A tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology

Abstract

The present invention relates to the field of image analysis technology, specifically a tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology, comprising: acquiring an infrared image frame sequence and performing preprocessing and feature enhancement processing; extracting gradient eigenvalues ​​and outlier eigenvalues ​​from the enhanced infrared image to identify initial leakage areas; tracking each initial leakage area in a continuous enhanced infrared image frame sequence to obtain a regional spatial sequence, and extracting the spatial gradient eigenvalues ​​of the initial leakage area; calculating a multi-feature comprehensive leakage index based on the gradient eigenvalues, outlier eigenvalues, and spatial gradient eigenvalues, processing the initial leakage area to obtain a leakage area; performing feature analysis on each leakage area to obtain regional multidimensional features, and performing a severity assessment based on the regional multidimensional features. The present invention improves the reliability of leakage analysis and assessment.

Description

Technical Field

[0001] The present invention relates to the field of image analysis technology, and in particular to a tunnel vehicle-mounted leakage perception and detection method based on infrared thermal imaging technology. Background Art

[0002] The current leakage perception method obtains thermal radiation distribution data from the tunnel lining surface and uses digital image processing technology to construct a mapping relationship between temperature and grayscale images. The core lies in converting temperature information into a multidimensional digital image matrix through grayscale mapping or pseudo-color coding algorithm, and processing the thermal radiation image using algorithms such as threshold segmentation and region growing. Morphological operations are combined to optimize the contour features of the thermal anomaly area. Specifically, a gradient edge detection method based on heat conduction difference is used to perform image processing on the lining surface temperature distribution matrix to generate a topological structure representation map of the thermal anomaly area.

[0003] However, existing technical solutions for mobile detection have limitations in image sequence processing, primarily due to a failure to analyze the spatiotemporal correlations between consecutive frames. Because the continuous image sequences generated by mobile imaging acquisition exhibit spatial displacement, traditional analysis methods based on single-frame static images cannot effectively capture the spatiotemporal evolution of the target area as the detection device moves. This leads to a break in the spatial continuity of the detection, reducing the reliability of the results.

[0004] Therefore, a tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology is proposed. Summary of the Invention

[0005] The present invention aims to provide a vehicle-mounted tunnel leakage detection method based on infrared thermal imaging technology. The method comprises: acquiring an infrared image frame sequence and performing preprocessing and feature enhancement processing; extracting gradient eigenvalues ​​and outlier eigenvalues ​​from the enhanced infrared image to identify the initial leakage area; tracking each initial leakage area in a continuous enhanced infrared image frame sequence to obtain a regional spatial sequence, and extracting the spatial gradient eigenvalues ​​of the initial leakage area; calculating a comprehensive leakage index based on the gradient eigenvalues, outlier eigenvalues, and spatial gradient eigenvalues, processing the initial leakage area to obtain the leakage area; performing feature analysis on each leakage area to obtain regional multidimensional features, and performing a severity assessment based on the regional multidimensional features. The present invention improves the reliability of leakage analysis and assessment.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology comprises:

[0008] Acquire an infrared image frame sequence of the tunnel detection area and perform preprocessing and feature enhancement processing on each frame of the infrared image to obtain an enhanced infrared image frame sequence;

[0009] Extracting the gradient eigenvalue and the outlier eigenvalue of each pixel from each frame of enhanced infrared image, and identifying the initial leakage area by combining the gradient eigenvalue and the outlier eigenvalue;

[0010] Tracking each of the initial leakage regions in the enhanced infrared image frame sequence to obtain a region space sequence, and extracting spatial gradient feature values ​​of the initial leakage region;

[0011] Calculating a comprehensive leakage index of the initial leakage area according to the gradient eigenvalue, the outlier eigenvalue, and the spatial gradient eigenvalue;

[0012] According to the comprehensive leakage index, the initial leakage area is processed by a region growing algorithm to obtain a leakage area;

[0013] A feature analysis is performed on each leakage area to obtain a regional multi-dimensional feature, and a severity assessment is performed on the leakage area based on the regional multi-dimensional feature.

