Highway green pass vehicle image feature extraction and rapid screening system

Abstract

The application relates to the technical field of image analysis, in particular to a highway green passing vehicle image feature extraction and rapid screening system; the highway green passing vehicle image feature extraction and rapid screening system comprises an image acquisition unit, an image extraction unit and an image screening unit; the image acquisition, extraction and screening process are automated, the detection efficiency is greatly improved, the vehicle waiting time is greatly reduced, the smooth passing of the highway is ensured, a method based on morphological gradient and distance transformation is adopted, the complex scene that goods in a cargo box of a highway green passing vehicle are randomly stacked and mutually shielded can be coped with, adjacent and feature-similar sub-regions are combined based on feature similarity in an image fusion process, the redundant information in the image is reduced, in addition, goods not meeting the green passing standard can be screened out, and the subjectivity and uncertainty of manual judgment are avoided.

Description

Technical Field

[0001] This invention relates to the field of image analysis technology, specifically a system for extracting and rapidly filtering image features of vehicles using green lanes on highways. Background Technology

[0002] To reduce transportation costs and improve efficiency for agricultural products and other fresh goods, and to promote the circulation of agricultural products, the government has introduced a green toll policy for highways. This policy provides toll reductions and exemptions for vehicles transporting specific fresh agricultural products, aiming to safeguard people's livelihoods and promote agricultural development.

[0003] Traditional inspection methods rely primarily on manual checks. Staff at toll booths or specific checkpoints manually inspect vehicle cargo, visually determining whether the goods meet the green passage standards. This method has several drawbacks. First, manual inspections are extremely inefficient, easily causing traffic congestion and reducing highway throughput during peak traffic periods. Second, manual inspections are subjective and uncertain; different staff members may have different judgment standards, leading to misjudgments. This could result in ineligible vehicles receiving green passage benefits, causing toll revenue loss, or compliant vehicles being mistakenly stopped, causing unnecessary losses for vehicle owners.

[0004] In recent years, image processing technology has been increasingly widely used in the transportation sector, achieving remarkable results in areas such as license plate recognition and traffic flow monitoring. However, for the specific application scenario of cargo recognition in highway green-pass vehicles, the application of existing image processing technologies still faces many challenges. For example, the goods transported by highway green-pass vehicles are diverse in type and shape, and their arrangement inside the cargo box is often haphazard, potentially involving mutual occlusion and stacking. This makes the scanned images of the cargo inside the cargo box highly complex, making it difficult for traditional image processing algorithms to accurately extract and analyze their features.

[0005] Based on this, the present invention provides a system for extracting and rapidly filtering image features of green-passing vehicles on highways to solve the aforementioned technical problems. Summary of the Invention

[0006] The purpose of this invention is to provide an image feature extraction and rapid screening system for green-pass vehicles on highways. This system automates the image acquisition, extraction, and screening processes, significantly improving detection efficiency, greatly reducing vehicle waiting time, and ensuring smooth traffic flow on highways. By employing a method based on morphological gradients and distance transformation, it can handle complex scenarios where goods are randomly stacked and mutually obstructed in the cargo boxes of green-pass vehicles on highways. During image fusion, adjacent and feature-similar sub-regions are merged based on feature similarity, reducing redundant information in the image. In addition, it can also screen out goods that do not meet the green-pass standards, avoiding the subjectivity and uncertainty of manual judgment.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] This invention provides a system for extracting and rapidly filtering image features of vehicles using green lanes on highways, comprising an image acquisition unit, an image extraction unit, and an image filtering unit, wherein:

[0009] The image acquisition unit is used to scan and image the cargo box of a green-pass vehicle on the highway, acquire scanned images of the goods inside the cargo box, and collect a group of scanned images of the same green-pass vehicle on the highway.

[0010] The image extraction unit is used to divide each scanned image into regions, extract features from each sub-region, fuse the segmented scanned images based on the extracted features, extract features from the fused image, acquire and summarize features, and the image extraction unit is connected to the image acquisition unit.

[0011] The image filtering unit obtains the matching and recognition results of each scanned image based on the pre-stored cargo identification features, and is used to filter out cargo that does not meet the green passage standard. The image filtering unit is connected to the image extraction unit.

