Transaction Management System Based on ETC Control Device

Abstract

The present invention provides a transaction management system based on an ETC control device, which relates to the field of intelligent transportation. The transaction management system based on the ETC control device includes a roadside unit, an on-vehicle unit, multiple photographing units, a data processing unit, and a central management unit. Image preprocessing is performed on multiple collected images. The multiple preprocessed images are screened through the Brenner gradient function to screen out the first group of images. The multiple preprocessed images are screened through the Tenengrad gradient function to screen out the second group of images. The first group of images and the second group of images are subjected to an intersection operation to obtain a preliminarily processed image set. The preliminarily processed image set is subjected to image registration and graphic splicing to obtain a target image. The present invention uses multiple photographing units to obtain multiple images. After obtaining multiple images, the multiple images are screened and fused, which is beneficial to obtaining clearer images and facilitating the accurate acquisition of vehicle information.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation, and particularly to a transaction management system based on an ETC control device. Background Art

[0002] ETC, the Chinese translation of which is Electronic Toll Collection, is for automatic toll collection on highways or bridges. Through dedicated short-range communication between an on-vehicle electronic tag installed on the vehicle windshield and a microwave antenna on the ETC lane of the toll station, and by using computer networking technology for back-office settlement processing with banks, the purpose of enabling vehicles to pass through highway or bridge toll stations without stopping while paying highway or bridge tolls is achieved.

[0003] When an ETC vehicle enters the toll station, a camera will also take pictures at the same time, recording information such as the license plate number and vehicle type through the pictures, accurately identifying each vehicle passing through the ETC toll station to ensure the accuracy of the toll collection object. However, in poor weather conditions, such as heavy rain, heavy snow, thick fog and other weather conditions, the transmission of microwave signals may be interfered. These weather phenomena may cause attenuation, scattering or reflection of microwave signals, thereby reducing the intensity and stability of the signals, and further affecting the accurate identification of the on-vehicle electronic tag by the ETC microwave antenna. Moreover, in poor weather conditions, the image information obtained by the imaging unit may also be unclear, which to a certain extent affects the normal transactions of ETC vehicles.

[0004] Therefore, it is necessary to provide a new transaction management system based on an ETC control device to solve the above technical problems. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a transaction management system based on an ETC control device.

[0006] The transaction management system based on an ETC control device provided by the present invention includes a roadside unit: installed on the ETC dedicated lane, responsible for sending microwave signals to the on-vehicle unit and obtaining first vehicle information;

[0007] An on-vehicle unit: installed in a vehicle using ETC services, receiving the microwave signals sent by the roadside unit, and sending the first vehicle information back to the roadside unit through the microwave signals;

[0008] Multiple imaging units: installed on the ETC dedicated lane, used for image acquisition of vehicles entering a predetermined area;

[0009] Perform image preprocessing on the collected multiple images, screen the preprocessed multiple images through the Brenner gradient function to screen out a first group of images, screen the preprocessed multiple images through the Tenengrad gradient function to screen out a second group of images, perform intersection operation on the first group of images and the second group of images to obtain an initial processing image set, perform image registration and graphic splicing on the initial processing image set to obtain a target image;

[0010] Data processing unit: used for receiving the first vehicle information acquired by the roadside unit and responsible for parsing the target image to acquire the second vehicle information;

[0011] Central management unit: compares the first vehicle information and the second vehicle information, generates transaction information when the first vehicle information and the second vehicle information coincide, and sends the transaction information to the vehicle-mounted unit, otherwise, issues an alarm.

[0012] Preferably, the first vehicle information and the second vehicle information both include a license plate number, a vehicle type, and a vehicle model.

[0013] Preferably, the step of screening the preprocessed multiple images using the Brenner gradient function comprises:

[0014] S301: convert multiple color images into grayscale images, grayscale value = 0.299R + 0.587G +0.114B;

[0015] S302: traverse each pixel of the grayscale image to calculate the overall clarity of the image;

[0016] D( )= ;

[0017] in, Representing images Corresponding pixels Gray value, D( ) is the image clarity value;

[0018] S303: Setting a threshold value for distinguishing a clear image from a blurred image;

[0019] S304: Compare the clarity value of each image with a threshold value. Images with a value greater than the threshold value are clear images, which are screened out and marked as "satisfying clarity requirements". Images with a value less than the threshold value are blurred images.