[0014] Furthermore, the process of preprocessing and feature enhancement of each frame of the infrared image specifically includes: performing Gaussian filtering denoising, geometric correction and temperature calibration on the infrared image to obtain a preprocessed infrared image; and performing feature enhancement on the preprocessed infrared image through adaptive nonlinear mapping, the formula is:

[0015] ;

[0016] in, and Pixels before and after enhancement The temperature value at is the average temperature of the preprocessed infrared image; is the adaptive enhancement coefficient; is the gradient sensitivity coefficient; is the pixel point in the preprocessed infrared image The gradient at .

[0017] Furthermore, the process of identifying the initial leakage area specifically includes: extracting the temperature gradient of each pixel point in the enhanced infrared image to obtain the gradient eigenvalue; dividing the enhanced infrared image into uniform local areas, calculating the temperature deviation of each pixel point and the temperature of the local area in which it is located, and obtaining the outlier eigenvalue; calculating the potential leakage index of each pixel point based on the gradient eigenvalue and the outlier eigenvalue; processing the pixels whose potential leakage index is greater than the potential leakage threshold through the connected component algorithm to obtain the initial leakage area set.

[0018] Furthermore, the process of tracking each of the initial leakage areas in the enhanced infrared image frame sequence specifically includes: assigning a different identifier to each of the initial leakage areas in the enhanced infrared image frame sequence and extracting characterization features; calculating the first leakage area in combination with vehicle motion parameters and image acquisition parameters; The predicted position of the initial leakage area in the frame image in the subsequent frame image; in the subsequent frame image, a search window is set with the predicted position as the center, and the representation matching degree between the initial leakage area to be matched in the search window and the initial leakage area is calculated according to the representation feature, and the initial leakage area to be matched with the largest representation matching degree in the search window is marked as the tracking object of the initial leakage area, if the representation matching degree of the tracking object is greater than or equal to the matching degree threshold, the identifier of the tracking object is changed to the identifier of the initial leakage area, if the representation matching degree of the tracking object is less than the matching degree threshold, the tracking of the initial leakage area is ended; the initial leakage areas to be matched with the same identifier as the initial leakage area in the enhanced infrared image frame sequence are summarized as the regional spatial sequence of the initial leakage area.

[0019] Furthermore, for each initial leakage area, the spatial gradient characteristic value is calculated based on the regional spatial sequence, and the calculation formula is:

[0020] ;

[0021] in, Initial leakage area The spatial gradient eigenvalue of Initial leakage area The length of the regional spatial sequence; is the serial number of the regional spatial sequence; For the The weight coefficient of each serial number; and Initial leakage area In the Hedi The average temperature value in the enhanced infrared image corresponding to the serial number; Enhance the spatial distance of infrared images for two adjacent frames.

[0022] Furthermore, the pixel point with the highest comprehensive leakage index in the initial leakage area is used as the seed point, and the region growing algorithm is applied to the initial leakage area to obtain the leakage area. The calculation formula of the comprehensive leakage index is:

[0023] ;

[0024] in, Initial leakage area Medium pixel Comprehensive leakage index; 、 and are the weight coefficients of outlier eigenvalue, gradient eigenvalue and spatial gradient eigenvalue respectively; is the outlier eigenvalue; is the gradient eigenvalue; Initial leakage area The maximum value of the gradient eigenvalue in the enhanced infrared image; Initial leakage area The spatial gradient eigenvalue of Initial leakage area The maximum value of the spatial gradient eigenvalue of all initial leakage areas in the enhanced infrared image.

[0025] Furthermore, the process of feature extraction and severity assessment of the leakage area includes: obtaining the regional spatial sequence of the leakage area according to the mapping relationship between each leakage area and the initial leakage area, extracting the regional multidimensional features to obtain a regional multidimensional feature sequence; the regional multidimensional features include regional morphological features, regional temperature features and regional permeability features; inputting the regional multidimensional feature sequence into the leakage severity assessment model, and outputting the leakage severity index.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] 1. First, the infrared image is preprocessed and feature enhanced. Then, the initial leakage area is identified using two dimensions: gradient eigenvalues ​​and outlier eigenvalues. The gradient eigenvalues ​​capture the temperature change rate between the leakage area and the surrounding environment, while the outlier eigenvalues ​​identify abnormal temperature points by calculating the deviation between the pixel temperature and the local area temperature. The combination of these two features can more accurately identify areas with abnormal temperature distribution and clear boundary features. Pixels with potential leakage indices greater than a threshold are processed using a connected component algorithm to determine the initial set of leakage areas. This significantly improves the accuracy of preliminary leakage identification and effectively reduces interference from environmental noise and non-leakage abnormal heat sources, laying the foundation for subsequent leakage area analysis.