[0012] The present invention is further configured such that: the image acquisition unit includes an X-ray scanning module, an image aggregation module, and a first communication module, wherein:

[0013] The X-ray scanning module uses X-rays to scan and image the cargo box, obtaining scanned images of the goods inside the cargo box.

[0014] The image aggregation module is used to number and aggregate the scanned images of vehicles using the green channel on the same highway into corresponding scanned image groups. The image aggregation module is connected to the X-ray scanning module.

[0015] The first communication module is used to realize information interaction between the image acquisition unit and the image extraction unit, and the first communication module is connected to the image aggregation module.

[0016] The present invention is further configured such that: the image extraction unit includes a second communication module, a region segmentation module, and a region fusion module, wherein:

[0017] The second communication module is used to realize information exchange between the image extraction unit, the image acquisition unit, and the image filtering unit;

[0018] The region division module is used to divide each scanned image into regions, and the region division module is connected to the second communication module.

[0019] The region fusion module extracts features from each segmented sub-region based on the segmented scan image, and fuses the segmented scan image based on the extracted features. The region fusion module is connected to the region division module.

[0020] The present invention is further configured such that the process of dividing each scanned image into regions is as follows:

[0021] Calculate the morphological gradient of the scanned image In the formula, This indicates that a dilation operation is performed on the original grayscale image I. This indicates that an erosion operation is performed on the original grayscale image I;

[0022] Perform a distance transform on the morphological gradient image to obtain the distance of each pixel to the nearest background point. In the formula, (x, y) are the pixel coordinates of the currently calculated distance transformation value, (s, t) are the coordinates of the background pixel, and Background is the set of background pixels;

[0023] The Otsu method is used to determine the threshold T, and the distance transform image is binarized to obtain the labeled image L;

[0024] For each pixel (x, y) in the labeled image L, check the pixel values ​​in its neighborhood. If the pixel value is less than all the pixel values ​​in its neighborhood, mark it as a local minimum point and assign it a unique label value.

[0025] Each local minimum point with a different label value in the labeled image L is taken as a seed point and placed in a priority queue. The priority of each seed point in the queue is determined by the value in its corresponding distance-transformed image. The smaller the distance value, the higher the priority.

[0026] Take the highest priority seed point from the priority queue, check the neighboring pixels of the seed point, and if the neighboring pixels are not marked, mark them with the same mark value as the seed point;

[0027] Repeat the above process. When the expansions of different marked regions meet, a dividing line is obtained. The scanned image is divided by the dividing line to obtain a segmented scanned image.

[0028] The present invention is further configured such that the process of fusing the segmented scanned images is as follows:

[0029] Obtain the grayscale and texture features of each sub-region;

[0030] The grayscale and texture features of each sub-region are compared for similarity to obtain grayscale similarity and texture similarity. These are then compared with preset grayscale similarity thresholds and texture similarity thresholds. If the grayscale similarity is greater than the grayscale similarity threshold and the texture similarity is greater than the texture similarity threshold, the corresponding sub-regions are merged. Otherwise, they are not merged, resulting in a fused large-area image.

[0031] The present invention is further configured such that: the image extraction unit further includes a feature extraction module and a feature summarization module, wherein:

[0032] The feature extraction module is used to extract features from a large area image, and the feature extraction module is connected to the region fusion module;

[0033] The feature aggregation module obtains a first feature set of the corresponding scanned image based on the acquired large-area image features, and aggregates a second feature set of different scanned images. The feature aggregation module is connected to both the second communication module and the feature extraction module.

[0034] The present invention is further configured such that the process of feature extraction for large-area images is as follows:

[0035] The Canny edge detection algorithm is used to extract the contours of large-area images;

[0036] Based on the extracted contour, obtain the area, perimeter, and aspect ratio of the contour. The formula for calculating the area is: In the formula, n is the number of points that form the closed contour, (x i y i Let be the coordinates of the i-th point on the contour, and the formula for calculating the perimeter is: The formula for calculating the aspect ratio is: In the formula, ω is the width of the bounding rectangle of the contour, and h is the height of the bounding rectangle of the contour.

