A method for identifying a highway fake-plate vehicle

Abstract

The present application relates to a kind of expressway suit license plate vehicle identification method, belong to image recognition technical field, solve the problem that current technology cannot accurately identify vehicle and license plate due to atmospheric turbulence phenomenon.The method comprises: obtaining the monitoring video of the expressway shot;Real-time turbulence is removed to each frame image of the monitoring video to obtain the turbulence-removed image of each frame image;Identify all vehicle images in the turbulence-removed video image of each frame image, and extract the license plate number of each vehicle image in the turbulence-removed video image;Compare each vehicle image and corresponding license plate number in the turbulence-removed video image with the information stored by traffic management bureau, and determine whether it is a suit license plate vehicle.Implement the accuracy of real-time identification of vehicle license plate on expressway is improved, and even determine whether it is a suit license plate vehicle.

Description

Technical Field

[0001] This invention relates to the field of image recognition technology, and in particular to a method for identifying vehicles using counterfeit license plates on highways. Background Technology

[0002] Typically, license plate recognition refers to identifying the license plate area within a specific region of an image from a static or video image, and then further recognizing the characters within that area. However, due to atmospheric turbulence caused by the temperature difference between the Earth's surface and the upper atmosphere, vehicles and license plates often become geometrically distorted and blurred during the imaging process. Existing vehicle and license plate recognition technologies are unable to effectively identify deformed or blurred vehicles and license plates. Summary of the Invention

[0003] Based on the above analysis, the present invention aims to provide a method for identifying vehicles using counterfeit license plates on highways, in order to solve the problem that existing methods cannot accurately identify vehicles and license plates due to atmospheric turbulence.

[0004] The objective of this invention is mainly achieved through the following technical solutions:

[0005] This invention provides a method for identifying vehicles using counterfeit license plates on highways, comprising the following steps:

[0006] Acquire surveillance video footage taken on the highway;

[0007] Real-time deturbulence is performed on each frame of the monitoring video to obtain the deturbulence-free image of each frame.

[0008] Identify all vehicle images in the deturbulence-free video images of each frame, and extract the license plate number of each vehicle image in the deturbulence-free video images;

[0009] The images of each vehicle and their corresponding license plate numbers in the deturbulence-free video images are compared with the information stored by the traffic management bureau to determine whether they are vehicles using counterfeit license plates.

[0010] Furthermore, the license plate numbers of each vehicle image in the deturbulence-free video image are extracted, including:

[0011] The license plate location algorithm is used to locate the license plate position in the vehicle image;

[0012] The located license plate image is segmented into characters;

[0013] The license plate information of the vehicle image is obtained by recognizing the segmented license plate characters.

[0014] Furthermore, the step of comparing the vehicle images and corresponding license plate numbers in the deturbulence-free video images with the information stored by the traffic management bureau to determine whether they are cloned vehicles includes:

[0015] Obtain the corresponding vehicle image stored by the traffic management bureau based on the vehicle's license plate number;

[0016] If the license plate number does not exist in the traffic management bureau's system, it is determined to be a vehicle using a counterfeit license plate;

[0017] Feature points are extracted from both the vehicle image and the corresponding vehicle image stored by the traffic management bureau.

[0018] The feature matching algorithm is used to perform similarity matching between the extracted feature points of the vehicle image and the feature points of the corresponding vehicle image stored by the traffic management bureau.

[0019] When the similarity is below a predetermined threshold, it is judged to be a cloned vehicle.

[0020] Furthermore, obtaining the deturbulentized image of each frame of the monitoring video using a real-time image deturbulence method includes:

[0021] The first deturbulence weight and the second deturbulence weight are used to fuse each frame of the monitoring video with the deturbulence-suppressed image of the previous frame of each frame to obtain the first weighted turbulence suppression image and the second weighted turbulence suppression image of each frame.

[0022] Motion values ​​of each pixel are obtained by detecting moving targets based on the normalized visual weights of each pixel in each frame of the image.

