A rapid detection method for road surface conditions based on two-path stereovision

Abstract

The application discloses a kind of based on two-way stereovision's road surface condition rapid detection method, it is related to fast detection field, this method includes following module composition: three-dimensional model optimization and texture mapping module: by using model optimization algorithm to three-dimensional model is carried out smooth processing and detail enhancement operation, simultaneously, using image texture information is mapped to model with texture, make model more realistic, the present application is through three-dimensional model optimization and texture mapping module using model optimization algorithm and texture mapping technique, the visual effect and authenticity of three-dimensional model are promoted, by to model is carried out smooth processing, detail enhancement operation, so that model is more realistic, simultaneously using texture mapping technique will the image information of road surface be attached to model surface, enhanced the visual expressiveness of model, the visual quality of three-dimensional model is improved, so that user can more intuitively understand the actual situation of road surface.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of rapid detection, in particular to a rapid detection method for road surface conditions based on double-path stereovision. BACKGROUND

[0002] With the vigorous development of intelligent transportation systems, accurate and real-time detection of road surface conditions has become a key link to ensure traffic safety and improve road maintenance efficiency. Traditional road surface detection methods cannot ensure the objectivity and accuracy of the detection results, and often cannot comprehensively and accurately reflect the true condition of the road surface. In recent years, the rapid development of computer vision technology has provided a new solution for road surface detection. The double-path stereovision technology can obtain three-dimensional geometric information and depth information of an object by simulating human binocular vision, thereby providing more comprehensive and accurate data support for road surface condition detection.

[0003] However, the existing road surface detection method based on double-path stereovision is affected by factors such as lighting conditions, texture features, or occlusion conditions when detecting complex and variable road surface conditions, which affects the accuracy and stability of the detection results. Secondly, most existing detection methods use complex algorithms and models, which have large computational load and poor real-time performance, making it difficult to meet the needs of practical applications. In addition, there is a lack of efficient and accurate methods for automatic identification and classification of road surface diseases in the existing detection methods.

[0004] Therefore, how to construct an efficient road surface condition rapid detection method based on double-path stereovision and a three-dimensional reconstruction road surface condition rapid detection method. However, most of the existing road surface condition rapid detection methods based on double-path stereovision on the market can only meet part of the above-mentioned requirements, and cannot realize the rapid and accurate acquisition of three-dimensional information of the road surface using double-path stereovision technology. Therefore, the development of a road surface condition rapid detection method based on double-path stereovision that can comprehensively realize the above-mentioned features is of great significance for accurate detection and intuitive display of road surface conditions, and provides efficient and accurate road surface information support for intelligent transportation systems. SUMMARY

[0005] The purpose of the present application is to overcome the shortcomings of the prior art and provide a road surface condition rapid detection method based on double-path stereovision, which can quickly acquire three-dimensional information of the road surface through double-path stereovision technology, realize efficient and accurate detection of road surface conditions, and display the actual situation of the road surface through various visualization methods, thereby providing real-time and accurate road surface information support for intelligent transportation systems and improving road maintenance level and traffic safety.

[0006] To solve the above technical problems, the present application provides the following technical solution: a road surface condition rapid detection method, characterized in that the method comprises the following modules:

[0007] Dual-channel stereo vision data acquisition and processing module: synchronously acquire image data of the road surface by using a dual-channel stereo vision system, extract feature points in the image through image processing technology, and realize accurate matching of the feature points by using a stereo matching algorithm, thereby providing data support for subsequent three-dimensional reconstruction and visualization;

[0008] Three-dimensional information extraction and model reconstruction module: generate a high-precision three-dimensional model of the road surface by using a three-dimensional reconstruction algorithm according to the three-dimensional information obtained by the dual-channel stereo vision system, and ensure the authenticity and accuracy of the model through advanced algorithms and technologies, thereby providing a reliable basis for subsequent road surface condition analysis;

