Parking space detection method based on panoramic image, electronic device and storage medium

Through the panoramic image detection method, the parking space map signal is generated using the vehicle license plate number and entry time, and the parking space ownership is marked and determined, which solves the problem of difficult to determine the ownership rights of parking spaces in the parking lot, reduces disputes, and improves the user experience.

CN112183409BActive Publication Date: 2024-11-19SHENZHEN DOWCAUSE TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011065898.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-09-30
Publication Date
2024-11-19
Estimated Expiration
2040-09-30

AI Technical Summary

Technical Problem

In the parking lot, it is difficult to determine the ownership of the parking space, which leads to prone to disputes when parking, affecting the user experience.

Method used

Using a panoramic image-based parking space detection method, by obtaining the vehicle's license plate number information and the time to enter the parking lot, generating a parking space map signal, marking the target parking space, and determining the ownership rights of the parking space according to preset rules, and clarifying the parking space by displaying the vehicle identification information. Affiliation.

Benefits of technology

It effectively reduces disputes caused by parking space ownership issues, ensures that vehicles can clearly know the ownership rights of the target parking space, and improves the user experience of the parking lot.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112183409B_ABST
    Figure CN112183409B_ABST
Patent Text Reader

Abstract

The present invention relates to a method for detecting parking spaces based on panoramic images, an electronic device and a storage medium, which comprises obtaining vehicle identification information of a user vehicle end and the time of entering a parking lot; receiving a request for obtaining a parking lot map from the user vehicle end to generate a parking space map signal, and sending the parking space map signal to the user vehicle end; receiving an area position signal from the user vehicle end, and sending the position information of the pre-parking area to the user vehicle end; receiving a marking signal from the user vehicle end to mark a target parking space; sorting the marking signal according to time, determining the ownership of the target parking space according to a preset rule, and marking the target parking space by displaying the vehicle identification information. The present invention allows the ownership of the target parking space to be clarified by marking the target parking space when parking, thereby effectively reducing disputes due to the ownership of the target parking space.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent parking, and in particular to a parking space detection method based on panoramic images, an electronic device and a storage medium. Background Art

[0002] With the improvement of people's living standards and the acceleration of urbanization, cars have become a common means of transportation for people. They are fast and can travel long distances, and are favored by consumers. However, the most troublesome problem for people when driving is the difficulty of parking.

[0003] When a user parks in a parking lot, the conditions of each parking space in the parking lot will change dynamically. When the vehicle drives to the parking lot, there may be an empty parking space. However, when the vehicle drives to the vicinity of the parking space, if other vehicles also arrive near the parking space from different routes, it will be difficult to determine who should park and use the parking space, which may easily lead to disputes between the two parties and affect the user experience. Summary of the invention

[0004] The first object of the present invention is to provide a method for detecting parking spaces based on panoramic images, which has the characteristic of clarifying the ownership of target parking spaces and effectively reduces disputes over ownership of parking spaces.

[0005] The above-mentioned object of the present invention is achieved through the following technical solutions:

[0006] A method for detecting parking spaces based on panoramic images, applied to a server, comprises:

[0007] Obtain the vehicle identification information of the user's vehicle and the time of entering the parking lot, wherein the vehicle identification information carries the vehicle license plate number information;

[0008] Receiving a parking lot map acquisition request from a user vehicle to generate a parking space map signal, and sending the parking space map signal to the user vehicle, wherein the parking space map signal carries parking lot map information;

[0009] Receive the area position signal from the user's vehicle end, and send the position information of the pre-parking area to the user's vehicle end;

[0010] Receiving a marking signal from a user's vehicle terminal marking the same target parking space, wherein the marking signal carries vehicle identification information;

[0011] The marking signals are sorted according to time, the ownership of the target parking space is determined according to preset rules, and the target parking space is marked by displaying the vehicle identification information.