[0020] Preferably, the step of screening the preprocessed multiple images using the Tenengrad gradient function comprises:

[0021] S401: Convert multiple color images into grayscale images. The grayscale value = 0.299R + 0.587G + 0.114B;

[0022] S402: Use the Sobel operator to calculate the gradient values of each image in the horizontal and vertical directions respectively;

[0023] S403: For each pixel point, calculate the sum of squares of its gradient values in the horizontal and vertical directions to obtain the sum of squared gradients of this point;

[0024] S404: Traverse the entire image, accumulate the sum of squared gradient values of all pixel points, and then divide by the total number of pixels to obtain the average gradient value of the entire image;

[0025] S405: Set a threshold to distinguish clear images and blurred images;

[0026] S406: Compare the average gradient value of each image to be screened with the set threshold, and screen out the clear images with an average gradient value greater than the threshold, and mark them as "meeting the clarity requirements".

[0027] Preferably, the intersection operation includes the following steps:

[0028] S501: Create a new boolean array to store images that simultaneously meet the threshold requirements of the Brenner gradient function and the Tenengrad gradient function;

[0029] S502: For each image, check the screening results of both the Brenner gradient function and the Tenengrad gradient function simultaneously;

[0030] S503: If an image is marked as "meeting the clarity requirements" in the screening of the Brenner gradient function and is also marked as "meeting the clarity requirements" in the screening of the Tenengrad gradient function, then add this image to the boolean array, otherwise, ignore this image;

[0031] S504: After traversing all images, the boolean array contains all images that simultaneously meet the clarity requirements of the two functions. Output the boolean array as the set of finally screened clear images, that is, the initial processed image set.

[0032] Preferably, the image registration and graphic splicing of the initial processed image set includes the following steps:

[0033] S601: Use the SIFT algorithm to extract feature points and their descriptors from the initial processed image set;

[0034] When extracting feature points, a judgment threshold for the number of extracted feature points is set, and the contrast of the image is obtained through the gray-level co-occurrence matrix. When the contrast is greater than the threshold, the number of extracted feature points is E, and when the contrast is less than the threshold, the number of extracted feature points is F, where E = 2F. Feature matching is performed through the feature points and their descriptors to find the matching feature points between different images;

[0035] S602: According to the matching feature points, calculate the geometric transformation relationship between the images in the initial processed image set, and transform the images to align multiple images;

[0036] S603: Use the weighted average algorithm to splice the aligned images.

[0037] Preferably, the image preprocessing is noise reduction processing, and the noise reduction processing adopts any one of Gaussian filtering, mean filtering, and non-local mean filtering.

[0038] Preferably, the image preprocessing is defogging processing, and the defogging processing includes the following steps:

[0039] S801: Perform graying processing on the image: Convert the collected image into a grayscale image, and use the weighted average method to convert the RGB three channels of the color image into grayscale values;

[0040] S802: Extract the dark channel: By calculating the minimum value of each pixel in the RGB three color channels of the image and finding the minimum value of this minimum value in the surrounding neighborhood of each pixel, a dark channel image is obtained;

[0041] S803: Estimate the atmospheric light: By performing threshold processing on the dark channel image, calculate the color average value of the corresponding points of the pixels with dark channel values higher than the threshold in the original color image as the estimated value of the atmospheric light;

[0042] S804: Calculate the transmittance and obtain the defogged image.

[0043] Compared with the related technology, the transaction management system based on the ETC control device provided by the present invention has the following beneficial effects:

[0044] 1. The present invention screens out the first group of images through the Brenner gradient function, screens out the second group of images through the Tenengrad gradient function, and performs intersection operation to obtain the initial processed image set. Since two algorithms are used for image processing, the respective advantages of the Brenner gradient function and the Tenengrad gradient function are utilized, making the obtained initial processed image set more stable.

[0045] 2. When the present invention captures images of a vehicle, multiple imaging units are used to obtain multiple images, increasing the basis for reference of vehicle information. After obtaining multiple images, the multiple images are screened and fused, which is conducive to obtaining clearer images and facilitating the accurate acquisition of vehicle information. In addition, since screening is performed before fusing multiple images, to a certain extent, the speed of image fusion is improved.

[0046] 3. When the present invention conducts transaction management, by improving the clarity of images, the error rate of transactions is reduced, and problems that may arise subsequently are minimized.

