Intelligent grating traffic control system

Abstract

The application discloses an intelligent grating traffic control system and belongs to the field of intelligent traffic. The system comprises a camera, an image processing module, a classification processing module and a grating indicator, wherein the camera is used for shooting appearance images of vehicles to be classified; the image processing module is used for extracting a plurality of vehicle features of the appearance images, the vehicle features comprising clear features and fuzzy features; the classification processing module is used for performing classification analysis on the vehicles to be classified according to the plurality of vehicle features, and determining vehicle types of the vehicles to be classified; and the grating indicator is used for indicating passing roads of the vehicles to be classified according to the vehicle types. The technical scheme provided by the application solves the problem of low classification guiding accuracy of a current highway toll station for passing vehicles.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent traffic, in particular to an intelligent grating traffic control system. BACKGROUND

[0002] When classifying and guiding the passing vehicles at the highway toll station, it is basically completed by manual in the past, but with the rapid development of visual detection technology and AI technology, this classification and guidance work is replaced by intelligent grating traffic system, which greatly saves the labor cost.

[0003] However, with more and more passing vehicles at the highway toll station, the vehicle shooting environment is more and more complex, and the image quality is often reduced due to motion blur, low light or shielding, etc., which makes it difficult for the current intelligent grating traffic system to accurately determine the vehicle type, thereby significantly reducing the classification accuracy. SUMMARY

[0004] In view of the problem of low classification and guidance accuracy of the passing vehicles at the highway toll station, the present application provides an intelligent grating traffic control system, which comprises a camera, an image processing module, a classification processing module and a grating indicator, wherein:

[0005] The camera is used for shooting the appearance image of the vehicle to be classified;

[0006] The image processing module is used for extracting a plurality of vehicle features of the appearance image, wherein the vehicle features include clear features and fuzzy features;

[0007] The classification processing module is used for classifying and analyzing the vehicle to be classified according to a plurality of vehicle features, and determining the vehicle type of the vehicle to be classified;

[0008] The grating indicator is used for indicating the passing road of the vehicle to be classified according to the vehicle type.

[0009] Optionally, the classification and analysis of the vehicle to be classified according to a plurality of vehicle features, and the determination of the vehicle type of the vehicle to be classified are specifically as follows:

[0010] The ratio between the number of clear features and the number of fuzzy features is calculated;

[0011] It is judged whether the ratio result is greater than or equal to a preset ratio;

[0012] If the ratio result is greater than or equal to the preset ratio, a plurality of vehicle features are input into a vehicle classification model for classification to obtain the vehicle type of the vehicle to be classified.

[0013] Optionally, determining whether the ratio result is greater than or equal to a preset ratio further includes:

[0014] If the ratio result is less than the preset ratio, performing correlation analysis on the fuzzy feature to obtain a first correlation feature of the fuzzy feature;

[0015] Performing a rationality evaluation on the first associated feature of the fuzzy feature and the clear feature to obtain a rationality score;

[0016] If the rationality score is greater than or equal to a preset rationality score, the clear feature and the first associated feature are input into the vehicle classification model for classification, and the vehicle type of the vehicle to be classified is determined.

[0017] Optionally, performing correlation analysis on the fuzzy feature to obtain a first correlation feature of the fuzzy feature specifically includes:

[0018] Performing wavelet decomposition on the fuzzy features to obtain intermediate frequency subbands;

[0019] determining a first gain coefficient of the fuzzy feature according to a proportion of the number of the fuzzy features in the plurality of vehicle features;

[0020] Based on the first gain coefficient, reconstructing the image of the intermediate frequency sub-band to obtain a fuzzy feature to be matched;

[0021] The fuzzy feature to be matched is matched with a preset vehicle feature table to obtain a first associated feature of the fuzzy feature.