[0012] By adopting the above technical solution, when a vehicle enters a parking lot, the server obtains the vehicle's license plate number information and the time of entering the parking lot for storage and recording. After the vehicle enters the parking lot, it sends a request for obtaining a parking lot map to the server, processes the request for obtaining a parking lot map to generate a parking space map signal carrying parking lot map information, and sends it to the user's vehicle end. After receiving the parking space map signal, the user's vehicle end selects a pre-parking area, sends an area location signal to the server so that the server returns the location information of the pre-parking area to the user's vehicle end, and the user's vehicle end drives to the pre-parking area according to the location information of the pre-parking area. When a target parking space, that is, an empty parking space, is found during driving, the user's vehicle sends a marking signal to the server to mark the target parking space. After receiving the marking signal, the server sorts the marking signal according to time, and then determines the ownership of the target parking space according to preset rules, and marks the target parking space by displaying the vehicle identification information. Thus, the target parking space is marked by displaying the vehicle identification information, so that when multiple users arrive near the target parking space in the same time period, they can clearly know the ownership of the current target parking space, thereby clarifying the ownership of the target parking space, so as to reduce disputes caused by the ownership of the same target parking space.

[0013] In a preferred example, the present invention can be further configured as follows: the preset rules include:

[0014] The ownership of the target parking space is determined based on the time of the earliest marking signal received.

[0015] By adopting the above technical solution, the marking signals are sorted according to time, and the ownership of the target parking space is determined in the order of time when the signals are received by the server.

[0016] In a preferred example, the present invention can be further configured as follows: the preset rules also include:

[0017] The vehicles are sorted according to the time when they enter the parking lot. When the time of receiving the marking signal from the vehicle is the same, the ownership of the target parking space is determined by the earliest time when the vehicle enters the parking lot.

[0018] By adopting the above technical solution, when the ownership of the target parking space cannot be determined by the marking signal, a secondary comparison is performed by comparing the time when the vehicle enters the parking lot, and the ownership of the target parking space is determined by the vehicle that entered the parking lot earlier.

[0019] The second objective of the present invention is to provide a method for detecting parking spaces based on panoramic images, which has the characteristic of being able to mark target parking spaces to determine the ownership of the target parking spaces.

[0020] The second object of the present invention is achieved through the following technical solutions:

[0021] A method for detecting parking spaces based on panoramic images, applied to a user's vehicle, comprises:

[0022] Sending a parking lot map acquisition request to the server, and receiving a parking space map signal returned from the server, wherein the parking space map signal carries parking lot map information;

[0023] Selecting a pre-parking area, and sending an area location signal to the parking lot server to obtain location information of the pre-parking area;

[0024] planning a driving route according to the location information of the pre-parking area;

[0025] Acquire vacant parking spaces in the parking lot during driving according to the driving route;

[0026] A marking signal is sent to the parking lot server so that the parking lot server marks the target parking space by displaying the vehicle identification information.

[0027] By adopting the above technical solution, when a vehicle enters a parking lot, it sends a request for obtaining a parking lot map to the server, so that the server returns a parking space map signal carrying the parking lot map information to the vehicle. When the vehicle receives the parking space map signal, the user selects the pre-parking area, and the user's vehicle plans a driving route according to the pre-parking area, and then drives to the pre-parking area according to the driving route. When the vehicle recognizes that there is an empty parking space in the process of driving to the pre-parking area, it sends a marking signal carrying the vehicle identification information to the parking lot server, so that the server can process the vehicle identification signal, thereby marking the target parking space by displaying the vehicle identification information.

[0028] In a preferred example, the present invention can be further configured as follows: before obtaining the vacant parking spaces in the parking lot during driving according to the driving route, the image of the surrounding environment of the vehicle is captured by a camera to obtain the suspected vacant parking spaces in the parking lot;

[0029] The obtaining of the suspected vacant parking space in the parking lot includes identifying the parking space line of the pre-parking area at a first position and identifying the parking distance between two adjacent vehicles. When the distance between the two adjacent vehicle image feature objects is greater than a preset value, the parking space is a suspected vacant parking space.