[0047] 4. When the present invention extracts feature points, by setting a judgment threshold for the number of feature points to be extracted, and obtaining the contrast of the image through a gray-level co-occurrence matrix, when the contrast is greater than the threshold, the number of feature points extracted is greater than the number of feature points extracted when the contrast is less than the threshold. In this way, feature points can be extracted more precisely, and to a certain extent, the accuracy of matching is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a flowchart block diagram of a transaction management system based on an ETC control device provided by the present invention;

[0049] Figure 2 is a schematic structural diagram of a central management unit and an in-vehicle unit provided by the present invention;

[0050] Figure 3 is a flowchart block diagram of the screening steps of the Brenner gradient function provided by the present invention;

[0051] Figure 4 is a flowchart block diagram of the screening steps of the Tenengrad gradient function provided by the present invention;

[0052] Figure 5 is a flowchart block diagram of the intersection operation provided by the present invention;

[0053] Figure 6 is a flowchart block diagram of image registration and graphic splicing provided by the present invention;

[0054] Figure 7 is a flowchart block diagram of haze removal processing provided by the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0055] The present invention will be further described below with reference to the drawings and embodiments.

[0056] Please refer to Figures 1-7 , where Figure 1 is a flowchart block diagram of a transaction management system based on an ETC control device provided by the present invention; Figure 2Schematic diagram of the central management unit and in-vehicle unit provided by the present invention; Figure 3 Flow chart block diagram of the screening steps of the Brenner gradient function provided by the present invention; Figure 4 Flow chart block diagram of the screening steps of the Tenengrad gradient function provided by the present invention; Figure 5 Flow chart block diagram of the intersection operation provided by the present invention; Figure 6 Flow chart block diagram of image registration and graphic stitching provided by the present invention; Figure 7 Flow chart block diagram of haze removal processing provided by the present invention.

[0057] In the specific implementation process, such as Figures 1-7 shown

[0058] Embodiment 1

[0059] A transaction management system based on an ETC control device, comprising:

[0060] Road side unit: Installed on the ETC dedicated lane, responsible for sending microwave signals to the in-vehicle unit and obtaining the first vehicle information;

[0061] In-vehicle unit: Installed in a vehicle using ETC services, receiving the microwave signals sent by the road side unit, and sending the first vehicle information back to the road side unit through the microwave signals;

[0062] Multiple shooting units: Installed on the ETC dedicated lane, used for image acquisition of vehicles entering a predetermined area;

[0063] Perform image preprocessing on the collected multiple images, screen out the first group of images by screening the preprocessed multiple images through the Brenner gradient function, screen out the second group of images by screening the preprocessed multiple images through the Tenengrad gradient function, perform an intersection operation on the first group of images and the second group of images to obtain a preliminary processed image set, and perform image registration and graphic stitching on the preliminary processed image set to obtain a target image;

[0064] Data processing unit: Used to receive the first vehicle information obtained by the road side unit and responsible for parsing the target image to obtain the second vehicle information;

[0065] Central management unit: Compare the first vehicle information and the second vehicle information. When the first vehicle information and the second vehicle information coincide, generate transaction information and send the transaction information to the in-vehicle unit. Otherwise, issue an alarm. Both the first vehicle information and the second vehicle information include license plate number, vehicle type, and vehicle model;

[0066] The steps of screening the preprocessed multiple images by the Brenner gradient function include:

[0067] S301: Convert multiple color images into grayscale images, where the grayscale value = 0.299R + 0.587G + 0.114B;

[0068] S302: Traverse each pixel of the grayscale image to calculate the overall clarity of the image;

[0069] D( ) = ;

[0070] where, represents the grayscale value of the corresponding pixel of the image corresponding pixel of the image, and D( ) is the image clarity value;

[0071] S303: Set a threshold to distinguish clear images and blurred images;

[0072] S304: Compare the clarity value of each image with the threshold. Images with a value greater than the threshold are clear images, which are screened out and marked as "meeting the clarity requirements", and images with a value less than the threshold are blurred images;

[0073] The steps of screening multiple pre - processed images using the Tenengrad gradient function include:

[0074] S401: Convert multiple color images into grayscale images, where the grayscale value = 0.299R + 0.587G + 0.114B;

[0075] S402: Use the Sobel operator to calculate the gradient values of each image in the horizontal and vertical directions respectively;

[0076] S403: For each pixel, calculate the sum of the squares of its gradient values in the horizontal and vertical directions to obtain the gradient sum of squares value of this point;

[0077] S404: Traverse the entire image, accumulate the gradient sum of squares values of all pixels, and then divide by the total number of pixels to obtain the average gradient value of the entire image;

[0078] S405: Set a threshold to distinguish clear images and blurred images;