[0023] Based on the motion values ​​of each pixel in each frame image, the first weighted turbulence suppression image of each frame image, and the second weighted turbulence suppression image of each frame image, a weighted superposition is performed to obtain the preliminary deturbulence image of each frame image.

[0024] The initial deturbulence images of each frame are enhanced with details to obtain the final deturbulence images.

[0025] Furthermore, the first deturbulence weight is applied to each frame of the monitoring video and fused with the deturbulence-reduced image of the previous frame to obtain the first weighted turbulence suppression image of each frame, and the formula is as follows:

[0026]

[0027] Where α1 represents the first deturbulence weight; f N-1 This represents the image after deturbulence removal in frame N-1; This represents the Nth frame of the image;

[0028] The second weighted turbulence suppression image of each frame of the monitoring video is obtained by fusing it with the deturbulence-suppressed image of the previous frame of each frame using a second deturbulence weight, and the formula is as follows:

[0029]

[0030] Where α2 represents the second deturbulence weight.

[0031] Furthermore, the normalized visual weights of each pixel in each frame of the image are obtained, including:

[0032] Transform each pixel of each frame of the image from the spatial domain to the frequency domain;

[0033] Perform a two-dimensional inverse Fourier transform on the phase portion of each pixel in the frequency domain of each frame image to obtain the transformed pixel value of each pixel in each frame image.

[0034] Based on the transformed pixel values ​​of each pixel in each frame of the image, the visual weight of each pixel in each frame of the image is obtained by using a two-dimensional Gaussian function to perform blur widening.

[0035] The visual weights of each pixel in each frame of the image are normalized to obtain the normalized visual weights belonging to the [0,1] interval.

[0036] Furthermore, the step of converting each pixel of each frame image from the spatial domain to the frequency domain includes:

[0037] The spatial domain of each pixel in each frame of the image is orthogonally decomposed into motion components and intensity components.

[0038] Two-dimensional Fourier transforms are performed on the motion and intensity components of each pixel after decomposition, transforming each pixel from the spatial domain to the frequency domain.

[0039] Furthermore, a preset threshold is used to normalize the visual weights of each pixel in each frame image to distinguish moving targets, including:

[0040] When the normalized visual weight of each pixel in each frame image is greater than or equal to the preset threshold, the pixel is determined to be a moving point and the motion value of the pixel is set to 1.

[0041] When the normalized visual weight of each pixel in each frame image is less than the preset threshold, the pixel is determined to be a stationary point and the motion value of the pixel is set to 0.

[0042] Furthermore, based on the motion values ​​of each pixel in each frame image, the first weighted turbulence suppression image of each pixel in each frame image, and the second weighted turbulence suppression image of each pixel in each frame image, the following formula is used to perform weighted superposition for deturbulence removal to obtain the preliminary deturbulence image of each frame image:

[0043]

[0044] Among them, MaskN (x,y) represents the motion value of pixel (x,y) in the Nth frame of the image; This represents the first weighted turbulence suppression image of the Nth frame; This represents the second-weighted turbulence suppression image of the Nth frame.

[0045] Furthermore, the step of enhancing the details of the preliminary deturbulence images of each frame to obtain the final deturbulence image includes:

[0046] Based on the preliminary deturbulence images of each frame, the preliminary deturbulence visual weights of each pixel in each frame are obtained.

[0047] Based on the preliminary deturbulence visual weights of each pixel in each frame, the final deturbulence image is obtained using the following formula:

[0048]

[0049] Where λ1 represents the first final deturbulence weight; λ2 represents the second final deturbulence weight; Represents the initial deturbulence-free visual weight of pixel (x,y) in the Nth frame image; This represents the pixel value (x, y) of the initial deturbulence image in frame N.

[0050] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0051] 1. This invention uses real-time deturbulence technology to identify vehicle information and license plate numbers for vehicles traveling on highways. This minimizes the impact of atmospheric turbulence on the identification technology and improves the accuracy of license plate information identification.

