a parking lot guidance system provided in an embodiment of the present application;

[0060] Figure 7 is a schematic diagram of a scene of switching cameras provided in an embodiment of the present application;

[0061] Figure 8is a structural schematic diagram of a parking lot guidance device based on dynamic projection provided in an embodiment of the present application;

[0062] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0064] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0065] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0066] 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 the embodiments of this application and are not intended to limit this application.

[0067] Before describing the embodiments of the present application in detail, some related technologies involved in the embodiments of the present application are first described.

[0068] Currently, the products on the market do not consider the parking lot as a whole. They only summarize the total number of vacant parking spaces and display them on the guide sign at the fork in the road. The guidance method is not smart and flexible enough. Car owners are still required to independently select parking spaces according to the instructions on the guide sign. When the vehicle enters the parking lot, car owners independently look for vacant parking spaces according to the instructions on the guide sign. Not only may they take a long detour and fail to accurately find the nearest vacant parking space, but also because the guide sign is installed above the lane, car owners need to look up while driving, which is not conducive to safe driving.

[0069] At the same time, during the guidance process, when an empty parking space is occupied, or when multiple vehicles choose the same direction and cause the road to be busy, the guide sign cannot change the guidance in real time according to the changes in the parking lot, which increases the time for car owners to find parking spaces and reduces parking efficiency.

[0070] In view of this, a parking lot guidance method, device and storage medium based on dynamic projection are provided in the embodiments of the present application. The scheme establishes a parking lot map of the parking lot; obtains video streams from all cameras in the parking lot; obtains a list of vacant parking spaces and lane congestion conditions based on the video streams; when a vehicle enters the parking lot, performs target detection on the video stream of the camera at the entrance of the parking lot to determine the vehicle characteristics of the target vehicle and the positioning information in the parking lot map; based on the positioning information, performs path planning according to the list of vacant parking spaces and lane congestion conditions to determine the target parking space and the parking guidance route; determines the guidance signs at the fork in the road according to the parking guidance route; tracks and locates the target vehicle using the vehicle characteristics, and pre-projects the guidance signs at the next fork in the road along the parking guidance route until the target vehicle arrives at the target parking space, so as to dynamically guide the vehicle to the target parking space and improve parking efficiency.

[0071] The parking lot guidance method based on dynamic projection provided in the embodiment of the present application relates to the field of parking lot management technology. The parking lot guidance method based on dynamic projection provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements a parking lot guidance method based on dynamic projection, etc., but is not limited to the above forms.

[0072] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0073] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics such as user location information, the user's permission or consent will be obtained first, and the collection, use and processing of these data will comply with relevant laws, regulations and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or jump to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0074] Figure 1 is an optional flow chart of a parking lot guidance method based on dynamic projection provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S107.

[0075] Step S101, creating a parking lot map.

[0076] Step S102, obtaining video streams from all cameras in the parking lot.

[0077] Step S103, obtaining a list of free parking spaces and lane congestion conditions according to the video stream.

[0078] Step S104, when a vehicle enters the parking lot, target detection is performed on the video stream of the camera at the entrance of the parking lot to determine the vehicle characteristics of the target vehicle and the positioning information in the parking lot map, wherein the vehicle characteristics include the vehicle head direction, vehicle color and license plate number.

[0079] Step S105 , based on the positioning information, path planning is performed according to the list of free parking spaces and lane congestion to determine the target parking space and parking guidance route.

[0080] Step S106, determining a guidance sign at a fork intersection according to the parking guidance route, wherein the guidance sign includes going straight, turning left, and turning right.

[0081] Step S107, tracking and locating the target vehicle using the vehicle features, and projecting a guidance sign at the next fork along the parking guidance route until the target vehicle reaches the target parking space.

[0082] Specifically, first, a parking lot map of the parking lot is established. The parking lot map of the parking lot is established according to the location distribution of parking spaces and the direction of lanes in the parking lot.

[0083] Then, the video streams of all cameras in the parking lot are obtained. The cameras are installed at appropriate locations in the parking lot, and a number is set for each camera. By obtaining the video streams of all cameras in the parking lot, the situation of the entire parking lot can be obtained in real time.

[0084] Next, the free parking space list and lane congestion are obtained based on the video stream. The free parking space list is a collection of currently available or unoccupied parking spaces. The parking spaces and vehicles in the entire parking lot are detected and analyzed based on the video stream, and parking spaces without parked vehicles are confirmed as free parking spaces. The location and parking space number of each free parking space are recorded to obtain the free parking space list. The lane congestion situation represents the lane capacity. The vehicles on the lane are detected based on the video stream. When there are parked vehicles on the lane or too many vehicles on the lane, causing the vehicles to have to pass slowly, the lane can be considered to be a busy section.

[0085] When a vehicle enters the parking lot, target detection is performed on the video stream of the camera at the entrance of the parking lot to determine the vehicle features of the target vehicle and its positioning information in the parking lot map, where the vehicle features include the vehicle head direction, vehicle color, and license plate number. Through the target detection algorithm, target detection is performed on the video stream of the camera at the entrance of the parking lot, and the vehicle entering the parking lot is determined as the target vehicle. The target vehicle in the video stream is identified and saved for features such as the vehicle head direction, vehicle color, and license plate number. After the target vehicle is identified according to the saved features, the current position and driving direction of the target vehicle in the parking lot map are determined based on the positional relationship between the target vehicle and the parking lot building, and the positioning information is obtained.

[0086] After obtaining the positioning information, the path planning is performed based on the positioning information, the list of free parking spaces and the lane congestion to determine the target parking space and the parking guidance route. The parking guidance task is established based on the positioning information through the end point screening method, and the free parking space closest to the target vehicle is searched in the free parking space list as the target parking space. The path planning result is adjusted in real time according to the lane congestion to select an optimal path for the car owner to avoid busy sections, thereby reducing waiting time and improving parking efficiency.