[0022] Optionally, matching the to-be-matched fuzzy feature with a preset vehicle feature table to obtain a first associated feature of the fuzzy feature specifically includes:

[0023] Extracting multiple key pixel points and feature descriptors of the fuzzy features to be matched;

[0024] Constructing a contour image of the fuzzy feature to be matched based on the plurality of key pixel points and feature descriptors;

[0025] The contour image is matched with the preset vehicle feature table to obtain a first associated feature of the fuzzy feature.

[0026] Optionally, the rationality evaluation of the first associated feature of the fuzzy feature and the clear feature to obtain a rationality score is specifically:

[0027] Identifying the fuzzy type of the fuzzy feature;

[0028] extracting texture features from the first associated features according to the fuzzy type;

[0029] The similarity calculation is performed on the texture feature and the clarity feature to obtain the rationality score, and the similarity calculation includes structural similarity, brightness similarity and contrast similarity.

[0030] Optionally, after performing a rationality evaluation on the first associated feature of the fuzzy feature and the clear feature to obtain a rationality score, the method further includes:

[0031] a. If the rationality score is less than the preset rationality score, calculating the difference between the rationality score and the preset rationality score;

[0032] b. amplifying and adjusting the first gain coefficient based on the score difference to obtain a second gain coefficient;

[0033] c. Using the second gain coefficient, performing image enhancement, correlation feature matching, and rationality evaluation on the fuzzy feature to obtain a second correlation feature and a second rationality score;

[0034] d. Determining whether the second rationality score is greater than or equal to the preset rationality score;

[0035] If yes, inputting the second associated feature and the clear feature into a vehicle classification model for classification to obtain the vehicle type of the vehicle to be classified;

[0036] If not, repeat steps a to d until the rationality score calculated by the rationality evaluation is greater than or equal to the preset rationality score.

[0037] Optionally, the image processing module further includes a cache unit and an image clarity recognition unit.

[0038] The cache unit is configured to store the first appearance image of the vehicle to be classified, and select, based on the memory usage of the plurality of first appearance images, a plurality of first appearance images having a memory usage greater than or equal to a preset memory usage as the appearance images to be processed;

[0039] The image definition recognition unit is configured to perform definition recognition on the plurality of appearance images to be processed, and select the image with the highest definition from the plurality of appearance images to be processed as the appearance image.

[0040] Optionally, the performing clarity recognition on the plurality of appearance images to be processed specifically includes:

[0041] A lightweight semantic segmentation network is used to extract multiple determination areas corresponding to each of the multiple appearance images to be processed, where the multiple determination areas are preset areas on the vehicle with low reflective interference;

[0042] performing wavelet decomposition on the plurality of judgment regions corresponding to the plurality of appearance images to be processed, to obtain the gradient energies of the plurality of appearance images to be processed in low-frequency sub-bands and high-frequency sub-bands;

[0043] The ratio of the gradient energy of the low-frequency sub-band to the gradient energy of the high-frequency sub-band of each of the plurality of appearance images to be processed is calculated to obtain the clarity of the plurality of appearance images to be processed.

[0044] Optionally, the extracting multiple vehicle features from the appearance image further includes:

[0045] Segmenting the appearance image into multiple feature images of the same size;

[0046] Identify the clear pixel points of the vehicle and the total pixel points of the vehicle corresponding to each of the plurality of feature images;

[0047] determining the clarity of the plurality of feature images according to a ratio of the vehicle clear pixels in the plurality of feature images to the total number of vehicle pixels;

[0048] If the clarity of the first feature image is greater than or equal to a preset clarity threshold, determining that the first feature image is a clear feature, the first feature image being any one of the plurality of feature images;

[0049] If the clarity of the second feature image is less than a preset clarity threshold, it is determined that the second feature image is a blurred feature, and the second feature image is any one of the multiple feature images.

