An underground garage intelligent management and car searching method based on area monitoring

Abstract

This invention discloses a smart management and vehicle location method for underground parking garages based on area monitoring, belonging to the fields of intelligent parking and computer vision technology. This invention deploys area monitoring cameras covering multiple parking spaces, using computer vision algorithms to identify parking space occupancy status and license plate information in real time; it constructs a digital two-dimensional map of the garage, calibrating the coordinates of cameras, entrances / exits, and intersections of passageways, and establishing a mapping relationship between parking space numbers and camera coordinates; after scanning a location QR code to obtain the current coordinates, users can enter their license plate number to determine the vehicle's parking location. An A* heuristic search algorithm is used to plan the optimal vehicle location path, and the path is dynamically updated during the journey. This invention replaces single-space sensors with area cameras, while reusing cameras to achieve security monitoring functions, reducing construction and maintenance costs and enabling real-time parking space management and intelligent reverse vehicle location.

Description

Technical Field

[0001] This invention relates to the field of intelligent parking technology, and in particular to a method for intelligent management and vehicle location in underground parking garages based on area monitoring. Background Technology

[0002] With the continuous increase in car ownership in my country, large underground parking garages have become standard parking facilities in commercial complexes and public buildings. However, underground parking garages are enclosed spaces with dense parking spaces and complex passage topology, resulting in low efficiency for car owners to find their parking spaces when entering and leaving. At the same time, parking garage operators face problems such as high parking space management costs and complex operation and maintenance of multiple independent systems.

[0003] Current mainstream parking space management and reverse vehicle search technologies have many limitations. Traditional single-parking-space sensor solutions detect occupancy status by deploying ultrasonic or geomagnetic sensors in each parking space. Hardware and wiring costs increase linearly with the number of parking spaces, and they can only output a binary status of occupancy / vacancy, unable to identify license plate information, requiring additional identification equipment. The humid and dusty environment of underground parking garages also easily leads to false detections and missed detections by sensors, making maintenance difficult.

[0004] QR code positioning solutions are widely used. CN107301787A discloses a method for positioning and guiding in large parking lots based on location QR codes. This solution achieves positioning and vehicle search guidance by deploying location QR codes, but the parking space status depends on updates to the backend database, resulting in data lag, and it does not combine visual perception to achieve automated collection of parking space information. CN104933886A discloses a QR code scanning reverse vehicle search system for smart terminals. This solution requires users to actively scan the code to mark the parking space location after parking, which is cumbersome and prone to failure due to forgetting to mark the location, thus failing to achieve automated parking space management.

[0005] In addition, CN119245652A discloses a navigation and vehicle-finding method for an automated inspection robot in an outdoor parking lot environment. This solution relies on mobile inspection to identify license plates, but the overall deployment and maintenance costs are high. Furthermore, the solution is designed for outdoor scenarios and relies on satellite positioning signals, making it unsuitable for underground enclosed parking garage environments. Additionally, the inspections have time intervals, making it difficult to achieve continuous real-time monitoring of parking space status.

[0006] Meanwhile, existing parking management and security monitoring systems in parking garages are generally deployed independently, resulting in redundant investment in hardware resources, overlapping construction and maintenance costs, and low overall resource utilization. In summary, existing technologies struggle to simultaneously achieve low-cost deployment, real-time status awareness, convenient vehicle location experience, and multi-functional integration, thus failing to meet the needs of intelligent operation in large underground parking garages. Summary of the Invention

[0007] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0008] In view of the aforementioned existing problems, this invention is proposed. Therefore, this invention provides a smart management and vehicle location method for underground parking garages based on area monitoring, to solve the problems mentioned in the background art.

