A smart road online diagnosis and evaluation system and its application

Abstract

A smart road online diagnosis and assessment system and application are disclosed, characterized by comprising a data acquisition hardware module, a road monitoring module, an image data transmission module, a processing center module, an image data processing module, a road defect intelligent detection module, and a road assessment module. The smart road online diagnosis and assessment system and application proposed in this invention uses unmanned aerial vehicles (UAVs) to detect and collect road surface image data, transmits the collected data wirelessly, proposes an image comparison processing algorithm to enhance the road surface image data and achieve image contour compensation, and analyzes the characteristics of the road surface image data through a feature matching analysis algorithm to intelligently detect road defects and assess the road health status.

Description

Technical Field

[0001] This invention relates to smart engineering, and in particular to a smart road online diagnosis and evaluation system and its application. Background Technology

[0002] With the acceleration of urbanization and rapid economic development, the construction of transportation infrastructure has received increasing attention. Roads, as a crucial infrastructure for socio-economic development, have a profound impact on urban sustainable development, economic vitality, and people's daily lives. However, with the increase in traffic flow and the surge in the number of vehicles, the carrying capacity and usage status of urban roads are facing unprecedented challenges. It is well known that roads are subject to damage from various factors during daily use, such as traffic load, natural climate change, and material aging. These factors can cause cracks, potholes, subsidence, and other defects in roads, seriously affecting driving safety, increasing the risk of traffic accidents, and reducing transportation efficiency. Therefore, how to monitor and assess roads in a timely and effective manner to provide a scientific basis for maintenance and management has become an important issue for governments at all levels and traffic management departments.

[0003] Traditional road monitoring and assessment methods rely heavily on manual patrols and periodic inspections. This approach is not only inefficient but also highly subjective, easily overlooking minor road damage that could have serious consequences. Furthermore, manual inspections are typically time-consuming, often failing to promptly identify urgent repair issues, allowing road damage to worsen before being discovered, leading to higher repair costs and longer recovery times. These problems necessitate that road managers seek more efficient and intelligent solutions. In recent years, with the rapid development of image processing, artificial intelligence, and big data technologies, the possibility of automating and intelligently monitoring roads using modern technology has become increasingly apparent, offering new insights into overcoming the bottlenecks in traditional road management.

[0004] In conclusion, with the advancement of modern technology, the concepts of smart transportation and smart cities have gradually gained widespread acceptance, leading to the emergence of intelligent road monitoring and evaluation systems. These systems are not only an effective means to address the shortcomings of traditional road management but also an inevitable requirement for promoting high-quality development of transportation infrastructure. As society's demands for road safety, comfort, and reliability continue to rise, building an intelligent and efficient online road monitoring and evaluation system has become an indispensable part of road management. This will not only promote the refined management of urban transportation infrastructure but also improve overall road operational efficiency, providing strong technical support for building a safer and more convenient transportation environment. Therefore, research on intelligent road online diagnostic and evaluation systems not only has significant theoretical importance but also broad practical application prospects. Summary of the Invention

[0005] The purpose of this invention is to provide an online diagnostic and evaluation system and application for intelligent roads, which aims to solve the problems mentioned in the background.

[0006] To achieve the above objectives, this invention proposes an intelligent road online diagnosis and evaluation system and application, characterized by comprising a data acquisition hardware module, a road monitoring module, an image data transmission module, a processing center module, an image data processing module, a road defect intelligent detection module, and a road evaluation module. The data acquisition hardware module utilizes an intelligent unmanned aerial vehicle (UAV) array for automated flight. The road monitoring module uses the UAV array to monitor road surface conditions in real time. The image data transmission module transmits the acquired road surface image data via radio technology. The processing center module receives, stores, and analyzes the road surface data through a central server. The image data processing module proposes an image comparison processing algorithm to enhance the road surface image data and achieve image contour compensation. The road defect intelligent detection module uses a feature matching analysis algorithm to analyze the features of the road surface image data and intelligently detect road defects. The road evaluation module assesses the health of the road surface based on the output results of the road defect intelligent detection module.

