Vehicle information recording management method and system

Abstract

The invention provides a vehicle information recording management method and system, and relates to the technical field of vehicle management, and the method comprises the steps: obtaining a collection image of a monitored vehicle; obtaining vehicle characteristics of the monitored vehicle according to the collected image; obtaining a license plate contour of the monitored vehicle through an edge detection algorithm according to the vehicle characteristics; according to the license plate contour, processing the license plate contour through morphological operation to obtain an enhanced image of the license plate contour; according to the enhanced image of the license plate contour, dividing the enhanced image of the license plate contour into a non-occlusion area and an occlusion area through a deep learning model; repairing according to the non-occlusion area through the context information to obtain an occlusion image of the occlusion area; obtaining a license plate number of the monitored vehicle according to the image of the non-shielding area and the shielding image; and inputting the license plate number and the vehicle type of the monitored vehicle. According to the invention, through combination of an advanced image processing technology and a deep learning algorithm, rapid and accurate collection of vehicle information is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle management, and in particular to a vehicle information collection and management method and system. Background Art

[0002] Vehicle information plays an important role in vehicle monitoring and management. The acquisition of vehicle information, such as the license plate number and vehicle model, helps the vehicle management department to better manage the vehicle, so as to record and manage the vehicle's technical condition, insurance information and driver, thereby improving traffic safety and preventing traffic accidents.

[0003] At present, the traditional method of collecting vehicle information mainly relies on manual recognition and recording, but the efficiency of manual operation is relatively low, especially in areas with heavy traffic, it is difficult to quickly and accurately record the information of each vehicle. In addition, when the vehicle license plate is deliberately blocked or the image is unclear due to mud, insufficient light, camera angle and other problems, the difficulty of manual recognition is further increased, and the error rate also increases accordingly. Summary of the invention

[0004] The problem solved by the present invention is how to improve the efficiency and accuracy of vehicle information collection.

[0005] In order to solve the above problems, the present invention provides a vehicle information collection and management method, comprising: Acquire the collected image of the monitored vehicle; Obtaining vehicle features of the monitored vehicle according to the collected image, wherein the vehicle features include the model, length-to-width ratio, and color distribution of the monitored vehicle; According to the aspect ratio and the color distribution, the license plate outline of the monitored vehicle is obtained by an edge detection algorithm; According to the license plate contour, the license plate contour is processed by morphological operation to obtain an enhanced image of the license plate contour; According to the enhanced image of the license plate contour, dividing the enhanced image of the license plate contour into a non-occluded area and an occluded area through a deep learning model; Repairing the non-occluded area using the context information to obtain an occluded image of the occluded area; Obtaining the license plate number of the monitored vehicle according to the image of the non-blocked area and the blocked image; Enter the license plate number and vehicle model of the monitored vehicle.

[0006] Optionally, obtaining the vehicle characteristics of the monitored vehicle according to the collected image includes: Preprocessing the acquired image to obtain the processed acquired image; By using image processing technology, feature extraction is performed on the processed collected image to obtain the outline of the monitored vehicle, the outline of the window, the outline of the headlight and the outline of the wheel; Obtaining vehicle features according to the outline of the monitored vehicle, the outline of the window, the outline of the headlight, and the outline of the wheel through a graph convolutional network; The vehicle characteristics are classified according to the vehicle management data to obtain the vehicle model corresponding to the monitored vehicle.

[0007] Optionally, obtaining the license plate outline of the monitored vehicle by an edge detection algorithm according to the aspect ratio and the color distribution includes: Performing binarization processing on the collected image to obtain a binarized image of the collected image; According to the binary image, a plurality of geometric features of the monitored vehicle are obtained by using a findcontours function; Obtaining the aspect ratio of each of the geometric features; According to the aspect ratio, the aspect ratio of the geometric feature and the color distribution, the geometric feature is screened to obtain the license plate outline.

[0008] Optionally, the screening of geometric features to obtain the license plate outline according to the aspect ratio, the aspect ratio of the geometric features and the color distribution includes: According to the color distribution, obtaining the color corresponding to the geometric feature in the acquired image; The geometric features are screened according to the aspect ratio, the preset license plate aspect ratio and the preset color; Among them, when the difference between the aspect ratio of the geometric feature and the preset license plate aspect ratio is less than a preset threshold, and the color difference between the color and the preset color is less than a preset color difference threshold, the outline of the geometric feature is judged to be the license plate outline.

[0009] Optionally, the processing the license plate contour by morphological operation to obtain an enhanced image of the license plate contour includes: Segmenting the area where the license plate contour is located in the binary image to obtain a license plate binary image; Performing an expansion operation on the license plate binary image to obtain an expanded binary image; An erosion operation is performed on the dilated binary image to obtain an eroded binary image, and the eroded binary image is used as the enhanced image of the license plate contour.

[0010] Optionally, dividing the enhanced image of the license plate contour into a non-occluded area and an occluded area by a deep learning model according to the enhanced image of the license plate contour comprises: Inputting the enhanced image into the deep learning model, and obtaining local features of the enhanced image through the convolution layer of the deep learning model; Inputting the local features into the pooling layer of the deep learning model to reduce the spatial dimension of the local features, and then passing through the activation function layer to obtain the feature representation of the enhanced image; Optimizing the feature representation by using an intersection-over-union loss function to obtain an optimized feature representation; According to the feature representation completed by the optimization, pixel classification is performed on the enhanced image to obtain the non-occluded area and the occluded area.