[0087] The guide signs at the fork in the road are determined according to the parking guidance route, wherein the guide signs include straight ahead, left turn and right turn. For the convenience of intuitive understanding, the guide signs may optionally use arrows to indicate straight ahead, left turn and right turn. According to the planned parking guidance route, the fork in the road along the parking guidance route is predetermined. When the parking guidance route turns at the fork in the road, the guide sign at the fork in the road is determined to be a left turn or a right turn according to the direction of the turn. When the parking guidance route does not turn at the fork in the road, the guide sign at the fork in the road is determined to be a straight ahead.

[0088] Finally, the target vehicle is tracked and located using the vehicle features, and a guidance sign is projected at the next fork along the parking guidance route until the target vehicle reaches the target parking space. The target vehicle is continuously tracked and located using the previously identified vehicle features, and when the vehicle approaches each predetermined fork, the corresponding guidance sign is projected at the next intersection until the target vehicle successfully arrives and parks at the designated target parking space, thus completing the entire parking guidance process.

[0089] In some embodiments, step S101 may include but is not limited to steps S201 to S204.

[0090] Step S201, dividing the parking lot into a plurality of grids by using a grid mapping method to create a grid map.

[0091] Step S202: determining lane grids in the grid map according to the lane layout of the parking lot, and marking the drivable direction for each lane grid.

[0092] Step S203, determining parking grids in the grid map according to the parking space layout of the parking lot, and marking a parking space number for each parking grid.

[0093] Step S204, obtaining a parking lot map of the parking lot according to the lane grid and the parking space grid.

[0094] Specifically, the parking lot is divided into multiple grids by the grid map method to establish a grid map. According to the scale and actual conditions of the parking lot (such as entrances and exits, lane widths or parking space sizes, etc.), an appropriate grid unit length is selected to divide the parking lot into multiple grids to establish a grid map.

[0095] The lane grid is determined in the grid map according to the lane layout of the parking lot, and the drivable direction is marked for each lane grid. The lane layout determines the route and direction of vehicle travel. The lanes are identified in the grid map according to the lane layout of the parking lot, and marked with lines or colors on the grid map. The grid where the lane is located is determined as the lane grid, and the drivable direction is marked for each lane grid.

[0096] At the same time, the parking space grid is determined in the grid map according to the parking space layout of the parking lot, and the parking space number is marked for each parking space grid. The parking space layout determines the location where the vehicle is parked. According to the parking space layout of the parking lot, the grid where the parking space is located is marked by a rectangle or other shape in the grid map, and the parking space number is marked for each parking space grid. Optionally, the parking space number can be represented in the form of numbers, letters, or a combination.

[0097] It should be noted that the parking space number should be unique and easily identifiable, and should be consistent with the actual parking space number in the parking lot.

[0098] The parking lot map of the parking lot is obtained according to the lane grid and the parking space grid. The lane grid, the parking space grid and the corresponding annotation information are integrated together to obtain the parking lot map of the parking lot.

[0099] For example, refer to Figure 2 , Figure 2 A parking lot layout map is provided. In the layout map, rectangles represent parking spaces and red dashed lines represent lanes for vehicles to drive. Based on the distribution of lanes and parking spaces in the parking lot, a grid map is used to establish the following Figure 3 The parking lot map shown. According to the lane layout, the lane grid is evenly arranged on the green dotted line, and the direction in which the vehicle can travel is marked for each grid, which is used for subsequent planning of the driving path from the starting point to the destination. According to the parking space layout of the parking lot, a parking space grid corresponding to the rectangle is established in the grid map, and starting from the upper left corner of the map, with 101 as the first parking space number, the parking space number is marked for each parking space grid in ascending order from top to bottom and from left to right.

[0100] In some embodiments, step S103 may include but is not limited to steps S301 to S303.

[0101] Step S301, determining the parking space status of each parking space according to the video stream, wherein the parking space status includes an idle state and an occupied state.

[0102] Step S302, recording the positions and parking space numbers of all idle parking spaces in the parking lot map, and obtaining an idle parking space list.

[0103] Step S303, identifying the number of vehicles on each lane and the driving speed according to the video stream to obtain the lane congestion situation.

[0104] Specifically, the parking status of each parking space is determined based on the video stream, where the parking status includes an idle state and an occupied state. After the video stream is acquired by the camera covering the entire parking lot, the images in the video stream are analyzed frame by frame to determine whether each parking space has a vehicle parked there to determine the parking space status. If a vehicle is parked there, the parking space status is confirmed to be occupied; if no vehicle is parked there, the parking space status is confirmed to be idle.

[0105] Optionally, the parking space state can be determined by identifying whether there are features such as wheels and vehicle body outlines in the parking space area in the video stream. If so, the parking space state is confirmed to be occupied, and if not, the parking space state is confirmed to be free. Alternatively, the parking space state can be determined by identifying whether the parking space number on the ground in the video stream is blocked. If the parking space number is blocked and cannot be seen for a long time, the parking space state is confirmed to be occupied, and if the parking space number on the ground in the image is completely visible, the parking space state is confirmed to be free.

[0106] The positions and parking space numbers of all idle parking spaces in the parking lot map are recorded to obtain an idle parking space list. Whenever an idle parking space is identified in step S301, the position and parking space number of the parking space in the parking lot map are recorded, and the positions, parking spaces and parking space numbers of all idle parking spaces are summarized to obtain an idle parking space list.

[0107] Alternatively, whenever it is identified that the parking space status changes from an occupied state to an idle state, the position and parking space number of the parking space in the parking lot map are recorded and added to the idle parking space list.

[0108] It is understandable that as vehicles enter and exit the parking lot, the status of parking spaces will continue to change, and the list of available parking spaces also needs to be updated in real time to reflect the latest parking space usage.

[0109] The number of vehicles in each lane and their driving speed are identified based on the video stream to obtain the lane congestion situation.

[0110] Optionally, the images in the video stream are analyzed frame by frame to detect the number of vehicles on the lane, and the vehicle's travel speed is calculated by comparing the position changes and time intervals of the vehicles in adjacent frames or more frames. By identifying the number of vehicles on each lane and the travel speed, the lane congestion situation is obtained.

[0111] In some embodiments, step S105 may include but is not limited to steps S401 to S403.

[0112] Step S401, taking the positioning information as the starting point of path planning, and taking the list of free parking spaces as the list of destinations to be screened.