[0030] By adopting the above technical solution, images of the vehicle's surroundings are captured by a camera while driving to obtain suspected vacant parking spaces in the parking lot, so that users can know in advance that there may be vacant parking spaces, thereby facilitating users to prepare in advance to mark the target parking spaces.

[0031] In a preferred example, the present invention may be further configured as follows: the obtaining of suspected vacant parking spaces in the parking lot further includes:

[0032] Obtain object movement information in the monitoring image of the pre-parking area. When it is detected that an object with vehicle image features in the monitoring image of the pre-parking area moves from inside the parking space line to outside the parking space line, and moves until the ground projection of the vehicle's mirror features contacts the vehicle entry and exit line of the parking space line, obtain a first image of the object, obtain a second image of the vehicle image feature object at a second position, and compare the first image and the second image to determine whether the vehicle's mirror features move outside the parking space line. When the vehicle's mirror features move outside the parking space line, the parking space where the object is located is marked as a suspected vacant parking space.

[0033] By adopting the above technical solution, when driving along the preset route, there may be other users leaving the parking lot. By judging that the object with vehicle image features moves from inside the parking space line to outside the parking space line, it can be judged whether the parking space ahead is a suspected vacant parking space.

[0034] In a preferred example, the present invention may be further configured as follows: after obtaining the suspected vacant parking space in the parking lot, determining whether the suspected vacant parking space is an vacant parking space according to a preset condition;

[0035] The preset conditions include identifying parking lines at a second position and identifying vehicle rearview mirror features within the parking lines, wherein the angle range for acquiring the target parking space at the second position is greater than the angle range for acquiring the target parking space at the first position, and when the vehicle rearview mirror features within the parking lines are detected, the current suspected vacant parking space is a non-vacant parking space; and when the number of label points detected within the parking lines reaches a preset number, the current suspected vacant parking space is marked as an vacant parking space.

[0036] By adopting the above technical solution, the status of the parking space can be judged by detecting the vehicle rearview mirror features and label points within the parking space line.

[0037] In a preferred example, the present invention can be further configured as follows: after the server marks the target parking space by displaying the vehicle identification information, a parking request instruction is sent to the server to obtain authorized parking, and the authorized parking instruction is received from the server.

[0038] By adopting the above technical solution, when the user vehicle successfully marks the target parking space, the user vehicle sends a parking request instruction to the server, so that the server returns an authorization parking instruction to the user vehicle to authorize the user vehicle to enter the target parking space for parking.

[0039] The third objective of the present invention is to provide an electronic device having the function of storing and executing the parking space detection method to ensure the normal operation of the parking space detection method.

[0040] The third object of the present invention is achieved through the following technical solutions:

[0041] An electronic device includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the above-mentioned method for detecting a parking space based on panoramic images.

[0042] By adopting the above technical solution, the memory is used to store a computer program using the method for detecting a parking space, and the computer program stored in the memory can control the operation of the user's vehicle terminal and the server of the parking lot through the processor.

[0043] The fourth object of the present invention is to provide a computer storage medium that can store corresponding programs and has the characteristic of facilitating the operation of the parking space detection method on other vehicles and parking lots.

[0044] The fourth object of the present invention is achieved by the following technical solutions:

[0045] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any of the above-mentioned methods for detecting parking spaces based on panoramic images.

