License plate recognition method and device, equipment, storage medium and program product

Abstract

The invention relates to a license plate recognition method, device and equipment, a storage medium and a program product, and relates to the field of intelligent traffic systems. The method comprises the following steps: acquiring video data collected for at least one parking space area in the view field of a low-position camera; for each parking space area, if it is detected that the parking space state of the parking space area changes based on the video data, a license plate recognition event for the parking space area is triggered; obtaining a target video clip corresponding to the parking space area from the video data according to the state change type of the parking space area and the trigger time point of the license plate recognition event; and based on the target video clip, identifying a license plate number of a target vehicle which enables the parking space state of the parking space area to change. By adopting the method, the license plate recognition accuracy can be improved on the premise of saving the cost.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation systems, and particularly to a license plate recognition method, device, equipment, storage medium, and program product. Background Art

[0002] License plate recognition technology in the parking scenario belongs to the field of intelligent transportation systems, and it is the product of the cross-integration of multiple disciplines such as computer vision technology, pattern recognition technology, communication technology, and automatic control technology. License plate recognition technology specifically involves using an image acquisition device (such as a high-definition camera) to obtain vehicle images in the parking scenario, processing the images through computer vision algorithms, extracting the license plate area and recognizing the license plate number, and then transmitting the recognition result to the management system through communication technology for operations such as parking timing, billing, and vehicle management.

[0003] In traditional license plate recognition methods, a high-position camera is mainly used to collect surveillance videos for parking spaces, and then the license plate numbers of vehicles located in the parking spaces are recognized in real time based on the surveillance videos, which belongs to license plate recognition under real-time videos. However, high-position cameras need to be installed at high places, with high installation and maintenance costs, and obstacles such as trees and buildings are likely to block the camera's line of sight, resulting in a low accuracy rate of license plate recognition when recognizing the license plate numbers of vehicles located in parking spaces based on surveillance videos. Summary of the Invention

[0004] Based on this, in order to solve the above technical problems, it is necessary to provide a license plate recognition method, device, equipment, storage medium, and program product that can improve the accuracy rate of license plate recognition on the premise of cost savings.

[0005] In a first aspect, the present application provides a license plate recognition method, and the method includes:

[0006] Obtain video data collected for at least one parking space area within the field of view of a low-position camera;

[0007] For each of the parking space areas, if it is detected based on the video data that the parking state of the parking space area has changed, then trigger a license plate recognition event for the parking space area;

[0008] According to the type of state change of the parking space area and the trigger time point of the license plate recognition event, obtain a target video segment corresponding to the parking space area from the video data;

[0009] Based on the target video segment, recognize the license plate number of the target vehicle that causes the parking state of the parking space area to change.

[0010] In one embodiment, obtaining a target video segment corresponding to the parking space area from the video data according to the type of change in the state of the parking space area and the trigger time point of the license plate recognition event includes:

[0011] If the type of change in the state of the parking space area is vehicle entry, obtain a video segment corresponding to a preset time period before the trigger time point of the license plate recognition event from the video data as the target video segment corresponding to the parking space area.

[0012] In one embodiment, obtaining a target video segment corresponding to the parking space area from the video data according to the type of change in the state of the parking space area and the trigger time point of the license plate recognition event includes:

[0013] If the type of change in the state of the parking space area is vehicle exit, obtain a video segment corresponding to a preset time period after the trigger time point of the license plate recognition event from the video data as the target video segment corresponding to the parking space area.

[0014] In one embodiment, the method further includes a step of detecting whether the parking space state of each of the at least one parking space area has changed based on the video data; detecting whether the parking space state of each of the at least one parking space area has changed based on the video data includes:

[0015] For each of the parking space areas, perform vehicle recognition on the parking space area based on the video frame sequence in the video data;

[0016] If it is recognized that there is no vehicle to a vehicle or from a vehicle to no vehicle in the parking space area, it is determined that the parking space state of the parking space area has changed; otherwise, it is determined that the parking space state of the parking space area has not changed.