[0007] Furthermore, in the data acquisition hardware module, the user can use the drone array to preset the detection route of the drone array, and the drone array will perform automated work based on the preset detection route.

[0008] Furthermore, the road monitoring module utilizes an array of drones to monitor road surface conditions in real time and collect data on these conditions.

[0009] Furthermore, the image data transmission module utilizes radio technology to establish a data transmission channel between the UAV array and the central server, enabling the transmission and storage of road surface image data.

[0010] Furthermore, the processing center module receives road surface image data collected by the UAV array through a central server, and stores and analyzes the road surface image data, as well as runs algorithms.

[0011] Furthermore, the image contrast processing algorithm enhances the road surface image data by performing filtering operations, deblurring, and overflow correction to achieve image contour compensation.

[0012] Furthermore, image contour compensation is performed on the road surface image data. The detailed process is as follows:

[0013] For the collected road surface image data, the road surface image data is represented by a grayscale matrix, as follows:

[0014]

[0015] Among them, D ori d represents the grayscale value matrix of the original road surface image data. 1,1 d 1,n d i,j d m,1 d m,n Let $\mathbf$ represent the grayscale values ​​of the pixels in the first row and first column of the original road surface image data, the pixels in the first row and nth column of the original road surface image data, the pixels in the i-th row and j-th column of the original road surface image data, the pixels in the m-th row and first column of the original road surface image data, and the pixels in the m-th row and n-th column of the original road surface image data, respectively. Based on the grayscale value matrix of the original road surface image data, the original road surface image data enhancement processing is performed, and the formula is as follows:

[0016]

[0017] Where, d′ i,j Let represent the grayscale value of the pixel in the i-th row and j-th column of the original road surface image data after processing. min(·) represents finding the minimum value of the elements in the matrix, and max(·) represents finding the maximum value of the elements in the matrix. Then, the high-frequency components of the enhanced original road surface image data are filtered. First, a blur filter function is constructed, and the function formula is as follows:

[0018]

[0019] Among them, h i,j σ represents the fuzzy filtering function. i,j The standard deviation of the fuzzy filter function is used to perform high-frequency enhancement of road surface image data based on the fuzzy filter function. This involves deblurring the grayscale values ​​of pixels, and the calculation formula is as follows:

[0020] I i,j =d′ i,j -α i,j ×h i,j ×d′ i,j

[0021] Among them, I i,j α represents the grayscale value of the pixel in the i-th row and j-th column of the original road surface image data after deblurring. i,j This represents the enhancement coefficient, which is used to correct pixel overflow by adjusting the grayscale value of the deblurred pixel. The calculation formula is as follows:

[0022]

[0023] Among them, I′i,j D represents the grayscale value of the pixel in the i-th row and j-th column of the original road surface image data after overflow correction. m D n β represents the number of vertical pixels and horizontal pixels in the original road surface image data, respectively. i,j The correction coefficient is used to compensate for image contours through pixel overflow correction. The image contrast processing algorithm proposed in this invention first performs image data enhancement processing based on the grayscale representation of the image data to improve the grayscale contrast. Then, a blur filtering function is constructed to perform high-frequency enhancement of the road surface image data. Finally, a deblurring operation is performed to correct pixel overflow, thereby achieving image contour compensation. The image contrast processing algorithm proposed in this invention increases the grayscale contrast of the image, achieves image contour compensation, and enhances image edges.

[0024] Furthermore, the feature matching analysis algorithm performs image data pooling on the processed road surface image data, then reconstructs image features, calculates feature values, and determines the condition of road surface defects through feature value matching analysis of the image data.

[0025] Furthermore, by using feature value matching analysis of image data, the condition of road surface defects is determined. The detailed process is as follows:

[0026] For the processed road surface image data, image feature extraction is first performed. Then, using an attention mechanism, pooling is applied to the processed road surface image data based on convolutional kernels, as shown below:

[0027]

[0028] Among them, I hand I represents the processed road surface image data. mean I represents the road surface image data after average pooling. max This represents the road surface image data after max pooling. `meanxpool(·)` represents average pooling, which averages the values ​​of all surrounding pixels within each pixel of the processed road surface image data. `maxpool(·)` represents max pooling, which maximizes the value of all surrounding pixels within each pixel of the processed road surface image data. The road surface image data after pooling is then reconstructed using the following formula:

