Video pile-based license plate recognition method, terminal equipment and storage medium

Abstract

The invention relates to a license plate recognition method based on video piles, terminal equipment and a storage medium, and the method comprises the steps: setting at least two berth frames for an image corresponding to each video pile, one berth frame corresponding to a berth occupied by the video pile, and the other berth frames corresponding to adjacent berths of the berth occupied by the video pile; the method comprises the following steps: when a vehicle parked at a certain parking space is determined, firstly, searching whether an image which meets the condition that the overlapping rate of the image and a parking space frame belonging to the parking space occupied by the video pile corresponding to the image is greater than an overlapping rate threshold value exists in all images shot by the video pile corresponding to the parking space or not; judging whether a license plate is extracted from the image with the maximum overlapping rate, and if yes, taking the extracted license plate as the license plate of the vehicle parked in the parking space; and otherwise, determining the license plate from all images shot by the video piles corresponding to the adjacent berths of the berth. The license plate recognition rate is improved, and manual intervention is reduced.

Description

Technical Field

[0001] The present invention relates to the field of license plate recognition, and in particular to a license plate recognition method based on a video pile, a terminal device and a storage medium. Background Art

[0002] With the acceleration of urbanization, the problem of urban parking has become increasingly prominent. When the growth rate of closed parking lots cannot meet the demand for parking spaces due to the increase in vehicles, roadside parking has become a fast and effective way to manage urban congestion, so it has attracted more and more attention from road traffic management departments. From the starting point, "roadside parking" is set up for temporary parking convenience and has public attributes. It can allocate effective resources to prevent parking spaces from being occupied for a long time or even for free, thereby improving the turnover rate of parking spaces. Existing roadside parking mainly uses hardware equipment such as geomagnetism, high-position video piles, low-position video piles, ground locks, induction screens, etc., combined with AI algorithms, to promote the realization of intelligent unattended parking charging mode. Car owners do not need to interact with management personnel, and can pay parking fees through self-service mobile phone APP or roadside QR code, which greatly improves payment efficiency.

[0003] At present, the low-position video piles on the market mainly use lateral recognition image technology as a means of terminal data collection. The equipment is placed on the front / rear side of the parking space. Relying on the "Internet + Big Data" technology, it consists of a road parking system, user mobile phone software, service and management center, etc. This type of video pile can be roughly divided into two working modes according to the principle. One is that the video pile has its own recognition algorithm chip, which analyzes and identifies the vehicles entering the parking area through its own recognition chip; the other is that the video pile has no analysis ability, and uses the radar to sense the movement of objects in the area, so as to collect and upload images, rely on the algorithm of the back-end service for recognition, and analyze and identify the corresponding results, and then feedback to the video pile for response. These two types of video piles have their own advantages and disadvantages: the first type has the advantage of high accuracy. From the beginning of the vehicle entering to the end of parking, it can deal with the recognition interference behavior in the video pile scene, and adopts a vehicle detection algorithm based on deep learning. By correctly identifying the license plate and its movement trajectory, in addition, the built-in algorithm chip can also be combined with the corresponding position to optimize the recognition. The disadvantage is that the cost is expensive, and the algorithm parameter tuning is more cumbersome due to the number of problems, but the accuracy based on daily recognition can reach more than 98%. The advantage of the second type is that the hardware cost is low, and the recognition operation relies on background recognition + algorithm services. Through targeted algorithms, the accuracy reaches more than 90%. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes a license plate recognition method based on a video pole, a terminal device and a storage medium, so as to assist in recognition in scenarios where recognition based on a video pole cannot be performed.

[0005] The specific plan is as follows:

[0006] A license plate recognition method based on a video pile comprises the following steps:

[0007] At least two berth frames are set for the image corresponding to each video post, wherein one berth frame corresponds to the berth occupied by the video post, and the other berth frames correspond to adjacent berths to the berth occupied by the video post;

[0008] Receive images captured by various video poles installed in roadside parking areas in real time;

[0009] Identify the collected images and extract all the vehicle frames and license plates;

[0010] Based on all the extracted vehicle frames, calculating the overlap rate between each vehicle frame and each parking space frame corresponding to the image;

