Inspection vehicle parking space positioning system and method based on deep learning

Abstract

The present invention discloses a parking space positioning system and method for patrol vehicles based on deep learning, which relates to the field of intelligent transportation technology. The system includes: an image acquisition module, which is designed to capture parking space images through a camera; a vehicle positioning module, which is designed to obtain positioning information of the video patrol vehicle through a GPS positioning device; a data processing module, which is designed to pre-process the parking space image and analyze the image data according to the image algorithm; a mobile communication module, which is designed to transmit license plate and parking space information to the operation management platform through mobile communication technology, and add a deep learning solution to improve the recognition accuracy and speed of the OCR text recognition algorithm. According to the technical solution of this application, the function of quickly identifying vehicle license plate information and matching parking spaces in parking fee scenarios can be realized, which has high application value.

Description

[0001] This application is a divisional application of the Chinese invention patent application with the application date of "2024.09.26", application number "202411349564.6", and invention name "A parking space positioning system and method for inspection vehicles based on OCR". Technical Field

[0002] The present invention relates to the field of intelligent transportation technology, and in particular to a patrol vehicle parking space positioning system and method based on deep learning. Background Art

[0003] In recent years, the number of motor vehicles in my country has continued to grow, making cars an essential means of transportation for daily commutes. Parking has become an increasingly prominent issue. Finding a suitable parking space has become a particular headache for many drivers, especially in busy commercial areas, residential communities, and near public transportation hubs. To improve the utilization of on-street parking spaces, a number of intelligent road inspection vehicles have emerged, reducing manual intervention while improving the efficiency of road inspections. Video inspection vehicles capture on-street parking conditions and capture evidence of vehicles in parking spaces. Matching vehicles to corresponding parking spaces is a core function of video inspection vehicles and a crucial factor in their inspection accuracy. Currently, most existing parking space matching solutions utilize high-frequency, high-precision GPS devices. Based on real-time GPS data received by the GPS devices, static GPS latitude and longitude data for each parking space is pre-calibrated to achieve parking space matching. However, this solution still has some significant problems. Before the video inspection vehicle is put into use, the latitude and longitude data of each parking space's starting and ending points must be collected. This process is extremely labor-intensive and requires a huge amount of data. In environments with weak satellite positioning signals, such as tall buildings, trees, and signal shielding, inaccurate GPS positioning can cause discrepancies between the pre-calibrated latitude and longitude data of parking spaces and the actual latitude and longitude data of parking spaces, thus affecting the normal operation of the video inspection vehicle. Therefore, the development of a simple and efficient parking space positioning method for inspection vehicles is urgent.

[0004] Most of the existing methods for patrol car parking space positioning currently have defects in some aspects. For example, the solution of NB geomagnetism combined with video patrol car, although the device layout is convenient and has the advantages of high precision and low false alarm rate, the dual-mode geomagnetism has insufficient performance stability in special weather environments, and the three-mode geomagnetism has the problem of high cost; the SLAM solution, although it can estimate the posture of the moving vehicle in real time and build a map of the surrounding environment, but the visual SLAM cannot work in dark or textureless areas, and the application scenarios of laser SLAM are relatively limited. Therefore, based on this problem, this application proposes a patrol car parking space positioning system and method based on OCR. Summary of the Invention

[0005] Technical Purpose

[0006] In order to solve the above problems, the purpose of the present invention is to provide a patrol vehicle parking positioning system and method based on OCR, which not only solves the time-consuming and labor-intensive problem of manually collecting berth longitude and latitude data in the traditional berth positioning process, but also avoids the occurrence of inaccurate longitude and latitude data due to human factors, realizes the simplification and automation of berth positioning, significantly improves the inspection accuracy of video patrol vehicles and their adaptability to different scenarios, and avoids the application obstacles of video patrol vehicles caused by objective factors such as satellite positioning.

[0007] Technical Solution

[0008] To achieve the above objectives, the present invention provides an OCR-based inspection vehicle parking space positioning system and method, which uses image segmentation and OCR text recognition algorithms to identify parking space numbers sprayed on the ground, thereby achieving accurate matching of on-street parking spaces.

