Parking lot license plate acquisition method, inspection vehicle and storage medium

Abstract

The embodiments of the present application relate to the field of patrol vehicles, and disclose a method for obtaining parking lot license plates, a patrol vehicle, and a storage medium. The method includes: capturing images of parking spaces where vehicles are parked in a parking lot to obtain parking space images, and the parking space images include license plate number images; calculating the first coordinate information of the license plate number image in the parking space image; obtaining the second coordinate information of the patrol vehicle in the geographic coordinate system and the third coordinate information of the current parking space corresponding to the parking space image in the geographic coordinate system; using the second coordinate information, converting the first coordinate information to the geographic coordinate system to obtain the fourth coordinate information; associating the third coordinate information, the fourth coordinate information, and the license plate number corresponding to the license plate number image to obtain the license plate number with the third coordinate information. The present application does not require the installation of a separate geomagnetic sensor on each parking space in the parking lot, and the modified patrol vehicle can be put into use, and the patrol efficiency is high.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of patrol vehicle technology, and in particular to a method for obtaining parking lot license plates, a patrol vehicle, and a storage medium. Background Art

[0002] In profitable roadside parking scenarios, there are cases where parkers fail to register and pay fees as required, causing economic losses to the operating companies.

[0003] During the implementation of the present invention, the inventors discovered that manual registration would require a large amount of manpower to count and register hundreds of parking spaces in half an hour, resulting in low efficiency. Automated parking space detection would require installing geomagnetic sensors in the parking spaces, which would damage the road surface, require high investment, and require a long construction period. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a method for obtaining parking license plates, a patrol vehicle and a storage medium. There is no need to install a geomagnetic sensor on each parking space in the parking lot. The modified patrol vehicle can be put into use, and the patrol efficiency is high.

[0005] To solve the above technical problems, the embodiments of the present application adopt the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for obtaining parking license plates, which is applied to a patrol vehicle. The method includes:

[0007] Capturing images of parking spaces where vehicles are parked in a parking lot to obtain parking space images, wherein the parking space images include license plate number images;

[0008] Calculating first coordinate information of the license plate image in the parking space image;

[0009] Acquire second coordinate information of the inspection vehicle in the geographic coordinate system and third coordinate information of the current parking space corresponding to the parking space image in the geographic coordinate system;

[0010] Using the second coordinate information, convert the first coordinate information into the geographic coordinate system to obtain fourth coordinate information;

[0011] The third coordinate information, the fourth coordinate information and the license plate number corresponding to the license plate number image are associated to obtain the license plate number having the third coordinate information.

[0012] In some embodiments, capturing an image of a parking space where a vehicle is parked in a parking lot to obtain a parking space image, wherein the parking space image includes a license plate number image, includes:

[0013] Obtain the parking space category of the parking lot;

[0014] According to the parking space category, start the corresponding image acquisition module;

[0015] The image acquisition module is used to acquire a parking space image, wherein the parking space image includes a license plate number image.

[0016] In some embodiments, starting the corresponding image acquisition module according to the parking space category includes:

[0017] If the parking space type is a straight-line parking space, the image acquisition modules at both ends of the side of the inspection vehicle are activated;

[0018] If the parking space category is a non-font parking space, an image acquisition module in the middle of the side of the inspection vehicle is started.

[0019] In some embodiments, after acquiring the parking space image, the method further includes:

[0020] A convolutional neural network is used to recognize the license plate image in the parking space image.

[0021] In some embodiments, calculating the first coordinate information of the license plate image in the parking space image includes:

[0022] Constructing a first coordinate system with the inspection vehicle as the origin;

[0023] In the first coordinate system, first coordinate information of the license plate image in the parking space image is calculated.

[0024] In some embodiments, the inspection vehicle is provided with a laser radar and an integrated navigation system, and obtaining the second coordinate information of the inspection vehicle in a geographic coordinate system and the third coordinate information of the current parking space corresponding to the parking space image in the geographic coordinate system includes:

[0025] Using the combined navigation to obtain the second coordinate information of the inspection vehicle in the geographic coordinate system and the geographic coordinates of the laser radar in the geographic coordinate system;

[0026] Acquiring point cloud data of a current environment using the laser radar, wherein the point cloud data includes a parking space cloud, and the parking space cloud corresponds to the parking space image;

[0027] Taking the geographic coordinates of the laser radar as the origin, measuring the parking space coordinates corresponding to the parking space cloud;

[0028] Based on the second coordinate information and the parking space coordinates, third coordinate information of the current parking space corresponding to the parking space image in a geographic coordinate system is obtained.