[0028] 2. For the dynamic tracking of initial leakage areas in a vehicle-mounted detection environment, a unique identifier is first assigned to each initial leakage area and characterization features are extracted. Then, the position of the leakage area in subsequent frames is predicted by combining the vehicle motion parameters and image acquisition parameters. By setting a search window at the predicted position and calculating the characterization match between the initial leakage area and the target area within the window, effective tracking of the leakage area is achieved. The concept of spatial gradient eigenvalues ​​is introduced. By calculating the temperature changes in the spatial sequence of the region, the law of temperature changes in the leakage area with space can be reflected, which significantly improves the adaptability and detection stability of leakage detection in a mobile environment, as well as the consistency and reliability of the detection process.

[0029] 3. By combining three key features—outlier eigenvalues, gradient eigenvalues, and spatial gradient eigenvalues—to calculate a comprehensive leakage index, this method comprehensively considers the static temperature characteristics and dynamic spatial variation characteristics of the leakage area, enabling a more comprehensive characterization of the leakage phenomenon. Based on the comprehensive leakage index, the leakage area is identified, and then a multidimensional feature sequence of the region is further extracted, which comprehensively describes the geometry, temperature distribution, and dynamic infiltration characteristics of the leakage area. Finally, these multidimensional feature sequences are input into the leakage severity assessment model, which outputs the leakage severity index, achieving a quantitative assessment of the leakage problem. This assessment method based on the regional multidimensional feature sequence improves the accuracy and reliability of leakage severity assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a flow chart of a tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology according to the present invention;

[0031] Figure 2 A schematic diagram of the process of tracking the initial leakage area according to the present invention;

[0032] Figure 3 Schematic diagram of the data flow of the present invention. DETAILED DESCRIPTION

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0034] See also Figures 1 to 3 The present invention provides a tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology. The technical solution is as follows:

[0035] Example 1:

[0036] This embodiment is applied to the leakage detection of a certain city tunnel. By using a vehicle-mounted infrared thermal imaging device to collect infrared images of the tunnel wall, in order to achieve automatic detection of leakage areas and severity assessment, a tunnel vehicle-mounted leakage perception and detection method based on infrared thermal imaging technology is applied. Figure 1 ,include:

[0037] Acquire an infrared image frame sequence of the tunnel detection area and perform preprocessing and feature enhancement processing on each frame of the infrared image to obtain an enhanced infrared image frame sequence;

[0038] Extracting the gradient eigenvalue and the outlier eigenvalue of each pixel from each frame of enhanced infrared image, and identifying the initial leakage area by combining the gradient eigenvalue and the outlier eigenvalue;

[0039] Tracking each of the initial leakage regions in the enhanced infrared image frame sequence to obtain a region space sequence, and extracting spatial gradient feature values ​​of the initial leakage region;

[0040] Calculating a comprehensive leakage index of the initial leakage area according to the gradient eigenvalue, the outlier eigenvalue, and the spatial gradient eigenvalue;

[0041] According to the comprehensive leakage index, the initial leakage area is processed by a region growing algorithm to obtain a leakage area;

[0042] A feature analysis is performed on each leakage area to obtain a regional multi-dimensional feature, and a severity assessment is performed on the leakage area based on the regional multi-dimensional feature.

[0043] Furthermore, the process of preprocessing and feature enhancement of each frame of the infrared image specifically includes: performing Gaussian filtering denoising, geometric correction and temperature calibration on the infrared image to obtain a preprocessed infrared image; and performing feature enhancement on the preprocessed infrared image through adaptive nonlinear mapping, the formula is:

[0044] ;

[0045] in, and Pixels before and after enhancement The temperature value at is the average temperature of the preprocessed infrared image; It is an adaptive enhancement factor, which is adjusted according to the type of fireproof panels installed in the tunnel; is the gradient sensitivity coefficient; is the pixel point in the preprocessed infrared image The gradient at .