[0009] Three-dimensional model optimization and texture mapping module: perform smoothing processing and detail enhancement operations on the three-dimensional model by using a model optimization algorithm, and perform texture mapping on the model by using image texture information, so that the model is more realistic, thereby improving the visual effect and authenticity of the three-dimensional model, and enabling users to more intuitively understand the actual situation of the road surface;

[0010] Road surface condition visualization and analysis module: the present application provides multiple visualization methods including three-dimensional rendering and texture mapping, so that users can intuitively view the three-dimensional model of the road surface, and the module has an automatic analysis function, which can detect cracks and pothole diseases of the road surface according to the three-dimensional model, generate a corresponding detection report, and users can view, analyze and export the detection report through an interactive interface, so as to timely process and maintain the road surface condition.

[0011] Further, the dual-channel stereo vision data acquisition and processing module synchronously photographs images of the road surface from two different angles by using dual-channel cameras, obtains left and right stereo images, ensures that the obtained images contain sufficient three-dimensional scene information, calibrates the dual-channel cameras to obtain internal and external parameters of the cameras such as focal length, principal point coordinates and distortion coefficients, so that the pixel points in the images can be mapped to points in the three-dimensional space in subsequent steps, pre-processes the obtained stereo images, including denoising, filtering and edge detection operations, to improve image quality and reduce errors in subsequent processing, extracts feature points or feature lines from the pre-processed images, matches the feature points or lines in the left and right images by using a stereo matching algorithm, finds corresponding points or lines in the left and right images by calculating the similarity or distance between the feature points, and thereby establishes a stereo correspondence relationship.

[0012] Further, the dual-channel stereo vision data acquisition and processing module determines the disparity value of each pixel by using the matching cost calculated by the stereo matching algorithm unit, and generates a disparity map, thereby further extracting three-dimensional information of the road surface, and the calculation formula is: Cx,y,d=∑ i∈Np I L x+i,y-IR x+i+d,y, where C(x, y, d) represents the matching cost of pixel point (x, y) with disparity d, N(p) is the neighborhood set centered on pixel point p(x, y), I L x+i+d,y, and I R x+i+d,y, respectively, are the gray values of corresponding pixels in left and right views. Through the stereo matching algorithm, this module can accurately and efficiently process dual-channel stereo vision data, realizing high-precision road surface three-dimensional reconstruction and visualization.

[0013] Further, the three-dimensional information extraction and model reconstruction module calculates the disparity of each pixel point according to the results of stereo matching, combines the internal and external parameters of the camera and the disparity information, and calculates the coordinates of each pixel point in three-dimensional space using the principle of triangulation. According to the calculated three-dimensional coordinate points, the three-dimensional model of the road surface is reconstructed using point cloud data or gridding method. During the reconstruction process, a smoothing algorithm is used to improve the accuracy and smoothness of the model.

[0014] Further, the three-dimensional information extraction and model reconstruction module uses a smoothing algorithm to process the obtained three-dimensional coordinate data to reduce noise and improve model accuracy. The smoothing algorithm uses a moving average method, and its algorithm formula is: where W is the weight, N = 2m + 1 is the number of moving average terms, X(i) is a variable within the window A, and each time the window A moves forward by one data point, the variable index j also moves backward by one data point. The three-dimensional coordinate data processed by the smoothing algorithm is used for subsequent model reconstruction steps, thereby generating a more accurate and smoother three-dimensional model.

[0015] Further, the three-dimensional model optimization and texture mapping module optimizes the reconstructed three-dimensional model through smoothing filtering and detail enhancement operations to improve the visual effect and realism of the model. The three-dimensional model is texture mapped using image information of the road surface, and the texture information is attached to the surface of the model by selecting appropriate texture images and mapping algorithms, making the model more realistic and lively.