[0029]

[0030] Among them, I mean (l,k) represents the value of the pixel in the l-th row and k-th column of the road surface image data after average pooling. max(l,k) represents the value of the pixel in the l-th row and k-th column of the road surface image data after max pooling, ω mean,r.l,k ω max,r,l,k These represent the average pooling weights and the max pooling weights, respectively. sigmoid(·) represents the activation function. r The reconstructed features are represented by the following formula:

[0031]

[0032] Where, η r Represents the eigenvector, γ r Represents the recombinant feature coefficient vector. This represents the element-wise multiplication of vectors. Based on the comparison of image data feature vectors, the similarity of image features is determined. Images are then clustered based on these feature vectors to identify road surface defects. First, different clustering feature vectors are selected from all image feature vectors as cluster centers. Clustering is then performed based on these centers. The clustering formula is as follows:

[0033] ρ r,i =||η r -η con,i ||2

[0034] Where, η con,i Let ρ represent the i-th cluster center. r,i Represents the eigenvector η r The cluster similarity with the i-th cluster center is denoted by ||·||2, which represents the 2-norm. The cluster space is formed by the feature vector and the cluster center with the smallest cluster similarity. Further clustering is performed within this space. Different cluster centers are selected within the cluster space, and clustering is repeated. This process is iterated until no new cluster space emerges, at which point the iteration ends. A standard road surface defect image dataset is used to construct experimental and validation sets. The experimental set data is used to optimize the feature matching analysis algorithm, while the validation set is used to verify the feature results. The accuracy of the validation results is used to determine the reliability of the feature matching analysis algorithm for intelligent detection of road surface defects. The proposed feature matching analysis algorithm performs max pooling and average pooling on the image data. Based on the max pooling and average pooling results, feature recombination is performed to calculate the feature vector of the image data. Based on the feature vector, clustering is performed. Based on the clustering results, matching analysis of road surface defects is conducted. The proposed feature matching analysis algorithm improves the degree of feature extraction and analysis of image data.

[0035] Furthermore, the road assessment module analyzes the road surface defects based on the feature matching analysis algorithm, outputs a health index, and assesses the urgency of road repair based on the health index.

[0036] Beneficial effects

[0037] 1. The image contrast processing algorithm proposed in this invention first performs image data enhancement processing based on the grayscale value representation of the image data to improve the grayscale contrast of the image data. Then, a fuzzy filtering function is constructed, and high-frequency enhancement operation is performed on the road surface image data through the fuzzy filtering function to obtain high-frequency components. Then, through defuzzing operation, pixel overflow correction is performed to achieve contour compensation of the image data. The image contrast processing algorithm proposed in this invention increases the grayscale contrast of the image, achieves contour compensation of the image, enhances the image edges, improves the image quality, and thus helps to improve the accuracy of the algorithm operation.

[0038] 2. The feature matching analysis algorithm proposed in this invention performs max pooling and average pooling on image data. Based on the results of max pooling and average pooling, feature recombination is performed to calculate the feature vector of the image data. Based on the feature vector, clustering operation is performed on the feature vector. Based on the clustering results, matching analysis of road surface defects is performed. The feature matching analysis algorithm proposed in this invention can improve the degree of feature extraction and analysis of image data and improve the accuracy of judging the condition of road surface defects. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0040] Figure 1 This is a system schematic diagram of the present invention; Detailed Implementation

[0041] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0042] To achieve the above objectives, this invention proposes an intelligent road online diagnosis and evaluation system and application, characterized by comprising a data acquisition hardware module, a road monitoring module, an image data transmission module, a processing center module, an image data processing module, a road defect intelligent detection module, and a road evaluation module. The data acquisition hardware module utilizes an intelligent unmanned aerial vehicle (UAV) array for automated flight. The road monitoring module uses the UAV array to monitor road surface conditions in real time. The image data transmission module transmits the acquired road surface image data via radio technology. The processing center module receives, stores, and analyzes the road surface data through a central server. The image data processing module proposes an image comparison processing algorithm to enhance the road surface image data and achieve image contour compensation. The road defect intelligent detection module uses a feature matching analysis algorithm to analyze the features of the road surface image data and intelligently detect road defects. The road evaluation module assesses the health of the road surface based on the output results of the road defect intelligent detection module.