[0113] Step S402: increase the cost of the lane grid according to the lane congestion situation, and determine the end point with the minimum total path cost as the target parking space through a path planning algorithm.

[0114] Step S403, tracing back to the starting point according to the target parking space to obtain a parking guidance route.

[0115] Specifically, the positioning information is used as the starting point of the path planning, and the list of free parking spaces is used as the list of destinations to be screened. In path planning, there is one starting point, that is, the current location contained in the positioning information, and there are multiple destinations. The list of free parking spaces is used as the list of destinations to be screened, and each free parking space in the list of free parking spaces is a destination.

[0116] The cost of the lane grid is increased according to the lane congestion, and the destination with the minimum total path cost is determined as the target parking space through the path planning algorithm. The congestion cost of the lane grid corresponding to the vehicle location is increased according to the number of vehicles on the lane and the driving speed. For example, when the number of vehicles on the lane is greater, the congestion cost of the corresponding lane grid is higher, or when the driving speed of the vehicle on the lane is slower, the congestion cost of the corresponding lane grid is higher.

[0117] Exemplarily, after receiving the starting point and the list of destinations to be screened, the destination screening method is used to search for the next reachable node from the starting point to obtain adjacent nodes, and the adjacent nodes are traversed to determine whether there are nodes in the list of destinations to be screened. If there are no nodes in the list of destinations to be screened among the adjacent nodes, the static cost is determined according to road characteristics such as lane width and trunk and branch distribution, and the congestion cost is determined according to the number of vehicles on the lane and the driving speed. The total cost F from the starting point to the current node is calculated by the first cost formula, and the first cost formula expression is:

[0118] F=F1+F2 (1);

[0119] In formula (1), F1 is the static cost and F2 is the congestion cost.

[0120] Furthermore, in another embodiment, considering that the turning action of the vehicle will also affect driving, the turning cost can also be added to the path planning. If the vehicle turns during driving, the turning cost is determined based on the cumulative number of turns from the starting point to the current node.

[0121] If there is no node in the list of destinations to be screened among the adjacent nodes, the total cost F from the starting point to the current node is calculated using the second cost formula. The second cost formula is:

[0122] F=F1+F2+F3 (2);

[0123] In formula (2), F3 is the turning cost.

[0124] Calculate the total cost value F of each adjacent node, and sort the adjacent nodes found this time according to the total cost value and put them into the linked list to be screened. Then, select the node with the smallest total cost value from the linked list, search the nodes that can be reached in the next step again to get the adjacent nodes, traverse the adjacent nodes to determine whether there are nodes in the list of destinations to be screened, until the node in the list of destinations to be screened is found for the first time from the adjacent nodes, then determine the parking space corresponding to the node as the target parking space.

[0125] Optionally, based on the above cost calculation, the distance cost of the current node from the starting point can also be obtained by accumulating the number of nodes passed. Each time a new node is reached by moving one step in any direction, the distance cost of the new node is accumulated by 1 on the basis of the distance cost of the previous node. For example, let the distance cost of the starting point D0 be 0, move one step to the left from the starting point to reach the next node D1, and add 1 to the distance cost of node D0, so that the distance cost of node D1 is 1, move one step to the right from node D1 to reach the next node D2, and add 1 to the distance cost of node D1, so that the distance cost of node D2 is 2.

[0126] The total cost F from the starting point to the current node is calculated by the third cost formula. The third cost formula is expressed as:

[0127] F=F0+F1+F2+F3 (3);

[0128] In formula (3), F0 is the distance cost.

[0129] It is understandable that the shortest path problem has the property of optimal substructure. If a path is the shortest path from the starting point to the end point, then any subpath on this path must also be the shortest path from the corresponding starting point to the corresponding end point. Therefore, selecting the node with the lowest cost at each step can ensure that the current subpath is optimal, laying the foundation for obtaining the global optimal solution. In each search process, the path planning algorithm selects the node with the lowest current cost for expansion to avoid falling into the local optimal solution, thereby finding the end point that minimizes the total path cost.

[0130] The parking guidance route is obtained by tracing back to the starting point according to the target parking space. The target parking space and the corresponding parking guidance route selected in this way are the driving route that avoids busy roads.

[0131] In some embodiments, the step of tracking and locating the target vehicle using vehicle features may include but is not limited to step S501 or step S502.

[0132] Step S501, when the target vehicle moves within the camera range of the same camera, target recognition is performed on the video stream of the same camera according to the vehicle characteristics, and the positioning information is updated to track the target vehicle.

[0133] Step S502, when the target vehicle moves to the edge of the camera range, switch to the adjacent camera according to the preset rules, perform target recognition on the video stream of the adjacent camera according to the vehicle characteristics, and update the positioning information to track the target vehicle.

[0134] In step S501 of some embodiments, when the target vehicle moves within the camera range of the same camera, target recognition is performed on the video stream of the same camera according to the vehicle characteristics, and the positioning information is updated to track the target vehicle. When the target vehicle moves within the camera range of the same camera, target recognition is continued on the video stream of the same camera according to the saved vehicle characteristics, and the positioning information is updated to track the target vehicle.

[0135] In step S502 of some embodiments, when the target vehicle moves to the edge of the camera range, the camera is switched to the adjacent camera according to the preset rules, the video stream of the adjacent camera is subjected to target recognition according to the vehicle characteristics, and the positioning information is updated to track the target vehicle. Optionally, the preset rules are to determine the overlapping area of ​​each camera's monitoring range according to the installation position of each camera, the monitoring range and its relative position relationship with the adjacent camera, and when the target vehicle enters these overlapping areas, the camera switching is triggered. When the target vehicle moves to the edge of the camera range and is about to move to the camera range of another camera, the camera is switched to the adjacent camera according to the pre-set camera number, and the video stream of the adjacent camera continues to be subjected to target recognition according to the same vehicle characteristics, and the positioning information is updated to track the target vehicle.

[0136] In some embodiments, the step of projecting a guidance sign at the next fork in the road along the parking guidance route until the target vehicle arrives at the target parking space may include but is not limited to step S601.