[0011] When determining a vehicle parked in a parking space, first, from all images taken by the video pole corresponding to the parking space, find out whether there is an image that satisfies the overlap rate with the parking space frame of the parking space occupied by the video pole corresponding to the image greater than the overlap rate threshold. If so, determine whether a license plate is extracted from the image with the largest overlap rate. If so, use the extracted license plate as the license plate of the vehicle parked in the parking space. Otherwise, from all images taken by the video poles corresponding to the adjacent parking spaces of the parking space, find out whether there is an image that satisfies the overlap rate with the parking space frame corresponding to the parking space in the image greater than the overlap rate threshold. If so, determine whether a license plate is extracted from the image with the largest overlap rate. If so, use the extracted license plate as the license plate of the vehicle parked in the parking space.

[0012] Furthermore, the adjacent berths include two berths, a front berth and a rear berth.

[0013] Furthermore, the video pole adopts a low-position video pole.

[0014] A license plate recognition terminal device based on a video pole includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method described above in the embodiment of the present invention are implemented.

[0015] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described above in an embodiment of the present invention are implemented.

[0016] The present invention adopts the above technical solution, which can improve the recognition rate of license plates and reduce manual intervention when the image recognition effect of the video pole is poor due to occlusion or light or angle. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1Shown is a flow chart of the method in Embodiment 1 of the present invention.

[0018] Figure 2 Shown is a schematic diagram of identifying abnormal conditions in this embodiment.

[0019] Figure 3 Shown is a schematic diagram of the identification method in this embodiment. DETAILED DESCRIPTION

[0020] To further illustrate various embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementations and advantages of the present invention.

[0021] The present invention will now be further described with reference to the accompanying drawings and specific implementation methods.

[0022] Embodiment 1:

[0023] The embodiment of the present invention provides a license plate recognition method based on a video pile, such as Figure 1 As shown, the method comprises the following steps:

[0024] S1: at least two berth frames are set for the image corresponding to each video post, wherein one berth frame corresponds to the berth occupied by the video post, and the other berth frames correspond to adjacent berths of the berth occupied by the video post.

[0025] In this embodiment, the video pile adopts a low-position video pile. The video pile is usually installed in front of the berth side, such as Figure 2 As shown in P1, P2, and P3, the corresponding berths are B1, B2, and B3 respectively.

[0026] In the prior art, only one berth frame is usually set for vehicle identification to identify whether the vehicle has entered the corresponding berth. In this embodiment, since the video poles of adjacent berths need to be used, at least two berth frames are set for the image. The berth frame corresponding to the berth itself can be used to identify whether a vehicle is parked at the berth, and the berth frame corresponding to the adjacent berth can be used to identify whether a vehicle is parked at the adjacent berth. The adjacent berths may include two berths, the front and the rear, or only one of the two. Due to different parking positions, when the berth is parked close to the front parking line, the image captured by the video pole corresponding to the berth itself may not be able to identify the license plate of the parked vehicle due to the viewing angle or occlusion. At this time, the image captured by the video pole corresponding to the adjacent berth can avoid occlusion and identify the license plate of the corresponding vehicle.

[0027] S2: Receive images captured by various video poles installed in the roadside parking area in real time.

[0028] When each video pole detects the movement of an object based on radar, it takes an image and uploads it to the server. The server receives the image in real time and performs subsequent analysis.

[0029] S3: Identify the collected images and extract all vehicle frames and license plates therein.

[0030] The image recognition algorithm can adopt the existing vehicle recognition and license plate recognition algorithms, and there is no limitation here.

[0031] S4: Based on all the extracted vehicle frames, the overlap ratio between each vehicle frame and each parking space frame corresponding to the image is calculated.

[0032] The vehicle frames extracted from the image may include multiple ones, so the overlap ratio between each vehicle and each parking space frame is calculated in sequence.

[0033] S5: When determining a vehicle parked in a parking space, first search from all images taken by the video pole corresponding to the parking space whether there is an image that satisfies an overlap rate greater than an overlap rate threshold with the parking space frame belonging to the parking space occupied by the video pole corresponding to the image. If so, determine whether a license plate is extracted from the image with the largest overlap rate. If so, use the extracted license plate as the license plate of the vehicle parked in the parking space. Otherwise, search from all images taken by the video poles corresponding to the adjacent parking spaces of the parking space whether there is an image that satisfies an overlap rate greater than an overlap rate threshold with the parking space frame corresponding to the parking space in the image. If so, determine whether a license plate is extracted from the image with the largest overlap rate. If so, use the extracted license plate as the license plate of the vehicle parked in the parking space.