[0050] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0051] 1. When a passing vehicle needs to pass through a highway toll station, this application uses a camera to capture the appearance image of the vehicle to be classified, and then the image processing module extracts clear features and fuzzy features from the appearance image. The classification processing module then determines whether the clarity of the appearance image can be recognized by the vehicle classification model based on the proportion of clear features in the entire appearance image; if the proportion is high, it means that the clarity of the appearance image meets the requirements and can be directly input into the vehicle classification model to determine the vehicle type; if the proportion is low, the fuzzy features need to be amplified for correct recognition. However, directly enhancing the fuzzy features not only requires high hardware resources, but may also introduce too much noise, causing image distortion; therefore, this application matches the fuzzy features with a preset vehicle feature table to obtain their corresponding associated features, and then recombine the associated features with the original clear features into a new complete image, and then performs a rationality analysis on the new image to obtain a rationality score. If the rationality score is high enough, it means that the new image can represent the original image, thereby indirectly improving the clarity of the original image to improve the accuracy of vehicle type recognition.

[0052] 2. Before matching the fuzzy features with the preset vehicle feature table, in order to improve the matching accuracy, the present application performs adaptive gain on the fuzzy features, determines the corresponding gain coefficient according to the proportion of the fuzzy features in the entire original image, and then performs image enhancement on the fuzzy features based on the gain coefficient. In addition, before image enhancement, the present application performs wavelet decomposition on the fuzzy features to determine the distribution of key information therein. It should be noted that the key information in the fuzzy features is mainly concentrated in the mid-frequency sub-band, and the noise has little effect on it. Although the high-frequency sub-band contains key information, its corresponding key information is detail information, and the noise has the greatest impact on the detail information, resulting in the effect of its gain being not ideal. Therefore, the present application gains the mid-frequency sub-band and then reconstructs the gained mid-frequency sub-band to obtain the gained fuzzy features, thereby improving the matching accuracy with the preset vehicle feature table. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a structural diagram of an intelligent grating traffic control system provided in an embodiment of the present application.

[0054] Figure 2 It is a structural diagram of an image processing module provided in an embodiment of the present application.

[0055] Explanation of the accompanying symbols: 1. Camera; 2. Image processing module; 3. Classification processing module; 31. Cache unit; 32. Image clarity recognition unit; 4. Grating sign. DETAILED DESCRIPTION

[0056] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in conjunction with the drawings in the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all.

[0057] In the description of the embodiments of the present application, the words such as "for example" or "for instance" are used to represent an example, illustration or description. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "for example" or "for instance" are intended to present the relevant concept in a specific manner.

[0058] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are used for description purposes only and should not be interpreted as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0059] With the rapid development of the economy, the number of car buyers has increased significantly, resulting in a significant increase in the traffic volume of highway toll stations. In order to avoid traffic congestion and improve traffic efficiency, vehicles approaching the highway toll station will be classified and guided at a distance of 2 kilometers from the highway toll station, so that vehicles of the same type are evenly distributed in corresponding multiple gate lanes, avoiding the situation that one gate lane is heavily loaded and one gate lane has a high idle rate. In the past, the classification and guidance of vehicles passing through the highway toll station were basically completed by manual work. However, with the rapid development of visual detection technology and AI technology, this classification and guidance work has been replaced by an intelligent grating traffic system. The intelligent grating traffic system captures passing vehicles, then inputs the captured images into an AI model for vehicle type recognition, and finally controls the intelligent grating indicator at the classification intersection to indicate passing vehicles to go to the gate lane with low congestion. At this time, not only the traffic efficiency is improved, but also the labor cost is greatly saved.

[0060] However, with more and more vehicles passing through the highway toll station, the vehicle shooting environment becomes more and more complex. The quality of the captured images often decreases due to motion blur, low light or obstruction, which makes it difficult for the current intelligent grating traffic system to accurately determine the type of vehicle, resulting in a significant decrease in classification accuracy.