[0016] Further, the three-dimensional model optimization and texture mapping module uses smoothing filtering and mapping algorithms to improve the visual effect and realism of the model. The smoothing filtering formula is: Among them, h(x, y) is the result after filtering, (i, j) is the coordinate of the signal value to be filtered in the image, and σ is the standard deviation of the Gaussian function, which determines the smoothness of the filter. Texture mapping usually involves coordinate transformation, mapping the coordinates (u, v) in the texture space to the vertex coordinates of the 3D model surface. Through the texture mapping algorithm, the noise and irregularities in the details of the model surface can be effectively removed, and the smoothness and visual effect of the model can be improved. The core formula of the texture mapping algorithm is: Tp = LerpTv1, Tv2, α, where T(p) is the texture coordinate corresponding to the point p on the model surface, Tv1 and Tv2 are the texture coordinates of the two vertices v1 and v2 adjacent to the point p, and α is the interpolation parameter, which represents the position of the point p relative to v1 and v2. Through this mapping algorithm, the texture can be smoothly fitted to the model surface, improving the realism and visual effect of the model. At the same time, combined with 3D model optimization processing, a high-quality, detailed 3D model can be generated, providing strong support for subsequent visualization and analysis.

[0017] Furthermore, the pavement condition visualization and analysis module displays the optimized and texture-mapped three-dimensional model to the user in a variety of visualization methods, such as three-dimensional rendering or texture mapping. The user can zoom, rotate and roam through the interactive interface to fully and intuitively understand the actual situation of the road surface. The three-dimensional model is used for automatic analysis to detect cracks or potholes in the road surface. By calculating the geometric features and color change information of the model, the location, size and severity of the disease can be identified and a corresponding detection report can be generated.

[0018] Furthermore, the method further includes a calibration module for periodically calibrating the camera to ensure the accuracy and stability of the collected image data.

[0019] Furthermore, the specific steps of the method are:

[0020] (1) System preparation and initialization: Start the 3D reconstruction visualization system based on dual-channel stereo vision, ensure that the dual-channel stereo vision system operates normally, and that the camera is in the appropriate position and angle to capture image data of the road surface.

[0021] (2) Dual-channel stereo vision data acquisition and processing: The dual-channel stereo vision system synchronously acquires image data of the road surface to ensure that the images captured by the left and right cameras are consistent in time for subsequent stereo matching. The acquired image data is pre-processed, including denoising and contrast enhancement, to improve image quality and prepare for subsequent feature point extraction and matching.

[0022] (3) Feature point extraction and stereo matching: In the pre-processed images, feature points are extracted using image processing techniques. These feature points are usually prominent regions in the image, such as edges and corners. Stereo matching algorithms are used to accurately match the feature points in the images captured by the left and right cameras, obtaining the corresponding relationship between the feature points.

[0023] (4) Three-dimensional information extraction and model reconstruction: Based on the matching results of the feature points, three-dimensional coordinates of the feature points are calculated through three-dimensional reconstruction algorithms, obtaining the three-dimensional information of the road surface. The acquired three-dimensional information is used to generate a high-precision three-dimensional model of the road surface through three-dimensional reconstruction algorithms.

[0024] (5) Three-dimensional model optimization and texture mapping: The generated three-dimensional model is smoothed to remove noise and irregularities, improving the smoothness and realism of the model. Detail enhancement operations are performed on the model to highlight the edges and texture information, making the model more vivid and realistic. Texture mapping is performed on the three-dimensional model using the texture information of the road surface image, making the model surface appear more detailed and realistic.

[0025] (6) Road surface condition visualization and analysis: The optimized three-dimensional model is displayed in three-dimensional rendering form, allowing users to intuitively view the three-dimensional structure of the road surface. The system automatically analyzes the three-dimensional model to detect cracks and pothole diseases in the road surface and generates corresponding detection reports. Users can view, analyze and export the detection reports through the interactive interface and timely handle and maintain the road surface conditions based on the report content.

[0026] Compared with the prior art, the road surface condition rapid detection method based on double road stereo vision has the following advantages

[0027] Advantages:

[0028] First, the three-dimensional model optimization and texture mapping module of the present application uses model optimization algorithms and texture mapping techniques to improve the visual effect and realism of the three-dimensional model. Through smoothing and detail enhancement operations on the model, the model becomes more realistic. At the same time, the texture mapping technology is used to attach the image information of the road surface to the model surface, enhancing the visual expressiveness of the model and improving the visual quality of the three-dimensional model, allowing users to more intuitively understand the actual situation of the road surface.