[0046] 1. In summary, the present invention includes at least one of the following beneficial technical effects:

[0047] By displaying the vehicle identification information to mark the target parking space, when multiple users arrive near the target parking space at the same time, they can clearly know the ownership of the current target parking space, thereby clarifying the ownership of the target parking space, thereby reducing disputes caused by the ownership of the same target parking space;

[0048] 2. While driving according to the driving route, the vehicle uses a camera to capture images of the environment around the vehicle to obtain suspected vacant parking spaces in the parking lot, so that users can understand possible vacant parking spaces in advance, thereby facilitating users to prepare in advance to mark the target parking spaces. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 1 is a flow chart of a method for detecting a parking space according to a first embodiment of the present invention;

[0050] Figure 2 is a block diagram of the connection principle between the user vehicle terminal and the server in the second embodiment of the present invention;

[0051] Figure 3 is a principle block diagram of the user vehicle end in the second embodiment of the present invention;

[0052] Figure 4 is a schematic diagram of a parking space detection method according to a third embodiment of the present invention;

[0053] Figure 5 is a block diagram of the connection principle between the user vehicle terminal and the server in the fourth embodiment of the present invention;

[0054] Figure 6 It is a principle block diagram of the server in the fourth embodiment of the present invention.

[0055] In the figure, 1, first identification module; 2, first transceiver module; 3, marking module; 4, second transceiver module; 5, processing module; 6, second identification module. DETAILED DESCRIPTION

[0056] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0057] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Embodiment 1:

[0059] Embodiment 1 of the present invention provides a method for detecting parking spaces based on panoramic images, which is applied to a server. The main process of the method is described as follows:

[0060] S110, obtaining vehicle identification information of the user's vehicle and the time of entering the parking lot, wherein the vehicle identification information carries the vehicle's license plate number information.

[0061] Specifically, when a vehicle enters a parking lot, a camera at the entrance of the parking lot captures the vehicle image to obtain the vehicle identification information of the user's vehicle and store it on the server. The vehicle identification information is the vehicle's license plate information. After the vehicle's license plate information is read, the server records the time when the vehicle enters the parking lot. The time when the vehicle enters the parking lot is the time when the server authorizes the vehicle to enter the parking lot after recognizing the license plate information of the vehicle image.

[0062] At the same time, when the vehicle is authorized to enter the parking lot, the user vehicle establishes a communication connection with the parking lot server. The communication connection can be a 2G / 3G / 4G / 5G connection, a Bluetooth connection, a GPRS connection, or a WiFi connection. After the user vehicle establishes a communication connection with the server, the server executes the following step S120.

[0063] S120: Receive a parking lot map acquisition request from the user vehicle to generate a parking space map signal, and send the parking space map signal to the user vehicle, where the parking space map signal carries parking lot map information.

[0064] Specifically, the server stores the map information of the parking lot. The map information of the parking lot is designed according to the actual layout of the parking lot. When the parking lot is a ground / underground parking lot with multiple floors, and the parking lot layout of each floor is different, the map information of the parking lot corresponding to each floor is stored in the server. When the car enters the parking lot on one of the floors, the server obtains the floor where the car enters the parking lot. The acquisition method can be to add a readable floor mark at the entrance of each floor of the parking lot, and the floor mark can be an RFID tag. At the same time, a camera for taking vehicle images and an RFID tag reader for reading RFID tags are provided at the entrance of each floor. When the car enters the parking lot, the camera takes the vehicle image, and the RFID reader reads the RFID tag to obtain the current floor information. After the server reads the floor information, it generates a signal carrying a parking space. The parking space map signal carries the parking lot map information of the current floor, and returns the parking space map signal to the user vehicle end so that the user vehicle end can display the parking lot map information.

[0065] After the server sends the parking space map signal to the user's vehicle, the following step S130 is performed.

[0066] S130: receiving a marking signal from a user vehicle terminal marking a same target parking space, wherein the marking signal carries vehicle identification information.

[0067] Specifically, the vehicle identification information includes the vehicle license plate number information; the target parking space is the parking space where the vehicle is expected to park after entering the parking lot. Before the vehicle parks in the target parking space, the user's vehicle terminal first sends a marking signal to the server to mark the target parking space. By setting a display connected to the server near the target parking space, the server processes the vehicle identification signal after receiving the marking signal, and displays the vehicle identification information of the user's vehicle terminal through the display near the target parking space, so that other users know that the current parking space has been selected.

