Intelligent parking guiding method and vehicle management system

Abstract

The invention relates to an intelligent parking guiding method and a vehicle management system.The intelligent parking guiding method comprises the steps that it is detected that a vehicle enters a parking lot, and a camera arranged on the vehicle is controlled to pre-record a target video; a sensor arranged on the vehicle is used for detecting the parking motion of the parking space to confirm whether the vehicle is parked in the parking space or not; under the condition that it is confirmed that the vehicle is parked in the parking space, the target video is sent to a semantic recognition model, and the semantic recognition model outputs a parking space number; and uploading the parking space number and the license plate number to a server. According to the invention, accurate identification of the parking space number by the vehicle is realized, and the parking space number is uploaded to the server to navigate the user so as to meet the vehicle searching demand.

Description

Technical Field

[0001] This invention relates to the field of intelligent parking, specifically to an intelligent parking guidance method and a vehicle management system. Background Technology

[0002] Nowadays, parking lots or shopping malls often have car-finding systems. Users can use these systems to quickly locate the floor and parking space number of their vehicle, and then find the vehicle based on the parking space number, solving the problem of some users not remembering where they parked their vehicles.

[0003] The car-finding system mainly relies on cameras installed in parking spaces to collect license plate numbers of vehicles in those spaces. The system then sends the parking space corresponding to the camera and the license plate number to the car-finding system so that users can locate their vehicles.

[0004] However, many old parking lots currently do not have a car-finding system installed. Adding a car-finding system would require installing a large number of cameras, which would increase the cost of finding cars. Furthermore, current car-finding apps include a map feature that uses the vehicle's GPS location and the GPS location of the smart device to display the relative position between the parking space and the user, generating navigation to guide the user to the parking space. However, GPS accuracy is only at the meter level, making it difficult to determine which floor the vehicle is on. Additionally, in underground parking garages, GPS signals are often weak, frequently causing navigation errors and leading users to the wrong location. Summary of the Invention

[0005] This invention addresses the problem of finding one's car by providing an intelligent parking guidance method and vehicle management system. It uses cameras installed on vehicles to collect parking space information, confirming the parking space number and license plate number, thus reducing the cost of finding one's car. Furthermore, it proposes a solution to the problem of parking space recognition errors that occur when collecting parking space information using vehicle-mounted cameras.

[0006] In a first aspect, this application provides an intelligent parking guidance method, comprising: When a vehicle enters the parking lot, the camera installed on the vehicle is controlled to pre-record target video. Sensors installed on the vehicle are used to detect parking actions to confirm whether the vehicle has parked in the parking space; Once it is confirmed that the vehicle is parked in the parking space, the target video is sent to the semantic recognition model, and the semantic recognition model outputs the parking space number. Upload the parking space number and license plate number to the server.

[0007] In some embodiments, sensors mounted on the vehicle are used to detect parking actions to confirm whether the vehicle has parked in the parking space, including: Acquire vehicle control information, or motion information collected by motion sensors installed on the vehicle; Based on the motion information or control information, confirm that the vehicle is performing one of the following actions: reversing into a parking space, driving forward into a parking space, or driving sideways into a parking space. When performing a parking action, confirm that the vehicle is parked in the parking space.

[0008] In some embodiments, sensors mounted on the vehicle are used to detect parking actions to confirm whether the vehicle has parked in the parking space, including: Acquire ground image information captured by cameras installed on the vehicle; The overlap between vehicles and parking spaces was determined based on multi-frame ground image information; If the overlap is greater than a preset percentage threshold and a parking action is detected, confirm that the vehicle has parked in the parking space.

[0009] In some embodiments, the percentage threshold is greater than or equal to 80%.

[0010] In some embodiments, the multi-frame ground image information includes: historical ground image information and current ground image information; the step of confirming the overlap between vehicles and parking spaces based on the multi-frame ground image information includes: Parking space locations in the current ground image are estimated based on multi-frame historical ground image information; Based on the current ground image information of the parking space location and the current vehicle location, the overlap between the vehicle and the parking space is determined.

[0011] In some embodiments, detecting a vehicle entering a parking lot and controlling a camera installed on the vehicle to pre-record target video includes: When an entry into the parking lot is detected, the camera installed on the vehicle is controlled to record pre-recorded video. Overwrite historical videos with the most recent pre-recorded video from the first preset time period; When a parking action is detected, the historical video is stopped from being overwritten, and the real-time recorded video and the pre-recorded video are merged into the target video.