[0029] In some embodiments, the using the second coordinate information to convert the first coordinate information into the geographic coordinate system to obtain fourth coordinate information includes:

[0030] The first coordinate information is converted from the first coordinate system to the geographic coordinate system using the second coordinate information to obtain fourth coordinate information.

[0031] In some embodiments, after obtaining the license plate number having the third coordinate information, the method further includes:

[0032] The license plate number with the third coordinate information is sent to the cloud server.

[0033] In a second aspect, the present application further provides a patrol vehicle, the patrol vehicle comprising:

[0034] at least one processor, and

[0035] A memory, the memory being communicatively connected to the processor, the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to implement the steps of the parking lot license plate acquisition method as described in the first aspect above.

[0036] In a third aspect, the present application also provides a non-volatile computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by the inspection vehicle, the steps of the parking lot license plate acquisition method described in the first aspect above are implemented.

[0037] Beneficial effects of the embodiments of the present application: Different from the prior art, the embodiments of the present application provide a parking lot license plate acquisition method, an inspection vehicle, and a storage medium. When the inspection vehicle is inspecting the parking lot, it captures images of parking spaces where vehicles are parked in the parking lot to obtain parking space images, and the parking space images include license plate number images, thereby preliminarily obtaining the license plate numbers of the vehicles in the parking spaces. By calculating the first coordinate information of the license plate image in the parking space image, the relative position of the license plate image in the parking space image can be estimated. Since the inspection vehicle is in a driving state, the geographical location of the inspection vehicle will continue to change. The second coordinate information of the inspection vehicle in the geographical coordinate system and the third coordinate information of the current parking space corresponding to the parking space image in the geographical coordinate system are obtained, thereby obtaining the location of the inspection vehicle when the license plate number is photographed and the location of the parking space. Using the second coordinate information, the first coordinate information is converted to the geographical coordinate system to obtain the fourth coordinate information, thereby obtaining the actual geographical location of the license plate image. The third coordinate information, the fourth coordinate information and the license plate number corresponding to the license plate image are associated to obtain the license plate number with the third coordinate information, and the license plate number is associated with the specific parking space, thereby completing the inspection of the parking space, so as to facilitate parking management of the parking lot. In addition, the inspection vehicle only needs to add an image acquisition module to facilitate image acquisition of the parking space, as well as the relevant hardware for calculating the specific location of the parking space. There is no need to install a geomagnetic sensor separately on each parking space. The modified inspection vehicle can be put into use, and the inspection efficiency is high. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] One or more embodiments are exemplarily illustrated by pictures in the corresponding drawings. These exemplifications do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0039] Figure 1 This is a first structural diagram of the inspection vehicle of this application;

[0040] Figure 2 This is a second structural diagram of the inspection vehicle of the present application;

[0041] Figure 3 This is a flow chart of an embodiment of the method for obtaining parking license plates in the present application;

[0042] Figure 4 This is a schematic diagram of the inspection vehicle of the present application inspecting a straight-line parking space;

[0043] Figure 5 This is a schematic diagram of the inspection vehicle of the present application inspecting a non-font parking space;

[0044] Figure 6This is a schematic structural diagram of an embodiment of the parking lot license plate acquisition device of the present application;

[0045] Figure 7 It is a schematic diagram of the hardware structure of the controller in one embodiment of the inspection vehicle of the present application. DETAILED DESCRIPTION

[0046] The present application is described in detail below with reference to specific embodiments. The following embodiments will help those skilled in the art to further understand the present application, but are not intended to limit the present application in any form. It should be noted that those skilled in the art may make several variations and improvements without departing from the scope of the present application. These all fall within the scope of protection of the present application.

[0047] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0048] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other and are all within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order than the module division in the device or the order in the flow chart. In addition, the words "first", "second", "third", "fourth" and the like used herein do not limit the data and execution order, but only distinguish between the same items or similar items with basically the same functions and effects.