[0034] The overlap rate threshold needs to be preset, and the value thereof can be set by technicians in this field according to their needs, and is not limited here.

[0035] like Figure 2 As shown, when a vehicle enters parking space B2, it may be blocked by obstacles next to video post P2 or parked close to the parking space line in front. These situations will cause the license plate of the vehicle parked in parking space B2 to be unable to be identified in the photo taken by video post P2.

[0036] like Figure 3 As shown, based on the above situation, the recognition result R2 based on the image taken by the video pole P2 cannot be used to extract the license plate of the parked vehicle. At this time, the recognition result R1 based on the image taken by the video pole P1 of the adjacent parking space B1 recognizes that the overlap rate of the parking space frame corresponding to the vehicle and the parking space B2 is greater than the threshold value. Therefore, the video pole of the adjacent parking space helps the video pole B2 to recognize the license plate of the parked vehicle.

[0037] The embodiments of the present invention can improve the recognition rate of license plates and reduce manual intervention when the image recognition effect of the video pole is poor due to occlusion, light or angle.

[0038] Embodiment 2:

[0039] The present invention also provides a license plate recognition terminal device based on a video pole, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the above-mentioned method embodiment of the first embodiment of the present invention when executing the computer program.

[0040] Further, as an executable solution, the license plate recognition terminal device based on the video pile can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The license plate recognition terminal device based on the video pile may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the composition structure of the license plate recognition terminal device based on the video pile is only an example of a license plate recognition terminal device based on the video pile, and does not constitute a limitation on the license plate recognition terminal device based on the video pile. It may include more or less components than the above, or a combination of certain components, or different components. For example, the license plate recognition terminal device based on the video pile may also include input and output devices, network access devices, buses, etc., and the embodiments of the present invention do not limit this.

[0041] Further, as an executable solution, the processor may be a central processing unit (CPU) or other general-purpose processors. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the license plate recognition terminal device based on the video pile, and uses various interfaces and lines to connect the various parts of the license plate recognition terminal device based on the video pile.

[0042] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the license plate recognition terminal device based on the video pile by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and an application required for at least one function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0043] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method in the embodiment of the present invention are implemented.

[0044] If the module / unit integrated in the license plate recognition terminal device based on the video pile is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory) and software distribution medium, etc.

[0045] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, it should be understood by those skilled in the art that various changes may be made to the present invention in form and details without departing from the spirit and scope of the present invention as defined by the appended claims, all of which are within the scope of protection of the present invention.

Claims

1. A license plate recognition method based on video pile, characterized in that: The following steps are involved: At least two berth frames are set for the image corresponding to each video post, wherein one berth frame corresponds to the berth occupied by the video post, and the other berth frames correspond to adjacent berths to the berth occupied by the video post; Receive images captured by various video poles installed in roadside parking areas in real time; Identify the collected images and extract all the vehicle frames and license plates; Based on all the extracted vehicle frames, calculating the overlap rate between each vehicle frame and each parking space frame corresponding to the image; When determining a vehicle parked in a parking space, first, from all images taken by the video pole corresponding to the parking space, find out whether there is an image that satisfies the overlap rate with the parking space frame of the parking space occupied by the video pole corresponding to the image greater than the overlap rate threshold. If so, determine whether a license plate is extracted from the image with the largest overlap rate. If so, use the extracted license plate as the license plate of the vehicle parked in the parking space. Otherwise, from all images taken by the video poles corresponding to the adjacent parking spaces of the parking space, find out whether there is an image that satisfies the overlap rate with the parking space frame corresponding to the parking space in the image greater than the overlap rate threshold. If so, determine whether a license plate is extracted from the image with the largest overlap rate. If so, use the extracted license plate as the license plate of the vehicle parked in the parking space.

2. The license plate recognition method based on video pile according to claim 1 is characterized in that: Adjacent berths include two berths, forward and rear.

3. The license plate recognition method based on video pile according to claim 1 is characterized in that: The video pile adopts a low-position video pile.

4. A license plate recognition terminal device based on a video pole, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 3 when executing the computer program.

5. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images