[0011] Optionally, context information of the non-blocked area is obtained, wherein the context information includes image information of a preset area around the non-blocked area; Obtaining overall structural features of the license plate outline and features of the non-blocked area based on the image information of a preset area surrounding the non-blocked area; Inputting the overall structural features and the features of the non-occluded area into an autoencoder to generate an estimated image of the occluded area; splicing the image of the non-occluded area with the estimated image, and determining whether the spliced ​​image is usable; If so, the estimated image is used as the occluded image of the occluded area.

[0012] Optionally, obtaining the license plate number of the monitored vehicle according to the image of the non-blocked area and the blocked image includes: splicing the image of the non-blocked area and the blocked image to obtain a clear image corresponding to the license plate outline; Performing character segmentation according to the clear image to obtain geometric features of each character in the clear image; Each of the characters is identified according to the geometric features to obtain the license plate number of the monitored vehicle.

[0013] Optionally, the inputting the license plate number and the vehicle model of the monitored vehicle includes: Associating the license plate number with the vehicle model to obtain a comprehensive data record of the monitored vehicle; A text file corresponding to the comprehensive data record is automatically generated through an automated script, and then the text file is entered into a database.

[0014] The present invention also provides a vehicle information collection and management system, comprising: A collection unit, used to obtain a collection image of the monitored vehicle; A feature extraction unit, configured to obtain vehicle features of the monitored vehicle according to the collected image, wherein the vehicle features include the model, length-to-width ratio and color distribution of the monitored vehicle; A contour extraction unit, used to obtain the license plate contour of the monitored vehicle through an edge detection algorithm according to the aspect ratio and the color distribution; An image processing unit, used for processing the license plate contour through morphological operations according to the license plate contour to obtain an enhanced image of the license plate contour; According to the enhanced image of the license plate contour, dividing the enhanced image of the license plate contour into a non-occluded area and an occluded area through a deep learning model; An image restoration unit, configured to perform restoration according to the non-occluded area by using context information to obtain an occluded image of the occluded area; A recognition unit, used for obtaining the license plate number of the monitored vehicle according to the image of the non-blocked area and the blocked image; A data import unit is used to input the license plate number and the vehicle model of the monitored vehicle.

[0015] The vehicle information collection and management method and system of the present invention can quickly capture the real-time status of the vehicle by collecting images of the monitored vehicle. Then, the vehicle features, including the model, length-width ratio and color distribution, are extracted by using image processing technology. These features provide basic information for subsequent license plate recognition. Then, through the edge detection algorithm, the system can accurately identify the outline of the license plate, and the morphological operation further enhances the clarity of the license plate outline, providing high-quality input for the recognition of the deep learning model. The application of the deep learning model is the key to improving efficiency and accuracy. It can distinguish between non-occluded areas and occluded areas in the license plate image, which is particularly important in practical applications because the license plate may be occluded by other objects, affecting the accuracy of recognition. The image restoration technology using context information is used to repair the non-occluded area, which can effectively restore the occluded license plate part, thereby improving the integrity and accuracy of license plate recognition. Finally, by combining the non-occluded area and the repaired occluded area, the system can accurately obtain the license plate number and enter the license plate number and the model information into the database. The system can adapt to different environments and lighting conditions, and maintain a high recognition accuracy even under complex or unfavorable conditions. It not only reduces manual intervention and the error rate, but also improves the speed of information processing, making the collection and management of vehicle information more efficient and accurate. By integrating the license plate number with the vehicle model and other information, the system provides a comprehensive data basis for subsequent data analysis and decision-making, realizes rapid response to the update of vehicle information, and provides real-time data support for traffic management and vehicle scheduling. The present invention combines advanced image processing technology and deep learning algorithms to achieve rapid and accurate collection of vehicle information, provides strong technical support for traffic management and vehicle monitoring, and improves the efficiency and accuracy of vehicle information collection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Flow chart of the vehicle information collection and management method in an embodiment of the present invention; Figure 2 It is a structural diagram of a vehicle information collection and management system in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0018] Combination Figure 1 As shown, the present invention provides a vehicle information collection and management method, comprising: Acquire the collected image of the monitored vehicle.

[0019] Specifically, the first step in collecting vehicle information is image acquisition, which is usually completed by high-definition cameras, which are generally deployed at key monitoring points such as traffic intersections, parking lot entrances or toll booths. These cameras can capture images of passing vehicles in real time, providing raw data for subsequent vehicle feature analysis. The quality of the image directly affects the accuracy of subsequent processing, so the collected images need to have sufficient resolution and clarity.

[0020] The vehicle characteristics of the monitored vehicle are obtained according to the collected image, and the vehicle characteristics include the model, length-to-width ratio and color distribution of the monitored vehicle.

[0021] Specifically, after acquiring the vehicle image, the next step is to extract vehicle features. This step involves image processing and computer vision technology, which uses algorithms to analyze the image to identify specific attributes of the vehicle, such as the model, length-to-width ratio, and color distribution. These features are crucial for the identification and classification of vehicles. For example, a machine learning algorithm can be used to train a model to identify the features of different models, or a color clustering algorithm can be used to analyze the color distribution of vehicles.