[0043] Specifically, the data acquisition hardware module allows users to preset detection routes for the drone array, which then performs automated operations based on these preset routes.

[0044] Specifically, the road monitoring module uses an array of drones to monitor road surface conditions in real time and collect data on these conditions.

[0045] Specifically, the image data transmission module uses radio technology to establish a data transmission channel between the UAV array and the central server, enabling the transmission and storage of road surface image data.

[0046] Specifically, the processing center module receives road surface image data collected by the UAV array through the central server, and stores and analyzes the road surface image data and runs algorithms.

[0047] Specifically, the image contrast processing algorithm enhances the road surface image data by performing filtering operations, deblurring, and then performing overflow correction to achieve image contour compensation. The detailed process is as follows:

[0048] For the collected road surface image data, the road surface image data is represented by a grayscale matrix, as follows:

[0049]

[0050] Among them, D ori d represents the grayscale value matrix of the original road surface image data. 1,1 d 1,n d i,j dm,1 d m,n Let $\mathbf$ represent the grayscale values ​​of the pixels in the first row and first column of the original road surface image data, the pixels in the first row and nth column of the original road surface image data, the pixels in the i-th row and j-th column of the original road surface image data, the pixels in the m-th row and first column of the original road surface image data, and the pixels in the m-th row and n-th column of the original road surface image data, respectively. Based on the grayscale value matrix of the original road surface image data, the original road surface image data enhancement processing is performed, and the formula is as follows:

[0051]

[0052] Where, d′ i,j Let represent the grayscale value of the pixel in the i-th row and j-th column of the original road surface image data after processing. min(·) represents finding the minimum value of the elements in the matrix, and max(·) represents finding the maximum value of the elements in the matrix. Then, the high-frequency components of the enhanced original road surface image data are filtered. First, a blur filter function is constructed, and the function formula is as follows:

[0053]

[0054] Among them, h i,j σ represents the fuzzy filtering function. i,j The standard deviation of the fuzzy filter function is used to perform high-frequency enhancement of road surface image data based on the fuzzy filter function. This involves deblurring the grayscale values ​​of pixels, and the calculation formula is as follows:

[0055] I i,j =d′ i,j -α i,j ×h i,j ×d′ i,j

[0056] Among them, I i,j α represents the grayscale value of the pixel in the i-th row and j-th column of the original road surface image data after deblurring. i,j This represents the enhancement coefficient, which is used to correct pixel overflow by adjusting the grayscale value of the deblurred pixel. The calculation formula is as follows:

[0057]

[0058] Among them, I′ i,j D represents the grayscale value of the pixel in the i-th row and j-th column of the original road surface image data after overflow correction. m D n β represents the number of vertical pixels and horizontal pixels in the original road surface image data, respectively. i,j This represents the correction coefficient, which compensates for image contours by correcting for overflow at the pixel level.

[0059] Specifically, the feature matching analysis algorithm performs image data pooling on the processed road surface image data, then reconstructs image features, calculates feature values, and uses feature value matching analysis to determine the condition of the road surface. The detailed process is as follows:

[0060] For the processed road surface image data, image feature extraction is first performed. Then, using an attention mechanism, pooling is applied to the processed road surface image data based on convolutional kernels, as shown below:

[0061]

[0062] Among them, I hand I represents the processed road surface image data. mean I represents the road surface image data after average pooling. max This represents the road surface image data after max pooling. `meanxpool(·)` represents average pooling, which averages the values ​​of all surrounding pixels within each pixel of the processed road surface image data. `maxpool(·)` represents max pooling, which maximizes the value of all surrounding pixels within each pixel of the processed road surface image data. The road surface image data after pooling is then reconstructed using the following formula:

[0063]