[0009] In a first aspect, the present invention provides an OCR-based parking space positioning system for patrol vehicles, comprising:

[0010] An image acquisition module, which acquires a parking space image through a camera, wherein the parking space image includes a vehicle license plate number and a parking space number;

[0011] Vehicle positioning module, which obtains the positioning information of the video inspection vehicle through GPS positioning equipment;

[0012] a data processing module that pre-processes the parking space image and analyzes the image data according to an image algorithm to obtain license plate information and parking space information, and determines the parking space corresponding to the captured image based on the time of the image frame, the time corresponding to the license plate capture, and the position of the parking space number in the image; wherein the image algorithm includes an OCR text recognition algorithm;

[0013] The mobile communication module transmits license plate and parking space information to the operation management platform through mobile communication technology.

[0014] Furthermore, the vehicle's license plate number is captured and identified in real time by an intelligent license plate recognition camera installed on the vehicle inspection vehicle; the berth number is captured and identified in real time by a special camera installed on the vehicle inspection vehicle for collecting a clear berth number video stream; the intelligent license plate recognition camera and the special camera are installed at the front end of the video inspection vehicle according to the relative positions of the vehicle's license plate and the berth number.

[0015] Furthermore, after receiving the video stream captured by the berth number acquisition camera, the data processing module obtains the berth number data through its built-in OCR text recognition algorithm. This algorithm pre-processes the image frames in the video stream, segments the berth number characters in the image frames, and recognizes the content of the berth number characters, thereby obtaining the berth number data. This not only solves the time-consuming and labor-intensive problem of manually collecting berth longitude and latitude data during traditional berth positioning, but also avoids the occurrence of inaccurate longitude and latitude data due to human factors, simplifies and automates berth positioning, significantly improves the inspection accuracy of video inspection vehicles and their adaptability to different scenarios, and avoids the application barriers of video inspection vehicles caused by objective factors such as satellite positioning.

[0016] Furthermore, the data processing module preprocesses the picture frames in the video stream, specifically including: marking text areas, determining the location of the text in each document by marking the text areas of the collected sample data, thereby building a model to learn the spatial structure of the text and improve the accuracy of text recognition; extracting text content, extracting the text content in the marked text area and establishing label data corresponding to the text content for supervised learning; data cleaning and preprocessing, cleaning and preprocessing the extracted text content, including removing noise, adjusting size and direction, etc., to ensure the quality of the text data.

[0017] Furthermore, the OCR text recognition algorithm supports multiple models, including traditional template matching algorithms, support vector machines, Bayesian classification algorithms, and neural network models based on deep learning, etc. It can select appropriate models for training according to specific application scenarios and needs; after the model training is completed, the data processing module improves the accuracy of the OCR text recognition algorithm through data set optimization, feature selection, and model structure optimization, among which data set optimization specifically uses a more accurate and comprehensive data set for training, and optimizes the data set by increasing the sample size, deleting duplicate samples, increasing randomness, etc.; feature selection specifically selects the most important features for the recognition task and reduces unnecessary features, thereby speeding up the response speed of the OCR system. The selection of relevant features is based on feature evaluation methods, such as information gain, correlation coefficient, etc.

[0018] Furthermore, the data processing module improves the accuracy and speed of the OCR text recognition algorithm based on a deep learning approach. This approach uses a convolutional neural network as its underlying model and continuously improves the OCR text recognition algorithm's recognition capabilities through the increasing amount of training data. The deep learning approach includes steps such as data preprocessing, building a convolutional neural network model, calculating a loss function, backpropagation and optimization, and regularization. This approach can help the OCR system better handle text in complex environments, improve the OCR system's accuracy in text recognition under non-ideal conditions, significantly speed up the model's computational speed, and reduce the need for manual feature engineering by automatically learning features from images, thereby simplifying the development process.