[0052] 2. This invention obtains a visual matrix by detecting and analyzing potential moving targets, and then segments the potential target region based on this matrix, which can effectively suppress motion region trailing and eliminate background region turbulence.

[0053] 3. This invention performs deturbulence fusion on the motion region and background region with different weights, and further enhances the fusion result, which can effectively suppress motion blur and improve detail clarity.

[0054] 4. This invention decomposes the pixel information of an image into a representation of motion components and intensity components. It represents the attention given to the motion of a pixel from both the actual motion of the pixel and the brightness, which can more accurately distinguish the foreground target and background information of the image and improve the accuracy of moving target tracking.

[0055] 5. This invention converts the pixel information of an image from the spatiotemporal domain to the frequency domain. In the field of optics, phase information has direct physical meaning. Therefore, the phase part is regarded as the best representation of information features. The inverse Fourier transform of the phase part is performed to extract moving targets in the image. Processing only phase information is simpler and more efficient than processing amplitude information.

[0056] In this invention, the above-described technical solutions can be combined with each other to achieve more preferred combinations. Other features and advantages of this invention will be set forth in the following description, and some advantages may become apparent from the description or be learned by practicing the invention. The objects and other advantages of this invention can be realized and obtained from what is particularly pointed out in the description and drawings. Attached Figure Description

[0057] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0058] Figure 1 This is a flowchart illustrating a method for identifying vehicles using counterfeit license plates on highways, as described in an embodiment of the present invention.

[0059] Figure 2 This is a flowchart illustrating the real-time deturbulence removal method in an embodiment of the present invention;

[0060] Figure 3 This is a schematic diagram illustrating the process of obtaining the visual weights of each pixel in each frame of an image in an embodiment of the present invention. Detailed Implementation

[0061] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0062] A specific embodiment of the present invention discloses a method for identifying vehicles using counterfeit license plates on highways, such as... Figure 1 As shown, it includes the following steps S1-S4:

[0063] Step S1: Obtain the surveillance video captured on the highway.

[0064] Specifically, video images captured by video surveillance equipment installed on each lane of the highway are obtained. The video surveillance equipment can be used for traffic monitoring or other purposes to reduce redundant construction.

[0065] Furthermore, for the captured video images, OpenCV is used to capture each frame of the video images.

[0066] Step S2: Perform real-time deturbulence on each frame of the monitoring video to obtain the deturbulence-free image of each frame.

[0067] Specifically, because the asphalt pavement of highways heats up rapidly under sunlight, creating a temperature difference with the surrounding vegetation, it causes air to rise and sink. Simultaneously, the large number of fast-moving vehicles disturbs the surrounding air, and the exhaust fumes generated by these vehicles increase atmospheric turbulence. Therefore, video images captured by highway surveillance cameras often suffer from geometric distortion and blurring of vehicles and license plates due to atmospheric turbulence. Real-time deturbulence removal is necessary to obtain clear images from the captured video footage.

[0068] Furthermore, such as Figure 2 As shown, each frame of the monitoring video is deturbulentized in real time using steps S21-S24.

[0069] Step S21: For each frame of the monitoring video, the first deturbulence weight and the second deturbulence weight are used to fuse with the previous frame of the deturbulence-suppressed image to obtain the first weighted turbulence suppression image and the second weighted turbulence suppression image of each frame.

[0070] Specifically, in a normal turbulent scene, the pixel information at each position is offset from its true position. Since atmospheric turbulence has a quasi-periodic property, it is statistically stationary in nature, meaning that the offset is statistically stationary over time. Therefore, by simulating short-exposure images through weighted averaging between frames in the sequence, the distortion effect can be reduced, making the background image, which has not undergone actual displacement, relatively stable.

[0071] Furthermore, the first deturbulence weight is applied to each frame of the monitoring video and fused with the deturbulence-reduced image of the previous frame to obtain the first weighted turbulence suppression image of each frame, and the formula is as follows:

[0072]

[0073] Where α1 represents the first deturbulence weight; f N-1 This represents the image after deturbulence removal in frame N-1; This represents the Nth frame image, i.e., the original Nth frame image.