[0137] Step S601, projecting a guide sign at the next fork in the road along the parking guide route in advance, and projecting the parking space number of the target parking space and the license plate number of the target vehicle next to the guide sign until the target vehicle arrives at the target parking space.

[0138] Specifically, a guide sign is projected at the next fork along the parking guide route in advance, and the parking space number of the target parking space and the license plate number of the target vehicle are projected next to the guide sign until the target vehicle arrives at the target parking space. A projector is controlled at the next fork along the parking guide route to project a guide sign on the ground in advance, and the parking space number of the target parking space and the license plate number of the target vehicle are projected next to the guide sign until the target vehicle arrives at the target parking space.

[0139] For example, refer to Figure 4 When the vehicle needs to turn right at the next intersection according to the parking guidance route, a right-turn guidance sign is projected on the ground, and the vacant parking space number C-128 and the license plate number A77777 are projected next to the guidance sign.

[0140] Further, in some embodiments, the step of projecting a guide sign at the next fork in the road in advance along the parking guidance route and projecting the parking space number of the target parking space and the license plate number of the target vehicle next to the guide sign may include but is not limited to step S701.

[0141] Step S701, when there are multiple target vehicles, a different guide color is assigned to each target vehicle, and guide signs are projected in advance at the next fork along the parking guide route according to the guide colors, and the parking space number of the target parking space and the license plate number of the target vehicle are projected next to the guide sign according to the guide color.

[0142] Furthermore, when there are multiple target vehicles, a different guide color is assigned to each target vehicle, and a guide sign is projected according to the guide color at the next fork along the parking guidance route, and the parking space number of the target parking space and the license plate number of the target vehicle are projected next to the guide sign according to the guide color. When multiple vehicles enter the parking lot, the system establishes corresponding parking guidance tasks in sequence according to the order in which the target vehicles enter the parking lot. For each additional parking guidance task, the system automatically assigns a unique guide color to the target vehicle for projecting the guide sign, parking space number and license plate number. The guide color can only be used in other parking guidance tasks after the parking guidance task is completed (i.e., the target vehicle arrives at the corresponding target parking space).

[0143] For example, refer to Figure 5 , when three vehicles enter the parking lot from three gates of one entrance at the same time, first, the license plate number of the first target vehicle is identified as A11111 through the video stream, the license plate number of the second target vehicle is A88888, and the license plate number of the third target vehicle is A66666. Then, the target parking space and the corresponding parking guidance route are planned for each target vehicle through path planning. Then, a different guidance color is assigned to each target vehicle, the first target vehicle is assigned red, the second target vehicle is assigned blue, and the third target vehicle is assigned green. Along the parking guidance routes of the target vehicles, guidance signs are projected according to the guidance colors at the next fork in the road in advance, and the license plate numbers of the same color are displayed and marked next to the guidance signs, so that the owners can drive the vehicles according to the license plate numbers and identification colors.

[0144] Specifically, in advance at the first fork in the road, respectively project a right turn guide sign and A11111 in red, project a right turn guide sign and A88888 in blue, and project a left turn guide sign and A66666 in green to guide the first target vehicle and the second target vehicle to turn right at the first fork in the road, and the second target vehicle to turn left at the first fork in the road. As the first target vehicle and the second target vehicle travel, in advance at the second fork in the road, respectively project a straight-ahead guide sign and A11111 in red, and project a left turn guide sign and A88888 in blue to guide the first target vehicle to continue to travel straight at the second fork in the road, and the second target vehicle to turn left at the second fork in the road to the designated target parking space. As the first target vehicle travels, in advance at the third fork in the road, project a right turn guide sign and A11111 in red to guide the first target vehicle to turn right at the third fork in the road to the designated target parking space.

[0145] In some embodiments, the parking lot guidance method based on dynamic projection may further include but is not limited to steps S801 to S803.

[0146] Step S801: When the parking space status of the target parking space changes from an idle state to an occupied state, the target parking space and the parking guidance route are updated according to the idle parking space list.

[0147] Step S802: When the target vehicle deviates from the parking guidance route, the target parking space and the parking guidance route are updated according to the vehicle head direction.

[0148] Step S803: When the lane congestion exceeds a preset threshold range, the target parking space and the parking guidance route are updated according to the lane congestion.

[0149] Specifically, when the parking space status of the target parking space changes from free to occupied, the target parking space and the parking guidance route are updated according to the free parking space list. During the driving process of the target vehicle, if the originally planned target parking space is preempted by other car owners to park their vehicles, the parking space status of the target parking space will change from free to occupied. If the car owner continues to be guided to the target parking space, the car owner will not be able to park. Therefore, it is necessary to re-determine the nearest free parking space according to the free parking space list to update the target parking space and the corresponding parking guidance route.

[0150] Alternatively, when the target vehicle deviates from the parking guidance route, the target parking space and parking guidance route are updated according to the vehicle head direction. During driving, when the driver does not follow the guidance signs at the fork in the road due to distraction or other unexpected factors, resulting in deviation from the parking guidance route, whether the driver chooses to turn around or detour, it will increase the time to find a parking space. Moreover, due to the deviation from the parking guidance route, the projection based on the old parking guidance route cannot provide guidance for the driver. Therefore, dynamic adjustment is required to adapt to the new situation, determine the actual driving direction of the target vehicle according to the vehicle head direction, re-plan the path according to the driving direction, and find the nearest vacant parking space along the driving direction to update the target parking space and the corresponding parking guidance route.

[0151] Alternatively, when the lane congestion exceeds the preset threshold range, the target parking space and parking guidance route are updated according to the lane congestion. The preset thresholds include a quantity threshold and a speed threshold, wherein the threshold range of the quantity threshold is determined by setting an upper limit of the quantity, and the threshold range of the speed threshold is determined by setting a lower limit of the speed. When the number of vehicles on the lane is greater than the upper limit of the quantity, or the driving speed is less than the lower limit of the speed, it is considered that the lane has a weak traffic capacity and belongs to a busy section. If you pass through this section, it is easy to increase the waiting time and affect the parking efficiency. Therefore, the path planning is re-performed according to the lane congestion to update the target parking space and parking guidance route.