[0068] After the server receives the marking signal, the following step S140 is executed to process the vehicle identification signal.

[0069] S140, sorting the marking signals according to time, determining the ownership of the target parking space according to a preset rule, and marking the target parking space by displaying vehicle identification information.

[0070] Among them, sorting the marking signals according to time can be understood as, when the server receives at least one marking signal marking the same target parking space from the user vehicle terminal within a preset time range (for example, within 2 seconds), the server sorts the marking signals in sequence according to the time sequence of receiving the marking signals, that is, when there are multiple user vehicle terminals in the parking lot driving from different routes to the vicinity of the same target parking space and sending marking signals to the target parking space, the server sorts the received marking signals and then determines the ownership of the target parking space according to preset rules. It should be noted that the ownership referred to in this embodiment is which user vehicle terminal should park in the current target parking space according to the preset rules.

[0071] After the user vehicle obtains the right to use the target parking space, the server will display the vehicle identification information of the user vehicle that has obtained the right to use through a display near the target parking space, so that other users know that the current parking space has been selected.

[0072] The preset rules in the above step S140 include: after the server sorts the marking signals in order according to the time sequence in which they are received, the server determines the ownership of the target parking space according to the earliest marking signal received.

[0073] The following example uses two user vehicles marking the same target in the same time period. When the server receives two marking signals for marking the same target parking space, the server sorts the two received marking signals in order of the receiving time, so that the server selects the marking signal with an earlier receiving time and processes the marking signal, thereby displaying the vehicle identification information on the display near the target parking space. When the time of the two marking signals received by the server is the same, the server performs a second comparison of the two received marking signals.

[0074] The server performs a secondary comparison of the two received tag signals according to the following rules:

[0075] First, the server reads the vehicle identification information and the time of entering the parking lot of the user vehicle terminals corresponding to the two marking signals, and then sorts the time sequence of the two user vehicle terminals entering the parking lot in sequence. The ownership of the target parking space is determined by the time sequence of the user vehicle terminals entering the parking lot. The user vehicle terminal that enters the parking lot earlier obtains the ownership of the target parking space.

[0076] In another embodiment, when the time of entry into the parking lot of two user vehicles is the same, the server allocates the ownership of the target parking space according to the allocation rules. Specifically, the allocation rules include obtaining the license plate numbers of the two target parking spaces and comparing the size of the last digits of the two license plate numbers, wherein when the license plate number has letters, each letter corresponds to a specific number, for example, the letters AZ correspond to the numbers 1-26 one by one. By comparing the size of the last digits of the two license plate numbers, the vehicle with the larger last digit of the license plate number obtains the ownership of the target parking space. When the last digits of the license plate numbers of the two user vehicles are the same, the second to last digits are compared, thereby comparing the license plate numbers of the two vehicles in turn to determine the ownership of the target parking space.

[0077] When the server determines the ownership of the target parking space, the license plate number of the vehicle to which it belongs is displayed on a display near the target parking space, and an ownership signal is generated and returned to the user's vehicle end. At the same time, the server initiates vehicle interception of the target parking space, thereby preventing vehicles that do not have ownership rights from using the target vehicle.

[0078] Embodiment 2:

[0079] Embodiment 2 of the present invention provides a parking space detection system based on panoramic images, comprising:

[0080] The first identification module 1 is used to obtain the vehicle identification information of the user's vehicle and the time of entering the parking lot, and store it in the server;

[0081] The first transceiver module 2 is used to receive a parking map acquisition request, an area location signal and a marking signal from a user vehicle terminal, and send the parking space map signal and the area location signal to the user vehicle terminal;

[0082] The marking module 3 is used to sort the marking signals according to time after receiving the marking signals, determine the ownership of the target parking space according to preset rules, and mark the target parking space by displaying vehicle identification information.