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for intelligent management and vehicle location in underground parking garages based on regional monitoring, comprising: S1: Deploy area monitoring cameras, which cover a parking area and use computer vision algorithms to identify the occupancy status of each parking space and the license plate information of parked vehicles in real time. S2: Construct a digital two-dimensional planar map of the underground parking garage, mark the internal planar coordinates of each area's surveillance camera, garage entrance / exit, and passageway intersection on the map, and establish a mapping relationship between the camera coordinates and parking space numbers; S3: When a user needs to find their car, they can scan the location QR code deployed in the garage using their mobile terminal to obtain the user's current location coordinates, and enter the target license plate number. Based on the target license plate number, the system will query the corresponding camera coordinates to determine the coordinates of the vehicle's parking location. S4: Using the user's current location coordinates as the starting point of the path planning and the coordinates of the vehicle's parking location as the ending point of the path planning, the A* heuristic search algorithm is used to perform path planning, generate the optimal vehicle-finding navigation path, and display it on the mobile terminal. S5: During the process of the user walking along the navigation path to find the car, the user is allowed to update their current location coordinates in real time by scanning the location QR code at the intersection of the passage, and the car-finding navigation path is replanned and updated based on the updated location coordinates.

[0010] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This invention adopts a solution of using a single area camera to cover 6 to 12 parking spaces, replacing the traditional mode of deploying sensors for each parking space, which can reduce the number of hardware and wiring workload; at the same time, since the stability of camera equipment is better than that of distributed sensors, it can also reduce the cost of troubleshooting and maintenance in the later stage.

[0011] 2. This invention automatically identifies parking space occupancy status and license plate information through computer vision algorithms, with data updates reaching the second level, eliminating the need for users to manually mark parking spaces; combined with QR code positioning and A* heuristic search algorithm, it can quickly generate the optimal car-finding route, supporting QR code relocation and dynamic route updates, effectively solving the problems of difficulty in finding cars and getting lost in underground parking garages.

[0012] 3. In addition, the present invention allows the same set of area cameras to perform the dual functions of parking space status recognition and security anomaly detection in parallel, without the need for a separate security monitoring system; it can also automatically identify abnormal behaviors such as people loitering and vehicles scratching, automatically store event recordings and push alarms, and support multi-dimensional historical recording tracing, thereby improving the security management capabilities of the garage while avoiding redundant hardware construction. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a flowchart illustrating the method described in one embodiment of the present invention; Figure 2 This is a schematic diagram of a regional camera management area according to an embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the construction of a digital two-dimensional planar map according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the location QR code encoding structure according to an embodiment of the present invention; Figure 5 This is a flowchart of the A* algorithm path planning process according to an embodiment of the present invention; Figure 6 This is a flowchart illustrating a face recognition-assisted guidance process according to an embodiment of the present invention; Figure 7 This is a complete flowchart of the user reverse vehicle search process according to one embodiment of the present invention; Figure 8 This is a flowchart illustrating the integrated camera security monitoring function according to one embodiment of the present invention; Figure 9 This is a system architecture diagram according to an embodiment of the present invention. Detailed Implementation

[0014] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0015] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0016] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0017] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0018] Example 1

[0019] Reference Figures 1 to 8 This is the first embodiment of the present invention, which provides a method for intelligent management and vehicle location in underground parking garages based on area monitoring, including: S1: Deploy area surveillance cameras that cover a parking area and use computer vision algorithms to identify the occupancy status of each parking space and the license plate information of parked vehicles in real time.

[0020] Specifically, in combination Figure 2 The diagram shown illustrates the area managed by the area cameras. Based on the parking space distribution information in the underground garage, area monitoring cameras are deployed on the garage ceiling according to the principle that each camera covers a certain number of adjacent parking spaces (preferably 6-12 spaces). The camera installation height is typically 2.5-3 meters, with a fan-shaped field of view covering the entire parking space area it manages. The specific processing flow for identification using computer vision algorithms is as follows: (1) Use the area monitoring camera to collect images of parking spaces in the covered area in real time at a fixed frame rate (e.g., 5 to 10 frames per second).

[0021] (2) Preprocess the acquired images, including grayscale conversion, Gaussian denoising (e.g., using a Gaussian filter with a 5×5 kernel size) and histogram equalization image enhancement, to improve the accuracy of subsequent target detection and license plate recognition.