[0017] In one embodiment, recognizing the license plate number of the target vehicle that causes the change in the parking space state of the parking space area based on the target video segment includes:

[0018] Segment the target video segment to obtain a sub-segment sequence composed of a plurality of video sub-segments;

[0019] Load the plurality of video sub-segments in the sub-segment sequence into the memory in sequence for decoding and frame extraction;

[0020] For each of the video sub-segments, push each video frame in the video frame sequence obtained by decoding and frame extraction of the video sub-segment into a cache queue with a cache capacity of two frames in sequence and perform sequential recognition to determine the license plate number of the target vehicle that causes the change in the parking space state of the parking space area.

[0021] In one embodiment, it is applied to an edge computing device installed on a roadside lamp post; the low-position camera is installed in the low-position area of the roadside lamp post; the parking space area is a roadside parking space area; the roadside parking space area is the area where the roadside parking spaces on the side of the road where the roadside lamp post is located are located.

[0022] In a second aspect, the present application provides a license plate recognition device, which includes:

[0023] An acquisition module, configured to acquire video data collected for at least one parking space area within the field of view of the low-position camera;

[0024] A trigger module, configured to trigger a license plate recognition event for each of the parking space areas if it is detected based on the video data that the parking space status of the parking space area has changed;

[0025] The acquisition module is further configured to obtain a target video segment corresponding to the parking space area from the video data according to the type of change in the status of the parking space area and the trigger time point of the license plate recognition event;

[0026] An identification module, configured to identify the license plate number of the target vehicle that causes the parking space status of the parking space area to change based on the target video segment.

[0027] In a third aspect, the present application provides a computer device, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the method embodiments of the present application are implemented.

[0028] In a fourth aspect, the present application provides a computer-readable storage medium, storing a computer program, and when the computer program is executed by a processor, the steps in the method embodiments of the present application are implemented.

[0029] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in the method embodiments of the present application are implemented.

[0030] The above license plate recognition method, device, equipment, storage medium, and program product obtain video data collected for at least one parking space area within the field of view of a low-position camera; for each parking space area, if it is detected based on the video data that the parking space status of the parking space area changes, a license plate recognition event for the parking space area is triggered; according to the type of status change of the parking space area and the trigger time point of the license plate recognition event, the target video segment corresponding to the parking space area is obtained from the video data; based on the target video segment, the license plate number of the target vehicle that causes the parking space status of the parking space area to change is recognized. Compared with the traditional license plate recognition method, in this application, the video data of the parking space area is collected by a low-position camera installed at a low position. When it is detected based on the video data that the parking space status of the parking space area changes, that is, when a vehicle enters or exits the parking space, a license plate recognition event is triggered, and then based on the video segment in the time period before or after the trigger of the license plate recognition event, that is, the video backtracking during the vehicle entering the parking space or during the vehicle exiting the parking space, the license plate number of the vehicle is recognized. The low-position camera is installed at a low position, which is convenient for installation and later maintenance, and the installation and maintenance costs are relatively low. It can also effectively avoid the occlusion of the monitoring line of sight by obstacles such as trees and buildings. Moreover, by recognizing the license plate number of the vehicle through video backtracking during the vehicle entering the parking space or during the vehicle exiting the parking space, the license plate recognition accuracy can be improved on the premise of cost savings. Description of the Drawings

[0031] Figure 1 It is a schematic flowchart of the license plate recognition method in an embodiment;

[0032] Figure 2 It is a schematic diagram of the application scenario of the license plate recognition method in an embodiment;

[0033] Figure 3 It is a structural block diagram of the license plate recognition device in an embodiment;

[0034] Figure 4 It is an internal structure diagram of a computer device in an embodiment;

[0035] Figure 5 It is an internal structure diagram of a computer device in another embodiment. Detailed Description of the Embodiment

[0036] In order to make the objectives, technical solutions, and advantages of this application clearer, 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 used to limit this application.

[0037] In one embodiment, as Figure 1As shown, a license plate recognition method is provided. In this embodiment, taking the application of this method to a computer device as an example, it includes the following steps:

[0038] Step 102, obtain video data collected for at least one parking space area within the field of view of a low-position camera.