[0029] Second, the three-dimensional information extraction and model reconstruction module of the present application uses an optimized three-dimensional reconstruction algorithm to realize rapid reconstruction of a high-precision three-dimensional model of the road surface, improving the realism and detail expressiveness of the model, allowing the model to more accurately reflect the actual situation of the road surface, and improving the efficiency and accuracy of three-dimensional reconstruction, providing a reliable model basis for the analysis and visualization of road surface conditions.

[0030] Additional advantages, objects, and features of the application will be apparent to those skilled in the art upon examination of the following detailed description, it being understood that each embodiment can not represent every such advantage, object, or feature of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without any creative effort.

[0032] Figure 1 The flow chart of the rapid road surface condition detection method based on dual-path stereo vision. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present application will be described clearly and completely below. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort are within the protection scope of the present application.

[0034] Embodiment 1: stereo matching and three-dimensional information extraction

[0035] The rapid road surface condition detection method based on dual-path stereo vision includes the following modules:

[0036] Dual-path stereo vision data acquisition and processing module: the dual-path stereo vision system is used to synchronously acquire image data of the road surface, feature points in the image are extracted through image processing technology, and accurate matching of the feature points is realized by using a stereo matching algorithm, thereby providing data support for subsequent three-dimensional reconstruction and visualization;

[0037] Three-dimensional information extraction and model reconstruction module: according to the three-dimensional information obtained by the dual-path stereo vision system, a high-precision three-dimensional model of the road surface is generated by using a three-dimensional reconstruction algorithm, the authenticity and accuracy of the model are ensured through advanced algorithms and technologies, and reliable basis is provided for subsequent road surface condition analysis;

[0038] Three-dimensional model optimization and texture mapping module: the three-dimensional model is subjected to smoothing processing and detail enhancement operation by using a model optimization algorithm, at the same time, the model is subjected to texture mapping by using image texture information, so that the model is more realistic, thereby improving the visual effect and authenticity of the three-dimensional model, and enabling the user to more intuitively understand the actual situation of the road surface;

[0039] The road surface condition visualization and analysis module provides various visualization modes including three-dimensional rendering and texture mapping, so that the user can intuitively view the three-dimensional model of the road surface, and the module has an automatic analysis function, which can detect cracks and pothole diseases of the road surface according to the three-dimensional model, and generate a corresponding detection report, and the user can view, analyze and export the detection report through an interactive interface, so as to timely process and maintain the road surface condition.

[0040] In the embodiment, how to extract three-dimensional information from the dual-path stereo vision data by using the stereo matching algorithm and reconstruct the three-dimensional model of the road surface is described in detail. The stereo matching algorithm is used to match the feature points in the left and right images. In the embodiment, the disparity value of each pixel is determined by using the matching cost calculated by the stereo matching algorithm unit, and a disparity map is generated, so as to further extract the three-dimensional information of the road surface. The calculation formula is:

[0041]

[0042] wherein C(x, y, d) represents the matching cost of the pixel point (x, y) when the disparity is d, N(p) is a neighborhood set with the pixel point p(x, y) as the center, I L x+i,y and I R x+i+d,y are the gray values of the corresponding pixels in the left and right views. After completing the stereo matching, the disparity value of each pixel point is obtained. The disparity value represents the horizontal displacement between the corresponding points in the left and right images, and contains the three-dimensional information of the road surface. According to the internal and external parameters of the camera (such as focal length, principal point coordinates, distortion coefficient) and the disparity information, the coordinates of each pixel point in the three-dimensional space are calculated by using the triangulation principle. The specific calculation formula is:

[0043]