[0019] Furthermore, the berth numbering is based on a custom OCR system-specific numbering standard. This standard includes the font, size, and color of the berth number, thereby improving the applicability of the berth number OCR algorithm. This helps the OCR system recognize berth numbers more accurately, reduces the time required for the OCR algorithm to process images, enables the OCR system to more easily adapt to different environmental conditions, and improves the OCR system's recognition capabilities in diverse scenarios.

[0020] Furthermore, the data processing module determines whether the berth information of the current berth is correct by comprehensively comparing the berth information of the previous berth and the positioning information of the video inspection vehicle with the berth information of the current berth and the positioning information of the video inspection vehicle. For example, if the berth number of the previous berth is 00050, and the physical distance between the positioning of the video inspection vehicle of the previous berth and the positioning of the video inspection vehicle of the current berth is only 6 meters, but the berth number of the current berth is calculated to be 00031, then it is determined that the berth number of the current berth may not be correctly identified. In this case, the berth number of the current berth can be correctly identified according to the berth number. The berth information of the next berth and the positioning information of the video inspection vehicle are comprehensively verified. If the video inspection vehicle recognizes the number of the next berth as 00052 after moving only about 6 meters, it can be basically concluded that the actual number of this berth should be 00051. The reason for failing to correctly identify the berth number of this berth may be that the berth number is blocked, contaminated, or damaged. Similar abnormal situations can be submitted to the operation management platform for subsequent processing, and the image algorithm can be assisted from multiple angles to judge the license plate information and berth information, thereby improving the recognition and positioning accuracy and improving the operation management efficiency.

[0021] Furthermore, the mobile communication module establishes a parking space geographic information database based on a geographic information solution, which displays the location distribution of parking spaces in the form of a map. This includes: matching data recognized by the OCR system with geographic information in the geographic information solution database, which should contain information such as the geographic coordinates, location, and type of parking spaces; combining real-time collected data with the geographic information solution, performing spatial analysis and processing, and utilizing the geographic information solution to monitor and manage vehicle location and parking status in real time; and displaying parking status, vehicle location, and related statistical information through a map view. By monitoring on-street parking status and nearby vehicle flow in real time, the system can quickly respond to parking issues, more effectively allocate and manage parking resources, provide drivers with fast and accurate parking information, and reduce the time drivers spend searching for parking spaces.

[0022] In a second aspect, the present invention further provides a method for locating parking spaces for patrol vehicles based on OCR. The method is based on the system described in the first aspect, and includes:

[0023] The berth image is obtained through the camera installed on the video inspection vehicle;

[0024] Get the positioning information of the video inspection vehicle through GPS positioning equipment;

[0025] Preprocess the berth image and analyze the image data according to the image algorithm;

[0026] Output license plate and parking space information through mobile communication technology.

[0027] In a third aspect, the present invention further 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 aforementioned OCR-based inspection vehicle parking space positioning method is implemented.

[0028] The present invention uses image segmentation and an OCR text recognition algorithm to identify berth space numbers painted on the ground. The berth space numbers are painted based on a custom OCR system-specific numbering standard. A parking space geographic information database is established based on a geographic information solution, displaying the location distribution of parking spaces in the form of a map. The recognition accuracy and speed of the OCR text recognition algorithm are improved based on a deep learning solution. This system and method not only solves the time-consuming and labor-intensive problem of manually collecting berth longitude and latitude data during traditional berth location, but also avoids the occurrence of inaccurate longitude and latitude data due to human factors, achieving simplified and automated berth location. This significantly improves the inspection accuracy of video inspection vehicles and their adaptability to different scenarios, avoiding application barriers to video inspection vehicles due to objective factors such as satellite positioning.

[0029] Beneficial effects

[0030] By implementing the OCR-based inspection vehicle parking space positioning system and method provided by the present invention, the following technical effects are achieved:

[0031] (1) The present invention identifies the berth number sprayed on the ground through image segmentation and OCR text recognition algorithm; it not only solves the time-consuming and labor-intensive problem of manually collecting berth longitude and latitude data in the traditional berth positioning process, but also avoids the occurrence of inaccurate longitude and latitude data due to human factors, realizes the simplification and automation of berth positioning, significantly improves the inspection accuracy of the video inspection vehicle and its adaptability to different scenarios, and avoids the application obstacles of the video inspection vehicle caused by objective factors such as satellite positioning.