[0061] In order to solve the above problems, the present application provides an intelligent grating traffic control system, such as Figure 1 As shown, the system includes a camera 1, an image processing module 2, a classification processing module 3 and a grating sign 4, wherein

[0062] Camera 1 is used to capture the exterior image of the vehicle being classified. Specifically, when a vehicle enters a preset capture range, camera 1 is immediately triggered to capture images. This can be triggered by infrared signals or road pressure sensors, thus avoiding incomplete images caused by premature or delayed capture. During the capture process, camera 1 captures multiple consecutive frames to accommodate the optimal shooting angle requirements of different vehicle models and ensure that the vehicle occupies at least 90% of the image. These frames are then transmitted to image processing module 2.

[0063] After acquiring multiple consecutive frame images, the image processing module 2 selects an image with higher definition as the appearance image for subsequent vehicle type identification, such as Figure 2 As shown, the image processing module 2 also includes a cache unit 31 and an image clarity recognition unit 32, wherein the cache unit 31 is used to store the first appearance image of the vehicle to be classified, and the first appearance image is a continuous frame image. Since some images in the multiple first appearance images may be affected by factors such as motion and lighting, resulting in a serious decrease in clarity, these first appearance images with severely decreased clarity will occupy more computing resources, thereby reducing data processing efficiency; therefore, this application needs to screen out images with higher clarity from the multiple first appearance images to improve the effective utilization of computing resources. Specifically: the cache module reads the memory usage of multiple first appearance images, and then selects multiple first appearance images with a memory usage greater than or equal to a preset usage from the multiple first appearance images as appearance images to be processed. It should be explained that the image usage reflects the richness of details in the image. For a clear image, it contains more details and accurate pixel information. Each pixel requires more bytes to store its color, brightness and other information, so its memory usage will be higher; and because a blurred image visually loses some details, its pixel information is relatively less rich. When stored, the specific color and brightness value of each pixel is not recorded as accurately as a clear image. For example, for some areas with complex color transitions, they can be approximated by fewer colors after blurring, thereby reducing the storage space required for each pixel, and the overall memory usage is lower than that of a clear image.

[0064] But the memory ratio only considers the richness of details in the image, if the area with rich details in the image is invalid area, the value of the image is not high, therefore, in order to select the image with the highest analysis value from the multiple appearance images to be processed, the image definition recognition unit 32 performs definition recognition on the multiple appearance images to be processed, which is to extract multiple judgment areas corresponding to the multiple appearance images to be processed by using a lightweight semantic segmentation network, the multiple judgment areas are preset areas with low reflection interference on the vehicle, the preset areas can be understood as pre-identified high value areas (such as vehicle lights, wheels and license plates), if the definition in the judgment area is high enough, it can be determined that it is a high value image, which can be used as a reference image for subsequent vehicle type recognition.

[0065] In the definition recognition of the multiple judgment images, the present application judges the noise distribution of the multiple judgment areas by wavelet decomposition of the multiple judgment areas. After wavelet decomposition of the judgment areas, the gradient energy of the low frequency subband and the gradient energy of the high frequency subband are obtained. The gradient energy of the low frequency subband mainly reflects the contour information of the image, and the gradient energy of the high frequency subband mainly reflects the detail information of the image. Noise has little effect on the contour information of the image, but has great effect on the detail information. Therefore, for a blurred image, the gradient energy of the low frequency subband does not change much, but the gradient energy of the high frequency subband decreases due to the loss of detail information. Therefore, the present application calculates the ratio of the gradient energy of the low frequency subband to the gradient energy of the high frequency subband of each of the multiple appearance images to be processed, so as to determine the detail loss of the multiple appearance images to be processed. This detail loss also represents the definition of the appearance image to be processed. At this time, the appearance image to be processed with the largest ratio result is selected as the reference appearance image for subsequent vehicle type recognition.