[0039] Among them, the low-position camera refers to a camera installed in the low-position area of the target object. The low-position area refers to the area in the target object with a height lower than a preset height. The target object can include roadside lamp posts and buildings, etc. It can be understood that compared with traditional high-position cameras, the installation position of the low-position camera in this application is lower, the installation and maintenance costs are lower, and it is less likely to be blocked by obstacles such as trees and buildings, resulting in better monitoring effects.

[0040] Specifically, within the field of view of the low-position camera, there are at least one parking space area. The low-position camera can perform real-time video collection for at least one parking space area, obtain the corresponding video data, and send the collected video data to the computer device. The computer device can receive the video data collected by the low-position camera for at least one parking space area within its field of view.

[0041] Step 104, for each parking space area, if it is detected based on the video data that the parking space status of the parking space area has changed, then trigger a license plate recognition event for the parking space area.

[0042] Among them, the types of status changes in the parking space area include vehicle entry and vehicle departure. Vehicle entry means that a vehicle drives into the parking space area. Vehicle departure means that a vehicle drives out of the parking space area.

[0043] Specifically, for each parking space area, the computer device can detect whether the parking space status of this parking space area has changed based on the video data. It can be understood that if the computer device detects based on the video data that a vehicle has driven into this parking space area, it is determined that the parking space status of this parking space area has changed, and the type of status change in this parking space area is vehicle entry. If the computer device detects based on the video data that a vehicle has driven out of this parking space area, it is determined that the parking space status of this parking space area has changed, and the type of status change in this parking space area is vehicle departure. If it is detected based on the video data that the parking space status of this parking space area has changed, the computer device can trigger a license plate recognition event for this parking space area.

[0044] Step 106, according to the type of status change in the parking space area and the trigger time point of the license plate recognition event, obtain the target video segment corresponding to the parking space area from the video data.

[0045] In one embodiment, the types of state changes in the parking space area include vehicle entry and vehicle exit. For each parking space area, the computer device can intercept the target video segment corresponding to the parking space area from the video data according to the type of state change in the parking space area and the trigger time point of the license plate recognition event. It can be understood that the target video segment is a sub-segment in the video data.

[0046] Step 108, based on the target video segment, identify the license plate number of the target vehicle that causes the parking space state in the parking space area to change.

[0047] In one embodiment, for each parking space area, the computer device can perform retrospective analysis on the target video segment corresponding to the parking space area, and use license plate recognition technology and target tracking technology to extract the license plate number of the target vehicle that causes the parking space state in the parking space area to change.

[0048] In the above license plate recognition method, video data collected for at least one parking space area within the field of view of the low-position camera is obtained; for each parking space area, if it is detected based on the video data that the parking space state in the parking space area changes, a license plate recognition event for the parking space area is triggered; according to the type of state change in the parking space area and the trigger time point of the license plate recognition event, the target video segment corresponding to the parking space area is obtained from the video data; based on the target video segment, the license plate number of the target vehicle that causes the parking space state in the parking space area to change is identified. Compared with the traditional license plate recognition method, in this application, the video data of the parking space area is collected by the low-position camera installed at a low position. When it is detected based on the video data that the parking space state in the parking space area changes, that is, when a vehicle enters or exits the parking space, a license plate recognition event is triggered, and then based on the video segment in the time period before or after the trigger of the license plate recognition event, that is, the video retrospective during the vehicle's entry into the parking space or during the vehicle's exit from the parking space, the license plate number of the vehicle is identified. The low-position camera is installed at a low position, which is convenient for installation and later maintenance, and the installation and maintenance costs are low. It can also effectively avoid obstacles such as trees and buildings from blocking the monitoring line of sight. Moreover, by retrospectively analyzing the video during the vehicle's entry into the parking space or during the vehicle's exit from the parking space to identify the license plate number of the vehicle, the license plate recognition accuracy can be improved on the premise of saving costs.

[0049] In one embodiment, obtaining the target video segment corresponding to the parking space area from the video data according to the type of state change in the parking space area and the trigger time point of the license plate recognition event includes: if the type of state change in the parking space area is vehicle entry, obtain the video segment corresponding to the preset time period before the trigger time point of the license plate recognition event from the video data as the target video segment corresponding to the parking space area.