[0022] According to the aspect ratio and the color distribution, an edge detection algorithm is used to obtain the license plate outline of the monitored vehicle.

[0023] Specifically, edge detection is a key technology in image processing, which is used to identify edge information in an image. In vehicle information collection, edge detection algorithms are used to identify the outline of license plates. Commonly used edge detection algorithms include Sobel, Prewitt, Canny, etc. These algorithms determine the location of the edge by calculating the gradient change of pixels in the image. For example, the Canny algorithm is widely used in license plate detection due to its high detection accuracy and robustness to noise.

[0024] According to the license plate contour, the license plate contour is processed through morphological operations to obtain an enhanced image of the license plate contour.

[0025] Specifically, morphological operations are another important type of technology in image processing, which analyzes and processes images based on their shape and structure. In the processing of license plate outlines, morphological operations such as dilation and erosion are used to enhance the recognizability of license plates. Dilation operations can fill small gaps between license plate characters, while erosion operations can remove noise and unnecessary details on license plates. These operations help improve the accuracy of license plate recognition.

[0026] According to the enhanced image of the license plate contour, the enhanced image of the license plate contour is divided into a non-occluded area and an occluded area through a deep learning model.

[0027] Specifically, deep learning technology has made revolutionary progress in the field of image recognition. In vehicle information collection, deep learning models are used to distinguish between non-occluded and occluded areas in license plate images. This usually involves using a trained convolutional neural network to identify and classify different areas in the image. For example, a deep learning model may be trained to recognize the text and numbers on a license plate while ignoring incomplete parts of the image due to occlusion or other reasons.

[0028] The non-occluded area is repaired by using the context information to obtain an occluded image of the occluded area.

[0029] Specifically, image restoration techniques using contextual information aim to restore damaged or incomplete parts of an image. In license plate recognition, if part of a license plate is occluded, image restoration techniques can predict and fill in the missing part based on the surrounding contextual information. This approach can improve the completeness and accuracy of license plate recognition. For example, if a character of a license plate is partially occluded, the missing part can be inferred using the surrounding visible characters and the known license plate format.

[0030] The license plate number of the monitored vehicle is obtained according to the image of the non-blocked area and the blocked image.

[0031] Specifically, in a preferred embodiment of the present invention, the recognition of the license plate number generally relies on optical character recognition technology. Optical character recognition technology can convert characters in an image into an editable text format. In a license plate recognition system, optical character recognition technology is used to extract the license plate number from a processed license plate image. This usually involves using a specific optical character recognition technology to recognize the characters in the image and convert them into a standard license plate number format.

[0032] Enter the license plate number and vehicle model of the monitored vehicle.

[0033] Specifically, the last step is to enter the identified license plate number and vehicle model information into the database. This step involves database management technology, including data storage, retrieval, and management. The entry of vehicle information requires not only accuracy, but also efficient data organization to facilitate subsequent query and analysis. For example, vehicle information can be classified and stored by time, location, or vehicle type to facilitate statistical analysis or traffic management decisions.

[0034] The vehicle information collection and management method of the present invention can quickly capture the real-time status of the vehicle by collecting images of the monitored vehicle. Then, the vehicle features, including the model, length-width ratio and color distribution, are extracted by using image processing technology. These features provide basic information for subsequent license plate recognition. Then, through the edge detection algorithm, the system can accurately identify the outline of the license plate, and the morphological operation further enhances the clarity of the license plate outline, providing high-quality input for the recognition of the deep learning model. The application of the deep learning model is the key to improving efficiency and accuracy. It can distinguish between non-occluded areas and occluded areas in the license plate image, which is particularly important in practical applications because the license plate may be occluded by other objects, affecting the accuracy of recognition. The image restoration technology using context information is used to repair the non-occluded area, which can effectively restore the occluded license plate part, thereby improving the integrity and accuracy of license plate recognition. Finally, by combining the non-occluded area and the repaired occluded area, the system can accurately obtain the license plate number and enter the license plate number and the model information into the database. The system can adapt to different environments and lighting conditions, and maintain a high recognition accuracy even under complex or unfavorable conditions. It not only reduces manual intervention and the error rate, but also improves the speed of information processing, making the collection and management of vehicle information more efficient and accurate. By integrating the license plate number with the vehicle model and other information, the system provides a comprehensive data basis for subsequent data analysis and decision-making, realizes rapid response to the update of vehicle information, and provides real-time data support for traffic management and vehicle scheduling. The present invention combines advanced image processing technology and deep learning algorithms to achieve rapid and accurate collection of vehicle information, provides strong technical support for traffic management and vehicle monitoring, and improves the efficiency and accuracy of vehicle information collection.

[0035] Optionally, obtaining the vehicle characteristics of the monitored vehicle according to the collected image includes: Preprocessing the acquired image to obtain the processed acquired image; By using image processing technology, feature extraction is performed on the processed collected image to obtain the outline of the monitored vehicle, the outline of the window, the outline of the headlight and the outline of the wheel; Obtaining vehicle features according to the outline of the monitored vehicle, the outline of the window, the outline of the headlight, and the outline of the wheel through a graph convolutional network; The vehicle characteristics are classified according to the vehicle management data to obtain the vehicle model corresponding to the monitored vehicle.