[0083] Embodiment three:

[0084] Embodiment 3 of the present invention provides a method for detecting parking spaces based on panoramic images, which is applied to a user's vehicle (hereinafter referred to as a vehicle). The main process of the method is described as follows:

[0085] S210: Send a parking lot map acquisition request to the server, and receive a parking space map signal returned from the server, wherein the parking space map signal carries parking lot map information.

[0086] Specifically, when a vehicle enters a parking lot, it establishes a wireless communication connection with the server of the parking lot. The wireless communication connection may be a 2G / 3G / 4G / 5G connection, a Bluetooth connection, a GPRS connection, or a WiFi connection. After the vehicle establishes a communication connection with the server, the user enters the license plate number information of the target vehicle. After the user enters the license plate number information of the vehicle, a request for obtaining a parking lot map is received from the user, so that the server returns a parking space map signal carrying the parking lot map information to the vehicle.

[0087] When the vehicle receives the parking space map signal, the parking lot map is displayed through the electronic display device on the vehicle, and the user can drive to the area where the vehicle is required to be parked according to the parking lot map.

[0088] After the display device of the vehicle displays the parking lot map, step S220 is executed.

[0089] S220: Select a pre-parking area, and send an area location signal to the server to obtain location information of the pre-parking area.

[0090] In the above step S220, the parking lot manager can divide the parking spaces in the parking lot into regions and store the divided region information in the parking lot server. The divided regions can be divided according to the layout of the parking lot and the location of the parking spaces, and each region contains multiple parking spaces.

[0091] Specifically, the selected pre-parking area is selected by the user. When the vehicle receives the pre-parking area selection instruction from the user, the vehicle processes the pre-parking area instruction and generates an area position signal, and the area position signal carries the pre-parking area information. The pre-parking area information includes the location information of the vehicle and the selected pre-parking area. The vehicle sends the area position signal to the server, and the server processes the area position signal and returns the area position information to the vehicle so that it can be displayed through the display device of the vehicle. In this embodiment, the area position information includes the location information and map information of the pre-parking area.

[0092] After the pre-parking area selection is completed, the following step S230 is performed.

[0093] S230: Plan a driving route according to the location information of the pre-parking area.

[0094] Specifically, the proposed driving route includes planning at least one route to the location of the pre-parking area according to the map information of the pre-parking area and the current location of the vehicle, and combining the map information of the parking lot, and selecting the optimal driving route. It can be understood that when there is only one driving route, the driving route is the optimal route; when there are more than two driving routes, the number of free parking spaces on each driving route is obtained, and the number of free parking spaces on each driving route is compared. The driving route with a large number of free parking spaces is the optimal route, so as to increase the possibility of having free parking spaces on the way to the pre-parking area. In addition, when there are two optimal driving routes, and the number of free parking spaces on the two optimal driving routes is the same, the distances of the two driving routes are compared, and the route with the shortest distance to the pre-parking area is selected as the optimal route, so that the user has a greater possibility of obtaining a parking space on the way to the pre-parking area.

[0095] S240: Acquire an available parking space in a parking lot during driving according to the driving route.

[0096] The method for obtaining the vacant parking space is to use a camera to capture a panoramic image of the surrounding environment of the vehicle, and to obtain the vacant parking space by recognizing the panoramic image. In this embodiment, there are four cameras, which can be installed at the four corners of the front and rear ends of the vehicle body, or at the four corners of the roof, so that the camera can obtain a wider angle range of the panoramic image.

[0097] Specifically, before obtaining an idle parking space in a parking lot while driving along the driving route, an image of the surrounding environment of the vehicle is captured by a camera to obtain suspected idle vehicles in the parking lot.