[0050] Specifically, the types of state changes in the parking space area include vehicle entry and vehicle exit. If the type of state change in the parking space area is vehicle entry, the computer device can obtain, from the video data, the video clip corresponding to a preset time period before the trigger time point of the license plate recognition event as the target video clip corresponding to the parking space area.

[0051] For example, if the type of state change in the parking space area is vehicle entry, the computer device can obtain, from the video data, the video clip of the 1 minute before the trigger time point of the license plate recognition event, and use the video clip of this 1 minute during the process of the vehicle driving into the parking space area as the target video clip corresponding to the parking space area.

[0052] In the above embodiments, in the case of vehicle entry, by using the video clip corresponding to a preset time period before the trigger time point of the license plate recognition event in the video data as the target video clip corresponding to the parking space area, the license plate of the vehicle can be recognized during the vehicle entry process, further improving the license plate recognition accuracy.

[0053] In one embodiment, obtaining the target video clip corresponding to the parking space area from the video data according to the type of state change in the parking space area and the trigger time point of the license plate recognition event includes: if the type of state change in the parking space area is vehicle exit, obtaining, from the video data, the video clip corresponding to a preset time period after the trigger time point of the license plate recognition event as the target video clip corresponding to the parking space area.

[0054] Specifically, the types of state changes in the parking space area include vehicle entry and vehicle exit. If the type of state change in the parking space area is vehicle exit, the computer device can obtain, from the video data, the video clip corresponding to a preset time period after the trigger time point of the license plate recognition event as the target video clip corresponding to the parking space area.

[0055] For example, if the type of state change in the parking space area is vehicle exit, the computer device can obtain, from the video data, the video clip of the 1 minute after the trigger time point of the license plate recognition event, and use the video clip of this 1 minute during the process of the vehicle driving out of the parking space area as the target video clip corresponding to the parking space area.

[0056] In the above embodiments, in the case of vehicle exit, by using the video clip corresponding to a preset time period after the trigger time point of the license plate recognition event in the video data as the target video clip corresponding to the parking space area, the license plate of the vehicle can be recognized during the vehicle exit process, further improving the license plate recognition accuracy.

[0057] In one embodiment, the method further includes the step of detecting whether the parking space state of each of at least one parking space area has changed based on video data; detecting whether the parking space state of each of at least one parking space area has changed based on video data includes: for each parking space area, performing vehicle recognition on the parking space area based on the video frame sequence in the video data; if it is recognized that there is a change from no vehicle to a vehicle or from a vehicle to no vehicle in the parking space area, it is determined that the parking space state of the parking space area has changed, otherwise, it is determined that the parking space state of the parking space area has not changed.

[0058] Specifically, the video data consists of a video frame sequence including multiple video frames. For each parking space area, the computer device can perform vehicle recognition on the parking space area of each video frame in the video frame sequence one by one. If it is recognized that there is a change from no vehicle to a vehicle or from a vehicle to no vehicle in the parking space area, it can be determined that the parking space state of the parking space area has changed, otherwise, it is determined that the parking space state of the parking space area has not changed. It can be understood that if it is recognized that there is a change from no vehicle to a vehicle in the parking space area, the computer device can determine the type of state change of the parking space area as vehicle entry. If it is recognized that there is a change from a vehicle to no vehicle in the parking space area, the computer device can determine the type of state change of the parking space area as vehicle departure.

[0059] In the above embodiment, by performing vehicle recognition on the parking space area through the video frame sequence in the video data, and by identifying the change situation of whether there is a vehicle in the parking space area to determine whether the parking space state of the parking space area has changed, the accuracy rate of parking space state judgment can be improved.