[0036] Specifically, first, the vehicle feature extraction process begins with the preprocessing of the captured image. This step is crucial because it can improve the accuracy and efficiency of subsequent processing. Preprocessing usually includes operations such as denoising, image enhancement, and histogram equalization, with the goal of removing noise from the image and enhancing the recognizability of vehicle features. For example, the use of a median filter can remove salt and pepper noise, while histogram equalization can improve the contrast of the image, making features such as the vehicle's outline, windows, lights, and wheels more prominent. Next, feature extraction is performed on the preprocessed image through image processing technology. This step can use edge detection algorithms such as the Canny operator to identify the outline of the vehicle; use Hough transform to detect circular parts of the vehicle, such as lights and wheels; and use color segmentation technology to identify the area of ​​the window. The key to feature extraction is to be able to accurately identify and locate the various components of the vehicle, providing reliable data for subsequent feature classification. Finally, the application of graph convolutional networks is based on these extracted features. Graph convolutional networks are a deep learning model that can process graph-structured data and are very suitable for processing interrelated features, such as different parts of a vehicle. By aggregating the feature information of each vehicle part and combining the topological relationship in the graph structure, the graph convolutional network can learn a richer and more robust vehicle feature representation. For example, the graph convolutional network can effectively integrate the features of the vehicle's outline, windows, lights, and wheels, thereby achieving accurate classification of the vehicle. In a preferred embodiment of the present invention, the collected vehicle image is first preprocessed, and the wavelet transform is used to remove noise and retain edge information. Next, edge detection is performed using the Canny operator to obtain the outline of the vehicle; the lights and wheels are identified through the Hough transform; and the window area is identified through color space conversion and cluster analysis. These features are then input into a well-trained graph convolutional network model that has been learned on a large number of vehicle images and can recognize and classify different types of vehicle models.

[0037] In this embodiment, the efficiency of vehicle information processing is greatly improved through automated feature extraction and classification, and the need for manual intervention is reduced. Secondly, image preprocessing and advanced image processing technology improve the accuracy of feature extraction, thereby improving the accuracy of vehicle model identification. It reduces manual intervention and errors caused by human factors, while improving processing speed and efficiency. Through continuous learning and optimization of the deep learning model, the system can adapt to various complex environments and conditions and maintain high-accuracy recognition capabilities. The present invention not only improves the level of intelligence in vehicle information management, but also provides strong technical support for traffic monitoring, vehicle scheduling, safety supervision and other fields.

[0038] Optionally, obtaining the license plate outline of the monitored vehicle by an edge detection algorithm according to the aspect ratio and the color distribution includes: Performing binarization processing on the collected image to obtain a binarized image of the collected image; According to the binary image, a plurality of geometric features of the monitored vehicle are obtained by using a findcontours function; Obtaining the aspect ratio of each of the geometric features; According to the aspect ratio, the aspect ratio of the geometric feature and the color distribution, the geometric feature is screened to obtain the license plate outline.

[0039] Specifically, the acquired image is first binarized, which is to convert the image into an image with only black and white pixel values, where white represents the foreground (areas of interest such as vehicles or license plates) and black represents the background. Binarization can be achieved by setting a threshold, where pixels above the threshold are considered white and pixels below the threshold are considered black. This step is crucial for subsequent edge detection and feature extraction because it simplifies the image and makes it easier for the algorithm to identify areas of interest. Secondly, the findcontours function is used to perform contour detection on the binary image. This function can identify all white areas in the image and extract their boundaries (contours). Each contour can be represented by a series of points that define the shape of the object. In this process, multiple geometric features can be obtained, such as the area, perimeter, center point, etc. of each contour. Finally, by analyzing these geometric features, especially their aspect ratio, the area that may be the license plate can be screened out. The aspect ratio is an important feature because the aspect ratio of the license plate is usually within a certain range, combined with the color distribution information, the detected contours are screened. For example, a reasonable aspect ratio range can be set, and only contours that meet this range are considered potential license plates, so as to further confirm the location of the license plate. For example, if the aspect ratio of a geometric feature meets the standard ratio of a license plate, and the color distribution matches the typical color of the license plate, then this feature is likely to represent a license plate. In a preferred embodiment of the present invention, the captured vehicle image is first binarized, and the Otsu method can be used to automatically determine the threshold to adapt to images under different lighting conditions. Then, the findcontours function in the OpenCV library is applied to extract the contours of all white areas. By calculating the aspect ratio of each contour, contours with an aspect ratio between 1.5 and 2.5 are screened out, and this range is usually consistent with the aspect ratio of the license plate. In addition, color histogram analysis can be used for further screening to exclude contours whose color distribution does not match the color of the license plate.

[0040] In this embodiment, the image information is greatly simplified by screening the aspect ratio, analyzing the color distribution, and binarizing the image. The complex image is converted into a black and white image that is easier to analyze through a thresholding operation. This step can accurately locate all connected white areas in the image, providing rich geometric information for extracting the license plate, further improving the accuracy of license plate detection, and reducing the possibility of false detection.