[0064] Among them, I mean (l,k) represents the value of the pixel in the l-th row and k-th column of the road surface image data after average pooling. max (l,k) represents the value of the pixel in the l-th row and k-th column of the road surface image data after max pooling, ω mean,r.l,k ω max,r,l,k These represent the average pooling weights and the max pooling weights, respectively. sigmoid(·) represents the activation function. r The reconstructed features are represented by the following formula:

[0065]

[0066] Where, η r Represents the eigenvector, γ r Represents the recombinant feature coefficient vector. This represents the element-wise multiplication of vectors. Based on the comparison of image data feature vectors, the similarity of image features is determined. Images are then clustered based on these feature vectors to identify road surface defects. First, different clustering feature vectors are selected from all image feature vectors as cluster centers. Clustering is then performed based on these centers. The clustering formula is as follows:

[0067] ρ r,i =||η r -η con,i ||2

[0068] Where, η con,i Let ρ represent the i-th cluster center. r,i Represents the eigenvector η r The cluster similarity with the i-th cluster center is denoted by ||·||2, which represents the 2-norm. The cluster space is formed by the feature vector and the cluster center with the smallest cluster similarity. Further clustering is then performed within this space. Different cluster centers are selected within the cluster space, and clustering is repeated. This process is iterated until no new cluster space emerges, at which point the iteration ends. A standard road surface defect image dataset is used to construct a test set and a validation set. The test set data is used to optimize the feature matching analysis algorithm, while the validation set is used to verify the feature results. Based on the accuracy of the validation results, the reliability of the feature matching analysis algorithm for intelligent detection of road surface defects is determined.

[0069] Specifically, the road assessment module analyzes the road surface defects based on the feature matching analysis algorithm, outputs a health index, and assesses the urgency of road repair based on the health index.

[0070] In a specific embodiment, the user monitors the road surface condition in real time using a high-definition camera installed above the road and transmits the collected road surface image data via a wired connection. Then, a central server receives the road surface image data transmitted from the high-definition camera, and the user performs algorithmic calculations on the central server. Next, the user uses an image comparison processing algorithm to enhance the road surface image data. Then, the user uses a feature matching analysis algorithm to analyze the collected road surface data and intelligently detect road defects. Finally, based on the output of the intelligent road defect detection module, a health assessment of the road surface condition is performed to determine the urgency of road repairs.

[0071] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0072] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0073] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A smart road online diagnosis and evaluation system, characterized in that, It includes a data acquisition hardware module, a road monitoring module, an image data transmission module, a processing center module, an image data processing module, a road defect intelligent detection module, and a road assessment module. The data acquisition hardware module uses an intelligent drone array for automated flight. The road monitoring module uses a drone array to monitor the road surface condition in real time. The image data transmission module transmits collected road surface image data via radio technology; the processing center module receives, stores, and analyzes the road surface data through a central server; the image data processing module proposes an image comparison processing algorithm to perform image enhancement processing on the road surface image data, achieving image contour compensation; the intelligent road defect detection module uses a feature matching analysis algorithm to analyze the characteristics of the road surface image data and intelligently detect road defects; and the road assessment module assesses the health of the road surface based on the output results of the intelligent road defect detection module. The feature matching analysis algorithm performs image data pooling on the processed road surface image data, then reconstructs image features, calculates feature values, and determines the road surface damage condition through feature value matching analysis of the image data. The detailed process of determining the road surface damage condition through feature value matching analysis of image data is as follows: For the processed road surface image data, image feature extraction is first performed. Then, using an attention mechanism, pooling is applied to the processed road surface image data based on convolutional kernels, as shown below: in, This represents the processed road surface image data. This represents the road surface image data after average pooling. This represents the road surface image data after max pooling. This indicates an average pooling operation, which averages the values ​​of all surrounding pixels within each pixel of the processed road surface image data. This represents the max pooling operation, which involves taking the maximum value among the surrounding pixels of each pixel in the processed road surface image data. After the pooling operation, the road surface image data undergoes feature reconstruction, as shown in the following formula: in, This represents the road surface image data after average pooling. Line 1 The value of each pixel. This represents the road surface image data after max pooling. Line 1 The value of each pixel. , These represent the average pooling weight and the max pooling weight, respectively. This represents the activation function. The reconstructed features are represented by the following formula: in, Represents the eigenvector. Represents the recombinant feature coefficient vector. This represents the element-wise multiplication of vectors. Based on the comparison of image data feature vectors, the similarity of image features is determined. Images are then clustered based on these feature vectors to identify road surface defects. First, different clustering feature vectors are selected from all image feature vectors as cluster centers. Clustering is then performed based on these centers. The clustering formula is as follows: in, Indicates the first Cluster centers, Representing the eigenvector With the Cluster similarity of cluster centers The 2-norm is used to represent the cluster space formed by the eigenvectors and the cluster centers with the lowest cluster similarity. Further clustering is then performed within this space, selecting different cluster centers and repeating the process. This iteration continues until no new cluster space emerges, at which point the iteration ends. A standard road surface defect image dataset is used to construct experimental and validation sets. The experimental set is used to optimize the feature matching analysis algorithm, while the validation set is used to verify the algorithm's feature results. Based on the accuracy of the validation results, the reliability of the feature matching analysis algorithm for intelligent detection of road surface defects is determined.