[0012] In some embodiments, feeding the target video into the semantic recognition model includes: Multiple target video frames are fed into the first recognition model, which is used to identify parking space numbers. After identifying the parking space number in the target video frame at the first moment, the second recognition model confirms that the parking space number is included in multiple different moments after the first moment, and then the parking space number is used as the output result.

[0013] In some embodiments, feeding the target video into the semantic recognition model includes: Detect the parking space number closest to the vehicle in the direction of its travel; The system will count the parking space number that appears most frequently during the process of a vehicle entering a parking space at a speed greater than a preset speed threshold, and use this count as the output result.

[0014] Secondly, this application provides a vehicle management system, including: The server is communicatively connected to the vehicle to receive the parking space number and license plate number output by the vehicle through the above-described intelligent parking guidance method. In addition, the vehicle location is generated on the map based on the parking space number and license plate number.

[0015] In some embodiments, it also includes: The control terminal device displays a map and the location of the terminal device and vehicle on the map to guide the route from the terminal device location to the vehicle location.

[0016] The technical solution of this application involves pre-recording a target video when a vehicle enters a parking lot; upon detecting that the vehicle has parked in a parking space, the target video is fed into a semantic recognition model, which outputs a parking space number; the parking space number and license plate number are then uploaded to a server, allowing users to obtain parking space information from the server and locate their vehicles. Currently, reversing cameras are widely used in almost all vehicles, and with the development of new energy vehicles, the frequency of in-vehicle infotainment systems connecting to the internet is also gradually increasing. This application can reduce the cost of locating vehicles for these types of vehicles. This system can be integrated into navigation software, allowing the navigation software to log in using the same account on both the mobile phone and the in-vehicle infotainment system, thereby improving the efficiency of locating vehicles without needing to distinguish between the in-vehicle infotainment system and the parking management platform. For vehicles without internet connectivity and reversing cameras, traditional vehicle locating methods can still be used. Attached Figure Description

[0017] Figure 1 This is a schematic diagram illustrating the application scenario of the intelligent parking guidance method of this application; Figure 2 This is a flowchart of an embodiment of the intelligent parking guidance method of this application; Figure 3 This is a flowchart of another embodiment of the intelligent parking guidance method of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0020] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein. Example 1

[0021] Reference Figure 1 In this embodiment, the intelligent parking guidance method is applied to the vehicle's infotainment system 10. The infotainment system 10 is connected to the server 20 via a mobile communication network, and the server 20 is connected to the smart terminal device 30 via a mobile communication network. During this process, the infotainment system 10 uploads the parking space number and license plate number to the server 20, and the server 20 sends the parking space number and license plate number to the smart terminal device 30 to guide the user to the parking space.

[0022] Reference Figure 2 The intelligent parking guidance method of this application includes: S100: Detect vehicles entering the parking lot and control the camera installed on the vehicle to pre-record target video; Vehicles can enter the parking lot through voice announcements at the turnstiles or by connecting to management platforms such as Zhijie Parking.

[0023] The vehicle's cameras are located at the front, rear, and sides of the vehicle to collect environmental information. For example, the vehicle also uses the cameras to achieve visual intelligent driving assistance.

[0024] Step S100 can prevent the camera from working continuously, reduce power consumption, and the use of a pre-recording design can reduce storage requirements.

[0025] Pre-recording refers to capturing video in real time and saving only the video content within the most recent preset time, deleting content older than the preset time. For example, if the preset time is 10 seconds, then the pre-recorded video will be saved for 10 seconds, and video content older than 10 seconds will be deleted. In practical applications, the preset time can be 5 seconds, 10 seconds, 15 seconds, 30 seconds, 1 minute, 2 minutes, 5 minutes, etc., without limitation here. The specific setting is based on the actual performance requirements of the semantic recognition model; the higher the performance requirements, the longer the preset time.

[0026] S200: Use sensors installed on the vehicle to detect parking actions to confirm whether the vehicle has parked in the parking space; Among them, parking space entry refers to the actions of a vehicle starting to reverse into a parking space, drive forward into a parking space, or drive sideways into a parking space.

[0027] It should be noted that during the above actions, the vehicle typically decelerates, shifts gears, and reverses. The recognition model only needs to be trained with sensor data and labels (reversing into a parking space, forward parking, and side parking). Later, the sensor data can be fed into the pre-trained recognition model to identify the parking maneuver. In other embodiments, logical judgments can also be used to confirm the parking maneuver. For example, for reversing into a parking space, the vehicle can be confirmed to be reversing into a parking space when the sequential logical actions of parking, reversing, counter-steering, slowly reversing straight, and parking are first identified. Similarly, forward parking and side parking actions also have certain action-specific characteristics, which will not be elaborated here.