[0044] where Z is the depth information, representing the distance from the object to the camera, f is the focal length of the camera, determining the focusing ability of the camera lens, T is the baseline distance between the two cameras, i.e. the distance between the optical centers of the two cameras in the stereo vision system, d is the disparity value, representing the horizontal displacement between corresponding points in the left and right camera images. With these three-dimensional coordinate points, the three-dimensional model of the road surface can be reconstructed. The calculated three-dimensional coordinate points are converted into point cloud data format, and the point cloud data is smoothed to remove noise and improve data quality. The point cloud data is converted into a three-dimensional grid model using a gridding method. This grid model is the three-dimensional reconstruction result of the road surface, which can intuitively show the geometric shape and structure of the road surface. In order to verify the accuracy and reliability of the three-dimensional reconstruction, it can be verified and calibrated, for example, actual measurement data or known road surface structure information can be used to compare and verify the reconstruction result. In addition, it is also very important to regularly calibrate the camera to ensure the accuracy and stability of the collected image data.

[0045] In summary, through the stereo matching and three-dimensional information extraction process described in this embodiment, the dual stereo vision data can be effectively used to reconstruct the three-dimensional model of the road surface, providing strong support for subsequent road surface condition analysis, visualization and intelligent transportation system applications.

[0046] Embodiment 2: Three-dimensional model optimization and texture mapping

[0047] The method includes the following modules:

[0048] Dual stereo vision data acquisition and processing module: using dual stereo vision system to synchronously acquire image data of road surface, extracting feature points in image through image processing technology, and realizing accurate matching of feature points by using stereo matching algorithm, providing data support for subsequent three-dimensional reconstruction and visualization;

[0049] Three-dimensional information extraction and model reconstruction module: generating high-precision three-dimensional model of road surface by using three-dimensional reconstruction algorithm according to three-dimensional information obtained by dual stereo vision system, ensuring the authenticity and accuracy of the model through advanced algorithms and technologies, and providing reliable basis for subsequent road surface condition analysis;

[0050] Three-dimensional model optimization and texture mapping module: performing smoothing and detail enhancement operations on the three-dimensional model by using model optimization algorithm, and at the same time, performing texture mapping on the model by using image texture information, so that the model is more realistic, thereby improving the visual effect and authenticity of the three-dimensional model, and enabling users to more intuitively understand the actual situation of the road surface;

[0051] The pavement condition visualization and analysis module: the present application provides various visualization methods including three-dimensional rendering and texture mapping, so that the user can intuitively view the three-dimensional model of the pavement, and at the same time, the module has an automatic analysis function, which can detect cracks and pothole diseases of the pavement according to the three-dimensional model, and generate a corresponding detection report, the user can view, analyze and export the detection report through the interactive interface, so as to timely process and maintain the pavement condition.

[0052] In this embodiment, the three-dimensional model of the pavement previously reconstructed by the stereo vision technology is optimized and texture mapped to enhance its visual effect and realism. In order to improve the smoothness and accuracy of the three-dimensional model, the model is smoothed by using a Gaussian filter algorithm. Gaussian filter is an algorithm widely used in image and model processing, and its mathematical expression is as follows:

[0053]

[0054] where hx,y is the filtered result, x,y is the point coordinate on the model surface, and σ is the standard deviation of the Gaussian function, which determines the smoothing degree of the filter. In practical applications, the value of σ can be adjusted according to the needs to achieve the best smoothing effect. After Gaussian filter processing, the noise and irregularity of the model surface will be effectively removed, and the smoothness and accuracy of the model will be significantly improved. In order to enhance the details and edge information of the model, a texture mapping algorithm is used for detail enhancement processing of the model. The core formula of the texture mapping algorithm is:

[0055] Tp=LerpTv1,Tv2,α

[0056] where T(p) is the texture coordinate corresponding to the point p on the model surface, Tv1 and Tv2 are the two vertices adjacent to the point p, v1 and v2 are the texture coordinates of the vertices, and α is the interpolation parameter representing the position of the point p relative to v1 and v2. Through this mapping algorithm, the texture can be smoothly attached to the model surface, improving the realism and visual effect of the model. At the same time, combined with the three-dimensional model optimization processing, a high-quality and detailed three-dimensional model can be generated, providing strong support for subsequent visualization and analysis.