[0066] After the image processing module 2 has determined the appearance image of the vehicle to be classified, it divides the appearance image into multiple feature images of the same size, extracts the vehicle features of the multiple feature images and analyzes their clarity, then compares the clarity of the multiple vehicle features with the preset clarity threshold, divides them into fuzzy features and clear features, and annotates them. The annotated multiple vehicle features are sent to the classification processing module 3, and the fuzzy features are blurred feature images, and the clear features are clear feature images. When analyzing the clarity of multiple feature images, since some feature images are not entirely composed of vehicles, the clarity of the feature images is determined based on the ratio of vehicle clear pixels to total vehicle pixels in the feature image. For example, if the feature image consists of 1,000 pixels, of which 800 are vehicle total pixels and 600 are vehicle clear pixels, then its clarity is 600 / 800=0.75. In addition, for the case where the feature image does not contain a vehicle, since it does not contain relevant features of the vehicle, its clarity does not affect the judgment of the vehicle type itself. Therefore, this application sets its clarity to 1 (high clarity) to reduce its occupation of excessive subsequent image processing resources.

[0067] Based on the image annotations of each feature image by the image processing module 2, the classification processing module 3 performs classification analysis on the vehicle to be classified, thereby determining the vehicle type of the vehicle to be classified. Specifically, the module first calculates the ratio of the number of clear features to the number of fuzzy features in the multiple vehicle features (feature images) to determine the overall clarity of the appearance image. The module then determines whether the resulting ratio is greater than or equal to a preset ratio. The preset ratio is set by the vehicle classification model. If the vehicle classification model has high accuracy, the preset ratio can be set relatively low; if the vehicle classification model has low accuracy, the preset ratio must be set relatively high. The vehicle classification model is a neural network model with image recognition capabilities. If the resulting ratio is greater than or equal to the preset ratio, the appearance image clarity can be recognized by the vehicle classification model. Therefore, the appearance image can be directly input into the vehicle classification model for image classification and recognition, thereby determining the vehicle type of the vehicle to be classified. If the resulting ratio is less than the preset ratio, the appearance image clarity is low, and the vehicle classification model's recognition accuracy is low. In this case, gain processing is required on the fuzzy features to improve the appearance image clarity.

[0068] However, directly gaining the fuzzy features not only requires high hardware resources, but also, in the process of gaining, in order to obtain a better gain effect, more noise may be introduced or some irrelevant features may be generated, resulting in poor correlation between the fuzzy features and the gained image; in order to solve this problem, the present application performs correlation analysis on the fuzzy features, matches the fuzzy features with a preset vehicle feature table, and obtains a first correlation feature corresponding to the fuzzy features. The first correlation feature is an associated image with a high degree of fuzzy feature similarity. The preset vehicle feature table contains clear images of various models. In addition, the preset vehicle feature table will be updated in real time, and new or changed models will be added to it to ensure that it can fully cover. When matching fuzzy features with a preset vehicle feature table, some key information in the fuzzy features may be blurred, resulting in inaccurate representation of key pixels and, in turn, poor matching results. To improve matching performance, this application uses SIFT (Scale-Invariant Feature Transform) to extract multiple key pixels and feature descriptors from the fuzzy features. A feature descriptor is a data representation that describes specific features (edges, corners, and textures) in an image. SIFT can accurately extract pixels at key locations even when the image is blurred, but it cannot change the properties of the pixels themselves. Therefore, blurry pixels may exist among the multiple key pixels extracted from the fuzzy features. In this case, this application constructs a contour image from these multiple key pixels, then uses feature descriptors to supplement the contour image with details. Finally, the supplemented contour image is matched with the preset vehicle feature table to obtain a first associated feature. This step uses contour similarity instead of pixel similarity. Feature descriptors are then used to supplement the contour's detailed information, making the contour more accurate. This describes the fuzzy features from the overall image perspective, rather than focusing excessively on detailed information, thereby reducing the problem of poor matching results caused by blurred pixels.