[0152] Exemplarily, when the target vehicle passes through an intersection without following the parking guidance route, or when the vacancy status of a parking space changes, or when lanes on the parking guidance route are congested, the vacant parking spaces and corresponding parking guidance routes are re-acquired based on the target vehicle's current position, driving direction, list of vacant parking spaces, number of vehicles in the lane and speed, etc., thereby achieving real-time, dynamic route guidance until the target vehicle is parked in the target parking space.

[0153] In some embodiments, the parking lot guidance method based on dynamic projection may further include but is not limited to steps S901 to S906 .

[0154] Step S901, recording the positions, parking space numbers and corresponding occupied vehicle license plate numbers of all occupied parking spaces in the parking lot map, and obtaining an occupied parking space list, wherein the occupied vehicle license plate number is the license plate number of the vehicle parked in the occupied parking space.

[0155] Step S902, obtaining the vehicle owner's vehicle search request information, wherein the vehicle search request information includes the requested location and the vehicle license plate number.

[0156] Step S903, matching the occupied license plate number in the occupied parking space list according to the license plate number of the vehicle being sought, and determining the parking space corresponding to the matched occupied license plate number as the parking space for the vehicle being sought.

[0157] Step S904, taking the requested location as the starting point of the vehicle search and the parking space as the end point of the vehicle search, performing path planning according to the starting point of the vehicle search and the end point of the vehicle search, and determining the vehicle search guidance route.

[0158] Step S905, determining the guidance sign of the fork intersection according to the vehicle search guidance route.

[0159] Step S906, projecting a guidance sign at the next fork in the road along the vehicle-finding guidance route.

[0160] Specifically, the positions of all occupied parking spaces in the parking lot map, the parking space numbers, and the corresponding occupied license plate numbers are recorded to obtain an occupied parking space list, wherein the occupied license plate number is the license plate number of the vehicle parked in the occupied parking space. Whenever an occupied parking space is identified in step S301, the position and parking space number of the parking space in the parking lot map are recorded, and the license plate number of the vehicle parked in the parking space is identified as the occupied license plate number corresponding to the occupied parking space in combination with image recognition technology. The positions, parking space numbers, and corresponding occupied license plate numbers of all currently occupied parking spaces are summarized to obtain an occupied parking space list.

[0161] Alternatively, whenever it is identified that the parking space status changes from an idle state to an occupied state, the location of the parking space in the parking lot map, the parking space number and the corresponding occupied vehicle license plate number are recorded and added to the occupied parking space list.

[0162] Obtain the car owner's car search request information, where the car search request information includes the requested location and the car search license plate number. Paste a QR code containing address information at the entrance and exit of the parking lot, intersection, etc. When the car owner needs to find the car, he can load the application (such as a mobile APP or mini program) by scanning the QR code on the wall. The application can read the address information provided by the QR code to determine the owner's current requested location, and obtain the car search license plate number entered by the car owner through the application interface for subsequent route planning.

[0163] The application performs a query operation in the occupied parking space list based on the license plate number of the car being searched, and searches for a placeholder license plate number that matches the license plate number of the car being searched. If the query is successful, the parking space corresponding to the placeholder license plate number is determined as the car being searched, and the location and parking space number of the parking space in the parking lot map are returned. If the query fails (i.e., no matching placeholder license plate number is found), the user may be prompted that the input is incorrect.

[0164] It should be noted that the car search request information may also include a parking space number for the car search. The parking space number input by the car owner is obtained through the application program interface. The parking space number is matched in the occupied parking space list according to the parking space number for the car search, and the parking space corresponding to the matched parking space number is determined as the parking space for the car search. The matching method for the parking space number for the car search is similar to the matching method for the license plate number for the car search, and will not be repeated in the embodiments of the present application.

[0165] The requested location is used as the starting point of the car search, and the parking space is used as the end point of the car search. The path is planned based on the starting point and end point of the car search to determine the car search guidance route. In the path planning process, the requested location is used as the starting point of the car search path planning, and the parking space is used as the end point of the car search path planning. The car search guidance task is established, and the adjacent nodes are traversed from the car search starting point to determine whether there is an end point where the parking space is located in the adjacent nodes. According to the minimum cost, the shortest walking route is found to obtain the car search guidance route.

[0166] Then, the guide sign of the fork road is determined according to the vehicle-finding guidance route. According to the turning situation of the vehicle-finding guidance route at the fork road, the guide sign of each fork road is determined.

[0167] Finally, a guidance sign is projected at the next fork in the road along the car-finding guidance route. By dynamically managing the projector, a guidance sign is projected at the next fork in the road along the car-finding guidance route to prevent the car owner from missing the intersection and improve the efficiency of car-finding.

[0168] In step S906 of some embodiments, the end timing of the vehicle search guidance projection may be determined according to the parking space status, and the projection guidance may be turned off according to the end timing.

[0169] When the parking space status of the parking space in the car-finding guidance task changes from occupied to idle, it is considered that the owner has found the vehicle according to the car-finding guidance route and driven away. The current time can be determined as the end time of the car-finding guidance projection, the car-finding guidance task is ended, and the projection guidance is turned off.

[0170] In step S906 of some other embodiments, the end timing of the vehicle search guidance projection may be determined according to a preset projection duration, and the projection guidance may be closed according to the end timing.

[0171] It is understandable that the preset projection duration can be set to different durations according to the size of the parking lot. Turning on the projection equipment for a long time will consume electricity, especially in large parking lots. If each projection device is turned on continuously, the energy consumption will be very large. By setting the preset projection duration, it is possible to avoid unnecessary energy waste while ensuring that the owner has enough time to find the vehicle. If the current projection duration meets the preset projection duration, it is assumed that the owner has found the vehicle according to the vehicle search guidance route, and the current time can be determined as the end time of the vehicle search guidance projection, the vehicle search guidance task is ended, and the projection guidance is turned off.