[0079] S406: Compare the average gradient value of each image to be screened with the set threshold, and screen out the clear images with an average gradient value greater than the threshold and mark them as "meeting the clarity requirements";

[0080] The intersection operation includes the following steps:

[0081] S501: Create a new boolean array to store images that meet the threshold requirements of both the Brenner gradient function and the Tenengrad gradient function;

[0082] S502: For each image, check the screening results of both the Brenner gradient function and the Tenengrad gradient function simultaneously;

[0083] S503: If an image is marked as "meeting the clarity requirements" in the screening of the Brenner gradient function and is also marked as "meeting the clarity requirements" in the screening of the Tenengrad gradient function, add the image to the boolean array; otherwise, ignore the image;

[0084] S504: After traversing all images, the boolean array contains all images that meet the clarity requirements of both functions. Output the boolean array as the set of finally screened clear images, i.e., the pre - processed image set;

[0085] Performing image registration and graphic stitching on the pre - processed image set includes the following steps:

[0086] S601: Use the SIFT algorithm to extract feature points and their descriptors from the pre - processed image set;

[0087] When extracting feature points, set the judgment threshold for the number of extracted feature points. Obtain the contrast of the image through the gray - level co - occurrence matrix. When the contrast is greater than the threshold, the number of extracted feature points is E; when the contrast is less than the threshold, the number of extracted feature points is F, where E = 2F. Perform feature matching through the feature points and their descriptors to find the matching feature points between different images;

[0088] S602: According to the matching feature points, calculate the geometric transformation relationship between the images in the pre - processed image set, and transform the images to align multiple images;

[0089] S603: Use the weighted average algorithm to stitch the aligned images. The image pre - processing is noise reduction processing, and the noise reduction processing uses any one of Gaussian filtering, mean filtering, and non - local mean filtering.

[0090] Embodiment 2

[0091] Different from Embodiment 1, the image pre - processing is defogging processing, and the defogging processing includes the following steps:

[0092] S801: Grayscale the image: Convert the captured image into a grayscale image. The calculation formula for the grayscale value is: Gray = 0.299R + 0.587G + 0.114B, where 0.299, 0.587, and 0.114 are the weight coefficients corresponding to the red channel, green channel, and blue channel respectively;

[0093] S802: Extract the dark channel: Calculate the minimum value of each pixel in the RGB three color channels of the image, and find the minimum value of this minimum value within the surrounding neighborhood of each pixel, thereby obtaining the dark channel image;

[0094] S803: Estimate the atmospheric light: Perform threshold processing on the dark channel image, and calculate the average color value of the corresponding points in the original color image of the pixel points where the dark channel value is higher than the threshold, as the estimated value of the atmospheric light;

[0095] S804: Calculate the transmittance and obtain the dehazed image;

[0096] Establish the atmospheric scattering model: I(x) = J(x)t(x) + A(1 - t(x));

[0097] Among them, I(x) is the captured image;

[0098] J(x) is the dehazed image to be restored;

[0099] t(x) is the transmittance;

[0100] A is the estimated value of the atmospheric light;

[0101] Calculation method of the dark channel: (x)= ;

[0102] represents each channel of the color image, ) represents the local tiny area centered on pixel x,

[0103] Approximate the grayscale value of the dark channel image to 0, then:

[0104] →0;

[0105] Normalize the model:

[0106] =t(x) +1 - t(X);

[0107] Assume that within a rectangular window Ω(x) of a certain size in the image, the value of t(x) is a fixed value t^(x). Perform a minimization operation on both sides of the above equation, and then apply the dark channel prior to J, we get:

[0108] (x) = = 0;

[0109] = 0;

[0110] Substitute the above equation into the minimization operation, introduce the parameter w = 0.95, and we can obtain that t(x) is the transmittance:

[0111] t(x) = 1 - ;

[0112] J(x) = .

[0113] The circuits and controls involved in the present invention are all prior arts and will not be elaborated here.