[0022] (3) Use deep learning-based target detection algorithms (such as YOLO series or SSD algorithm) to identify vehicles in the image. By matching the detection results with the parking space area bounding box that is pre-labeled, the occupancy status (vacant or occupied) of each numbered parking space can be determined.

[0023] (4) For vehicles in occupied parking spaces, license plate recognition is performed. The license plate number is extracted using OCR (Optical Character Recognition) technology. The specific process includes license plate area positioning, character segmentation and character recognition.

[0024] (5) Upload parking space status information, including parking space number, occupancy status, license plate number and timestamp, to the backend database for storage and management via wired or wireless network.

[0025] S2: Construct a digital two-dimensional planar map of the underground parking garage, mark the internal planar coordinates of each area's surveillance camera, garage entrance / exit, and passageway intersection on the map, and establish a mapping relationship between the camera coordinates and parking space numbers.

[0026] Specifically, in combination Figure 3 The diagram shown illustrates the construction of a digital two-dimensional planar map. The process of constructing a digital map includes: First, based on the actual layout plan of the underground parking garage, establish a relative planar coordinate system (including...) with a fixed reference point of the garage (such as the entrance) as the origin. shaft and The coordinate system uses axes (with meters as the coordinate unit). Then, the installation position of each camera is marked as a coordinate point in this coordinate system. The system records the camera numbers and the range of parking space numbers they cover. Finally, it marks garage entrances and exits, passageway intersections, stairwells and elevator entrances as key nodes in the coordinate system, assigning each key node a unique node number and coordinates. By establishing a mapping table between parking space numbers and camera coverage areas, when a user queries by license plate number, the system can first associate it with the corresponding camera number, and then accurately obtain the coordinates of the vehicle's parking location through the internal planar coordinates of the camera.

[0027] S3: When a user needs to find their car, they can scan the location QR code placed in the garage with their mobile terminal to obtain the user's current location coordinates, and enter the target license plate number. Based on the target license plate number, the system will query the corresponding camera coordinates to determine the coordinates of the vehicle's parking location.

[0028] Specifically, in combination Figure 4 The diagram shows the location QR code encoding structure. These location QR codes are primarily placed at garage entrances / exits, passageway intersections, and stairwell / elevator entrances. The encoded information within the QR code uses a JSON data structure and includes: garage number, floor number, QR code number, and location coordinates. And the topological relationship of the channel (i.e., information on adjacent nodes, used for path planning).

[0029] Specifically, the mobile terminal uses a cross-platform mini-program application developed based on the Uni-app framework, supporting multi-platform operation and enabling one-time development and multi-terminal deployment. Users can use the car-finding and navigation function without installing a separate app. After the user scans the QR code, the system parses the QR code to obtain the user's current precise location. After the user enters the target license plate number on the mobile terminal, the system queries the background database for the camera number that records that license plate number and determines the vehicle's parking location coordinates based on the internal planar coordinates corresponding to that camera number on the digital two-dimensional map.

[0030] S4: Using the user's current location coordinates as the starting point of the path planning and the coordinates of the vehicle's parking location as the ending point of the path planning, the A* heuristic search algorithm is used to perform path planning, generate the optimal vehicle-finding navigation path, and display it on the mobile terminal.

[0031] Specifically, in combination Figure 5 The flowchart of the A* algorithm path planning is shown below. The specific implementation of path planning is as follows: The digital two-dimensional planar map is abstracted into a graph structure. ,in It is a set of nodes (i.e., intersections and key locations). Let's define a set of edges (i.e., channel segments), with each edge's weight equal to the physical length of the channel segment. Then, the coordinates obtained from the user's current scan of the QR code will be used as the starting point. The coordinates corresponding to the vehicle's parking location are used as the endpoint. And match it to the nearest node in the graph structure. Define a heuristic function. This represents the estimated distance cost from the current node n to the planned destination t. In this embodiment, Euclidean distance is used as the heuristic function to ensure admissibility (not overestimating the actual cost) and guarantee that the algorithm finds the optimal path. The formula is expressed as:

[0032] in, This represents the node currently being evaluated; Represents the endpoint of the car search; These represent the x-coordinate and y-coordinate of the current node n in the digital two-dimensional plane map, respectively; Representing the finish line The horizontal and vertical coordinates in a digital two-dimensional planar map.