[0037] The present invention is further configured such that: the image filtering unit includes a third communication module, a feature matching module, and a database module, wherein:

[0038] The third communication module is used to realize information interaction between the image filtering unit and the image extraction unit.

[0039] The feature matching module is used to match the features in the second feature set with the pre-stored cargo identification features to obtain the matching and identification results of each scanned image. The feature matching module is connected to the third communication module.

[0040] The database module is used to store preset identification features and received data information. The database module is connected to both the third communication module and the feature matching module.

[0041] The present invention is further configured such that: the image filtering unit further includes an image filtering module, wherein the image filtering module is used to filter out goods that do not meet the green passage standard, and the image filtering module is connected to both the feature matching module and the database module.

[0042] The present invention is further configured such that the process of screening out goods that do not meet the green passage standards is as follows:

[0043] Based on the matching and recognition results of each scanned image, information on the type and quantity of goods is obtained;

[0044] The types and quantities of goods obtained from each scanned image are compared. If they are within a preset error threshold, the average types and quantities are calculated. Otherwise, the cargo box is scanned again.

[0045] When the error is within the preset error threshold, the system also compares the type and quantity of goods with the pre-stored green passage standards to filter out goods that do not meet the green passage standards.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] This invention automates the image acquisition, extraction, and screening processes, significantly improving detection efficiency, greatly reducing vehicle waiting time, and ensuring smooth traffic flow on highways. In region segmentation, a method based on morphological gradients and distance transformation is employed, effectively addressing complex scenarios where goods are haphazardly stacked and obstructed within the cargo compartments of vehicles eligible for green passage on highways. This accurately distinguishes different goods or different parts of the same goods, greatly improving the accuracy of region segmentation. During image fusion, adjacent and similar sub-regions are merged based on feature similarity, reducing redundant information in the images. Simultaneously, the fused large region contains more pixel information, improving the representativeness and stability of the features. Furthermore, based on pre-stored cargo identification features, the summarized features are matched to obtain the matching and identification results of each scanned image. The invention also compares the type and quantity of goods with green passage standards, filtering out goods that do not meet the green passage standards. This avoids the subjectivity and uncertainty of manual judgment, improving the accuracy and fairness of the screening process. Attached Figure Description

[0048] Figure 1 This is a system diagram of the highway green passage vehicle image feature extraction and rapid screening system of the present invention.

[0049] Figure 2 This is a system diagram of the image acquisition unit in the highway green passage vehicle image feature extraction and rapid screening system of the present invention.

[0050] Figure 3 This is a system diagram of the image extraction unit in the highway green passage vehicle image feature extraction and rapid screening system of the present invention.

[0051] Figure 4 This is a system diagram of the image filtering unit in the highway green passage vehicle image feature extraction and rapid filtering system of the present invention.

[0052] Explanation of icon numbers:

[0053] 100. Image acquisition unit; 110. X-ray scanning module; 120. Image aggregation module; 130. First communication module; 200. Image extraction unit; 210. Second communication module; 220. Region division module; 230. Region fusion module; 240. Feature extraction module; 250. Feature aggregation module; 300. Image filtering unit; 310. Third communication module; 320. Feature matching module; 330. Database module; 340. Image filtering module. Detailed Implementation

[0054] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0055] Example:

[0056] like Figures 1-4As shown, this embodiment provides a system for image feature extraction and rapid screening of green-pass vehicles on highways, including an image acquisition unit 100, an image extraction unit 200, and an image screening unit 300. The image acquisition unit 100 scans the cargo box of a green-pass vehicle on the highway, acquiring scanned images of the goods inside the cargo box, and then aggregates scanned images of the same green-pass vehicle. The image extraction unit 200 divides each scanned image into regions, extracts features from each sub-region, fuses the segmented scanned images based on the extracted features, extracts features from the fused images, and acquires and summarizes the features. The image extraction unit 200 is connected to the image acquisition unit 100. The image screening unit 300 acquires the matching recognition results of each scanned image based on pre-stored cargo identification features, and filters out goods that do not meet the green-pass standards. The image screening unit 300 is connected to the image extraction unit 200.