[0041] Optionally, the screening of geometric features to obtain the license plate outline according to the aspect ratio, the aspect ratio of the geometric features and the color distribution includes: According to the color distribution, obtaining the color corresponding to the geometric feature in the acquired image; The geometric features are screened according to the aspect ratio, the preset license plate aspect ratio and the preset color; Among them, when the difference between the aspect ratio of the geometric feature and the preset license plate aspect ratio is less than a preset threshold, and the color difference between the color and the preset color is less than a preset color difference threshold, the outline of the geometric feature is judged to be the license plate outline.

[0042] Specifically, first, the system analyzes the color of each geometric feature in the captured image. This can be done by converting each geometric feature in the image to an appropriate color space (such as RGB) so that the color can be more accurately represented and compared. Next, the system screens these geometric features based on the preset license plate aspect ratio and color. The preset aspect ratio is based on the standardized size of the license plate, and the preset color is the typical color of the license plate, such as white or yellow. During the screening process, the system compares the difference between the aspect ratio of each geometric feature and the preset license plate aspect ratio. If this difference is less than a preset threshold, it indicates that the geometric feature may be a license plate. At the same time, the system also calculates the color difference between the color of the geometric feature and the preset color. The calculation of the color difference can be achieved by a variety of methods, such as using the Euclidean distance to measure the proximity of two colors in the color space. If the color difference is also less than the preset color difference threshold, this further increases the possibility that the geometric feature is a license plate. In a preferred embodiment of the present invention, it is assumed that the preset license plate aspect ratio is 3:1, the preset color is white, and the color difference threshold is set to 30 (in the HSV color space). The system first processes the acquired image and extracts all possible geometric features. Then, the system calculates the aspect ratio of each geometric feature and compares it with the preset aspect ratio. For geometric features with an aspect ratio between 2.7 and 3.3, the system further analyzes their color. If the color of the geometric feature is within 30 units of the white color range, the system marks it as a potential license plate. In this way, the system is able to effectively identify the license plate from the image.

[0043] In this embodiment, by considering both the aspect ratio and color, the system can more accurately screen out geometric features that meet the characteristics of the license plate, reducing the interference of other non-license plate objects. At the same time, the preset aspect ratio and color thresholds can be adjusted according to the standards of different regions or different types of license plates, so that the system can adapt to a variety of license plate specifications and colors. The two dimensions of shape and color of geometric features are comprehensively considered, reducing the possibility of misidentification and improving the accuracy of license plate recognition.

[0044] Optionally, the processing the license plate contour by morphological operation to obtain an enhanced image of the license plate contour includes: Segmenting the area where the license plate contour is located in the binary image to obtain a license plate binary image; Performing an expansion operation on the license plate binary image to obtain an expanded binary image; An erosion operation is performed on the dilated binary image to obtain an eroded binary image, and the eroded binary image is used as the enhanced image of the license plate contour.

[0045] Specifically, in license plate recognition, morphological operations are used to enhance the outline of the license plate and improve the accuracy of recognition. First, the acquired image is binarized to obtain the binary outline of the license plate. Then, the dilation operation is used to increase the white pixels in the license plate area. This can fill the small cracks or disconnected strokes that may exist inside the license plate and make the license plate area more complete. The dilation operation uses a predefined structural element to slide in the image and increase the pixel value according to certain rules (usually assigning the value of the foreground pixel to the background pixel covered by the structural element), thereby achieving the "expansion" effect of the image. Next, the dilated image is eroded. The erosion operation is the opposite of dilation. It refines the outline of the license plate by reducing the white pixels at the edge of the image. The erosion operation uses the same structural element, but this time the value of the background pixel is assigned to the foreground pixel covered by the structural element. If the foreground pixel under the structural element is not all white, the pixel value at that position will be eroded to the background value. This helps to remove noise and burrs at the edge of the license plate, making the outline of the license plate clearer and more precise. In a preferred embodiment of the present invention, the collected vehicle image is first binarized to obtain a clear license plate outline. Then, a 5x5 rectangular structure element is defined, and a dilation operation is performed on the binary image. After the dilation operation, the same structure element is used again to perform an erosion operation on the image. Through these two consecutive morphological operations, a license plate image with a clearer outline and a more complete interior can be obtained.

[0046] In this embodiment, the expansion operation enhances the internal integrity of the license plate and fills the possible cracks. By increasing the white pixels in the license plate area, the small cracks or disconnected strokes that may exist inside are filled, making the license plate area more complete and reducing recognition errors caused by image noise or quality problems. The corrosion operation removes the noise at the edge of the license plate, making the outline of the license plate clearer and reducing the possibility of misrecognition.

[0047] Optionally, dividing the enhanced image of the license plate contour into a non-occluded area and an occluded area by a deep learning model according to the enhanced image of the license plate contour comprises: Inputting the enhanced image into the deep learning model, and obtaining local features of the enhanced image through the convolution layer of the deep learning model; Inputting the local features into the pooling layer of the deep learning model to reduce the spatial dimension of the local features, and then passing through the activation function layer to obtain the feature representation of the enhanced image; Optimizing the feature representation by using an intersection-over-union loss function to obtain an optimized feature representation; According to the feature representation completed by the optimization, pixel classification is performed on the enhanced image to obtain the non-occluded area and the occluded area.