[0074] The second weighted turbulence suppression image of each frame of the monitoring video is obtained by fusing it with the deturbulence-suppressed image of the previous frame of each frame using a second deturbulence weight, and the formula is as follows:

[0075]

[0076] Where α2 represents the second deturbulence weight.

[0077] It should be noted that when processing the first frame, since there is no previous frame after deturbulence removal, the formula is used directly: As the first weighted turbulence suppression image of the first frame, and This serves as the second weighted turbulence suppression image for the first frame.

[0078] Specifically, when the deturbulence weight is small, more information from the previous frame after deturbulence is introduced, which slows down the turbulence. However, information in areas with motion is prone to remainder and superimpose, resulting in information loss in these areas, i.e., motion blur or strong blurring. When the deturbulence weight is large, more information from the current frame is introduced, reducing motion information from the previous frame and suppressing motion blur. It also introduces more turbulence information from the current frame, i.e., turbulence remains are obvious.

[0079] Therefore, it is necessary to separate the potential moving target region of the image from the background region and assign different deturbulence weight values ​​to different regions. In this embodiment, α1 < α2 is set, that is, the first deturbulence weight is used for the background region and the second deturbulence weight is used for the moving region. For example, α1 = 0.1 and α2 = 0.9 are set.

[0080] Step S22: Based on the normalized visual weights of each pixel in each frame image, perform moving target detection to obtain the motion value of each pixel.

[0081] Furthermore, such as Figure 3 As shown, the visual weights of each pixel in each frame of the image are obtained, including steps S221-S224:

[0082] Step S221: Convert each pixel of each frame image from the spatial domain to the frequency domain.

[0083] Specifically, in the frequency domain of an image, noise is usually present in the high-frequency part, while useful information is mainly distributed in the low-frequency region. By converting the image from the spatial domain to the frequency domain, noise in the image can be removed more effectively.

[0084] Furthermore, the step of converting each pixel of each frame image from the spatial domain to the frequency domain includes:

[0085] The spatial domain of each pixel in each frame of the image is orthogonally decomposed into motion and intensity components using the following formula:

[0086] q N (x,y)=M N (x,y)u1+I N (x,y)·u2

[0087] (u1) 2 =(u2) 2 =-1

[0088] u1⊥u2

[0089] Among them, M N (x,y) represents the motion component of pixel (x,y) in the Nth frame of the image; I N (x,y) represents the intensity component of pixel (x,y) in the Nth frame image; u1 represents the first unit vector; u2 represents the second unit vector.

[0090] Specifically, the motion component of a pixel (x, y) represents the difference between the current frame and the previous frame, that is, the motion change value between two consecutive frames, where M N (x,y)=|g N (x,y)-g N-1 (x,y)|;g N (x,y) represents the pixel value of pixel (x,y) in the Nth frame of the image; g N-1 (x,y) represents the pixel value of pixel (x,y) in the (N-1)th frame of the image.

[0091] On the other hand, the intensity component of a pixel (x,y), i.e., the brightness or color intensity of the pixel, can be used to characterize the difference between the target region and the background region, where I N (x,y)=average(g N (x,y)); when the image is three-channel, average(g) N (x,y)) represents the average of the three channels; when the image is a single-channel image, i.e., a grayscale image, then average(g) = 0. N (x,y))=g N (x,y).

[0092] It should be noted that decomposing the pixel information of an image into motion and intensity components, and representing the attention given to pixel motion from both the actual pixel motion and brightness aspects, can more accurately distinguish between foreground and background information in an image, thereby improving the accuracy of moving target tracking.

[0093] Furthermore, a two-dimensional Fourier transform is performed on the motion component and intensity component of each pixel after decomposition, transforming each pixel from the spatial domain to the frequency domain.