[0114] The above are only embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A transaction management system based on an ETC control device, characterized in that, Including: Road side unit: Installed on the dedicated ETC lane, responsible for sending microwave signals to the on-vehicle unit and obtaining the first vehicle information; On-vehicle unit: Installed in the vehicle using ETC service, receiving the microwave signals sent by the road side unit, and sending the first vehicle information back to the road side unit through the microwave signals; Multiple shooting units: Installed on the dedicated ETC lane, used for image acquisition of the vehicles entering the predetermined area; Perform image preprocessing on the collected multiple images, screen out the first group of images by using the Brenner gradient function for the preprocessed multiple images, screen out the second group of images by using the Tenengrad gradient function for the preprocessed multiple images, perform intersection operation on the first group of images and the second group of images to obtain the initially processed image set, perform image registration and graphic splicing on the initially processed image set to obtain the target image; The intersection operation includes the following steps: S501: Create a new boolean array for storing the images that simultaneously meet the threshold requirements of the Brenner gradient function and the Tenengrad gradient function; S502: For each image, check its screening results in both the Brenner gradient function and the Tenengrad gradient function simultaneously; S503: If an image is marked as "meeting the clarity requirement" in the screening of the Brenner gradient function and is also marked as "meeting the clarity requirement" in the screening of the Tenengrad gradient function, add the image to the boolean array, otherwise, ignore the image; S504: After traversing all the images, the boolean array contains all the images that simultaneously meet the clarity requirements of the two functions. Output the boolean array as the finally screened clear image set, that is, the initially processed image set; The performing image registration and graphic splicing on the initially processed image set includes the following steps: S601: Use the SIFT algorithm to extract feature points and their descriptors from the initially processed image set; When extracting feature points, set the judgment threshold for the number of extracted feature points, obtain the contrast of the image through the gray level co-occurrence matrix. When the contrast is greater than the threshold, the number of extracted feature points is E, and when the contrast is less than the threshold, the number of extracted feature points is F, where E = 2F; S602: Perform feature matching through the feature points and their descriptors to find the matching feature points between different images; S603: According to the matching feature points, calculate the geometric transformation relationship between the images in the initially processed image set, and transform the images to align multiple images; S604: Use the weighted average algorithm to splice the aligned images; Data processing unit: Used for receiving the first vehicle information obtained by the road side unit and responsible for parsing the target image to obtain the second vehicle information; Central management unit: Compare the first vehicle information and the second vehicle information. When the first vehicle information and the second vehicle information coincide, generate a transaction information, send the transaction information to the on-vehicle unit, otherwise, issue an alarm.

2. The transaction management system based on the ETC control device according to claim 1, characterized in that, Both the first vehicle information and the second vehicle information include license plate number, vehicle type, and vehicle model.

3. The transaction management system based on the ETC control device according to claim 1, characterized in that, The steps of screening multiple preprocessed images by the Brenner gradient function include: S301: Convert multiple color images into grayscale images; S302: Traverse each pixel of the grayscale image to calculate the overall clarity of the image; S303: Set a threshold to distinguish clear images from blurred images; S304: Compare the clarity value of each image with the threshold. Images with a value greater than the threshold are clear images, which are screened out and marked as "meeting the clarity requirements", while images with a value less than the threshold are blurred images.

4. The transaction management system based on the ETC control device according to claim 3, characterized in that, The steps of screening multiple preprocessed images by the Tenengrad gradient function include: S401: Convert multiple color images into grayscale images; S402: Use the Sobel operator to calculate the gradient values of each image in the horizontal and vertical directions respectively; S403: For each pixel, calculate the sum of the squares of its gradient values in the horizontal and vertical directions to obtain the sum of squared gradients of this point; S404: Traverse the entire image, accumulate the sum of squared gradient values of all pixels, and then divide by the total number of pixels to obtain the average gradient value of the entire image; S405: Set a threshold to distinguish clear images from blurred images; S406: Compare the average gradient value of each image to be screened with the set threshold, and screen out the clear images with an average gradient value greater than the threshold and mark them as "meeting the clarity requirements".

5. The transaction management system based on the ETC control device according to claim 1, wherein The image preprocessing is noise reduction processing, and any one of Gaussian filtering, mean filtering, and non-local mean filtering is used for the noise reduction processing.

6. The transaction management system based on the ETC control device according to claim 1, characterized in that The image preprocessing is defogging processing, and the defogging processing includes the following steps: S801: Perform grayscale processing on the image: Convert the captured image into a grayscale image; S802: Extract the dark channel: By calculating the minimum value of each pixel in the RGB three color channels of the image and finding the minimum value of this minimum value in the surrounding neighborhood of each pixel, a dark channel image is obtained; S803: Estimate the atmospheric light: By performing threshold processing on the dark channel image, calculate the color average value of the corresponding points in the original color image of the pixel points with dark channel values higher than the threshold as the estimated value of the atmospheric light; S804: Calculate the transmittance and obtain the defogged image.

Images