[0069] After obtaining the first correlation feature, since the fuzzy feature lacks detailed information, the first correlation feature does not necessarily match the original clear feature. Therefore, further rationality evaluation is required to judge the correlation between the first correlation feature and the original clear feature. If the correlation is high, it means that the first correlation feature can well represent the original fuzzy feature. Specifically: first identify the blur type of the blur feature. In the scenario of a highway toll station, the blur type mainly focuses on motion blur, low-light blur and local occlusion blur; each blur type has different texture features in the image, among which motion blur is manifested as a directional texture feature, low-light blur is manifested as a non-uniform texture feature, and local occlusion blur is manifested as a discontinuous texture feature; then, according to the blur type of the blur feature, extract the corresponding texture feature in the first associated feature. At this time, the extracted texture feature reflects the essence of the blur feature. For example, if the blur type of the blur feature is motion blur, extract its directional texture feature from the first associated feature. At this time, if the directional texture feature of the first associated feature has a high correlation with the clear feature, it means that the directional texture feature of the first associated feature can well characterize the directional texture feature in the blur feature, further indicating that the first associated feature is more reasonable than the original clear feature; in judging When judging rationality, the present application calculates the similarity between the texture feature of the first associated feature and the clear feature to obtain a rationality score. The calculation dimensions include structure, brightness and contrast, wherein the structural similarity represents the similarity of the directional texture feature, the brightness similarity represents the similarity of the non-uniform texture feature, and the contrast similarity represents the similarity of the non-continuous texture feature. Since the fuzzy type of the fuzzy feature may not only include one fuzzy type, the present application sets the weights of multiple calculation dimensions according to the degree of influence of each calculation dimension in the fuzzy feature, and then performs weighted summation on the calculated similarities of the multiple dimensions according to the weights of the multiple calculation dimensions to obtain the final rationality score. Among them, the degree of influence of each calculation dimension in the fuzzy feature can be achieved by using the probability distribution of each fuzzy type in the fuzzy feature output by the lightweight CNN. At this time, these probability distributions reflect the proportion of various fuzzy types in the fuzzy feature, that is, the degree of influence of each calculation dimension in the fuzzy feature.

[0070] When the rationality score of the first associated feature and the original clear feature is greater than or equal to the preset rationality score, the first associated feature can replace the original fuzzy feature, and then the first associated feature and the original clear feature are input into the vehicle classification model for identification, so as to obtain a more accurate vehicle type.

[0071] In one possible implementation, before matching the fuzzy features with a preset vehicle feature table, in order to improve the accuracy of the match, the present application needs to perform image gain on the fuzzy features in advance to improve their clarity; specifically: first, the fuzzy features are subjected to wavelet decomposition, at which time low-frequency sub-bands, intermediate-frequency sub-bands, and high-frequency sub-bands are obtained, wherein the low-frequency sub-band contains the outline of the image, the intermediate-frequency sub-band contains the medium-scale details of the image, and the high-frequency sub-band contains the fine details of the image. It should be noted that since blurring will significantly attenuate high-frequency information, resulting in a significant decrease in the energy of the high-frequency sub-band, the high-frequency sub-band is not suitable as a gain object. Although the low-frequency sub-band is least affected by blurring, it cannot provide the detail information required for matching. Therefore, the low-frequency sub-band is also not suitable as a gain object; the intermediate-frequency sub-band not only contains the key structural information of the vehicle, but also this information will still be partially retained after blurring. Therefore, after performing wavelet decomposition on the fuzzy features, the present application extracts the mid-frequency sub-band as the subsequent gain object; in the gain process, in order to avoid distortion of the fuzzy features after gain due to excessive gain, the gain coefficient needs to be adaptively adjusted. The present application determines the first gain coefficient of the fuzzy features based on the proportion of the number of fuzzy features in multiple vehicle features. If the proportion of fuzzy features is high, it means that the image is blurred as a whole and requires strong enhancement to restore key information. If the proportion of fuzzy features is low, it means that the image is clear as a whole and only requires slight enhancement to avoid noise amplification. Then, after gaining the mid-frequency sub-band using the first gain coefficient, the image is reconstructed to obtain the fuzzy features to be matched for matching. Finally, the fuzzy features to be matched are matched with the preset vehicle feature table to obtain the first associated features of the fuzzy features, thereby improving the matching accuracy of the fuzzy features. The present application adopts the wavelet domain finite enhancement technology for the gain of the mid-frequency sub-band.