[0057] In summary, through the three-dimensional model optimization and texture mapping processing in this embodiment, a smooth, fine and realistic textured three-dimensional model of the pavement can be obtained. This model can not only be used for subsequent pavement condition analysis and visualization display, but also can provide strong data support for intelligent transportation systems and autonomous driving fields.

[0058] Embodiment 3: Application of pavement condition rapid detection method based on double-path stereo vision

[0059] The specific steps of the road surface condition rapid detection method based on dual stereo vision are as follows:

[0060] (1) System preparation and initialization: start the three-dimensional reconstruction visualization system based on dual stereo vision, ensure the normal operation of the dual stereo vision system, and place the camera at a suitable position and angle to capture image data of the road surface.

[0061] (2) Dual stereo vision data acquisition and processing: the dual stereo vision system synchronously acquires image data of the road surface, ensures that the images captured by the left and right cameras are consistent in time for subsequent stereo matching, and pre-processes the acquired image data, including denoising and contrast enhancement, to improve image quality and prepare for subsequent feature point extraction and matching.

[0062] (3) Feature point extraction and stereo matching: in the pre-processed images, feature points are extracted using image processing techniques, which are usually prominent regions in the image such as edges and corners, and stereo matching algorithms are used to accurately match the feature points in the images captured by the left and right cameras to obtain the corresponding relationship between the feature points.

[0063] (4) Three-dimensional information extraction and model reconstruction: based on the matching results of the feature points, three-dimensional coordinates of the feature points are calculated through three-dimensional reconstruction algorithms to obtain three-dimensional information of the road surface, and a high-precision three-dimensional model of the road surface is generated through three-dimensional reconstruction algorithms using the obtained three-dimensional information.

[0064] (5) Three-dimensional model optimization and texture mapping: the generated three-dimensional model is smoothed to remove noise and irregularities, improving the smoothness and realism of the model, and the model is enhanced with details to highlight the edges and texture information of the model, making the model more vivid and realistic. The three-dimensional model is texture-mapped using the texture information of the road surface image, making the model surface appear more detailed and realistic.

[0065] (6) Road surface condition visualization and analysis: the optimized three-dimensional model is displayed in the form of three-dimensional rendering, allowing users to intuitively view the three-dimensional structure of the road surface, and the system automatically analyzes the three-dimensional model to detect cracks and pothole diseases in the road surface and generates a corresponding detection report. Users can view, analyze and export the detection report through the interactive interface, and timely handle and maintain the road surface condition according to the report content.

[0066] It will be apparent to those skilled in the art that the application is not limited to the details of the above-exemplified embodiments and that the present application can be implemented in other particular forms without departing from the spirit or essential characteristics of the present application. The embodiments should therefore be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the above description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. No reference signs in the claims should be considered as limiting the scope of the claims with respect to the figures of the patent document.

Claims

1. A method for rapid detection of road conditions based on dual-path stereo vision, characterized in that: The method consists of the following modules: Dual-channel stereo vision data acquisition and processing module: Utilizes a dual-channel stereo vision system to synchronously collect road image data, extracts feature points from the images through image processing technology, and uses a stereo matching algorithm to achieve precise matching of feature points, providing data support for subsequent 3D reconstruction and visualization; 3D Information Extraction and Model Reconstruction Module: Based on the 3D information obtained by the dual-channel stereo vision system, a 3D reconstruction algorithm is used to generate a high-precision 3D model of the road surface. Advanced algorithms and technologies ensure the authenticity and accuracy of the model, providing a reliable basis for subsequent road condition analysis. 3D model optimization and texture mapping module: This module uses a model optimization algorithm to smooth and enhance the details of the 3D model. It also uses image texture information to perform texture mapping on the model, making it more realistic. This improves the visual quality and authenticity of the 3D model, allowing users to more intuitively understand the actual road conditions. Pavement condition visualization and analysis module: This invention provides a variety of visualization methods, including 3D rendering and texture mapping, so that users can intuitively view the 3D model of the road surface. At the same time, the module has an automatic analysis function, which can detect cracks and potholes in the road surface based on the 3D model and generate corresponding inspection reports. Users can view, analyze and export the inspection reports through the interactive interface to timely handle and maintain the road surface condition.