[0057] In this embodiment, it should be noted that the image acquisition unit 100 uses X-rays to scan the goods inside the cargo container from different angles, thereby obtaining scanned images from different angles. Multiple scanned images of the same truck are numbered and uploaded to the image extraction unit 200. The image extraction unit 200 receives the scanned image group from the image acquisition unit 100 and divides each scanned image into regions. That is, it performs region division by calculating morphological gradients, distance transformations, Otsu's method, etc., which can effectively distinguish different goods or different parts of the same goods, and accurately find the dividing line even in complex image scenes, achieving reasonable region division. Then, the segmented scanned images are fused, and feature extraction is performed on the fused image to obtain and summarize features. The feature extraction of sub-regions can deeply explore the information contained in each sub-region. Among them, grayscale features reflect the brightness distribution of the sub-region. Texture features reflect the surface texture information of sub-regions, which can effectively improve the ability to distinguish different types. Through image fusion, similar sub-regions can be merged into a large region, reducing redundant information in the image, making the image more concise, and facilitating subsequent analysis and processing. By extracting features from the fused image, features can be captured better, improving the accuracy and reliability of cargo identification. The image extraction unit 200 uploads the processed image information to the image filtering unit 300. The image filtering unit 300 obtains the type and quantity information of the cargo based on the matching and recognition results of each scanned image. It compares the type and quantity information of the cargo obtained from each scanned image and then compares this information with the pre-stored green passage standards. If it is found that a batch of cargo contains non-agricultural products that do not meet the green passage standards, such as some industrial products, the cargo information that does not meet the green passage standards is filtered out.

[0058] In this invention, the image acquisition unit 100 includes an X-ray scanning module 110, an image aggregation module 120, and a first communication module 130. Specifically: the X-ray scanning module 110 uses X-rays to scan and image the cargo box, acquiring scanned images of the goods inside; the image aggregation module 120 is used to number and aggregate scanned images of vehicles using the same highway green channel into corresponding scanned image groups, and is connected to the X-ray scanning module 110; the first communication module 130 is used to realize information interaction between the image acquisition unit 100 and the image extraction unit 200, and is connected to the image aggregation module 120.

[0059] In this embodiment, it should be noted that the X-ray scanning module 110 uses X-rays to scan and image the cargo box of a truck. For example, if the cargo box contains fruits such as apples and bananas, as well as some vegetables, the X-rays penetrate the cargo box and the goods, forming a scanned image of the goods. The scanned image is transmitted to the image aggregation module 120. The image aggregation module 120 numbers multiple scanned images of the same truck, such as S001, S002, etc., and aggregates them into corresponding scanned image groups. As an example, assuming that a total of 5 scanned images from different angles are obtained in this scan, the image aggregation module 120 organizes them together to form corresponding scanned image groups. The obtained scanned image groups are uploaded to the image extraction unit 200 through the first communication module 130.

[0060] In this invention, the image extraction unit 200 includes a second communication module 210, a region division module 220, and a region fusion module 230, wherein: the second communication module 210 is used to realize information interaction between the image extraction unit 200, the image acquisition unit 100, and the image filtering unit 300; the region division module 220 is used to divide each scanned image into regions, and the region division module 220 is connected to the second communication module 210; the region fusion module 230 extracts features from each sub-region obtained by the segmentation of the scanned image, and fuses the segmented scanned image based on the extracted features, and the region fusion module 230 is connected to the region division module 220.

[0061] The process of dividing each scanned image into regions is as follows:

[0062] Calculate the morphological gradient of the scanned image In the formula, This indicates that a dilation operation is performed on the original grayscale image I. This indicates that an erosion operation is performed on the original grayscale image I.

[0063] Perform a distance transform on the morphological gradient image to obtain the distance of each pixel to the nearest background point. In the formula, (x, y) are the pixel coordinates of the currently calculated distance transformation value, (s, t) are the coordinates of the background pixel, and Background is the set of background pixels.

[0064] The Otsu method is used to determine the threshold T, and the distance-transformed image is binarized to obtain the labeled image L.