[0072] In a possible implementation, if the rationality score of the first associated feature and the original clear feature is less than the preset rationality score, it means that the first associated feature obtained by matching the fuzzy feature to be matched cannot well represent the original fuzzy feature. At this time, in order to improve the matching accuracy of the fuzzy feature, the present application needs to further perform image gain based on the original gain. Specifically: calculate the score difference between the current rationality score and the preset rationality score. The score difference at this time indicates the degree to which the original gain image needs further gain; then, based on the score difference, amplify and adjust the first gain coefficient to obtain the second gain coefficient, specifically, calculate the ratio of the score difference to the preset rationality score, then add 1 to the ratio result, and multiply it by the first gain coefficient to obtain the amplified second gain coefficient. This step is to further improve the clarity of the fuzzy feature on the one hand, and to avoid image distortion caused by excessive gain on the other hand; then, use the second gain coefficient to re-enhance the fuzzy feature, and then pre-process the enhanced image and match it with the preset vehicle feature table to obtain the second associated feature, wherein the pre-processing is to use SIFT to match the image according to the second The fuzzy features after gain coefficient gain are used to extract key pixels and feature descriptors, and then a contour image is constructed based on the key pixels and feature descriptors. During matching, the contour image is matched with the preset vehicle feature table to ensure matching accuracy; then the texture features of the obtained second associated features are calculated similarity with the clear features to obtain a second rationality score, where the similarity calculation includes structural similarity, brightness similarity and contrast similarity; at this time, it is judged whether the second rationality score is greater than or equal to the preset rationality score. If so, the second associated features and the clear features are input into the vehicle classification model for classification to obtain the vehicle type of the vehicle to be classified. If not, the above steps are repeated until the rationality score obtained by the rationality evaluation calculation is greater than or equal to the preset rationality score.

[0073] Finally, the grating sign 4 allocates the corresponding traffic lane for the vehicle to be classified according to the vehicle type to be classified obtained by the classification processing module 3, and indicates the traffic route of the vehicle to be classified through the grating indicator light to complete the classification guidance work of the vehicle to be classified.

[0074] The foregoing is merely an exemplary embodiment of the present disclosure and is not intended to limit the scope of the present disclosure. In other words, any equivalent variations and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the disclosure and the practical implications thereof.

[0075] This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not described herein. The description and examples are to be considered as exemplary only, and the scope and spirit of the present disclosure are to be defined by the claims.

Claims

1. An intelligent grating traffic control system, characterized in that: The system comprises a camera (1), an image processing module (2), a classification processing module (3) and a grating indicator board (4), wherein: The camera (1) is used to capture an appearance image of the vehicle to be classified; The image processing module (2) is used to extract multiple vehicle features from the appearance image, wherein the vehicle features include clear features and fuzzy features; The classification processing module (3) is used to perform classification analysis on the vehicle to be classified based on the plurality of vehicle features, and determine the vehicle type of the vehicle to be classified, which is specifically: calculating a ratio between the number of the sharp features and the number of the blurred features; Determine whether the ratio result is greater than or equal to a preset ratio; If the ratio result is greater than or equal to a preset ratio, the plurality of vehicle features are input into a vehicle classification model for classification to obtain the vehicle type of the vehicle to be classified; If the ratio result is less than the preset ratio, performing correlation analysis on the fuzzy feature to obtain a first correlation feature of the fuzzy feature, which specifically includes: Performing wavelet decomposition on the fuzzy features to obtain intermediate frequency subbands; determining a first gain coefficient of the fuzzy feature according to a proportion of the number of the fuzzy features in the plurality of vehicle features; Based on the first gain coefficient, reconstructing the image of the intermediate frequency sub-band to obtain a fuzzy feature to be matched; Matching the fuzzy feature to be matched with a preset vehicle feature table to obtain a first associated feature of the fuzzy feature, which specifically includes: extracting a plurality of key pixel points and feature descriptors of the fuzzy feature to be matched; Constructing a contour image of the fuzzy feature to be matched based on the plurality of key pixel points and feature descriptors; Matching the contour image with the preset vehicle feature table to obtain a first associated feature of the fuzzy feature; The rationality of the first associated feature of the fuzzy feature and the clear feature is evaluated to obtain a rationality score, which is specifically: Identifying the fuzzy type of the fuzzy feature; extracting texture features from the first associated features according to the fuzzy type; Calculating the similarity between the texture feature and the clarity feature to obtain the rationality score; If the rationality score is greater than or equal to a preset rationality score, inputting the clear feature and the first associated feature into the vehicle classification model for classification, the vehicle type of the vehicle to be classified; The grating sign (4) is used to indicate the passage road for the vehicle to be classified according to the vehicle type.