[0048] Specifically, in the license plate recognition system, the enhanced license plate image is first input into the deep learning model. The convolutional layers of the model are responsible for extracting local features of the image. These convolutional layers recognize patterns in the image, such as edges, textures, etc., through a series of learnable filters. For example, the first convolutional layer may focus on recognizing simple edge features, while deeper convolutional layers may recognize more complex shapes and structural features. Subsequently, these local features are fed into the pooling layer, which usually uses the maximum pooling or average pooling technique to reduce the spatial dimension of the features while increasing the invariance to image displacement. This step reduces the spatial size of the data, thereby reducing the number of parameters and the complexity of the calculation. Next, through the activation function layer, nonlinearity is introduced, allowing the model to learn and simulate more complex function mappings. Finally, the feature representation of the model is optimized using the intersection over union loss function. IoU is an indicator that measures the degree of overlap between the predicted area and the true area. By minimizing the IoU loss between the predicted box and the true box, the position and shape of the license plate can be more accurately located. After the optimization is completed, the model can classify the enhanced image at the pixel level according to the feature representation and distinguish between non-occluded and occluded areas.

[0049] In this embodiment, through the hierarchical structure of the deep learning model, features can be extracted step by step from simple to complex, which not only improves the generalization ability of the model for different types of license plates, but also enables the model to better adapt to license plate recognition tasks under different environments and conditions. The combined use of convolutional layers and pooling layers significantly improves the ability to extract features, allowing the model to capture richer and more abstract feature representations. The model is optimized using the intersection-over-union loss function to ensure a high degree of consistency between the predicted area output by the model and the actual license plate area, thereby improving the recognition accuracy of the occluded area, reducing recognition errors caused by occlusion, and improving the accuracy and robustness of license plate recognition.

[0050] Optionally, context information of the non-blocked area is obtained, wherein the context information includes image information of a preset area around the non-blocked area; Obtaining overall structural features of the license plate outline and features of the non-blocked area based on the image information of a preset area surrounding the non-blocked area; Inputting the overall structural features and the features of the non-occluded area into an autoencoder to generate an estimated image of the occluded area; splicing the image of the non-occluded area with the estimated image, and determining whether the spliced ​​image is usable; If so, the estimated image is used as the occluded image of the occluded area.

[0051] Specifically, first, the system analyzes the non-occluded area to extract the overall structural features of the license plate, such as the edge, color, and texture of the license plate. These features are then used to infer the possible appearance and properties of the occluded area. Based on the image information of the non-occluded area and the preset area around it, the overall structural features of the license plate outline and the features of the non-occluded area are extracted. Autoencoders are powerful neural networks that can learn effective representations of data and are particularly suitable for image restoration tasks. In the restoration of the occluded area of ​​the license plate, the encoder part of the autoencoder compresses the features of the non-occluded area into a low-dimensional representation, while the decoder part expands this representation back to the dimension of the original image to generate an estimated image of the occluded area. For example, an autoencoder can be designed whose encoder and decoder both use convolutional neural network layers to maintain the spatial hierarchy of the image. In practical applications, a pre-trained autoencoder model can be used, which has been trained on a large number of unoccluded license plate images to learn the typical features of the license plate. When the occluded license plate image needs to be restored, the non-occluded area is input into the autoencoder to generate an estimated image of the occluded area. Then, this estimated image is spliced ​​with the image of the non-occluded area to form a complete license plate image. If the generated image is visually consistent with the non-occluded area and conforms to the typical structural features of the license plate, the estimated image is considered usable.

[0052] In this embodiment, by using context information and autoencoder to repair the occluded area, the robustness of the license plate recognition system is improved, the integrity of the license plate is restored, and the license plate can be accurately recognized even in the case of partial occlusion, providing more complete and reliable visual information for subsequent license plate recognition. The repaired image improves the accuracy of the license plate recognition system due to the coherence of structure and features, especially when the occluded area is large or the occluded features are not obvious.

[0053] Optionally, obtaining the license plate number of the monitored vehicle according to the image of the non-blocked area and the blocked image includes: splicing the image of the non-blocked area and the blocked image to obtain a clear image corresponding to the license plate outline; Performing character segmentation according to the clear image to obtain geometric features of each character in the clear image; Each of the characters is identified according to the geometric features to obtain the license plate number of the monitored vehicle.

[0054] Specifically, stitching the non-occluded area and the occluded image is a key step in the license plate recognition process. First, the estimated image of the occluded area generated by the autoencoder is accurately aligned and fused with the actual non-occluded area image on the edge. This step needs to ensure that the stitched image is visually coherent, without obvious seams or unnatural changes, so as to facilitate subsequent character segmentation and recognition. The stitching technology can use seamless stitching algorithms in image processing, such as stitching methods based on feature point matching, or use image fusion techniques such as Poisson fusion to smooth the transition area. Then perform character segmentation on the stitched clear image. This step usually involves binarization of the image to highlight the contrast between the characters and the background, and then applying connected domain analysis or edge detection algorithms to identify and separate each character. For example, the Otsu method can be used for automatic binarization, and then the characters can be located by finding contours. The geometric features of each character, such as size, shape, and position, will be extracted to prepare for character recognition. In the character recognition stage, deep learning models such as convolutional neural networks can be used to identify each character in the image. The convolutional neural network model has been pre-trained on a large amount of license plate character data and is able to recognize different character shapes and styles. The extracted geometric features are input into the convolutional neural network, and the model will output the predicted category for each character.