2. The intelligent road online diagnosis and evaluation system according to claim 1, characterized in that, The data acquisition hardware module allows users to preset detection routes for the UAV array, which then performs automated operations based on these preset routes.

3. The intelligent road online diagnosis and evaluation system according to claim 1, characterized in that, The road monitoring module uses an array of drones to monitor road surface conditions in real time and collect data on these conditions.

4. The intelligent road online diagnosis and evaluation system according to claim 1, characterized in that, The image data transmission module utilizes radio technology to establish a data transmission channel between the UAV array and the central server, enabling the transmission and storage of road surface image data.

5. The intelligent road online diagnosis and evaluation system according to claim 1, characterized in that, The processing center module receives road surface image data collected by the UAV array through a central server, and stores and analyzes the road surface image data and runs algorithms.

6. The intelligent road online diagnosis and evaluation system according to claim 1, characterized in that, The image comparison processing algorithm enhances road surface image data by performing filtering operations, deblurring, and overflow correction to achieve image contour compensation.

7. The intelligent road online diagnosis and evaluation system according to claim 6, characterized in that, The detailed process of performing image contour compensation on road surface image data is as follows: For the collected road surface image data, the road surface image data is represented by a grayscale matrix, as follows: in, This represents the grayscale matrix of the original road surface image data. These represent the grayscale values ​​of the first pixel in the first row and first column of the original road surface image data, respectively. The grayscale values ​​of the columns of pixels, the original road surface image data Line 1 The grayscale values ​​of the columns of pixels, the original road surface image data The grayscale value of the first pixel in the first row and the first column of the original road surface image data. Line 1 The grayscale values ​​of the column pixels are used to perform image enhancement processing on the original road surface image data based on the grayscale value matrix of the original road surface image data, as follows: in, This represents the processed original road surface image data. Line 1 The grayscale values ​​of the column pixels, This indicates finding the minimum value of the elements in a matrix. This indicates finding the maximum value of each element in the matrix. Then, the high-frequency components of the enhanced original road surface image data are filtered. First, a blur filtering function is constructed, with the following formula: in, This represents the fuzzy filtering function. The standard deviation of the fuzzy filter function is used to perform high-frequency enhancement on road surface image data based on the fuzzy filter function, obtaining the high-frequency components of the image. Then, the pixel grayscale values ​​are deblurred. The calculation formula is as follows: in, This represents the original road surface image data after deblurring. Line 1 The grayscale values ​​of the column pixels, This represents the enhancement coefficient, which is used to correct pixel overflow by adjusting the grayscale value of the deblurred pixel. The calculation formula is as follows: in, Represents the original road surface image data. Line 1 Gray values ​​of column pixels after overflow correction These represent the number of vertical pixels and the number of horizontal pixels in the original road surface image data, respectively. This represents the correction coefficient, which compensates for image contours by correcting for overflow at the pixel level.

8. The intelligent road online diagnosis and evaluation system according to claim 1, characterized in that, The road assessment module analyzes the road surface defects based on the feature matching analysis algorithm, outputs a health index, and assesses the urgency of road repair based on the health index.

Images