2. The method for rapid detection of road conditions based on dual-path stereo vision according to claim 1, characterized in that: The dual-channel stereo vision data acquisition and processing module uses a dual-channel camera to synchronously capture images of the road surface from two different angles to obtain two left and right stereo images, ensuring that the acquired images contain sufficient three-dimensional scene information, calibrating the dual-channel camera, and obtaining the camera's internal and external parameters, such as focal length, principal point coordinates, and distortion coefficient, so that in subsequent steps, pixel points in the image can be mapped to points in three-dimensional space. The acquired stereo images are preprocessed, including denoising, filtering, and edge detection operations, to improve image quality and reduce errors in subsequent processing. Feature points or feature lines are extracted from the preprocessed images, and the feature points or lines in the left and right images are matched using a stereo matching algorithm. By calculating the similarity or distance between the feature points, the corresponding points or lines in the left and right images are found, thereby establishing a stereo correspondence.

3. The method for rapid detection of road conditions based on dual-path stereo vision according to claim 2, characterized in that: The dual-channel stereo vision data acquisition and processing module determines the disparity value of each pixel by using the matching cost calculated by the stereo matching algorithm unit, and generates a disparity map, thereby further extracting the three-dimensional information of the road surface. The calculation formula is: C(x, y, d) = ∑ i∈N(p) |I L (x+i,y)-I R (x+i+d,y)|, where C(x, y, d) represents the matching cost of the pixel point (x, y) when the disparity is d, N(p) is the neighborhood set centered on the pixel point p(x, y), and I L (x+i,y) and I R (x+i+d,y) are the grayscale values ​​of the corresponding pixels in the left and right views respectively. Through the stereo matching algorithm, this module can accurately and efficiently process dual-channel stereo vision data to achieve high-precision three-dimensional reconstruction and visualization of the road surface.

4. The method for rapid detection of road conditions based on dual-path stereo vision according to claim 1, characterized in that: The three-dimensional information extraction and model reconstruction module calculates the disparity of each pixel point based on the results of stereo matching, combines the internal and external parameters of the camera and the disparity information, and uses the principle of triangulation to calculate the coordinates of each pixel point in three-dimensional space. Based on the calculated three-dimensional coordinate points, the three-dimensional model of the road surface is reconstructed using point cloud data or gridding methods. A smoothing algorithm is used in the reconstruction process to improve the accuracy and smoothness of the model.

5. The method for rapid detection of road conditions based on dual-path stereo vision according to claim 4, characterized in that: The three-dimensional information extraction and model reconstruction module uses a smoothing algorithm to process the acquired three-dimensional coordinate data to reduce noise and improve model accuracy. The smoothing algorithm uses a moving average method, and its algorithm formula is: Where W is the weight, N = 2m + 1 is the number of moving average terms, and X(i) is the variable in window A. Each time window A moves forward by one data point, the variable index j also moves backward by one data point. The three-dimensional coordinate data processed by the smoothing algorithm is used in the subsequent model reconstruction step to generate a more accurate and smoother three-dimensional model.

6. The method for rapid detection of road conditions based on dual-path stereo vision according to claim 1, characterized in that: The 3D model optimization and texture mapping module optimizes the reconstructed 3D model, including smoothing filtering and detail enhancement operations, to improve the visual effect and authenticity of the model. It uses image information of the road surface to perform texture mapping on the 3D model. By selecting appropriate texture images and mapping algorithms, the texture information is attached to the surface of the model, making the model more realistic and vivid.