[0028] For example, sensors can refer to cameras, attitude sensors, gear sensors, throttle sensors, etc.

[0029] S300. After confirming that the vehicle is parked in the parking space, the target video is sent to the semantic recognition model, and the semantic recognition model outputs the parking space number. In this embodiment, after confirming that the vehicle has been parked and the computing power is available, the target video is sent to the semantic recognition model to identify the parking space number. The semantic recognition model is a neural network model; the training and testing process of the text recognition model is not detailed here.

[0030] After the vehicle has been parked, the computing power is available in step S300, so parking space identification is performed to reduce the computing power consumption per unit time.

[0031] S400. Upload the parking space number and license plate number to server 20.

[0032] The vehicle system 10 communicates with the server 20 via a mobile communication network, and the server 20 connects to the smart terminal device 30 via a mobile communication network. During this process, the vehicle system 10 uploads the parking space number and license plate number to the server 20, and the server 20 sends the parking space number and license plate number to the smart terminal to guide the user to the parking space.

[0033] Server 20 can store the corresponding parking space number and license plate number, and send the parking space number to the user's smart terminal device 30 when the user initiates a car search request based on the license plate number.

[0034] The technical solution of this application involves pre-recording a target video when a vehicle enters a parking lot; when a vehicle is detected to have parked in a parking space, the target video is sent to a semantic recognition model, which outputs a parking space number; the parking space number and license plate number are then uploaded to a server 20, so that users can obtain parking space information from the server 20 and find their vehicles.

[0035] Reference Figure 3 In some embodiments, S200 involves using sensors installed on the vehicle to detect parking maneuvers to confirm whether the vehicle has parked in the parking space, including: S201. Obtain vehicle control information or motion information collected by motion sensors installed on the vehicle; S202. Based on the motion information or control information, confirm that the vehicle is performing one of the following actions: reversing into a parking space, forward parking, or side parking. When performing a parking action, confirm that the vehicle is parked in the parking space.

[0036] It should be noted that using vehicle control and motion information to confirm whether the vehicle is parked in a parking space may have several problems: the parking space may not be numbered, the parking space may be misaligned, and there may be identification errors.

[0037] Continue to refer to Figure 3 To address the aforementioned issues, in some embodiments, step S200 involves using sensors installed on the vehicle to detect parking maneuvers to confirm whether the vehicle has parked in the parking space, including: S203. Obtain ground image information captured by a camera installed on the vehicle; S204. Confirm the overlap between vehicles and parking spaces based on multi-frame ground image information; S205. If the overlap is greater than a preset percentage threshold and a parking action is detected, confirm that the vehicle has parked in the parking space.

[0038] Wherein, the percentage threshold is greater than or equal to 80%.

[0039] Specifically, in some embodiments, the multi-frame ground image information includes: historical ground image information and current ground image information; the step of confirming the overlap between vehicles and parking spaces based on the multi-frame ground image information includes: estimating the parking space position in the current ground image information based on the multi-frame historical ground image information; and confirming the overlap between vehicles and parking spaces based on the parking space position in the current ground image information and the vehicle position at the current moment.

[0040] In this embodiment, the camera acquiring ground image information can be a camera used for intelligent driving assistance. Specifically, this embodiment can establish a ground coordinate system based on the vehicle's positioning information, display the vehicle model on the ground coordinate system, and stitch together the current ground images collected in real time by multiple cameras surrounding the vehicle to obtain a stitched image. Based on the vehicle's posture, the stitched image is mapped to the vehicle coordinate system, and the parking space position is obtained from the front or rear view of historical ground image information at historical moments to obtain a top-view image including the vehicle model and the parking space. The origin of the vehicle coordinate system is the origin of the ground coordinate system. At this time, the overlap can be confirmed in the top-view image.

[0041] In practical applications, vehicle parking methods based on motion sensors and cameras can be combined. For example, the vehicle can only be confirmed as parked when both outputs show that the vehicle is parked in the parking space.

[0042] In some embodiments, detecting a vehicle entering a parking lot and controlling a camera installed on the vehicle to pre-record target video includes: When an entry into the parking lot is detected, the camera installed on the vehicle is controlled to record pre-recorded video. Overwrite historical videos with the most recent pre-recorded video from the first preset time period; When a parking action is detected, the historical video is stopped from being overwritten, and the real-time recorded video and the pre-recorded video are merged into the target video.