[0055] In this embodiment, the integrity of the license plate image is ensured by accurately splicing the non-occluded area with the occluded image, providing high-quality input for character segmentation and recognition. Secondly, the accuracy of character segmentation directly affects the final recognition result. By using advanced image processing technology, the accuracy of segmentation can be improved and the risk of misrecognition can be reduced.

[0056] Optionally, the inputting the license plate number and the vehicle model of the monitored vehicle includes: Associating the license plate number with the vehicle model to obtain a comprehensive data record of the monitored vehicle; A text file corresponding to the comprehensive data record is automatically generated through an automated script, and then the text file is entered into a database.

[0057] Specifically, first a data structure is needed to store the license plate number and model information of each monitored vehicle. This data structure is usually a record containing multiple fields. For example, in a relational database, it can be a table containing fields such as license plate number, model, timestamp, etc. Among them, the writing of automated scripts is an important means to achieve automatic data entry. This script can be implemented in various programming languages. The core functions of the script include receiving license plate number and model information as input, and then formatting this information into a specific text file format, such as CSV or JSON. In a preferred embodiment of the present invention, the Python script can use the built-in csv module to generate a CSV file, and each line in the file represents a comprehensive data record of a vehicle.

[0058] In this embodiment, the need for manual input is reduced through the automation process, which significantly improves the efficiency and speed of data entry. At the same time, the possibility of human input errors is reduced, ensuring the accuracy and consistency of the data. The text files generated by the script (such as CSV or JSON format) are easy to integrate with other systems or applications, providing good flexibility and scalability. It not only improves the speed and quality of data processing, but also provides data support for intelligent transportation and vehicle management.

[0059] like Figure 2 As shown, the present invention also provides a vehicle information collection and management system, comprising: A collection unit, used to obtain a collection image of the monitored vehicle; A feature extraction unit, configured to obtain vehicle features of the monitored vehicle according to the collected image, wherein the vehicle features include the model, length-to-width ratio and color distribution of the monitored vehicle; A contour extraction unit, used to obtain the license plate contour of the monitored vehicle through an edge detection algorithm according to the aspect ratio and the color distribution; An image processing unit, used for processing the license plate contour through morphological operations according to the license plate contour to obtain an enhanced image of the license plate contour; According to the enhanced image of the license plate contour, dividing the enhanced image of the license plate contour into a non-occluded area and an occluded area through a deep learning model; An image restoration unit, configured to perform restoration according to the non-occluded area by using context information to obtain an occluded image of the occluded area; A recognition unit, used for obtaining the license plate number of the monitored vehicle according to the image of the non-blocked area and the blocked image; A data import unit is used to input the license plate number and the vehicle model of the monitored vehicle.

[0060] The vehicle information collection and management system of the present invention can quickly capture the real-time status of the vehicle by collecting images of the monitored vehicle. Then, the vehicle features, including the model, length-width ratio and color distribution, are extracted by using image processing technology. These features provide basic information for subsequent license plate recognition. Through the edge detection algorithm, the system can accurately identify the outline of the license plate, and the morphological operation further enhances the clarity of the license plate outline, providing high-quality input for the recognition of the deep learning model. The application of the deep learning model is the key to improving efficiency and accuracy. It can distinguish between non-occluded areas and occluded areas in the license plate image, which is particularly important in practical applications because the license plate may be occluded by other objects, affecting the accuracy of recognition. Using context information to repair the non-occluded area can effectively restore the occluded license plate part, thereby improving the integrity and accuracy of license plate recognition. Finally, by combining the non-occluded area and the repaired occluded area, the system can accurately obtain the license plate number and enter the license plate number and the model information into the database. Not only does it reduce manual intervention and reduce the error rate, but it also improves the speed of information processing, making the collection and management of vehicle information more efficient and accurate. By combining advanced image processing technology and deep learning algorithms, the present invention realizes the rapid and accurate collection of vehicle information, provides strong technical support for traffic management and vehicle monitoring, and improves the efficiency and accuracy of vehicle information collection.

[0061] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0062] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0063] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A vehicle information collection and management method, characterized in that: include: Acquire the collected image of the monitored vehicle; Obtaining vehicle features of the monitored vehicle according to the collected image, wherein the vehicle features include the model, length-to-width ratio, and color distribution of the monitored vehicle; According to the aspect ratio and the color distribution, the license plate outline of the monitored vehicle is obtained by an edge detection algorithm; According to the license plate contour, the license plate contour is processed by morphological operation to obtain an enhanced image of the license plate contour; According to the enhanced image of the license plate contour, dividing the enhanced image of the license plate contour into a non-occluded area and an occluded area through a deep learning model; Repairing the non-occluded area using the context information to obtain an occluded image of the occluded area; Obtaining the license plate number of the monitored vehicle according to the image of the non-blocked area and the blocked image; Enter the license plate number and vehicle model of the monitored vehicle.