7. The method for rapid detection of road conditions based on dual-path stereo vision according to claim 6, characterized in that: The 3D model optimization and texture mapping module uses smoothing filtering and mapping algorithms to improve the visual effect and authenticity of the model. The smoothing filtering formula is: Here, h(x, y) is the filtered result, (i, j) is the coordinate of the signal value to be filtered in the image, and σ is the standard deviation of the Gaussian function, which determines the smoothness of the filter. Texture mapping usually involves coordinate transformation, mapping the coordinates (u, v) in the texture space to the vertex coordinates of the 3D model surface. Through the mapping algorithm, the noise and irregularities in the details of the model surface can be effectively removed, and the smoothness and visual effect of the model can be improved. The core formula of the texture mapping algorithm is: T(p) = Lerp(T(v1), T(v2), α), where T(p) is the texture coordinate corresponding to the point p on the model surface, T(v1) and T(v2) are the texture coordinates of the two vertices v1 and v2 adjacent to the point p, and α is the interpolation parameter, which represents the position of the point p relative to v1 and v2. Through this mapping algorithm, the texture can be smoothly fitted to the model surface, improving the realism and visual effect of the model. At the same time, combined with 3D model optimization processing, a high-quality and detailed 3D model can be generated, providing strong support for subsequent visualization and analysis.

8. The method for rapid detection of road conditions based on dual-path stereo vision according to claim 1, characterized in that: The pavement condition visualization and analysis module displays the optimized and texture-mapped three-dimensional model to the user in a variety of visualization methods, such as three-dimensional rendering or texture mapping. The user can zoom, rotate, and roam through the interactive interface to fully and intuitively understand the actual situation of the road surface. The 3D model is used for automatic analysis to detect cracks or potholes in the road surface. By calculating the geometric features and color change information of the model, the location, size, and severity of the disease are identified, and a corresponding inspection report is generated.

9. The method for rapid detection of road conditions based on dual-path stereo vision according to claim 5, characterized in that: The method further comprises a calibration module for periodically calibrating the camera to ensure the accuracy and stability of the collected image data.

10. The method for rapid detection of road conditions based on dual-path stereo vision according to claim 1, characterized in that: The specific steps of the method are: (1) System preparation and initialization: Start the 3D reconstruction and visualization system based on dual-channel stereo vision, ensure that the dual-channel stereo vision system operates normally, and that the camera is in the appropriate position and angle to capture image data of the road surface; (2) Dual-channel stereo vision data acquisition and processing: The dual-channel stereo vision system synchronously acquires image data of the road surface to ensure that the images captured by the left and right cameras are consistent in time for subsequent stereo matching. The acquired image data is pre-processed, including denoising and contrast enhancement, to improve image quality and prepare for subsequent feature point extraction and matching. (3) Feature point extraction and stereo matching: In the pre-processed image, feature points are extracted using image processing technology. These feature points are usually significant areas in the image, such as edges and corners. The feature points in the images captured by the left and right cameras are accurately matched using a stereo matching algorithm to obtain the correspondence between the feature points. (4) 3D information extraction and model reconstruction: Based on the matching results of feature points, the 3D coordinates of the feature points are calculated through a 3D reconstruction algorithm to obtain the 3D information of the road surface. The obtained 3D information is then used to generate a high-precision 3D model of the road surface through a 3D reconstruction algorithm. (5) 3D model optimization and texture mapping: Smoothing the generated 3D model to remove noise and irregularities, improving the smoothness and realism of the model, performing detail enhancement on the model to highlight the edge and texture information of the model, making the model more vivid and realistic, and using the texture information of the road surface image to perform texture mapping on the 3D model to make the model surface present richer details and realism; (6) Visualization and analysis of road conditions: The optimized 3D model is displayed in the form of 3D rendering, allowing users to intuitively view the 3D structure of the road surface. The system automatically analyzes the 3D model, detects cracks and potholes in the road surface, and generates corresponding inspection reports. Users can view, analyze and export the inspection reports through the interactive interface, and promptly process and maintain the road surface conditions based on the report content.

Images