[0043] It should be noted that, in order to increase the length of the target video and avoid the pre-recorded video from being too long, the pre-recorded video can be lengthened when parking is detected, for example, from 10 seconds to 1 minute. However, a fixed-length pre-recording cannot dynamically meet the video length requirements because different users park at different times, which may result in the pre-recorded video containing images taken when the vehicle is stationary. This is not conducive to subsequent identification of "parking space number included at multiple different times" and "parking space number with the most counts".

[0044] To improve the completeness of the target video, this example stops pre-recording when parking is detected, and then merges the real-time recorded video and the pre-recorded video into the target video until the parking action is completed. At this point, regardless of the user's parking speed and duration, the entire parking process is recorded, providing the semantic recognition model with as much complete parking information as possible for better identification of parking space numbers.

[0045] In some embodiments, feeding the target video into the semantic recognition model includes: Multiple target video frames are fed into the first recognition model, which is used to identify parking space numbers. After identifying the parking space number in the target video frame at the first moment, the second recognition model confirms that the parking space number is included in multiple different moments after the first moment, and then the parking space number is used as the output result.

[0046] Specifically, the multiple different times can be consecutive or discontinuous. In this embodiment, discontinuous times are preferred to avoid the current parking space number not being captured when the parking space is blocked by a vehicle, resulting in the output of an incorrect parking space number (such as the parking space number next to the vehicle). Using the complete parking video can confirm that the identified parking space number is the current parking space number, because during the parking process, the current parking space number is the closest to the vehicle for a period of time after the parking space number is identified.

[0047] In some embodiments, feeding the target video into the semantic recognition model includes: Detect the parking space number closest to the vehicle in the direction of its travel; The system will count the parking space number that appears most frequently during the process of a vehicle entering a parking space at a speed greater than a preset speed threshold, and use this count as the output result.

[0048] In this embodiment, to avoid collecting too much ground image information with stationary vehicles, the statistical process is designed to be the process where the vehicle speed is greater than or equal to a preset speed threshold, i.e., the process of the vehicle stopping. In other words, this embodiment can confirm that the vehicle is stopping based on a speed greater than the preset speed threshold, and consider the vehicle to be stationary if the speed is less than the preset speed threshold. Then, the ground image information with stationary vehicles is deleted, reducing the computational load of the semantic recognition model. Example 2

[0049] Secondly, this application provides a vehicle management system, comprising: Server 20, communicatively connected to the vehicle, receives the parking space number and license plate number output by the vehicle through the aforementioned intelligent parking guidance method; and generates the vehicle's location on a map based on the parking space number and license plate number. The intelligent parking guidance method includes: When a vehicle enters the parking lot, the camera installed on the vehicle is controlled to pre-record target video. Sensors installed on the vehicle are used to detect parking actions to confirm whether the vehicle has parked in the parking space; Once it is confirmed that the vehicle is parked in the parking space, the target video is sent to the semantic recognition model, and the semantic recognition model outputs the parking space number. The parking space number and license plate number are uploaded to server 20.

[0050] In some embodiments, sensors mounted on the vehicle are used to detect parking actions to confirm whether the vehicle has parked in the parking space, including: Acquire vehicle control information, or motion information collected by motion sensors installed on the vehicle; Based on the motion information or control information, confirm that the vehicle is performing one of the following actions: reversing into a parking space, driving forward into a parking space, or driving sideways into a parking space. When performing a parking action, confirm that the vehicle is parked in the parking space.

[0051] In some embodiments, sensors mounted on the vehicle are used to detect parking actions to confirm whether the vehicle has parked in the parking space, including: Acquire ground image information captured by cameras installed on the vehicle; The overlap between vehicles and parking spaces was determined based on multi-frame ground image information; If the overlap is greater than a preset percentage threshold and a parking action is detected, confirm that the vehicle has parked in the parking space.

[0052] In some embodiments, the percentage threshold is greater than or equal to 80%.

[0053] In some embodiments, the multi-frame ground image information includes: historical ground image information and current ground image information; the step of confirming the overlap between vehicles and parking spaces based on the multi-frame ground image information includes: Parking space locations in the current ground image are estimated based on multi-frame historical ground image information; Based on the current ground image information of the parking space location and the current vehicle location, the overlap between the vehicle and the parking space is determined.

[0054] In some embodiments, detecting a vehicle entering a parking lot and controlling a camera installed on the vehicle to pre-record target video includes: When an entry into the parking lot is detected, the camera installed on the vehicle is controlled to record pre-recorded video. Overwrite historical videos with the most recent pre-recorded video from the first preset time period; When a parking action is detected, the historical video is stopped from being overwritten, and the real-time recorded video and the pre-recorded video are merged into the target video.