[0172] For example, assuming that the preset projection time is ten minutes, if the same car search guidance task has been projected for ten minutes at multiple forked intersections, but the parking space status in the car search guidance task is always occupied, it is assumed that the owner has found the vehicle according to the car search guidance route, but due to personal reasons, the owner has not left the parking space temporarily. Therefore, the car search guidance task can be ended and the projection guidance can be turned off. If the owner does not find the vehicle according to the car search guidance route within the preset projection time, he can also rescan the nearby car search QR code, perform path planning again according to the current request location, and establish a new car search guidance task.

[0173] The following is a detailed introduction and description of the solution of the embodiment of the present invention in conjunction with a specific application example.

[0174] The embodiment of the present application can be applied to a parking lot guidance system. Figure 6 The parking lot guidance system includes a parking lot parking space monitoring system, a server, an ARM host, a projector and a car search QR code. The monitoring system includes devices such as cameras and network video recorders (NVRs), and the server includes a target recognition module, a path planning module and a projection control module.

[0175] In parking guidance scenarios and car-searching guidance scenarios, the entire parking lot is treated as a whole, taking into account factors such as parking spaces, vehicles, and pedestrians.

[0176] During parking guidance, when factors such as parking spaces and vehicles in the parking lot change, or when the owner does not drive according to the guidance route, the guidance system will update the parking guidance route in real time.

[0177] When guiding the driver to find the car, the guidance system uses a ground projector to display the guidance path at the intersection to prevent the driver from missing the intersection and accurately guide the driver to the nearest target parking space.

[0178] Specifically, to implement the parking lot guidance method based on dynamic projection, it is necessary to install cameras, ARM hosts, projectors and car-finding QR codes throughout the parking lot, wherein cameras are arranged in the parking lot according to the layout of parking spaces in the parking lot and the field of view and focal length of the cameras, so that all parking spaces in the parking lot are within the camera range, so as to obtain the situation of the entire parking lot; projectors are installed at each intersection, and these projectors will display the guidance signs and license plate numbers on the road in real time according to the information received by the ARM host from the projection control module, so as to guide the car owners to drive according to the route; the car-finding QR code is pasted near the entrance or intersection, and the character string represented by the QR code contains location information, and different QR codes correspond to a certain entrance or exit or a certain intersection of the parking lot.

[0179] According to the distribution of parking lanes and parking spaces in the parking lot, a path map is established using the grid map method to plan the path from the starting point to the destination.

[0180] The server obtains video streams from all cameras in the parking lot in real time and uses NVR to save the video streams. The target recognition module identifies the location and number of free parking spaces based on the video stream, counts the total number of free parking spaces, and obtains a list of free parking spaces. The license plate number, driving direction, number and speed of vehicles traveling on the lane are identified based on the video stream to obtain lane congestion conditions, providing data for dynamically guiding target vehicles to avoid busy sections.

[0181] It should be noted that counting the total number of vacant parking spaces in a parking lot can also be used to determine the usage of parking spaces, providing reference data for analyzing user parking habits and predicting parking lot traffic.

[0182] Furthermore, in order to improve the safety of guidance, it can also include identifying the walking direction of pedestrians on the lane based on the video stream and providing the car owner with early warning information to pay attention to pedestrians.

[0183] In some embodiments, irregularly parked vehicles can also be identified based on the video stream, such as vehicles parked irregularly in parking spaces (parked across multiple parking spaces, not fully parked in a parking space, etc.) or vehicles parked in driveways, and an alarm message can be sent to the parking lot manager to provide data for standardized management of the parking lot.

[0184] When a vehicle enters the parking lot, the target vehicle is identified, tracked, and located based on the video stream at the entrance. When the vehicle is about to leave the current camera's video range and enter the next camera's video range, the video stream of the corresponding camera is switched to continue identifying, tracking, and locating the target vehicle.

[0185] For example, the target vehicle in the video stream is identified and saved by the target detection algorithm, such as the vehicle head direction, vehicle color, and license plate number. When the vehicle moves within the same camera range, the target vehicle is identified according to the saved vehicle features to achieve the purpose of tracking. When the vehicle is about to move from one camera range to another, the video stream of the next camera is identified and tracked according to the same features according to the pre-set camera number.

[0186] After the target vehicle is identified according to the saved vehicle features, the permanent or semi-permanent buildings are identified in the same picture. In a parking lot, the permanent or semi-permanent buildings are usually the column grid and parking spaces of the parking lot. Through image processing technology, such as edge detection, shape recognition, etc., the outline and position of these buildings in the picture are identified. Then, using the text recognition algorithm, the column grid is determined by identifying the column grid number posted on the column grid in the picture, and the parking space is determined by identifying the parking space number printed on the parking space in the picture. According to the positional relationship between the target vehicle and the permanent or semi-permanent building, the position and direction of the target vehicle in the grid map are determined, so as to realize the positioning of the target vehicle and provide parameters such as the position and direction of the target vehicle for subsequent path planning. For example, according to the left and right, front and back positions of the target vehicle relative to the column grid, and the relative position of the target vehicle and the parking space, the positional relationship between the identified target vehicle and the building is mapped to the grid map to determine the specific position and direction of the target vehicle in the grid map.

[0187] Reference Figure 7 , the blue frame indicates the camera range of the first camera, the yellow frame indicates the camera range of the second camera, and the green frame indicates the camera range of the third camera. After the vehicle enters the entrance, the license plate number, vehicle color, and vehicle head direction of the target vehicle are recognized and saved through the video stream of the first camera, and the position and direction of the target vehicle in the grid map are determined through column grids #12, #13, #22, and #23.

[0188] When the target vehicle moves to the place where the blue border overlaps with the yellow border, the source of the video stream is switched from the first camera to the second camera. The target vehicle is further identified based on the saved vehicle features through the video stream of the second camera, and the position and direction of the target vehicle in the grid map are updated based on the positional relationship between the target vehicle and column grids #11, #12, #21, and #22, so as to realize the identification, tracking, and positioning of the target vehicle during driving, and provide a data basis for the subsequent planning of an accurate path trajectory for the target vehicle.