[0094] Specifically, the motion components of each pixel after decomposition are used to obtain the motion components of the pixel in the frequency domain using a two-dimensional Fourier transform, as follows:

[0095]

[0096] Among them, |(F M (u,v)) N| represents the magnitude of the motion component of the frequency domain pixel (u,v) in the Nth frame of the image; The phase information of the motion component of the frequency domain pixel (u,v) of the Nth frame image;

[0097] The intensity components of each pixel after decomposition are used to obtain the intensity components of the pixel in the frequency domain using a two-dimensional Fourier transform, as follows:

[0098]

[0099] Among them, |(F I (u,v)) N | represents the magnitude of the intensity component of the frequency domain pixel (u,v) in the Nth frame image; This represents the phase information of the intensity component of the frequency domain pixel (u,v) in the Nth frame image.

[0100] Step S222: Perform a two-dimensional inverse Fourier transform on the phase part of each frequency domain pixel in each frame image to obtain the transformed pixel value of each pixel in each frame image.

[0101] Specifically, the phase information of an image mainly carries the image's edge and texture information. By preserving the phase information and converting it back to the spatial domain, we can remove noise while preserving as many important structural features of the image as possible.

[0102] Furthermore, the magnitudes of the motion component and intensity component of each frequency domain pixel are set to 1, resulting in motion and intensity components of each frequency domain pixel containing only phase information. A two-dimensional inverse Fourier transform is then performed on the motion and intensity components of each frequency domain pixel containing only phase information to obtain the transformed pixel value. The transformed pixel value is expressed as follows:

[0103] q′ N (x,y)=M′ N (x,y)u1+I′ N (x,y)·u2

[0104] Among them, M′ N (x,y) represents the transformed motion component of pixel (x,y) in the Nth frame image; I′ N (x,y) represents the transformed intensity component of pixel (x,y) in the Nth frame of the image.

[0105] Step S223: Based on the transformed pixel values ​​of each pixel in each frame image, use a two-dimensional Gaussian function to perform blur widening to obtain the visual weight of each pixel in each frame image.

[0106] Furthermore, based on the transformed pixel values, the visual weight of each pixel in each frame image is obtained using the following formula:

[0107]

[0108] Among them, Sa N (x,y) represents the visual weight of pixel (x,y) in the Nth frame image; gauss(r,σ) represents the two-dimensional Gaussian function; q′ N (x,y) represents the transformed pixel value of pixel (x,y) in the Nth frame of the image; |q′ N (x,y)| represents q′ N The modulus of (x,y); This indicates a convolution operation.

[0109] Specifically, the two-dimensional Gaussian function is often used for appropriate blurring and broadening, which can enhance visually important areas in an image, while making the image look smoother, making the details of the image more harmonious, and reducing abrupt transitions.

[0110] Step S224: Assign the visual weight Sa to each pixel in each frame image. N (x,y) is normalized to obtain the normalized visual weight Sa' belonging to the interval [0,1]. N (x,y).

[0111] It should be noted that the closer the visual weight of each pixel is to 1, the more likely it is a potential motion area, and the closer it is to 0, the more likely it is a background area.

[0112] Furthermore, a preset threshold is used to normalize the visual weights of each pixel in each frame image to distinguish moving targets, including:

[0113] When the normalized visual weight of each pixel in each frame image is greater than or equal to the preset threshold, the pixel is determined to be a moving point and the motion value of the pixel is set to 1.

[0114] When the normalized visual weight of each pixel in each frame image is less than the preset threshold, the pixel is determined to be a stationary point and the motion value of the pixel is set to 0.

[0115] Specifically, the following formula is used to determine pixels larger than the threshold Th as moving target regions, thereby achieving the separation of moving targets;

[0116]

[0117] Among them, Mask N (x,y) represents the motion value of pixel (x,y) in the Nth frame of the image; Sa' N(x,y) represents the normalized visual weight of pixel (x,y) in the Nth frame image; pixels with a motion value of 1 are considered moving points, and pixels with a motion value of 0 are considered stationary points; the preset threshold Th can be set to a value between 0 and 1 depending on different situations.