[0060] In one embodiment, based on the target video segment, identifying the license plate number of the target vehicle that causes the parking space state of the parking space area to change includes: splitting the target video segment to obtain a sub-segment sequence composed of multiple video sub-segments; sequentially loading the multiple video sub-segments in the sub-segment sequence into the memory for decoding and frame extraction; for each video sub-segment, sequentially pushing each video frame in the video frame sequence obtained by decoding and frame extraction of the video sub-segment into a buffer queue with a buffer capacity of two frames and performing sequential recognition to determine the license plate number of the target vehicle that causes the parking space state of the parking space area to change.

[0061] Specifically, the computer device can segment the target video clip to obtain a sub-clip sequence composed of multiple video sub-clips, and sequentially load the multiple video sub-clips in the sub-clip sequence into the memory for decoding and frame extraction. It can be understood that during the decoding and frame extraction process, only one video sub-clip exists in the memory. After the decoding and frame extraction of this video sub-clip is completed, the next video sub-clip of this video sub-clip is loaded into the memory for decoding and frame extraction. For each video sub-clip, the computer device can sequentially push each video frame in the video frame sequence obtained by decoding and frame extraction of this video sub-clip into a buffer queue with a buffer capacity of two frames, and consume the video frames in order, that is, use the license plate recognition algorithm and the target tracking algorithm to recognize the license plate number of the target vehicle that changes the parking space state in the parking space area. Among them, the target tracking algorithm is to find the vehicle entering or leaving the parking space area. It can be understood that after the first video frame in the buffer queue is consumed, the next video frame is continuously pushed into the buffer queue, and the second video frame in the buffer queue is continuously consumed. The whole process is repeated until all the multiple video sub-clips in the target video clip are processed.

[0062] In the above embodiment, by segmenting the target video clip into multiple video sub-clips and sequentially loading them into the memory for decoding and frame extraction, and then sequentially pushing each video frame obtained by decoding and frame extraction into a buffer queue with a buffer capacity of two frames and recognizing them in order, the memory occupied during the license plate recognition process can be reduced, the license plate video efficiency can be improved, and the accuracy of license plate recognition can be further improved.

[0063] In one embodiment, it is applied to an edge computing device installed on a roadside lamp post; a low-position camera is installed in the low-position area of the roadside lamp post; the parking space area is a roadside parking space area; the roadside parking space area is the area where the roadside parking spaces are located on the side of the road where the roadside lamp post is located.

[0064] In one embodiment, the license plate recognition method of the present application can be applied to an edge computing device installed on a roadside lamp post. It can be understood that the computer device mentioned in the present application is an edge computing device. Specifically, the edge computing device can obtain video data collected for at least one roadside parking space area within the field of view of the low-position camera. For each roadside parking space area, if it is detected based on the video data that the parking space state of this roadside parking space area has changed, the edge computing device triggers a license plate recognition event for this roadside parking space area, and according to the type of state change of this roadside parking space area and the trigger time point of the license plate recognition event, obtains the target video clip corresponding to this roadside parking space area from the video data. Furthermore, the edge computing device can recognize the license plate number of the target vehicle that changes the parking space state of this roadside parking space area based on the target video clip.

[0065] In one embodiment, the trigger time points of license plate recognition events may include the vehicle entry time and the vehicle departure time. The vehicle entry time refers to the time when the vehicle drives into the roadside parking space area, and the vehicle departure time refers to the time when the vehicle drives out of the roadside parking space area. The edge computing device may upload data such as the vehicle entry time, the vehicle departure time, and the license plate number to the cloud server. The cloud server may store, process, and analyze the received data such as the vehicle entry time, the vehicle departure time, and the license plate number, and provide services such as parking fee calculation and data analysis.

[0066] In one embodiment, as Figure 2 shown, an edge computing device and two low-position cameras are installed on the roadside lamp post. These two low-position cameras can respectively collect video data for at least one roadside parking space area within their respective fields of view, and send the collected video data to the edge computing device. If the status change type of the roadside parking space area is vehicle entry, the edge computing device can obtain the video clip of the previous 1 minute before the trigger time point of the license plate recognition event from the video data, and use the 1-minute video clip of the vehicle driving into this roadside parking space area as the target video clip corresponding to the roadside parking space area. Furthermore, the edge computing device can identify the license plate number of the target vehicle that changes the parking space status of this roadside parking space area based on the target video clip. It can be understood that usually, the license plate number of the target vehicle can be identified at position 2.