[0189] When a vehicle enters the parking lot, the current position of the vehicle, the driving direction, the list of free parking spaces, and the lane congestion are provided to the path planning module for real-time path planning. The current position and driving direction of the vehicle are used as the starting point of the destination screening method, and the list of free parking spaces is used as the list of destinations to be screened. According to the location of the vehicle in the lane and the driving speed, the cost of the corresponding grid is increased. The minimum total cost is used as the selection criterion, so that the selected target parking space and the corresponding parking guidance route meet the requirements of the nearest free parking space and the driving route that avoids busy sections.

[0190] After receiving the parking guidance route sent by the path planning module, the projection control module determines the projectors and guidance signs involved in the route according to the parking guidance route. These guidance signs include direction information such as straight, left turn, and right turn. Then, the guidance signs, license plate numbers, and vacant parking space numbers of each intersection are sent to the corresponding projector. The projector displays the guidance signs, license plate numbers, and parking space numbers of vacant parking spaces at the intersection according to the received projection information.

[0191] When the same ground projector has multiple guidance routes, the guidance system will distinguish them by different colors.

[0192] When finding a car, car owners can scan the car-finding QR code at entrances, stairs, and elevator entrances, enter the license plate number or parking space number on their mobile phone, use the location information contained in the QR code as the starting point of path planning, and the vehicle location or parking space number as the end point of path planning. The car-finding guidance route can be dynamically displayed at the intersection through a ground projector to improve car-finding efficiency.

[0193] In this embodiment, target detection technology is used to identify, track, and locate parking spaces, vehicles, pedestrians, etc. in the entire parking lot through real-time cameras. It identifies whether the parking space is idle and provides data for parking guidance. If the parking space is not idle, the license plate number of the vehicle parked in the parking space is identified to provide data for vehicle search guidance.

[0194] When guiding the parking vehicle, the system searches for the nearest vacant parking space with less busy lanes based on the current position of the parking vehicle, and displays the guidance route for the parking vehicle through a ground projector installed at the intersection. If the vehicle does not follow the guidance route, or if the originally planned guidance route is congested, or if there is a vacant and less congested parking space closer to the current position of the parking vehicle, the guidance system will dynamically guide the vehicle at the next intersection based on the direction of travel, and adjust the guidance route in real time, so that the owner can park the vehicle as soon as possible, thus improving parking efficiency.

[0195] When guided to find a car, car owners can scan the car-finding QR code at entrances, stairs, and elevator entrances, and enter the license plate number or parking space number on their mobile phone. The guidance system will dynamically display the car-finding route at the intersection through a ground projector, thereby improving car-finding efficiency.

[0196] In some embodiments, the parking lot guidance method based on dynamic projection can also be applied to the reserved parking scenario.

[0197] Specifically, when the car owner enters the license plate number in advance through the application software APP or mini program and specifies a reserved parking space in the available parking spaces for reservation parking, the ground lock of the reserved parking space is controlled to rise. When the reserved vehicle enters the parking lot, the license plate number of the identified target vehicle is matched with the license plate number entered in advance. When the numbers are consistent, it is confirmed that the target vehicle is the reserved vehicle, and the route is planned with the reserved parking space as the destination. The guidance sign and the parking space number of the reserved parking space are projected according to the parking guidance route. When the reserved vehicle is tracked and identified to arrive at the reserved parking space according to the parking guidance route, the ground lock is controlled to descend so that the vehicle can be parked in the parking space.

[0198] If the parking lot is a private parking lot, the car owner can enter the designated number of the reserved parking space in advance when making a parking reservation through an application APP or mini program. After the reserved vehicle is identified as entering the parking lot, the vehicle will be guided to the reserved parking space by the car owner through a projector.

[0199] In some embodiments, when there is still remaining area in a projector display area after projecting a guide sign, advertising content of corresponding size is selected and sent to the projector based on the size of the remaining area, and the advertisement is projected next to the guide sign to provide additional information without affecting the guidance effect.

[0200] Furthermore, when the projector has no guiding task, the projector is controlled to be in standby mode to reduce the energy consumption of the device. If a pedestrian is detected passing through the intersection, the projector is controlled to display an advertisement to make full use of the idle time of the projector and optimize resource allocation.

[0201] Reference Figure 8 The embodiment of the present application further provides a parking lot guidance device based on dynamic projection, which can implement the above-mentioned parking lot guidance method based on dynamic projection, and the device includes:

[0202] The first module is used to create a parking lot map.

[0203] The second module is used to obtain the video streams of all cameras in the parking lot.

[0204] The third module is used to obtain a list of available parking spaces and lane congestion conditions based on the video stream.

[0205] The fourth module is used to perform target detection on the video stream of the camera at the entrance of the parking lot when a vehicle enters the parking lot, determine the vehicle characteristics of the target vehicle and the positioning information in the parking lot map, where the vehicle characteristics include the direction of the vehicle head, vehicle color and license plate number.

[0206] The fifth module is used to plan the path based on the positioning information, the list of available parking spaces and the lane congestion, and determine the target parking space and the parking guidance route.

[0207] The sixth module is used to determine the guidance signs of the fork intersection according to the parking guidance route, wherein the guidance signs include straight ahead, left turn and right turn.

[0208] The seventh module is used to track and locate the target vehicle using vehicle features, and to project a guide sign at the next fork in the road along the parking guidance route until the target vehicle reaches the target parking space.

[0209] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0210] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned parking lot guidance method based on dynamic projection when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car-mounted computer, etc.

[0211] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0212] Reference Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0213] The processor 901 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0214] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the parking lot guidance method based on dynamic projection in the embodiment of the present application.

[0215] The input / output interface 903 is used to implement information input and output.

[0216] The communication interface 904 is used to realize the communication interaction between this device and other devices. Communication can be realized through wired methods (such as USB, network cable, etc.) or wireless methods (such as mobile network, WI FI, Bluetooth, etc.).

[0217] The bus 905 transmits information between various components of the device (eg, the processor 901 , the memory 902 , the input / output interface 903 , and the communication interface 904 ).

[0218] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0219] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned parking lot guidance method based on dynamic projection is implemented.