[0049] Unless otherwise defined, all technical and scientific terms used in this specification have the same meanings as those commonly understood by those skilled in the art to which this application belongs. The terms used in this specification and in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" as used in this specification includes any and all combinations of one or more of the relevant listed items.

[0050] In addition, the technical features involved in each embodiment of the present application described below can be combined with each other as long as they do not conflict with each other.

[0051] The parking lot license plate acquisition method and device provided in the embodiment of the present application can be applied to patrol vehicles. The patrol vehicles of the present application patrol the parking lot, and the parking lot can be a profitable roadside parking space. It is not convenient to modify the parking space, that is, there is no need to install a geomagnetic sensor.

[0052] The inspection vehicle is provided with multiple image acquisition modules, which can be cameras, which are arranged on the sides of the inspection vehicle, such as Figure 1 As shown in the figure, there are three cameras, which are respectively set at the front, middle and rear ends of the side of the inspection vehicle; the inspection vehicle is also equipped with a laser radar for emitting laser lines and receiving reflected laser lines to obtain laser point clouds; the inspection vehicle is also equipped with a combined navigation system for locating the geographical location of the inspection vehicle, and, as shown in the figure, Figure 2 As shown, the integrated navigation is located at the bottom of the lidar, and the centers of the two share the same Z axis. The installation positions of the three cameras are on the same XY plane as the integrated navigation center, reducing the dimensions that the coordinate conversion algorithm needs to process.

[0053] See Figure 3 , Figure 3 1 is a flow chart of an embodiment of a method for acquiring parking license plates applied to the present application. The method can be executed by a controller in the inspection vehicle 100 , and the method includes steps S301 to S305 .

[0054] S301: Capturing images of parking spaces where vehicles are parked in a parking lot to obtain parking space images, where the parking space images include license plate number images.

[0055] The inspection vehicle can inspect each parking space in the parking lot at a speed of 30km / h. Then, when the length of a parking space is 5 meters, each inspection vehicle can inspect 100 parking spaces with a length of 500 meters in one minute.

[0056] There are many types of parking spaces in parking lots, such as straight-line parking spaces, non-line parking spaces, and diagonal parking spaces.

[0057] In some embodiments, an image of a parking space where a vehicle is parked is captured to obtain a parking space image, wherein the parking space image includes a license plate image, including:

[0058] Obtain the parking space category of the parking lot;

[0059] According to the parking space category, start the corresponding image acquisition module;

[0060] The image acquisition module is used to acquire a parking space image, wherein the parking space image includes a license plate number image.

[0061] Specifically, it is first necessary to obtain the parking space category of the parking lot, and then start the corresponding image acquisition module according to the parking space category. The image acquisition module is used to acquire the parking space image, which includes the license plate number image.

[0062] Furthermore, according to the parking space category, starting the corresponding image acquisition module includes:

[0063] If the parking space type is a straight parking space, the image acquisition modules at both ends of the inspection vehicle are activated; if the parking space type is a non-straight parking space, the image acquisition module in the middle of the inspection vehicle is activated.

[0064] like Figure 4 As shown, when the parking space category is a straight-line parking space, when a vehicle is parked in the parking space, the vehicle's license plate number will be located on the left and right ends of the parking space. Then, the image acquisition modules (cameras) installed at both ends of the side of the inspection vehicle can more easily capture images with license plate numbers. Therefore, if the parking space category is a straight-line parking space, the image acquisition modules at both ends of the inspection vehicle are started to facilitate the collection of the license plate number of the vehicle currently in the parking space.

[0065] like Figure 5 As shown, when the parking space category is a non-font parking space, when the vehicle is parked in the parking space, the vehicle's license plate number will face the side of the inspection vehicle. Therefore, the image acquisition module installed in the middle position of the side of the inspection vehicle can more easily capture images with license plate numbers. Therefore, if the parking space category is a non-font parking space, the image acquisition module in the middle of the inspection vehicle is started to facilitate the collection of the license plate number of the vehicle currently in the parking space.

[0066] After determining the different parking space categories, different image acquisition modules are activated to capture parking space images, including license plate images. This license plate image can identify the current vehicle's license plate number and register the license plate number to facilitate parking billing and other operations for that license plate number.