[0033] At the same time, an evaluation function is adopted. The nodes are prioritized and evaluated using the following formula:

[0034] in, The overall priority evaluation value of node n; This represents the actual path cost from the starting point s to the current node $n$ (i.e., the sum of the physical lengths of the passage segments already traversed). This represents the estimated distance cost from the current node to the destination, as described above.

[0035] Finally, starting from the beginning To begin, maintain an open list (nodes to be expanded) and a closed list (nodes that have already been expanded), and iteratively select... The unvisited node with the smallest value (highest priority) is expanded, and its neighboring nodes are added to the open list until the destination t is reached. The optimal car-finding navigation path is generated by backtracking through the parent node pointer and displayed as a highlighted route on the mobile terminal's flat map.

[0036] S5: During the process of the user walking along the navigation path to find the car, the user is allowed to update their current location coordinates in real time by scanning the location QR code at the intersection of the passage, and the car-finding navigation path is replanned and updated based on the updated location coordinates.

[0037] Specifically, in combination Figure 7 The flowchart shown illustrates the complete process of a user's reverse vehicle search. When a user deviates from the original route or gets lost in the garage, there is no need to re-enter the license plate number. The user only needs to scan the QR code at the nearest intersection, and the system can obtain the coordinates again and use this as a new starting point to re-run the A* algorithm to generate the latest navigation path, ensuring that the user always receives the correct guidance.

[0038] Furthermore, this method also integrates a comprehensive security monitoring function to achieve intelligent and integrated management of the parking garage.

[0039] Specifically, in combination Figure 8 The flowchart shown illustrates the integrated security monitoring function of the camera system. The area monitoring camera functions as a security monitoring device while simultaneously performing parking space management tasks, offering dual functionality without requiring a separate security system. Specifically, it includes: By using computer vision algorithms to analyze the acquired video streams in real time, a series of abnormal behavioral events can be automatically detected, such as people loitering for a long time, vehicles being scratched or collided, and illegal intrusions outside of business hours.

[0040] When an abnormal event is detected, the system automatically extracts and stores video clips of a preset duration (e.g., 30 seconds before and after the event) before and after the event, and marks the event type, time of occurrence, camera number, and location information.

[0041] Alarm information for abnormal events is pushed to the garage management terminal in real time, allowing the management to manually review and handle the situation on-site through real-time video.

[0042] It supports post-event traceability, and through license plate recognition records and timestamp indexes, it supports searching historical surveillance videos by license plate number, time period, or parking space area, providing a complete video evidence chain for vehicle scratch disputes, lost items, etc.

[0043] Furthermore, this method also integrates a parking guidance function (forward vehicle search).

[0044] Specifically, based on the real-time parking space occupancy status reported by cameras in each area, when a vehicle enters the garage and is recognized by the entrance camera, the system automatically selects the nearest available parking space and uses the A* algorithm to plan a navigation route to that available parking space. The system then displays the guidance information through mobile terminals or electronic displays in the garage, realizing a two-way closed-loop navigation system for parking guidance upon entry and reverse vehicle search upon exit.

[0045] Furthermore, this method also integrates a facial recognition-assisted guidance function.

[0046] Specifically, in combination Figure 6 The flowchart shown illustrates a facial recognition-assisted guidance process. With prior user authorization, the system can capture facial images of users passing by via cameras installed at garage entrances or passageway intersections. It then compares these images with the facial features of registered users in the database using a feature extraction model (e.g., FaceNet) (e.g., cosine similarity comparison). Upon successful recognition, the system automatically obtains the user's current location and queries the parking locations of vehicles linked to that user's name. It then automatically plans and proactively pushes a vehicle-finding navigation route to the mobile terminal, eliminating the need for users to manually scan codes or enter license plate numbers, thus achieving a seamless vehicle-finding experience.