[0065] For each pixel (x, y) in the labeled image L, check the pixel values ​​in its neighborhood. If the pixel value is less than all the pixel values ​​in its neighborhood, mark it as a local minimum and assign it a unique label value.

[0066] Each local minimum point with a different label value in the labeled image L is taken as a seed point and placed in a priority queue. The priority of each seed point in the queue is determined by the value in its corresponding distance-transformed image. The smaller the distance value, the higher the priority.

[0067] Take the highest priority seed point from the priority queue, check the neighboring pixels of the seed point, and if the neighboring pixels are not marked, mark them with the same mark value as the seed point.

[0068] Repeat the above process. When the expansions of different marked regions meet, a dividing line is obtained. The scanned image is divided by the dividing line to obtain a segmented scanned image.

[0069] Furthermore, the process of fusing the segmented scanned images is as follows:

[0070] Obtain the grayscale and texture features of each sub-region.

[0071] The grayscale and texture features of each sub-region are compared for similarity to obtain grayscale similarity and texture similarity. These are then compared with preset grayscale similarity thresholds and texture similarity thresholds. If the grayscale similarity is greater than the grayscale similarity threshold and the texture similarity is greater than the texture similarity threshold, the corresponding sub-regions are merged. Otherwise, they are not merged, resulting in a fused large-area image.

[0072] In this embodiment, it should be noted that the second communication module 210 receives information from the image acquisition unit 100 and uploads it to the region segmentation module 220. The region segmentation module 220 divides each scanned image into regions and transmits the segmented scanned images to the region fusion module 230. The region fusion module 230 extracts features from each segmented sub-region and fuses the segmented scanned images based on the extracted features. As an example, it is assumed that the grayscale similarity threshold is 0.8 and the texture similarity threshold is 0.7. If the grayscale similarity of two sub-regions is greater than 0.8 and the texture similarity is greater than 0.7, they are merged; otherwise, they are not merged to obtain a fused large-area image.

[0073] In this invention, the image extraction unit 200 further includes a feature extraction module 240 and a feature summarization module 250, wherein: the feature extraction module 240 is used to extract features from a large area image, and the feature extraction module 240 is connected to the region fusion module 230; the feature summarization module 250 obtains a first feature set of the corresponding scanned image and summarizes a second feature set of different scanned images based on the obtained large area image features, and the feature summarization module 250 is connected to both the second communication module 210 and the feature extraction module 240.

[0074] The process of feature extraction for large-area images is as follows:

[0075] The Canny edge detection algorithm is used to extract the contours of large-area images.

[0076] Based on the extracted contour, obtain the area, perimeter, and aspect ratio of the contour. The formula for calculating the area is: In the formula, n is the number of points that form the closed contour, (x i y i Let be the coordinates of the i-th point on the contour, and the formula for calculating the perimeter is: The formula for calculating the aspect ratio is: In the formula, ω is the width of the bounding rectangle of the contour, and h is the height of the bounding rectangle of the contour.

[0077] In this embodiment, it should be noted that the feature extraction module 240 receives information from the region fusion module 230 and obtains feature information of a large area image, which is then transmitted to the feature aggregation module 250. After aggregation by the feature aggregation module 250, it is uploaded to the image filtering unit 300 through the second communication module 210. As an example, suppose the outline of a watermelon is composed of 100 points, whose coordinates are (x1, y1), (x2, y2), ..., (x...). 100 y 100 According to the area calculation formula Substitute the coordinate values ​​to calculate the area of ​​the watermelon outline; for the watermelon outline, calculate the distance between adjacent points according to the perimeter calculation formula and sum them to obtain the perimeter of the watermelon outline; measure the width of the circumscribed rectangle of the watermelon outline as 30 and the height as 20, and calculate the aspect ratio of the watermelon outline as 1.5 according to the aspect ratio calculation formula.

[0078] In this invention, the image filtering unit 300 includes a third communication module 310, a feature matching module 320, and a database module 330, wherein: the third communication module 310 is used to realize information interaction between the image filtering unit 300 and the image extraction unit 200; the feature matching module 320 is used to match the features in the second feature set with the pre-stored cargo identification features to obtain the matching identification results of each scanned image, and the feature matching module 320 is connected to the third communication module 310; the database module 330 is used to store the preset identification features and the received data information, and the database module 330 is connected to both the third communication module 310 and the feature matching module 320.