[0118] Step S23: Based on the motion values ​​of each pixel in each frame image, the first weighted turbulence suppression image of each frame image, and the second weighted turbulence suppression image of each frame image, perform weighted superposition to obtain the preliminary deturbulence image of each frame image.

[0119] Furthermore, the following formula is used for weighted superposition to obtain preliminary deturbulence images for each frame:

[0120]

[0121] Among them, Mask N (x,y) represents the motion value of pixel (x,y) in the Nth frame of the image; This represents the first weighted turbulence suppression image of the Nth frame; This represents the second-weighted turbulence suppression image of the Nth frame.

[0122] Specifically, as mentioned earlier, for the background area, i.e., the Mask... N Pixels with (x,y) = 0 use the first deturbulence weight α1; for the motion region, i.e., the Mask... N The pixel (x,y)=1 is subjected to the second deturbulence weight α2 for initial deturbulence removal.

[0123] Step S24: Perform detail enhancement on the preliminary deturbulence images of each frame to obtain the final deturbulence image.

[0124] Furthermore, based on the preliminary deturbulence images of each frame, the preliminary deturbulence visual weights of each pixel in each frame are obtained.

[0125] Specifically, for the preliminary deturbulence images of each frame, the method of steps S221-S224 is used to obtain the preliminary deturbulence normalized visual weights of each pixel in each frame. Among them, the normalized visual weights after preliminary deturbulence removal The values ​​are those that belong to the interval [0,1].

[0126] Furthermore, a weighted enhancement approach is adopted to further enhance image pixels of interest and appropriately suppress image pixels of uninteresting interest, thereby improving image contrast.

[0127] Specifically, based on the preliminary deturbulence visual weights of each pixel in each frame of the image, the final deturbulence image is obtained using the following formula:

[0128]

[0129] in, λ1 represents the final deturbulence pixel value of pixel (x,y) in the Nth frame image; λ2 represents the first final deturbulence weight; λ3 represents the second final deturbulence weight. Represents the initial deturbulence-free normalized visual weight of the pixel (x,y) in the Nth frame image; This represents the pixel value (x, y) of the initial deturbulence image in frame N.

[0130] It should be noted that in this embodiment, λ1 > λ2, and λ1 + λ2 = 1.

[0131] Step S3: Identify all vehicle images in the deturbulence-free video images of each frame, and extract the license plate numbers of each vehicle image in the deturbulence-free video images.

[0132] Furthermore, the extraction of license plate numbers from each vehicle image in the deturbulence-free video image includes:

[0133] First, a license plate localization algorithm is used to locate the license plate position in the vehicle image.

[0134] Specifically, this embodiment employs an edge-based license plate localization algorithm, which features fast recognition speed and low false detection rate for license plate identification. Preferably, this embodiment uses the Canny operator to detect image edges.

[0135] Furthermore, the license plate image is obtained by tilt correction using the Hough transform method after positioning.

[0136] Secondly, the located license plate image is segmented into characters.

[0137] Specifically, in this embodiment, a character segmentation method based on edge features is used to obtain the contour of each character through edge detection, thereby achieving character segmentation.

[0138] Finally, the license plate characters after segmentation are recognized to obtain the license plate information of the vehicle image.

[0139] Specifically, the segmented license plate characters are matched with the character features of a standard template, and their similarity is calculated to identify the license plate information of the moving target.

[0140] Step S4: Compare the vehicle images and corresponding license plate numbers in the deturbulence-free video images with the information stored by the traffic management bureau to determine whether they are cloned vehicles.

[0141] Specifically, this includes steps S41-S45:

[0142] Step S41: Obtain the corresponding vehicle image stored by the traffic management bureau based on the vehicle's license plate number.

[0143] Step S42: If the license plate number does not exist in the traffic management bureau's system, it is determined to be a vehicle using a counterfeit license plate.

[0144] It should be noted that when the identified license plate number does not exist in the traffic management bureau's system, the license plate number in the image is manually checked again to confirm that the license plate number is correctly identified.