[0047] Example 2

[0048] Reference Figure 9 This is the second embodiment of the present invention, which provides a smart management and vehicle locating system for underground parking garages based on regional monitoring, used to implement the vehicle locating and management method in Embodiment 1. The architecture specifically includes: I. Area surveillance camera group.

[0049] This module is deployed on the ceiling of the underground parking garage, with each camera covering an area containing 6-12 parking spaces. The cameras act as front-end sensing nodes, maintaining a connection to the back-end server (wired Ethernet or wireless network). They are responsible for not only acquiring real-time images of the parking spaces at a fixed frame rate of 5-10 frames per second for the back-end to perform YOLO / SSD object detection and OCR license plate recognition, but also synchronously transmitting the real-time video stream to the abnormal behavior detection module, enabling parallel processing of both parking space status monitoring and security monitoring.

[0050] II. Physical location marker (location QR code).

[0051] The system is deployed discontinuously within the parking garage, primarily at key locations such as garage entrances / exits, passageway intersections (e.g., nodes J01~J18), and stairwell / elevator entrances. Each QR code carries JSON-encoded data in a specific format, including the garage floor, node ID, precise planar coordinates, and topological mapping relationship with its adjacent passageway nodes. These identifiers form a bridge connecting the physical space and the digital map.

[0052] III. Backend Server System.

[0053] As the brain of the entire intelligent management system, this system mainly comprises three core modules: Visual processing and AI analysis module: responsible for processing images and videos streamed from the front-end camera, performing image preprocessing, parking space status recognition, license plate information extraction, and intelligent analysis of security anomalies such as people loitering or scratching.

[0054] Data and Map Management Module: Maintains the digital two-dimensional planar map and coordinate system of the parking garage, establishes and continuously updates a three-dimensional mapping database of parking space number-camera number-planar coordinates; and archives and stores parking space status records and captured security alarm video clips.

[0055] Route planning engine: When a vehicle search or location search request is received, the engine quickly retrieves map structure data and runs the built-in A* heuristic search algorithm (which relies on the Euclidean distance heuristic function) to calculate the optimal physical driving or walking navigation route.

[0056] IV. Mobile terminals and interactive display devices.

[0057] This primarily includes smartphones for users and PCs / large-screen devices for garage management. Users don't need to download a bulky app; they can directly access a lightweight mini-program developed using the Uni-app framework via platforms like WeChat or Alipay. After scanning a location QR code, they send their coordinates and query requests to the backend server via the internet. The mini-program interface receives and renders visually highlighted routes for finding parking spaces in either the reverse or forward direction. Garage managers can receive real-time security alarm notifications pushed by the backend server through their management terminals and review surveillance footage to complete comprehensive garage operation scheduling.

[0058] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for intelligent management and vehicle location in underground parking garages based on regional monitoring, characterized in that, include: S1: Deploy area monitoring cameras, which cover a parking area and use computer vision algorithms to identify the occupancy status of each parking space and the license plate information of parked vehicles in real time. S2: Construct a digital two-dimensional planar map of the underground parking garage, mark the internal planar coordinates of each area's surveillance camera, garage entrance / exit, and passageway intersection on the map, and establish a mapping relationship between the camera coordinates and parking space numbers; S3: When a user needs to find their car, they can scan the location QR code deployed in the garage using their mobile terminal to obtain the user's current location coordinates, and enter the target license plate number. Based on the target license plate number, the system will query the corresponding camera coordinates to determine the coordinates of the vehicle's parking location. S4: Using the user's current location coordinates as the starting point of the path planning and the coordinates of the vehicle's parking location as the ending point of the path planning, the A* heuristic search algorithm is used to perform path planning, generate the optimal vehicle-finding navigation path, and display it on the mobile terminal. S5: During the process of the user walking along the navigation path to find the car, the user is allowed to update their current location coordinates in real time by scanning the location QR code at the intersection of the passage, and the car-finding navigation path is replanned and updated based on the updated location coordinates.