[0079] In addition, the image filtering unit 300 also includes an image filtering module 340, which is used to filter out goods that do not meet the green passage standards. The image filtering module 340 is connected to both the feature matching module 320 and the database module 330.

[0080] The process for identifying goods that do not meet the green passage standards is as follows:

[0081] Based on the matching and recognition results of each scanned image, information on the type and quantity of goods is obtained.

[0082] The types and quantities of goods obtained from each scanned image are compared. If they are within a preset error threshold, the average types and quantities are calculated. Otherwise, the cargo boxes are scanned again.

[0083] When the error is within the preset error threshold, the system also compares the type and quantity of goods with the pre-stored green passage standards to filter out goods that do not meet the green passage standards.

[0084] In this embodiment, it should be noted that the information received by the image extraction unit 200 through the third communication module 310 is transmitted to the feature matching module 320 to obtain the matching and recognition results of each scanned image. Then, the image filtering module 340 filters out goods that do not meet the green passage standard. As an example, the type and quantity information of goods obtained from each scanned image are compared. Assuming that the preset error threshold is 5%, if the difference in the quantity and type information of goods in each scanned image is within 5%, the average type and quantity information is calculated. Then, this information is compared with the pre-stored green passage standard. If it is found that there are non-agricultural products that do not meet the green passage standard in a certain batch of goods, such as some industrial products, then the information of these goods that do not meet the green passage standard is filtered out.

[0085] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0086] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A system for image feature extraction and rapid screening of green pass vehicles on highways, characterized in that, The system comprises an image acquisition unit (100), an image extraction unit (200) and an image screening unit (300), wherein: The image acquisition unit (100) is configured to scan and image the container of a green-passing vehicle on a highway, acquire a scan image of the goods in the container, and collect a scan image group of the same green-passing vehicle on the highway; The image extraction unit (200) is configured to divide each scan image into regions, extract features of each segmented sub-region, fuse the segmented scan images based on the extracted features, extract features of the fused image, and collect and summarize the features, and the image extraction unit (200) is connected with the image acquisition unit (100); The process of dividing each scan image into regions is as follows: Computing morphological gradients of scanned images wherein, denotes an expansion operation on the original gray scale image I, denotes an erosion operation on the original gray scale image I; Distance transform is performed on the morphological gradient image to obtain the distance of each pixel to the nearest background point In the formula, (x, y) is the pixel coordinate currently calculating the distance transform value, (s, t) is the coordinate of the background pixel, and Background is the background pixel set. The threshold value T is determined by using the Otsu method to binarize the distance transform image, and a label image L is obtained; For each pixel (x, y) in the label image L, check the pixel values in its neighborhood, if the pixel value is less than all pixel values in its neighborhood, mark it as a local minimum point and assign it a unique label value; Each local minimum point with a different label value in the label image L is taken as a seed point and put into a priority queue, wherein the priority of each seed point in the queue is determined by its corresponding value in the distance transform image, and the smaller the distance value, the higher the priority; The seed point with the highest priority is taken out from the priority queue, and the neighborhood pixels of the seed point are checked, if the neighborhood pixels are not marked, they are marked with the same label value as the seed point; The above process is repeated, and when the expansion of different labeled regions meets, a division line is obtained, the scan image is divided by the division line, and the segmented scan image is obtained; The image screening unit (300) is configured to acquire a matching recognition result of each scan image according to pre-stored goods recognition features, and screen out goods that do not meet the green-passing standard, and the image screening unit (300) is connected with the image extraction unit (200).