[0067] In some embodiments, after acquiring the parking space image, the method further includes:

[0068] A convolutional neural network is used to recognize the license plate image in the parking space image.

[0069] Specifically, after collecting the parking space image, a convolutional neural network is used to identify the license plate number image in the parking space image, thereby efficiently and accurately identifying the license plate number image and the license plate number.

[0070] S302: Calculate first coordinate information of the license plate image in the parking space image.

[0071] In some embodiments, calculating first coordinate information of the license plate image in the parking space image includes:

[0072] Constructing a first coordinate system with the inspection vehicle as the origin;

[0073] In the first coordinate system, first coordinate information of the license plate image in the parking space image is calculated.

[0074] Specifically, after the license plate number image is identified, a first coordinate system is constructed with the inspection car as the center, that is, the origin of the first coordinate system is the inspection car. Under the first coordinate system, the first coordinate information of the license plate number image in the parking space image is calculated to obtain the relative position of the license plate number image in the parking space image.

[0075] S303: Acquire the second coordinate information of the inspection vehicle in the geographic coordinate system and the third coordinate information of the current parking space corresponding to the parking space image in the geographic coordinate system.

[0076] like Figure 1 and Figure 2 As shown, the inspection vehicle is also equipped with a laser radar and integrated navigation. The integrated navigation is used to locate the location information of the inspection vehicle. In some embodiments, obtaining the second coordinate information of the inspection vehicle in the geographic coordinate system and the third coordinate information of the current parking space corresponding to the parking space image in the geographic coordinate system includes:

[0077] Using the combined navigation to obtain the second coordinate information of the inspection vehicle in the geographic coordinate system and the geographic coordinates of the laser radar in the geographic coordinate system;

[0078] Acquiring point cloud data of a current environment using the laser radar, wherein the point cloud data includes a parking space cloud, and the parking space cloud corresponds to the parking space image;

[0079] Taking the geographic coordinates of the laser radar as the origin, measuring the parking space coordinates corresponding to the parking space cloud;

[0080] Based on the second coordinate information and the parking space coordinates, third coordinate information of the current parking space corresponding to the parking space image in a geographic coordinate system is obtained.

[0081] Specifically, the inspection vehicle uses the combined navigation to obtain the second coordinate information of the inspection vehicle in the geographic coordinate system, and can also obtain the geographic coordinates of the laser radar in the geographic coordinate system, and use the laser radar, the laser radar through SLAM (Simultaneous Localization and Mapping (real-time positioning and map construction) is used to construct a map and obtain point cloud data of the current environment. The point cloud data includes a parking spot cloud, and the parking spot cloud is the point cloud data corresponding to the parking space image. The laser radar is then used to measure the parking space coordinates corresponding to the parking spot cloud, and the parking space coordinates are based on the geographic coordinates of the laser radar as the origin. Since the combined radar is located at the bottom of the laser radar, the laser radar and the combined navigation center share the Z axis, and the camera and the combined navigation center share the XY plane. Therefore, the second coordinate information of the inspection vehicle in the geographic coordinate system and the geographic coordinates of the laser radar in the geographic coordinate system only differ on the Z axis. Therefore, based on the second coordinate information and the parking space coordinates, when obtaining the third coordinate information of the current parking space corresponding to the parking space image in the geographic coordinate system, the second coordinate information of the inspection vehicle in the geographic coordinate system and the parking space coordinates can be directly superimposed on the Z axis, and the X and Y axes of the parking space coordinates remain the X and Y axes of the coordinates of the parking spot cloud measured by the laser radar.

[0082] By combining navigation to locate the inspection vehicle and the laser radar, the specific geographic location of the inspection vehicle during the inspection process is obtained. By measuring the parking space with the laser radar, the relative position of the parking space is obtained. By combining the combined navigation and laser radar measurements, the specific geographic location of the parking space is determined, which is the third coordinate information.

[0083] S304: Using the second coordinate information, convert the first coordinate information into the geographic coordinate system to obtain fourth coordinate information.

[0084] The second coordinate information is the coordinate information of the inspection vehicle in the geographic coordinate system. In order to obtain the specific geographic location of the parking space where the vehicle is parked, the first coordinate information of the license plate number image in the parking space image is converted to the geographic coordinate system to obtain the fourth coordinate information. The fourth coordinate information is the actual geographic location of the parking space.