2. The intelligent management and vehicle location method for underground parking garages based on regional monitoring as described in claim 1, characterized in that, The area surveillance cameras are reused as security monitoring devices to achieve integrated security monitoring functions, including: Using computer vision algorithms to analyze video streams in real time, detect people loitering, vehicle scratches, and a series of abnormal behavioral events; When an abnormal event is detected, video clips before and after the event are automatically extracted and stored, and event information is marked. Information on abnormal events is pushed to the garage management terminal for manual review and handling. It supports retrieving historical surveillance footage based on license plate number, time period, or parking space area, providing evidence for tracing incidents.

3. The intelligent management and vehicle location method for underground parking garages based on regional monitoring as described in claim 1, characterized in that, The identification using computer vision algorithms includes: The area surveillance camera is used to collect real-time images of parking spaces within the coverage area; Preprocess the acquired images; Use object detection algorithms to identify vehicles in images and determine the occupancy status of parking spaces; For vehicles already occupying parking spaces, perform license plate recognition and extract the license plate number; Upload parking space status information, including parking space number, occupancy status, and license plate number, to the backend database.

4. The intelligent management and vehicle locating method for underground parking garages based on regional monitoring as described in claim 1, characterized in that, Constructing the digital two-dimensional planar map and establishing the mapping relationship includes: Establish a relative coordinate system for the underground parking garage; The installation location of each camera, the garage entrance / exit, and the passageway intersection are marked as coordinate points in the coordinate system. Establish a mapping table between parking space numbers and camera coverage areas to obtain the coordinates of a vehicle's parking location by querying the camera associated with the license plate number.

5. The intelligent management and vehicle locating method for underground parking garages based on regional monitoring as described in claim 1, characterized in that, The location QR codes are placed at garage entrances and exits, passageway intersections, and stairwell / elevator entrances. The information encoded in the QR codes includes location coordinates and the topological relationship of the passageway.

6. The intelligent management and vehicle location method for underground parking garages based on regional monitoring as described in claim 1, characterized in that, The path planning using the A* heuristic search algorithm includes: The digital two-dimensional planar map is abstracted into a graph structure, where the nodes of the graph structure are channel intersections and key location points, and the edges are channel segments. Define the heuristic function as the estimated distance cost from the current node to the destination of the path planning; Nodes are prioritized using an evaluation function, which is the sum of the actual path cost from the starting point of the path planning to the current node and the estimated distance cost of the heuristic function. Starting from the path planning starting point, iteratively select the highest priority unvisited node for expansion until the path planning endpoint is reached, and backtrack to generate the optimal car-finding navigation path.

7. The intelligent management and vehicle locating method for underground parking garages based on regional monitoring as described in claim 1, characterized in that, The mobile terminal is an application developed based on a cross-platform application framework, allowing users to use the car-finding and navigation function without installing a separate application.

8. The intelligent management and vehicle locating method for underground parking garages based on regional monitoring as described in claim 1, characterized in that, The coordinates for determining the vehicle's parking location include: Based on the target license plate number, the camera number that records the license plate number is retrieved from the background database, and the coordinates of the vehicle's parking location are determined according to the internal plane coordinates corresponding to the camera number in the digital two-dimensional map.

9. The intelligent management and vehicle locating method for underground parking garages based on regional monitoring as described in claim 1, characterized in that, The method also provides a parking guidance function, which includes: When a vehicle enters the garage, the system plans and displays a navigation route to the nearest available parking space based on the real-time parking space occupancy status reported by each camera.

10. The intelligent management and vehicle locating method for underground parking garages based on regional monitoring as described in claim 1, characterized in that, The method further includes a face recognition-assisted guidance step, the step comprising: With the user's permission, the system captures and recognizes the user's facial image through cameras installed at garage entrances or passageway intersections. Once recognition is successful, the system automatically obtains the user's current location and queries the parking location of the vehicle registered under the user's name. Then, it automatically plans and pushes a car-finding navigation route to the mobile terminal.

Images