[0067] In the above embodiment, by applying the license plate recognition method of the present application to the license plate recognition scenario of roadside parking, the license plate recognition accuracy in the roadside parking scenario can be improved on the premise of cost savings.

[0068] It should be understood that although the steps in the flowcharts of the above embodiments are shown in sequence, these steps are not necessarily executed in sequence. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0069] In one embodiment, as Figure 3 shown, a license plate recognition device 300 is provided. The device specifically includes:

[0070] An acquisition module, configured to acquire video data collected for at least one parking space area within the field of view of a low-position camera;

[0071] A triggering module, configured to, for each parking space area, trigger a license plate recognition event for the parking space area if it is detected based on video data that the parking space status of the parking space area has changed;

[0072] The obtaining module is further configured to obtain, from the video data, a target video segment corresponding to the parking space area according to the type of status change of the parking space area and the triggering time point of the license plate recognition event;

[0073] An identification module, configured to identify the license plate number of the target vehicle that causes the parking space status of the parking space area to change based on the target video segment.

[0074] In one embodiment, the obtaining module is further configured to, if the type of status change of the parking space area is vehicle entry, obtain, from the video data, a video segment corresponding to a preset time period before the triggering time point of the license plate recognition event as the target video segment corresponding to the parking space area.

[0075] In one embodiment, the obtaining module is further configured to, if the type of status change of the parking space area is vehicle departure, obtain, from the video data, a video segment corresponding to a preset time period after the triggering time point of the license plate recognition event as the target video segment corresponding to the parking space area.

[0076] In one embodiment, the device further includes:

[0077] A detection module, configured to, for each parking space area, perform vehicle recognition on the parking space area based on the video frame sequence in the video data; if it is recognized that there is no vehicle to having a vehicle or from having a vehicle to having no vehicle in the parking space area, it is determined that the parking space status of the parking space area has changed, otherwise, it is determined that the parking space status of the parking space area has not changed.

[0078] In one embodiment, the identification module is further configured to segment the target video segment to obtain a sub-segment sequence composed of multiple video sub-segments; sequentially load the multiple video sub-segments in the sub-segment sequence into the memory for decoding and frame extraction; for each video sub-segment, sequentially push each video frame in the video frame sequence obtained by decoding and frame extraction of the video sub-segment into a buffer queue with a buffer capacity of two frames and perform sequential identification to determine the license plate number of the target vehicle that causes the parking space status of the parking space area to change.

[0079] In one embodiment, it is applied to an edge computing device installed on a roadside lamp post; a low-position camera is installed in the low-position area of the roadside lamp post; the parking space area is a roadside parking space area; the roadside parking space area is the area where the roadside parking spaces are located on the side of the road where the roadside lamp post is located.

[0080] The above license plate recognition device obtains video data collected for at least one parking space area within the field of view of a low-position camera; for each parking space area, if it is detected based on the video data that the parking space status of the parking space area changes, a license plate recognition event for the parking space area is triggered; according to the type of status change of the parking space area and the trigger time point of the license plate recognition event, the target video segment corresponding to the parking space area is obtained from the video data; based on the target video segment, the license plate number of the target vehicle that causes the parking space status of the parking space area to change is recognized. Compared with the traditional license plate recognition method, in this application, the video data of the parking space area is collected by a low-position camera installed at a low position. When it is detected based on the video data that the parking space status of the parking space area changes, that is, when a vehicle enters or exits the parking space, a license plate recognition event is triggered, and then based on the video segment in the time period before or after the trigger of the license plate recognition event, that is, the video backtracking during the vehicle's entry into the parking space or during the vehicle's exit from the parking space, the license plate number of the vehicle is recognized. The low-position camera is installed at a low position, which is convenient for installation and later maintenance, and the installation and maintenance costs are relatively low. It can also effectively avoid the occlusion of the monitoring line of sight by obstacles such as trees and buildings. Moreover, by recognizing the license plate number of the vehicle through the video backtracking during the vehicle's entry into the parking space or during the vehicle's exit from the parking space, the license plate recognition accuracy can be improved on the premise of cost savings.