[0145] Step S43: Extract feature points from the vehicle image and the corresponding vehicle image stored by the traffic management bureau.

[0146] Furthermore, when the license plate number exists in the traffic management bureau system, the vehicle image corresponding to the license plate number is obtained, and feature points of the vehicle image in the deturbulence-free video image and the vehicle image stored by the traffic management bureau are extracted respectively; for example, the feature point extraction methods include SURF feature detector, SIFT feature detector, FAST feature detector and ORB feature detector, etc.

[0147] Step S44: Use a feature matching algorithm to perform similarity matching between the extracted feature points of the vehicle image and the feature points of the corresponding vehicle image stored by the traffic management bureau.

[0148] For example, the feature matching algorithm includes brute-force matching, FLANN matching, etc., to calculate the similarity of the matched features; for example, the similarity calculation method includes Euclidean distance and cosine similarity.

[0149] Step S45: When the similarity is lower than a predetermined threshold, it is determined to be a cloned vehicle.

[0150] For example, in this embodiment, the threshold is set to 80%.

[0151] In summary, the highway vehicle clone identification method of this invention has the following beneficial effects:

[0152] 1. This invention uses real-time deturbulence technology to identify vehicle information and license plate numbers for vehicles traveling on highways. This minimizes the impact of atmospheric turbulence on the identification technology and improves the accuracy of license plate information identification.

[0153] 2. This invention obtains a visual matrix by detecting and analyzing potential moving targets, and then segments the potential target region based on this matrix, which can effectively suppress motion region trailing and eliminate background region turbulence.

[0154] 3. This invention performs deturbulence fusion on the motion region and background region with different weights, and further enhances the fusion result, which can effectively suppress motion blur and improve detail clarity.

[0155] 4. This invention decomposes the pixel information of an image into a representation of motion components and intensity components. It represents the attention given to the motion of a pixel from both the actual motion of the pixel and the brightness, which can more accurately distinguish the foreground target and background information of the image and improve the accuracy of moving target tracking.

[0156] 5. This invention converts the pixel information of an image from the spatiotemporal domain to the frequency domain. In the field of optics, phase information has direct physical meaning. Therefore, the phase part is regarded as the best representation of information features. The inverse Fourier transform of the phase part is performed to extract moving targets in the image. Processing only phase information is simpler and more efficient than processing amplitude information.

[0157] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for identifying vehicles using counterfeit license plates on highways, characterized in that, Includes the following steps: Acquire surveillance video footage taken on the highway; Real-time deturbulence is performed on each frame of the monitoring video to obtain the deturbulence-free image of each frame. Identify all vehicle images in the deturbulence-free images of each frame and extract the license plate numbers of each vehicle image in the deturbulence-free images; The images of each vehicle and their corresponding license plate numbers in the deturbulence-free image are compared with the information stored by the traffic management bureau to determine whether they are cloned vehicles. The process of performing real-time deturbulence removal on each frame of the monitoring video to obtain the deturbulence-removed image of each frame includes: The first deturbulence weight and the second deturbulence weight are used to fuse each frame of the monitoring video with the deturbulence-suppressed image of the previous frame of each frame to obtain the first weighted turbulence suppression image and the second weighted turbulence suppression image of each frame. Motion values ​​of each pixel are obtained by detecting moving targets based on the normalized visual weights of each pixel in each frame of the image. Based on the motion values ​​of each pixel in each frame image, the first weighted turbulence suppression image of each frame image, and the second weighted turbulence suppression image of each frame image, a weighted superposition is performed to obtain the preliminary deturbulence image of each frame image. The initial deturbulence images of each frame are enhanced with details to obtain the final deturbulence images.

2. The method according to claim 1, characterized in that, Extracting the license plate numbers of each vehicle image from the deturbulence-free image, including: The license plate location algorithm is used to locate the license plate position in the vehicle image; The located license plate image is segmented into characters; The license plate information of the vehicle image is obtained by recognizing the segmented license plate characters.