[0098] The method of obtaining a suspected vacant parking space in a parking lot includes identifying the parking space line of the pre-parking area at a first position and identifying the parking distance between two adjacent objects of vehicle image features. Specifically, when the distance between two adjacent objects of vehicle image features is greater than a preset value, there is a suspected vacant parking space between the two vehicle image feature objects. That is, after the camera obtains the image, it determines the parking mode of the parking space. There are three main parking modes of the parking space, namely, transverse parking, longitudinal parking and inclined parking. In this embodiment, transverse parking means that the parking space is vertically distributed with the vehicle aisle, longitudinal parking means that the parking space is parallelly distributed with the vehicle aisle, and inclined parking means that the angle formed by the parking space and the vehicle aisle is an obtuse angle or an acute angle. After the parking mode of the parking space is identified, the image obtained by the camera at the first position is scaled according to the proportion, so as to obtain the distance between the two vehicle image feature objects. In this embodiment, the preset values ​​of the three parking modes are 2.3 meters, 3.8 meters and 2 meters, respectively, thereby improving the accuracy of recognition.

[0099] In addition, the suspected vacant parking spaces in the parking lot also include:

[0100] The object movement information in the monitoring image of the pre-parking area is obtained. When the object with the vehicle image feature in the monitoring image of the pre-parking area is detected at the first position to move from the inside of the parking space line to the outside of the parking space line, and moves to the ground projection of the vehicle mirror feature (the rearview mirror feature of the vehicle) and contacts the vehicle entry and exit edge line of the parking space line, the first image of the object is obtained, and the second image of the vehicle image feature object is obtained at the second position. The angle of the target parking space that the vehicle can obtain at the second position is greater than the angle of the target parking space obtained at the first position.

[0101] After the vehicle acquires the first image and the second image, the first image and the second image are scaled to facilitate comparison of the first image and the second image, thereby determining whether the vehicle's mirror feature moves outside the parking space line. When the vehicle's mirror feature moves outside the parking space line, the parking space where the object is located is marked as a suspected vacant parking space.

[0102] After obtaining the suspected vacant parking spaces in the parking lot, it is determined whether the suspected vacant parking spaces are vacant parking spaces according to preset conditions.

[0103] Specifically, the preset conditions include identifying the parking line at the second position and identifying the mirror features within the parking line. When the mirror features within the parking line are detected, the current suspected vacant parking space is a non-vacant parking space; and when the mirror features are not detected, the label points within the parking line are detected. That is, multiple label points are set within the parking line, and the label points can be distributed at the four corners and the middle of the parking space, or can be set according to actual needs. When the number of label points detected within the parking line reaches a preset number, the current suspected vacant parking space is marked as an vacant parking space.

[0104] After determining that the target parking space is an empty parking space, the following step S250 is performed.

[0105] S250: Send a marking signal to the parking lot server so that the parking lot server can mark the target parking space by displaying the vehicle identification information.

[0106] Specifically, the marking signal carries vehicle identification information, including the vehicle license plate number information. The marking method is that the vehicle sends a marking signal to the parking lot server, and the server processes the vehicle identification signal after receiving the marking signal to obtain the ownership of the current target parking space. At the same time, the vehicle identification information of the user's vehicle is displayed on a display near the target parking space, so that other users know that the current parking space has been selected.

[0107] After the target parking space is marked, the vehicle performs a parking operation. When parking, the vehicle sends a request parking instruction to the server to obtain authorization to park, and receives an authorization parking instruction from the server to authorize the vehicle to enter the target parking space.

[0108] Embodiment 4:

[0109] Embodiment 4 of the present invention provides a parking space detection system based on panoramic images, including:

[0110] The second transceiver module 4 sends a parking map acquisition request and an area location signal to the server, and receives a parking space map signal and location information of a pre-parking area returned from the server;

[0111] Processing module 5, planning a driving route according to the location information of the pre-parking area;

[0112] The second recognition module 6 is configured to obtain vacant parking spaces in the parking lot during driving according to the driving route.

[0113] Embodiment five:

[0114] Embodiment 5 of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute any of the above methods. Specifically, the electronic device includes a mobile phone, a tablet, a reader, and the like.