[0032] (2) The spraying of berth numbers in the present invention is based on a customized number spraying standard dedicated to the OCR system; this helps the OCR system to more accurately identify berth numbers, reduces the time required for the OCR algorithm to process images, enables the OCR system to more easily adapt to different environmental conditions, and improves the recognition ability of the OCR system in diverse scenarios.

[0033] (3) The present invention establishes a parking space geographic information database based on a geographic information solution, and displays the location distribution of parking spaces in the form of a map; it quickly responds to parking problems by monitoring the status of on-street parking spaces and the flow of nearby vehicles in real time, and can more effectively allocate and manage parking space resources, provide drivers with fast and accurate parking space information, and reduce the time drivers spend looking for parking spaces.

[0034] (4) The present invention improves the recognition accuracy and speed of the OCR text recognition algorithm based on a deep learning solution, and adopts a convolutional neural network as the basic model; it can help the OCR system better process text in complex environments, improve the OCR system's recognition accuracy for text under non-ideal conditions, significantly speed up the model's operation speed, and reduce the need for manual feature engineering by automatically learning features in the image, thereby simplifying the development process. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to make the above-mentioned OCR-based inspection vehicle parking space positioning system and method of the present invention more obvious and easy to understand, the following is a brief introduction to the drawings required for use in the specific implementation of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0036] Figure 1 A schematic diagram showing the principle of the inspection vehicle parking positioning system;

[0037] Figure 2 A schematic diagram showing the location of cameras collecting berth numbers;

[0038] Figure 3 Schematic diagram showing the standard for spraying berth numbers;

[0039] Figure 4 A schematic diagram showing the effect of the OCR text recognition algorithm;

[0040] Figure 5 A schematic diagram showing the effect of the geographic information solution. DETAILED DESCRIPTION

[0041] Example 1:

[0042] Provides an OCR-based inspection vehicle parking space positioning system, such as Figure 1 As shown in the figure, the inspection vehicle is equipped with a GPS receiver to receive signals from satellites, which include timestamps and satellite position information. The base station is a fixed GPS receiver with a known location. The base station receives the same satellite signals and sends the received data to the inspection vehicle via radio broadcast. The radio acts as a communication medium, transmitting the correction information received by the base station to the inspection vehicle in real time. After receiving the correction information broadcast by the base station, the PTK positioning module on the inspection vehicle uses this information to correct the original GPS signal to eliminate or reduce satellite signal errors, such as ionospheric delay and tropospheric delay. After PTK processing, the inspection vehicle can obtain higher positioning accuracy than using GPS alone. The inspection vehicle integrates the precise position information obtained by the PTK positioning module with other sensor data to achieve more accurate parking space positioning. Finally, the inspection vehicle transmits the positioning information, as well as license plate and parking space information, to the operation management platform through the mobile communication module for final processing and analysis. The system includes: an image acquisition module, which is designed to obtain a parking space image through a camera, wherein the parking space image includes the vehicle's license plate number and parking space number; a vehicle positioning module, which is designed to obtain the positioning information of the video inspection vehicle through a GPS positioning device; a data processing module, which is designed to pre-process the parking space image and analyze the image data according to an image algorithm to obtain license plate information and parking space information, and judge the parking space corresponding to the captured image by the time of the picture frame, the time corresponding to the license plate shooting, and the position of the parking space number in the image, wherein the image algorithm includes an OCR text recognition algorithm; a mobile communication module, which is designed to transmit the license plate and parking space information to the operation management platform through mobile communication technology.