[0055] In some embodiments, feeding the target video into the semantic recognition model includes: Multiple target video frames are fed into the first recognition model, which is used to identify parking space numbers. After identifying the parking space number in the target video frame at the first moment, the second recognition model confirms that the parking space number is included in multiple different moments after the first moment, and then the parking space number is used as the output result.

[0056] In some embodiments, feeding the target video into the semantic recognition model includes: Detect the parking space number closest to the vehicle in the direction of its travel; The system will count the parking space number that appears most frequently during the process of a vehicle entering a parking space at a speed greater than a preset speed threshold, and use this count as the output result.

[0057] In some embodiments, it also includes: The control terminal device displays a map and the location of the terminal device and vehicle on the map to guide the route from the terminal device location to the vehicle location.

[0058] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0059] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0060] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0061] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0062] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0063] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0064] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An intelligent parking guidance method, characterized in that, include: When a vehicle enters the parking lot, the camera installed on the vehicle is controlled to pre-record target video. Sensors installed on the vehicle are used to detect parking actions to confirm whether the vehicle has parked in the parking space; Once it is confirmed that the vehicle is parked in the parking space, the target video is sent to the semantic recognition model, and the semantic recognition model outputs the parking space number. Upload the parking space number and license plate number to the server.

2. The intelligent parking guidance method as described in claim 1, characterized in that, Using sensors installed on the vehicle to detect parking actions to confirm whether the vehicle has parked in the parking space, including: Acquire vehicle control information, or motion information collected by motion sensors installed on the vehicle; Based on the motion information or control information, confirm that the vehicle is performing one of the following actions: reversing into a parking space, driving forward into a parking space, or driving sideways into a parking space. When performing a parking action, confirm that the vehicle is parked in the parking space.

3. The intelligent parking guidance method as described in claim 1 or 2, characterized in that, Using sensors installed on the vehicle to detect parking actions to confirm whether the vehicle has parked in the parking space, including: Acquire ground image information captured by cameras installed on the vehicle; The overlap between vehicles and parking spaces was determined based on multi-frame ground image information; If the overlap is greater than a preset percentage threshold and a parking action is detected, confirm that the vehicle has parked in the parking space.

4. The intelligent parking guidance method as described in claim 1, characterized in that, The percentage threshold is greater than or equal to 80%.

5. The intelligent parking guidance method as described in claim 1, characterized in that, The multi-frame ground image information includes: historical ground image information and current ground image information; the step of confirming the overlap between vehicles and parking spaces based on the multi-frame ground image information includes: Parking space locations in the current ground image are estimated based on multi-frame historical ground image information; Based on the current ground image information of the parking space location and the current vehicle location, the overlap between the vehicle and the parking space is determined.

6. The intelligent parking guidance method as described in claim 3, characterized in that, Upon detecting a vehicle entering the parking lot, the camera installed on the vehicle is controlled to pre-record target video, including: When an entry into the parking lot is detected, the camera installed on the vehicle is controlled to record pre-recorded video. Overwrite historical videos with the most recent pre-recorded video from the first preset time period; When a parking action is detected, the historical video is stopped from being overwritten, and the real-time recorded video and the pre-recorded video are merged into the target video.

7. The intelligent parking guidance method as described in claim 6, characterized in that, The step of feeding the target video into the semantic recognition model includes: Multiple target video frames are fed into the first recognition model, which is used to identify parking space numbers. After identifying the parking space number in the target video frame at the first moment, the second recognition model confirms that the parking space number is included in multiple different moments after the first moment, and then the parking space number is used as the output result.

8. The intelligent parking guidance method as described in claim 6, characterized in that, The step of feeding the target video into the semantic recognition model includes: Detect the parking space number closest to the vehicle in the direction of its travel; The system will count the parking space number that appears most frequently during the process of a vehicle entering a parking space at a speed greater than a preset speed threshold, and use this count as the output result.

9. A vehicle management system, characterized in that, include: A server, which is communicatively connected to the vehicle, receives the parking space number and license plate number output by the vehicle through the intelligent parking guidance method as described in any one of claims 1-8. In addition, the vehicle location is generated on the map based on the parking space number and license plate number.

10. The vehicle management system as described in claim 9, characterized in that, Also includes: The control terminal device displays a map and the location of the terminal device and vehicle on the map to guide the route from the terminal device location to the vehicle location.

Images