[0220] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0221] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0222] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0223] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0224] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0225] Those skilled in the art will appreciate that all or some of the steps, devices, and functional modules / units in the above disclosed methods may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0226] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0227] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A parking lot guidance method based on dynamic projection, characterized in that: The method comprises the following steps: Create a parking lot map for the parking lot; Get the video streams from all the cameras in the parking lot; Obtaining a list of available parking spaces and lane congestion conditions according to the video stream; When a vehicle enters the parking lot, target detection is performed on the video stream of the camera at the entrance of the parking lot to determine the vehicle characteristics of the target vehicle and the positioning information in the parking lot map, wherein the vehicle characteristics include the vehicle head direction, vehicle color and license plate number; Based on the positioning information, path planning is performed according to the list of available parking spaces and the lane congestion situation to determine the target parking space and the parking guidance route; Determine a guide sign at a fork intersection according to the parking guide route, wherein the guide sign includes going straight, turning left, and turning right; The target vehicle is tracked and located using the vehicle features, and the guide mark is projected in advance at the next fork along the parking guide route until the target vehicle arrives at the target parking space.

2. The method according to claim 1, characterized in that The method of establishing a parking lot map comprises the following steps: The parking lot is divided into multiple grids by using the grid map method to establish a grid map; Determining lane grids in the grid map according to the lane layout of the parking lot, and marking a drivable direction for each lane grid; Determine a parking space grid in the grid map according to the parking space layout of the parking lot, and mark a parking space number for each parking space grid; A parking lot map of the parking lot is obtained according to the lane grid and the parking space grid.

3. The method according to claim 2, characterized in that The step of obtaining a list of free parking spaces and lane congestion conditions according to the video stream comprises the following steps: Determining the parking space status of each parking space according to the video stream, wherein the parking space status includes an idle state and an occupied state; Record the positions and parking space numbers of all the idle parking spaces in the parking lot map to obtain an idle parking space list; The number of vehicles on each lane and the driving speed are identified according to the video stream to obtain the lane congestion situation.

4. The method according to claim 2, characterized in that: The method of performing path planning based on the positioning information and according to the list of free parking spaces and the lane congestion to determine the target parking space and the parking guidance route includes the following steps: The positioning information is used as the starting point of the path planning, and the list of free parking spaces is used as the list of destinations to be screened; Increasing the cost of the lane grid according to the lane congestion situation, and determining the end point with the minimum total path cost as the target parking space through a path planning algorithm; The parking guidance route is obtained by tracing back to the starting point according to the target parking space.

5. The method according to claim 1, characterized in that: The method of tracking and locating the target vehicle by utilizing the vehicle characteristics comprises the following steps: When the target vehicle moves within the camera range of the same camera, target recognition is performed on the video stream of the same camera according to the vehicle characteristics, and the positioning information is updated to track the target vehicle; When the target vehicle moves to the edge of the camera range, the camera is switched to an adjacent camera according to a preset rule, the video stream of the adjacent camera is subjected to target recognition according to the characteristics of the vehicle, and the positioning information is updated to track the target vehicle.

6. The method according to claim 1, characterized in that The method of projecting the guide mark at the next fork in the road along the parking guide route until the target vehicle reaches the target parking space comprises the following steps: Projecting the guide sign at the next fork in the road in advance along the parking guide route, and projecting the parking space number of the target parking space and the license plate number of the target vehicle next to the guide sign until the target vehicle arrives at the target parking space; The step of projecting the guide sign at the next fork in the road along the parking guide route in advance, and projecting the parking space number of the target parking space and the license plate number of the target vehicle next to the guide sign, comprises the following steps: When there are multiple target vehicles, a different guide color is assigned to each target vehicle, and the guide signs are projected according to the guide colors at the next fork along the parking guide route in advance, and the parking space number of the target parking space and the license plate number of the target vehicle are projected next to the guide sign according to the guide color.

7. The method according to claim 3, characterized in that The parking lot guidance method based on dynamic projection also includes the following steps: When the parking space state of the target parking space changes from an idle state to an occupied state, updating the target parking space and the parking guidance route according to the idle parking space list; When the target vehicle deviates from the parking guidance route, the target parking space and the parking guidance route are updated according to the vehicle head direction; When the lane congestion exceeds a preset threshold range, the target parking space and the parking guidance route are updated according to the lane congestion.

8. The method according to claim 3, characterized in that The parking lot guidance method based on dynamic projection also includes the following steps: Recording the positions, parking space numbers and corresponding occupied vehicle license plate numbers of all the occupied parking spaces in the parking lot map to obtain an occupied parking space list, wherein the occupied vehicle license plate numbers are the license plate numbers of vehicles parked in the occupied parking spaces; Obtaining the vehicle owner's vehicle search request information, wherein the vehicle search request information includes the requested location and the vehicle license plate number; Matching the occupied license plate number in the occupied parking space list according to the sought-for vehicle license plate number, and determining the parking space corresponding to the matched occupied license plate number as the sought-for vehicle parking space; The requested location is used as the starting point of the car search, and the parking space is used as the end point of the car search. A path is planned according to the starting point and the end point of the car search to determine the car search guidance route; Determine the guidance sign of the fork in the road according to the vehicle-finding guidance route; The guide mark is projected in advance at the next fork in the road along the vehicle-finding guide route.

9. A parking lot guidance device based on dynamic projection, characterized in that: The device comprises: The first module is used to establish a parking lot map; The second module is used to obtain the video streams of all cameras in the parking lot; The third module is used to obtain a list of free parking spaces and lane congestion conditions according to the video stream; The fourth module is used to detect the target on the video stream of the camera at the entrance of the parking lot when a vehicle enters the parking lot, and determine the vehicle characteristics of the target vehicle and the positioning information in the parking lot map, wherein the vehicle characteristics include the vehicle head direction, vehicle color and license plate number; A fifth module is used to perform path planning based on the positioning information, the list of available parking spaces and the lane congestion, and determine a target parking space and a parking guidance route; A sixth module is used to determine a guide sign at a fork intersection according to the parking guide route, wherein the guide sign includes going straight, turning left, and turning right; The seventh module is used to track and locate the target vehicle using the vehicle features, and to project the guide sign at the next fork in the road along the parking guide route until the target vehicle arrives at the target parking space.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images