2. The expressway green pass vehicle image feature extraction and rapid screening system according to claim 1, characterized in that, The image acquisition unit (100) comprises an X-ray scanning module (110), an image collection module (120) and a first communication module (130), wherein: The X-ray scanning module (110) scans and images the container by using X-rays, and acquires a scan image of the goods in the container; The image collection module (120) is configured to number the scan images of the same green-passing vehicle on the highway, and collect the scan images into a corresponding scan image group, and the image collection module (120) is connected with the X-ray scanning module (110); The first communication module (130) is configured to realize information interaction between the image acquisition unit (100) and the image extraction unit (200), and the first communication module (130) is connected with the image collection module (120). 3.The expressway green pass vehicle image feature extraction and rapid screening system according to claim 1, characterized in that, The image extraction unit (200) comprises a second communication module (210), a region division module (220) and a region fusion module (230), wherein: The second communication module (210) is configured to realize information interaction between the image extraction unit (200) and the image acquisition unit (100) and the image screening unit (300); The region division module (220) is configured to divide each scanning image into regions, and the region division module (220) is connected with the second communication module (210); The region fusion module (230) is configured to extract features of each sub-region obtained by division according to the divided scanning image, and fuse the divided scanning image based on the extracted features, and the region fusion module (230) is connected with the region division module (220).

4. The expressway green pass vehicle image feature extraction and rapid screening system according to claim 3, characterized in that, The process of fusing the divided scanning image is as follows: Obtain the gray scale and texture features of each sub-region; The gray scale and texture features of each sub-region are compared in similarity, respectively, to obtain the gray scale similarity and the texture similarity, and compared with the preset gray scale similarity threshold and the texture similarity threshold, if the gray scale similarity is greater than the gray scale similarity threshold, and if the texture similarity is greater than the texture similarity threshold, the corresponding sub-region is merged, otherwise, not merged, to obtain a large region image after fusion.

5. The expressway green pass vehicle image feature extraction and rapid screening system according to claim 4, characterized in that, The image extraction unit (200) further comprises a feature extraction module (240) and a feature summary module (250), wherein: The feature extraction module (240) is configured to extract features of the large region image, and the feature extraction module (240) is connected with the region fusion module (230); The feature summary module (250) is configured to obtain a first feature set of the corresponding scanning image according to the obtained large region image features, and to summarize a second feature set of different scanning images, and the feature summary module (250) is connected with the second communication module (210) and the feature extraction module (240).

6. The expressway green pass vehicle image feature extraction and rapid screening system according to claim 5, characterized in that, The process of extracting features of the large region image is as follows: The Canny edge detection algorithm is used to extract the contour of the large region image; According to the extracted contour, an area, a perimeter and an aspect ratio of the contour are obtained, wherein the area is calculated by the formula wherein n is the number of points constituting the closed contour, (x i , y i ) is the coordinate of the i-th point on the contour, the perimeter is calculated by the formula and the aspect ratio is calculated by the formula wherein ω is the width of the circumscribed rectangle of the contour, and h is the height of the circumscribed rectangle of the contour.

7. The expressway green pass vehicle image feature extraction and rapid screening system according to claim 6, characterized in that, The image screening unit (300) comprises a third communication module (310), a feature matching module (320) and a database module (330), wherein: The third communication module (310) is configured to realize information interaction between the image screening unit (300) and the image extraction unit (200); The feature matching module (320) is configured to match the features in the second feature set with the pre-stored cargo identification features to obtain a matching identification result of each scanning image, and the feature matching module (320) is connected with the third communication module (310); The database module (330) is configured to store the pre-set identification features and store the received data information, and the database module (330) is connected with the third communication module (310) and the feature matching module (320).

8. The expressway green pass vehicle image feature extraction and rapid screening system according to claim 7, characterized in that, The image screening unit (300) further comprises an image screening module (340), wherein the image screening module (340) is configured to screen out cargos that do not meet the green pass standard, and the image screening module (340) is connected with the feature matching module (320) and the database module (330). 9.The expressway green pass vehicle image feature extraction and rapid screening system according to claim 8, characterized in that, The process of screening out cargos that do not meet the green pass standard is as follows: According to the matching recognition result of each scanning image, the kind and quantity information of the goods are obtained; The kind and quantity information of the goods obtained from each scanning image are compared, if within a preset error threshold, the average kind and quantity information are obtained, otherwise, the scanning of the container is re-performed; When within the preset error threshold, the kind and quantity information of the goods are compared with the pre-stored green pass standard, and the goods information not meeting the green pass standard is screened out.

Images