3. The method according to claim 1, characterized in that, The step of comparing the vehicle images and corresponding license plate numbers in the deturbulence-free image with the information stored by the traffic management bureau to determine whether a vehicle is using a fake license plate includes: Obtain the corresponding vehicle image stored by the traffic management bureau based on the vehicle's license plate number; If the license plate number does not exist in the traffic management bureau's system, it is determined to be a vehicle using a counterfeit license plate; Feature points are extracted from both the vehicle image and the corresponding vehicle image stored by the traffic management bureau. The feature matching algorithm is used to perform similarity matching between the extracted feature points of the vehicle image and the feature points of the corresponding vehicle image stored by the traffic management bureau. When the similarity is below a predetermined threshold, it is judged to be a cloned vehicle.

4. The method according to claim 1, characterized in that, The first weighted turbulence suppression image of each frame of the monitoring video is obtained by fusing it with the deturbulence-reduced image of the previous frame of each frame using a first deturbulence weight, and the formula is as follows: Where α1 represents the first deturbulence weight; This represents the image after deturbulence removal in frame N-1; This represents the Nth frame of the image; The second weighted turbulence suppression image of each frame of the monitoring video is obtained by fusing it with the deturbulence-suppressed image of the previous frame of each frame using a second deturbulence weight, and the formula is as follows: Where α2 represents the second deturbulence weight.

5. The method according to claim 1, characterized in that, The normalized visual weights of each pixel in each frame of the image are obtained, including: Transform each pixel of each frame of the image from the spatial domain to the frequency domain; Perform a two-dimensional inverse Fourier transform on the phase portion of each pixel in the frequency domain of each frame image to obtain the transformed pixel value of each pixel in each frame image. Based on the transformed pixel values ​​of each pixel in each frame of the image, the visual weight of each pixel in each frame of the image is obtained by using a two-dimensional Gaussian function to perform blur widening. The visual weights of each pixel in each frame of the image are normalized to obtain the normalized visual weights belonging to the [0, 1] interval.

6. The method according to claim 5, characterized in that, The step of converting each pixel of each frame image from the spatial domain to the frequency domain includes: The spatial domain of each pixel in each frame of the image is orthogonally decomposed into motion components and intensity components. Two-dimensional Fourier transforms are performed on the motion and intensity components of each pixel after decomposition, transforming each pixel from the spatial domain to the frequency domain.

7. The method according to claim 6, characterized in that, Moving targets are distinguished using the normalized visual weights of each pixel in each frame of the image based on a preset threshold, including: When the normalized visual weight of each pixel in each frame image is greater than or equal to the preset threshold, the pixel is determined to be a moving point and the motion value of the pixel is set to 1. When the normalized visual weight of each pixel in each frame image is less than the preset threshold, the pixel is determined to be a stationary point and the motion value of the pixel is set to 0.

8. The method according to claim 7, characterized in that, Based on the motion values ​​of each pixel in each frame, the first-weighted turbulence suppression image of each pixel in each frame, and the second-weighted turbulence suppression image of each pixel in each frame, the following formula is used to perform weighted superposition for deturbulence removal to obtain the preliminary deturbulence image of each frame: in, This represents the motion value of pixel (x, y) in the Nth frame of the image; This represents the first weighted turbulence suppression image of the Nth frame; This represents the second-weighted turbulence suppression image of the Nth frame.

9. The method according to claim 8, characterized in that, The process of enhancing the details of the preliminary deturbulence images of each frame to obtain the final deturbulence image includes: Based on the preliminary deturbulence images of each frame, the preliminary deturbulence visual weights of each pixel in each frame are obtained. Based on the preliminary deturbulence visual weights of each pixel in each frame, the final deturbulence image is obtained using the following formula: Where λ1 represents the first final deturbulence weight; λ2 represents the second final deturbulence weight; Represents the initial deturbulence-free visual weight of pixel (x,y) in the Nth frame image; This represents the pixel value (x, y) of the initial deturbulence image in frame N.

Images