[0043] The OCR-based inspection vehicle parking space positioning system provided by the present invention specifically includes:

[0044] The vehicle's license plate number is captured and identified in real time by an intelligent license plate recognition camera installed on the vehicle inspection vehicle; the berth number is captured and identified in real time by a special camera installed on the vehicle inspection vehicle for collecting a clear berth number video stream; the intelligent license plate recognition camera and the special camera are installed at the front end of the video inspection vehicle according to the relative positions of the vehicle's license plate and the berth number.

[0045] After receiving the video stream captured by the berth number acquisition camera, the data processing module obtains the berth number data through the built-in OCR text recognition algorithm of the data processing module. It pre-processes the picture frames in the video stream, segments the berth number characters in the picture frames, and recognizes the content of the berth number characters, thereby obtaining the berth number data. The position of the berth number acquisition camera is as follows: Figure 2 shown.

[0046] The data processing module preprocesses the picture frames in the video stream, specifically including: marking text areas, determining the location of the text in each document by marking the text areas of the collected sample data, thereby building a model to learn the spatial structure of the text and improve the accuracy of text recognition; extracting text content, extracting the text content in the marked text area and establishing label data corresponding to the text content for supervised learning; data cleaning and preprocessing, cleaning and preprocessing the extracted text content, including removing noise, adjusting size and direction, etc., to ensure the quality of the text data.

[0047] The OCR text recognition algorithm supports multiple models, including traditional template matching algorithms, support vector machines, Bayesian classification algorithms, and neural network models based on deep learning, etc. It can select appropriate models for training according to specific application scenarios and needs; after the model training is completed, the data processing module improves the accuracy of the OCR text recognition algorithm through data set optimization, feature selection, and model structure optimization, among which data set optimization specifically uses a more accurate and comprehensive data set for training, and optimizes the data set by increasing the sample size, deleting duplicate samples, increasing randomness, etc.; feature selection specifically selects the most important features for the recognition task and reduces unnecessary features, thereby speeding up the response speed of the OCR system. The selection of relevant features is based on feature evaluation methods, such as information gain, correlation coefficient, etc.

[0048] The berth number is sprayed based on a custom OCR system-specific number spraying standard, which involves the font, size and color of the berth number to improve the applicability of the berth number OCR algorithm. Figure 3 As shown, the effect of the OCR text recognition algorithm is as follows Figure 4 shown.

[0049] The data processing module determines whether the berth information of the current berth is correct by comprehensively comparing the berth information of the previous berth and the positioning information of the video inspection vehicle with the berth information of the current berth and the positioning information of the video inspection vehicle. For example, if the berth number of the previous berth is 00050, and the physical distance between the positioning information of the video inspection vehicle of the previous berth and the positioning information of the video inspection vehicle of the current berth is only 6 meters, but the berth number of the current berth is 00031, then it is determined that the berth number of the current berth may not be correctly identified. In this case, the berth number of the current berth can be correctly identified according to the positioning information of the next berth. The berth information of the berth and the positioning information of the video inspection vehicle are comprehensively verified. If the video inspection vehicle recognizes the next berth as 00052 after moving only about 6 meters, it can be basically concluded that the actual number of this berth should be 00051. The reason for failing to correctly identify the berth number of this berth may be that the berth number is blocked, contaminated, or damaged. Similar abnormal situations can be submitted to the operation management platform for subsequent processing, which assists the image algorithm in judging the license plate information and berth information from multiple angles, improves the recognition and positioning accuracy, and improves the operation management efficiency.

[0050] The mobile communication module establishes a parking space geographic information database based on the geographic information solution, which displays the location distribution map of parking spaces in the form of a map, including: matching the data recognized by the OCR system with the geographic information in the geographic information solution database, which should contain the geographic coordinates, belonging area, type and other information of the parking space; combining the real-time collected data with the geographic information solution, and performing spatial analysis and processing, using the geographic information solution to monitor and manage the vehicle position and parking space status in real time; displaying the parking space status, vehicle position and related statistical information through a map view. The effect of the geographic information solution is as follows: Figure 5 shown.