[0085] When converting coordinates, since the first coordinate information is the coordinate information under the first coordinate system, the first coordinate system is a coordinate system with the inspection vehicle as the origin, rather than the coordinate under the geographic coordinate system. Therefore, the second coordinate information is used to convert the first coordinate information from the first coordinate system to the geographic coordinate system to obtain the fourth coordinate information.

[0086] The coordinate transformation can utilize existing coordinate transformation technology, which is not limited here.

[0087] Moreover, since the laser radar and the combined navigation center share the Z axis, and the camera and the combined navigation center share the XY plane, the second coordinate information is the specific position of the combined navigation positioning inspection vehicle in the geographic coordinate system, and the first coordinate information is the laser radar's estimate of the relative position of the license plate number, so that when the coordinates are converted, the dimensions that the coordinate conversion algorithm needs to process can be reduced.

[0088] S305: Associating the third coordinate information, the fourth coordinate information, and the license plate number corresponding to the license plate image to obtain the license plate number having the third coordinate information.

[0089] Specifically, the third coordinate information is the coordinate of the current parking space in the geographic coordinate system, and the fourth coordinate information is the coordinate of the license plate number on the current parking space. The third coordinate information and the fourth coordinate information are associated with the license plate number corresponding to the license plate number image of the current parking space to obtain the license plate number on the current parking space and complete the acquisition of the vehicle license plate of the parking space.

[0090] In some embodiments, after obtaining the license plate number having the third coordinate information, the method further includes:

[0091] The license plate number with the third coordinate information is sent to the cloud server.

[0092] Specifically, the license plate number with the third coordinate information is sent to the cloud server to facilitate subsequent fee management, illegal parking fines and other services.

[0093] In an embodiment of the present application, when inspecting a parking lot, a patrol vehicle captures images of parking spaces with parked vehicles in the parking lot to obtain parking space images, which include license plate images, thereby preliminarily obtaining the license plate number of the vehicle in the parking space. By calculating first coordinate information of the license plate image in the parking space image, the relative position of the license plate image in the parking space image can be estimated. Since the patrol vehicle is in motion, its geographic location will continuously change. Second coordinate information of the patrol vehicle in a geographic coordinate system and third coordinate information of the current parking space corresponding to the parking space image in the geographic coordinate system are obtained, thereby obtaining the patrol vehicle's position when the license plate number was captured and the location of the parking space. Using the second coordinate information, the first coordinate information is converted to the geographic coordinate system to obtain fourth coordinate information, thereby obtaining the actual geographic location of the license plate image. The third and fourth coordinate information are then associated with the license plate number corresponding to the license plate image to obtain the license plate number with the third coordinate information, thereby associating the license plate number with a specific parking space, thereby completing the inspection of the parking space and facilitating parking management in the parking lot. Moreover, the inspection vehicle only needs to add an image acquisition module to facilitate image acquisition of parking spaces, as well as related hardware to calculate the specific location of parking spaces. There is no need to install a geomagnetic sensor separately on each parking space. The modified inspection vehicle can be put into use with high inspection efficiency.

[0094] The present application also provides a parking lot license plate acquisition device. Figure 6 , which shows the structure of a parking lot license plate acquisition device provided in an embodiment of the present application. The parking lot license plate acquisition device 600 includes:

[0095] The license plate number image acquisition module 601 is used to collect images of parking spaces where vehicles are parked in a parking lot to obtain parking space images, where the parking space images include license plate number images;

[0096] A first coordinate acquisition module 602 is configured to calculate first coordinate information of the license plate image in the parking space image;

[0097] The second coordinate acquisition module 603 is configured to acquire the second coordinate information of the inspection vehicle in the geographic coordinate system and the third coordinate information of the current parking space corresponding to the parking space image in the geographic coordinate system;

[0098] A coordinate conversion module 604 is configured to convert the first coordinate information into the geographic coordinate system using the second coordinate information to obtain fourth coordinate information;

[0099] The association module 605 is configured to associate the third coordinate information, the fourth coordinate information, and the license plate number corresponding to the license plate image to obtain the license plate number having the third coordinate information.