[0081] Each module in the above license plate recognition device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in the form of hardware or be independent of it, or can be stored in the memory of the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above modules.

[0082] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, a license plate recognition method is implemented.

[0083] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in Figure 5 . The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. The computer program, when executed by the processor, implements a license plate recognition method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0084] Those skilled in the art can understand that Figure 4 and Figure 5 the structures shown in are only block diagrams of some structures related to the solution of this application, and do not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0085] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0086] In one embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0087] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0088] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0089] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0090] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0091] The above-described embodiments merely represent several implementation manners of this application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of the patent of this application should be subject to the appended claims.

Claims

1. A license plate recognition method, characterized in that, The method includes: Obtaining video data collected for at least one parking space area within the field of view of a low-position camera; For each of the parking space areas, if it is detected based on the video data that the parking state of the parking space area changes, triggering a license plate recognition event for the parking space area; According to the type of state change of the parking space area and the trigger time point of the license plate recognition event, obtaining a target video segment corresponding to the parking space area from the video data; Based on the target video segment, recognizing the license plate number of the target vehicle that causes the parking state of the parking space area to change.

2. The method according to claim 1, characterized in that, The obtaining a target video segment corresponding to the parking space area from the video data according to the type of state change of the parking space area and the trigger time point of the license plate recognition event includes: If the type of state change of the parking space area is vehicle entry, obtaining a video segment corresponding to a preset time period before the trigger time point of the license plate recognition event from the video data as the target video segment corresponding to the parking space area.

3. The method according to claim 1, wherein The obtaining a target video segment corresponding to the parking space area from the video data according to the type of state change of the parking space area and the trigger time point of the license plate recognition event includes: If the type of state change of the parking space area is vehicle departure, obtaining a video segment corresponding to a preset time period after the trigger time point of the license plate recognition event from the video data as the target video segment corresponding to the parking space area.

4. The method according to claim 1, wherein The method further includes the step of detecting whether the parking state of each of the at least one parking space area changes based on the video data; The detecting whether the parking state of each of the at least one parking space area changes based on the video data includes: For each of the parking space areas, performing vehicle recognition on the parking space area based on the video frame sequence in the video data; If it is recognized that there is a change from no vehicle to a vehicle or from a vehicle to no vehicle in the parking space area, determining that the parking state of the parking space area changes; otherwise, determining that the parking state of the parking space area does not change.

5. The method according to claim 1, wherein The recognizing the license plate number of the target vehicle that causes the parking state of the parking space area to change based on the target video segment includes: Segmenting the target video segment to obtain a sub-segment sequence composed of a plurality of video sub-segments; Successively loading the plurality of video sub-segments in the sub-segment sequence into the memory for decoding and frame extraction; For each of the video sub-segments, successively pushing each video frame in the video frame sequence obtained by decoding and frame extraction of the video sub-segment into a buffer queue with a buffer capacity of two frames and sequentially recognizing to determine the license plate number of the target vehicle that causes the parking state of the parking space area to change.

6. The method according to any one of claims 1 to 5, characterized in that, Applied to an edge computing device installed on a roadside lamp post; the low-position camera is installed in the low-position area of the roadside lamp post; The parking space area is a roadside parking space area; The roadside parking space area is the area where the roadside parking spaces are located on the side of the road where the roadside lamp post is located.

7. A license plate recognition device, characterized in that, The device includes: An acquisition module, configured to acquire video data collected for at least one parking space area within the field of view of a low-position camera; A triggering module, configured to, for each of the parking space areas, if it is detected based on the video data that the parking space state of the parking space area changes, trigger a license plate recognition event for the parking space area; The acquisition module is further configured to obtain a target video segment corresponding to the parking space area from the video data according to the type of change in the state of the parking space area and the trigger time point of the license plate recognition event; An identification module, configured to identify the license plate number of a target vehicle that causes the parking space state of the parking space area to change based on the target video segment.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 6 are implemented.

10. A computer program product, comprising 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 6 are implemented.

Images