[0051] Example 2:

[0052] On the basis of the above embodiment, a deep learning solution is added to improve the recognition accuracy and speed of the OCR text recognition algorithm. The convolutional neural network is used as the basic model, and the recognition ability of the OCR text recognition algorithm is continuously improved by increasing the amount of training data.

[0053] Among them, it is necessary to pre-process the data in advance and normalize the image data to a uniform range, such as or , ;

[0054] in, Represents the original image pixel value; Indicates the minimum value of the image pixel value, usually 0; Indicates the maximum value of the image pixel value, usually 255; Represents the normalized pixel value, ranging from 0 to 1.

[0055] Building a convolutional neural network involves:

[0056] Apply multiple convolution kernels in the convolution layer to extract image features:

[0057]

[0058] in, Represents the convolution kernel Output; Represents the weight of the convolution kernel; Represents the pixel value of the input image; Indicates bias; Represents the total number of convolution kernels;

[0059] use As a non-linear activation function:

[0060]

[0061] By using max pooling to reduce the dimensionality of the feature map:

[0062]

[0063] in, Represents an element on the feature map output by the pooling layer; Represents the elements on the input feature map, and Defines the position within the pooling window;

[0064] Flatten the feature map and connect it to the output layer:

[0065]

[0066] in, Indicates the The output of a neuron; represents weight; Represents input features; represents the bias term of the fully connected layer; Indicates the length of the input feature vector.

[0067] Loss function for multi-classification problems:

[0068]

[0069] in, Represents the value of the loss function, which measures the difference between the model prediction and the true label; represents the encoding of the true label; represents the probability distribution predicted by the model; Indicates the total number of categories.

[0070] Calculate the gradient of the loss function with respect to the model parameters:

[0071]

[0072] in, Represents the loss function with respect to weights gradient; Represents the loss function with respect to the fully connected layer output gradient; Represents the activation function with respect to its input gradient; Represents the fully connected layer input About weight gradient;

[0073] And update the model parameters using gradient descent:

[0074]

[0075] in, represents the learning rate; Represents the weight in the next iteration; Represents the weight in the current iteration.

[0076] Prevent overfitting through L2 regularization:

[0077]

[0078] in, Represents the regularization coefficient, which controls the strength of the regularization term.

[0079] For example, there is a dataset containing 1000 pictures of parking lot numbers, each picture is of size Pixels, the picture is grayscale, the picture has been preprocessed and normalized to Range, berth number has 10 possible digits, from 0 to 9;

[0080] Suppose there is a berth number map , whose pixel values ​​range from 0 to 255, normalize them to scope:

[0081]

[0082] Build a convolutional neural network model, including:

[0083] Convolution layer: 32 convolution kernels, size , using ReLU activation function;

[0084] Pooling layer: maximum pooling, window size is ;

[0085] Fully connected layer: 128 neurons, also using ReLU activation function;

[0086] Output layer: 10 neurons, corresponding to 10 digital categories;

[0087] Using the cross entropy loss function, assuming the true label is , the model predicts :

[0088]

[0089] Assuming a learning rate of 0.01, after one forward propagation and loss calculation, the gradient is calculated and the weights are updated:

[0090]

[0091]

[0092] L2 regularization is used with a regularization coefficient of 0.001:

[0093]

[0094]

[0095] The effect of the deep learning solution is shown in Table 1:

[0096] Table 1. Summary of deep learning solution effects

[0097] Training cycle Training loss Training accuracy Validation loss Verification accuracy 1 2.30 0.20 2.35 0.18 2 1.50 0.45 1.60 0.40 3 1.10 0.60 1.25 0.55 4 0.90 0.70 1.10 0.60 5 0.75 0.75 0.95 0.65 6 0.65 0.80 0.85 0.70 7 0.55 0.85 0.75 0.75

[0098] As shown in the table, as training progresses, the training loss gradually decreases and the training accuracy gradually increases, indicating that the model's performance on the training data is improving. At the same time, the validation loss and validation accuracy also show that the model's performance on unseen data is improving, but the improvement is not as large as that on the training set.