2. The system according to claim 1, wherein: The similarity calculation includes structural similarity, brightness similarity and contrast similarity.

3. The system according to claim 1, wherein: After performing a rationality evaluation on the first associated feature of the fuzzy feature and the clear feature to obtain a rationality score, the method further includes: a. If the rationality score is less than the preset rationality score, calculating the difference between the rationality score and the preset rationality score; b. amplifying and adjusting the first gain coefficient based on the score difference to obtain a second gain coefficient; c. Using the second gain coefficient, performing image enhancement, correlation feature matching, and rationality evaluation on the fuzzy feature to obtain a second correlation feature and a second rationality score; d. Determining whether the second rationality score is greater than or equal to the preset rationality score; If yes, inputting the second associated feature and the clear feature into a vehicle classification model for classification to obtain the vehicle type of the vehicle to be classified; If not, repeat steps a to d until the rationality score calculated by the rationality evaluation is greater than or equal to the preset rationality score.

4. The system according to claim 1, wherein: The image processing module (2) further includes a cache unit (31) and an image clarity recognition unit (32). The cache unit (31) is used to store the first appearance image of the vehicle to be classified, and select, from the plurality of first appearance images, a plurality of first appearance images whose memory proportions are greater than or equal to a preset proportion as appearance images to be processed according to the memory proportions of the plurality of first appearance images; The image definition recognition unit (32) is used to perform definition recognition on a plurality of the appearance images to be processed, and select the image with the highest definition from the plurality of the appearance images to be processed as the appearance image.

5. The system according to claim 4, characterized in that The performing clarity recognition on the plurality of appearance images to be processed specifically includes: A lightweight semantic segmentation network is used to extract multiple determination areas corresponding to each of the multiple appearance images to be processed, where the multiple determination areas are preset areas on the vehicle with low reflective interference; performing wavelet decomposition on the plurality of judgment regions corresponding to the plurality of appearance images to be processed, to obtain the gradient energies of the plurality of appearance images to be processed in low-frequency sub-bands and high-frequency sub-bands; The ratio of the gradient energy of the low-frequency sub-band to the gradient energy of the high-frequency sub-band of each of the plurality of appearance images to be processed is calculated to obtain the clarity of the plurality of appearance images to be processed.

6. The system according to claim 1, wherein: The extracting of multiple vehicle features from the appearance image specifically further includes: Segmenting the appearance image into multiple feature images of the same size; Identify the clear pixel points of the vehicle and the total pixel points of the vehicle corresponding to each of the plurality of feature images; determining the clarity of the plurality of feature images according to a ratio of the vehicle clear pixels in the plurality of feature images to the total number of vehicle pixels; If the clarity of the first feature image is greater than or equal to a preset clarity threshold, determining that the first feature image is a clear feature, the first feature image being any one of the plurality of feature images; If the clarity of the second feature image is less than a preset clarity threshold, it is determined that the second feature image is a blurred feature, and the second feature image is any one of the multiple feature images.

Images