[0100] In an embodiment of the present application, when inspecting a parking lot, a patrol vehicle captures images of parking spaces with parked vehicles in the parking lot to obtain parking space images, which include license plate images, thereby preliminarily obtaining the license plate number of the vehicle in the parking space. By calculating first coordinate information of the license plate image in the parking space image, the relative position of the license plate image in the parking space image can be estimated. Since the patrol vehicle is in motion, its geographic location will continuously change. Second coordinate information of the patrol vehicle in a geographic coordinate system and third coordinate information of the current parking space corresponding to the parking space image in the geographic coordinate system are obtained, thereby obtaining the patrol vehicle's position when the license plate number was captured and the location of the parking space. Using the second coordinate information, the first coordinate information is converted to the geographic coordinate system to obtain fourth coordinate information, thereby obtaining the actual geographic location of the license plate image. The third and fourth coordinate information are then associated with the license plate number corresponding to the license plate image to obtain the license plate number with the third coordinate information, thereby associating the license plate number with a specific parking space, thereby completing the inspection of the parking space and facilitating parking management in the parking lot. Moreover, the inspection vehicle only needs to add an image acquisition module to facilitate image acquisition of parking spaces, as well as related hardware to calculate the specific location of parking spaces. There is no need to install a geomagnetic sensor separately on each parking space. The modified inspection vehicle can be put into use with high inspection efficiency.

[0101] In some embodiments, the license plate image acquisition module 601 is further configured to:

[0102] Obtain the parking space category of the parking lot;

[0103] According to the parking space category, start the corresponding image acquisition module;

[0104] The image acquisition module is used to acquire a parking space image, wherein the parking space image includes a license plate number image.

[0105] In some embodiments, the license plate image acquisition module 601 is further configured to:

[0106] If the parking space type is a straight-line parking space, the image acquisition modules at both ends of the side of the inspection vehicle are activated;

[0107] If the parking space category is a non-font parking space, an image acquisition module in the middle of the side of the inspection vehicle is started.

[0108] In some embodiments, the license plate image acquisition module 601 is further configured to:

[0109] A convolutional neural network is used to recognize the license plate image in the parking space image.

[0110] In some embodiments, the first coordinate acquisition module 602 is further configured to:

[0111] Constructing a first coordinate system with the inspection vehicle as the origin;

[0112] In the first coordinate system, first coordinate information of the license plate image in the parking space image is calculated.

[0113] In some embodiments, the inspection vehicle is equipped with a laser radar and integrated navigation, and the second coordinate acquisition module 603 is further used to:

[0114] Using the combined navigation to obtain the second coordinate information of the inspection vehicle in the geographic coordinate system and the geographic coordinates of the laser radar in the geographic coordinate system;

[0115] Acquiring point cloud data of a current environment using the laser radar, wherein the point cloud data includes a parking space cloud, and the parking space cloud corresponds to the parking space image;

[0116] Taking the geographic coordinates of the laser radar as the origin, measuring the parking space coordinates corresponding to the parking space cloud;

[0117] Based on the second coordinate information and the parking space coordinates, third coordinate information of the current parking space corresponding to the parking space image in a geographic coordinate system is obtained.

[0118] In some embodiments, the coordinate conversion module 604 is further configured to:

[0119] The first coordinate information is converted from the first coordinate system to the geographic coordinate system using the second coordinate information to obtain fourth coordinate information.

[0120] In some embodiments, the apparatus 600 further includes a sending module 606 configured to:

[0121] The license plate number with the third coordinate information is sent to the cloud server.

[0122] It should be noted that the above device can execute the method provided in the embodiment of this application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in the device embodiment, please refer to the method provided in the embodiment of this application.

[0123] Figure 7 FIG. 1 is a schematic diagram of the hardware structure of a controller of an inspection vehicle 100 in one embodiment of the inspection vehicle. Figure 7 As shown, the controller includes:

[0124] One or more processors 111 and memory 112 . Figure 7 In the figure, a processor 111 and a memory 112 are taken as an example.

[0125] The processor 111 and the memory 112 may be connected via a bus or other means. Figure 7 The bus connection is taken as an example.

[0126] The memory 112 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the program instructions / modules corresponding to the parking lot license plate acquisition method in the embodiment of the present application (for example, the attached Figure 6 The processor 111 executes the various functional applications and data processing of the controller by running the non-volatile software programs, instructions, and modules stored in the memory 112, thereby implementing the parking lot license plate acquisition method of the above method embodiment.