2. The vehicle information collection and management method according to claim 1, characterized in that: The step of obtaining the vehicle characteristics of the monitored vehicle according to the collected image includes: Preprocessing the acquired image to obtain the processed acquired image; By using image processing technology, feature extraction is performed on the processed collected image to obtain the outline of the monitored vehicle, the outline of the window, the outline of the headlight and the outline of the wheel; Obtaining vehicle features according to the outline of the monitored vehicle, the outline of the window, the outline of the headlight, and the outline of the wheel through a graph convolutional network; The vehicle characteristics are classified according to the vehicle management data to obtain the vehicle model corresponding to the monitored vehicle.

3. The vehicle information collection and management method according to claim 2, characterized in that: The step of obtaining the license plate outline of the monitored vehicle by an edge detection algorithm according to the aspect ratio and the color distribution includes: Performing binarization processing on the collected image to obtain a binarized image of the collected image; According to the binary image, a plurality of geometric features of the monitored vehicle are obtained by using a findcontours function; Obtaining the aspect ratio of each of the geometric features; According to the aspect ratio, the aspect ratio of the geometric feature and the color distribution, the geometric feature is screened to obtain the license plate outline.

4. The vehicle information collection and management method according to claim 3, characterized in that: The step of screening the geometric features according to the aspect ratio, the aspect ratio of the geometric features and the color distribution to obtain the license plate outline includes: According to the color distribution, obtaining the color corresponding to the geometric feature in the acquired image; The geometric features are screened according to the aspect ratio, the preset license plate aspect ratio and the preset color; Among them, when the difference between the aspect ratio of the geometric feature and the preset license plate aspect ratio is less than a preset threshold, and the color difference between the color and the preset color is less than a preset color difference threshold, the outline of the geometric feature is judged to be the license plate outline.

5. The vehicle information collection and management method according to claim 3, characterized in that: The method of processing the license plate contour by morphological operation to obtain an enhanced image of the license plate contour includes: Segmenting the area where the license plate contour is located in the binary image to obtain a license plate binary image; Performing an expansion operation on the license plate binary image to obtain an expanded binary image; An erosion operation is performed on the dilated binary image to obtain an eroded binary image, and the eroded binary image is used as the enhanced image of the license plate contour.

6. The vehicle information collection and management method according to claim 1, characterized in that: The method of dividing the enhanced image of the license plate contour into a non-occluded area and an occluded area according to the enhanced image of the license plate contour by a deep learning model includes: Inputting the enhanced image into the deep learning model, and obtaining local features of the enhanced image through the convolution layer of the deep learning model; Inputting the local features into the pooling layer of the deep learning model to reduce the spatial dimension of the local features, and then passing through the activation function layer to obtain the feature representation of the enhanced image; Optimizing the feature representation by using an intersection-over-union loss function to obtain an optimized feature representation; According to the feature representation completed by the optimization, pixel classification is performed on the enhanced image to obtain the non-occluded area and the occluded area.

7. The vehicle information collection and management method according to claim 1, characterized in that: The repairing is performed according to the non-occluded area by using the context information to obtain the occluded image of the occluded area, including: Acquire context information of the non-blocked area, wherein the context information includes image information of a preset area around the non-blocked area; Obtaining overall structural features of the license plate outline and features of the non-blocked area based on the image information of a preset area surrounding the non-blocked area; Inputting the overall structural features and the features of the non-occluded area into an autoencoder to generate an estimated image of the occluded area; splicing the image of the non-occluded area with the estimated image, and determining whether the spliced ​​image is usable; If so, the estimated image is used as the occluded image of the occluded area.

8. The vehicle information collection and management method according to claim 2, characterized in that: The obtaining the license plate number of the monitored vehicle according to the image of the non-blocked area and the blocked image comprises: splicing the image of the non-blocked area and the blocked image to obtain a clear image corresponding to the license plate outline; Performing character segmentation according to the clear image to obtain geometric features of each character in the clear image; Each of the characters is identified according to the geometric features to obtain the license plate number of the monitored vehicle.

9. The vehicle information collection and management method according to claim 2, characterized in that: The step of inputting the license plate number and the vehicle model of the monitored vehicle includes: Associating the license plate number with the vehicle model to obtain a comprehensive data record of the monitored vehicle; A text file corresponding to the comprehensive data record is automatically generated through an automated script, and then the text file is entered into a database.

10. A vehicle information collection and management system, characterized in that: include: A collection unit, used to obtain a collection image of the monitored vehicle; A feature extraction unit, configured to obtain vehicle features of the monitored vehicle according to the collected image, wherein the vehicle features include the model, length-to-width ratio and color distribution of the monitored vehicle; A contour extraction unit, used to obtain the license plate contour of the monitored vehicle through an edge detection algorithm according to the aspect ratio and the color distribution; An image processing unit, used for processing the license plate contour through morphological operations according to the license plate contour to obtain an enhanced image of the license plate contour; According to the enhanced image of the license plate contour, dividing the enhanced image of the license plate contour into a non-occluded area and an occluded area through a deep learning model; An image restoration unit, configured to perform restoration according to the non-occluded area by using context information to obtain an occluded image of the occluded area; A recognition unit, used for obtaining the license plate number of the monitored vehicle according to the image of the non-blocked area and the blocked image; A data import unit is used to input the license plate number and the vehicle model of the monitored vehicle.

Images