[0115] Embodiment six:

[0116] Embodiment 6 of the present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program that can be loaded by a processor and execute any of the above methods. A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0117] This specific embodiment is merely an explanation of the present invention and is not a limitation of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by the patent law.

Claims

1. A parking space detection method based on panoramic images, applied to the server, It is characterized in that The method comprises: Obtain the vehicle identification information of the user's vehicle and the time of entering the parking lot, wherein the vehicle identification information carries the vehicle license plate number information; Receiving a parking lot map acquisition request from a user vehicle to generate a parking space map signal, and sending the parking space map signal to the user vehicle, wherein the parking space map signal carries parking lot map information; Receive the area position signal from the user's vehicle end, and send the position information of the pre-parking area to the user's vehicle end; The user vehicle sends a request to the server for obtaining a parking lot map, and receives a parking space map signal returned from the server, wherein the parking space map signal carries parking lot map information; Selecting a pre-parking area, and sending an area location signal to the server to obtain location information of the pre-parking area; planning a driving route according to the location information of the pre-parking area; The camera captures images of the environment around the vehicle to obtain suspected vacant parking spaces in the parking lot; The obtaining of the suspected vacant parking space in the parking lot includes identifying the parking space line of the pre-parking area at a first position and identifying the parking distance between two adjacent objects with vehicle image features, and when the distance between the two adjacent objects with vehicle image features is greater than a preset value, there is a suspected vacant parking space between the two objects with vehicle image features; The method of obtaining suspected vacant parking spaces in the parking lot further includes: obtaining object movement information in the surveillance image of the pre-parking area, and when it is detected at a first position that an object with a vehicle image feature in the surveillance image of the pre-parking area moves from inside the parking space line to outside the parking space line, and moves until the ground projection of the vehicle's mirror feature contacts the vehicle entry and exit line of the parking space line, obtaining a first image of the object, and obtaining a second image of the object with the vehicle image feature at a second position, wherein an angle of the target parking space that can be obtained by the vehicle at the second position is greater than an angle of the target parking space obtained at the first position, and comparing the first image and the second image to determine whether the vehicle's mirror feature moves outside the parking space line, and when the vehicle's mirror feature moves outside the parking space line, the parking space where the object is located is marked as a suspected vacant parking space; obtaining vacant parking spaces in the parking lot while driving according to the driving route; After obtaining the suspected vacant parking space in the parking lot, judging whether the suspected vacant parking space is an vacant parking space according to preset conditions; the preset conditions include identifying the parking space line at the second position and identifying the vehicle mirror feature within the parking space line, when the vehicle mirror feature within the parking space line at the second position is detected, the current suspected vacant parking space is a non-vacant parking space; when it is detected that the number of label points within the parking space line reaches a preset number, the current suspected vacant parking space is marked as an vacant parking space, wherein the label points are distributed at the four corners and the middle of the parking space; Sending a marking signal to the parking lot server so that the parking lot server can mark the target parking space by displaying the vehicle identification information; Receiving a marking signal from a user's vehicle terminal marking the same target parking space, wherein the marking signal carries vehicle identification information; The marking signals are sorted according to time, the ownership of the target parking space is determined according to preset rules, and the target parking space is marked by displaying the vehicle identification information.

2. The method according to claim 1, It is characterized in that The preset rules include: The ownership of the target parking space is determined based on the time of the earliest marking signal received.

3. The method according to claim 2, It is characterized in that The preset rules also include: The vehicles are sorted according to the time when they enter the parking lot. When the time of receiving the marking signal from the vehicle is the same, the ownership of the target parking space is determined by the earliest time when the vehicle enters the parking lot.

4. The method according to claim 1, It is characterized in that After the server marks the target parking space by displaying the vehicle identification information, a parking request instruction is sent to the server to obtain authorized parking, and the authorized parking instruction is received from the server.

5. An electronic device, It is characterized in that The method comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and executes the method according to any one of claims 1 to 4.

6. A computer-readable storage medium, It is characterized in that A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 4.