[0127] The memory 112 may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the personnel entry and exit detection device. In addition, the memory 112 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 112 may optionally include a memory remotely located relative to the processor 111, and these remote memories may be connected to the inspection vehicle via a network. Examples of the aforementioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0128] The one or more modules are stored in the memory 112, and when executed by the one or more processors 111, the parking lot license plate acquisition method in any of the above method embodiments is executed, for example, the above described Figure 3 Method steps S301 to S305; implement Figure 6 The functions of modules 601-606 in FIG.

[0129] The above-mentioned product can execute the method provided in the embodiment of this application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided in the embodiment of this application.

[0130] The embodiment of the present application provides a non-volatile computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors, for example Figure 7A processor 111 in the embodiment may enable the one or more processors to execute the parking lot license plate acquisition method in any of the above method embodiments, for example, executing the above described Figure 3 Method steps S301 to S305; implement Figure 6 The functions of modules 601-606 in FIG.

[0131] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0132] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, can also be implemented by hardware. Those skilled in the art can understand that all or part of the processes in the above embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Under the concept of the present invention, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the present invention as described above. For the sake of simplicity, they are not provided in detail. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for obtaining license plates in a parking lot, characterized in that: Applied to an inspection vehicle equipped with a laser radar and integrated navigation, the method includes: Capturing images of parking spaces where vehicles are parked in a parking lot to obtain parking space images, wherein the parking space images include license plate number images; Calculating first coordinate information of the license plate image in the parking space image; Using the combined navigation to obtain the second coordinate information of the inspection vehicle in the geographic coordinate system and the geographic coordinates of the laser radar in the geographic coordinate system; Acquiring point cloud data of a current environment using the laser radar, wherein the point cloud data includes a parking space cloud, and the parking space cloud corresponds to the parking space image; Taking the geographic coordinates of the laser radar as the origin, measuring the parking space coordinates corresponding to the parking space cloud; Based on the second coordinate information and the parking space coordinates, obtaining third coordinate information of the current parking space corresponding to the parking space image in a geographic coordinate system; Using the second coordinate information, convert the first coordinate information into the geographic coordinate system to obtain fourth coordinate information; The third coordinate information, the fourth coordinate information and the license plate number corresponding to the license plate number image are associated to obtain the license plate number having the third coordinate information.

2. The method according to claim 1, characterized in that The method of capturing an image of a parking space where a vehicle is parked in a parking lot to obtain a parking space image, wherein the parking space image includes a license plate number image, includes: Obtain the parking space category of the parking lot; According to the parking space category, start the corresponding image acquisition module; The image acquisition module is used to acquire a parking space image, wherein the parking space image includes a license plate number image.

3. The method according to claim 2, characterized in that The starting of the corresponding image acquisition module according to the parking space category includes: If the parking space type is a straight-line parking space, the image acquisition modules at both ends of the side of the inspection vehicle are activated; If the parking space category is a non-font parking space, an image acquisition module in the middle of the side of the inspection vehicle is started.

4. The method according to claim 2, characterized in that After acquiring the parking space image, the method further includes: A convolutional neural network is used to recognize the license plate image in the parking space image.

5. The method according to claim 1, wherein The calculating first coordinate information of the license plate image in the parking space image includes: Constructing a first coordinate system with the inspection vehicle as the origin; In the first coordinate system, first coordinate information of the license plate image in the parking space image is calculated.

6. The method according to claim 5, characterized in that The converting the first coordinate information into the geographic coordinate system using the second coordinate information to obtain fourth coordinate information includes: The first coordinate information is converted from the first coordinate system to the geographic coordinate system using the second coordinate information to obtain fourth coordinate information.

7. The method according to any one of claims 1 to 6, characterized in that After obtaining the license plate number having the third coordinate information, the method further includes: The license plate number with the third coordinate information is sent to the cloud server.

8. A patrol vehicle, characterized in that: The inspection vehicle includes: at least one processor, and A memory, the memory being communicatively connected to the processor, the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to implement the steps of the method according to any one of claims 1 to 7.

9. A non-volatile computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by the inspection vehicle, the steps of the method according to any one of claims 1 to 7 are implemented.

Images