[0099] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media containing computer-usable program code.

[0100] The present invention can provide computer program instructions to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce means for implementing the system.

[0101] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device that implements the functions of the system.

[0102] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions of the described system.

Claims

1. Inspection vehicle parking space positioning system, characterized by: include: An image acquisition module is designed to acquire a parking space image through a camera, wherein the parking space image includes a vehicle license plate number and a parking space number; The vehicle positioning module is designed to obtain the positioning information of the video inspection vehicle through the GPS positioning device; a data processing module, designed to pre-process the parking space image and analyze the image data according to an image algorithm to obtain license plate information and parking space information, and to determine the parking space corresponding to the captured image based on the time of the image frame, the time corresponding to the license plate capture, and the position of the parking space number in the image; wherein the image algorithm includes an OCR text recognition algorithm; The mobile communication module is designed to transmit license plate and parking space information to the operation management platform via mobile communication technology; The system adds a deep learning solution to improve the recognition accuracy and speed of the OCR text recognition algorithm. It uses a convolutional neural network as the basic model and continuously improves the recognition ability of the OCR text recognition algorithm through the continuous increase of training data; After receiving the video stream captured by the berth number acquisition camera, the data processing module obtains the berth number data through the OCR text recognition algorithm built into the data processing module. The OCR algorithm pre-processes the picture frames in the video stream, segments the berth number characters in the picture frames, and recognizes the content of the berth number characters, thereby obtaining the berth number data. The data processing module pre-processes the frames in the video stream, specifically including: marking text areas, determining the location of text in each image by marking text areas in the collected sample data; extracting text content, extracting text content in the marked text areas and establishing label data corresponding to the text content; data cleaning and pre-processing, cleaning and pre-processing the extracted text content, including removing noise, adjusting size and orientation; The OCR text recognition algorithm supports multiple models, including traditional template matching algorithms, support vector machines, Bayesian classification algorithms, and neural network models based on deep learning. It can select the appropriate model for training based on specific application scenarios and needs. After model training is completed, the data processing module improves the accuracy of the OCR text recognition algorithm through data set optimization, feature selection, and model structure optimization. The data processing module determines whether the berth information of the current berth is correct by comprehensively comparing the berth information of the previous berth and the positioning information of the video inspection vehicle with the berth information of the current berth and the positioning information of the video inspection vehicle.

2. The parking space positioning system for patrol vehicles according to claim 1, characterized in that: The vehicle's license plate number is captured and identified in real time by an intelligent license plate recognition camera installed on the inspection vehicle; the berth number is captured and identified in real time by a special camera installed on the inspection vehicle for collecting a clear berth number video stream; the intelligent license plate recognition camera and the special camera are installed at the front end of the video inspection vehicle according to the relative positions of the vehicle's license plate and the berth number.

3. The parking space positioning system for patrol vehicles according to claim 1, characterized in that: The mobile communication module establishes a parking space geographic information database based on a geographic information solution, which displays the location distribution of parking spaces in the form of a map.

4. The parking space positioning system for patrol vehicles according to claim 1 is characterized in that Specifically include: Match the data identified by the OCR system with the geographic information in the geographic information solution database, which should contain the geographic coordinates, belonging area, and type information of the berth; Combine real-time collected data with geographic information solutions, perform spatial analysis and processing, and use geographic information solutions to monitor and manage vehicle locations and berth status in real time; display berth status, vehicle location, and related statistical information through map views.

5. A method for locating parking spaces for patrol vehicles, characterized by: The method is implemented based on the system according to any one of claims 1 to 4: The method comprises: The berth image is obtained through the camera installed on the video inspection vehicle; Get the positioning information of the video inspection vehicle through GPS positioning equipment; Preprocess the berth image and analyze the image data according to the image algorithm; Output license plate and parking space information through mobile communication technology.

6. A computer-readable storage medium storing a computer program, wherein: When the computer program is executed, the inspection vehicle parking space positioning method according to claim 5 is implemented.

Images