[0046] The adjustment formula of the adaptive enhancement coefficient is: ;in, is the basic enhancement coefficient, which is 1.2; The material adjustment coefficient is used for different materials. For example, the value of cement-based fireproof board is 0, the value of calcium silicate fireproof board is 0.15, the value of fiber-reinforced fireproof board is 0.3, and the value of mineral fiber fireproof board is 0.25. is the thickness adjustment coefficient, and the calculation formula is: ;in, is the actual thickness of the fireproof board (mm), The standard thickness is 10mm.

[0047] Using a material- and thickness-based enhancement coefficient adjustment formula, we optimize parameters for fireproof panels of varying materials and thicknesses, improving the pertinence and adaptability of image enhancement. Preprocessing and feature enhancement effectively improve the quality of infrared images, making leak areas more prominent within the image and providing a more reliable data foundation for subsequent leak detection.

[0048] Furthermore, the process of identifying the initial leakage area specifically includes: extracting the temperature gradient of each pixel point in the enhanced infrared image to obtain the gradient eigenvalue; dividing the enhanced infrared image into uniform local areas, calculating the temperature deviation of each pixel point and the temperature of the local area in which it is located, and obtaining the outlier eigenvalue; calculating the potential leakage index of each pixel point based on the gradient eigenvalue and the outlier eigenvalue; processing the pixels whose potential leakage index is greater than the potential leakage threshold through the connected component algorithm to obtain the initial leakage area set.

[0049] Specifically, the maximum inter-class variance method is used to determine the potential leakage threshold; the calculation formula for the potential leakage index is:

[0050] ;

[0051] in, is the pixel point in the initial leakage area potential leakage index; and are the weight coefficients of the outlier eigenvalue and gradient eigenvalue respectively; is the outlier eigenvalue; is the gradient eigenvalue; is the maximum value of the gradient eigenvalue in the enhanced infrared image where the initial leakage area is located.

[0052] By calculating the gradient eigenvalue and the outlier eigenvalue, and combining them to calculate the potential leakage index, the maximum inter-class variance method is used to determine the threshold for pixel screening. Finally, the connected component algorithm is applied to obtain the initial leakage area set. This method takes into account both local temperature changes and global temperature anomalies, can capture leakage characteristics more comprehensively, reduce the misjudgment easily caused by a single feature, and improve the accuracy and reliability of initial leakage area identification.

[0053] Further, see Figure 2 The process of tracking each of the initial leakage areas in the enhanced infrared image frame sequence specifically includes:

[0054] assigning a different identifier to each of the initial leakage areas in the enhanced infrared image frame sequence and extracting characterizing features;

[0055] Combine the vehicle motion parameters and image acquisition parameters to calculate the The predicted position of the initial leakage area in the frame image in the subsequent frame image;

[0056] In a subsequent frame image, a search window is set with the predicted position as the center, and a representation matching degree between the initial leakage region to be matched within the search window and the initial leakage region is calculated based on the representation feature, and the initial leakage region to be matched with the maximum representation matching degree within the search window is marked as a tracking object of the initial leakage region; if the representation matching degree of the tracking object is greater than or equal to a matching degree threshold, the identifier of the tracking object is changed to the identifier of the initial leakage region; if the representation matching degree of the tracking object is less than the matching degree threshold, the tracking of the initial leakage region is terminated;

[0057] The initial leakage regions to be matched that have the same identifier as the initial leakage region in the enhanced infrared image frame sequence are summarized as a region space sequence of the initial leakage region.

[0058] Specifically, the characterization features include geometric features, temperature features, and texture features; the geometric features include the area, perimeter, circularity, and rectangularity of the region; the temperature features include the average temperature, maximum temperature, minimum temperature, and temperature standard deviation within the region; the texture features include entropy, contrast, correlation, and homogeneity calculated from the gray-level co-occurrence matrix; the geometric similarity, temperature similarity, and shape similarity are calculated based on the geometric features, temperature features, and texture features, and the geometric similarity, temperature similarity, and shape similarity are weightedly fused to obtain the characterization matching degree;

[0059] The calculation method of the predicted position is as follows: considering that the imaging device is installed on the vehicle, the movement of the vehicle causes the relative displacement of the stationary object in the image. If the vehicle moves forward in the longitudinal direction of the tunnel, the stationary point on the tunnel wall will move backward in the image, and the default point will not change in the vertical direction. Taking the tunnel wall on the right side of the vehicle's travel direction as an example, the time interval between the two frames of the vehicle is obtained. Speed ​​within and imaging device parameters to calculate the horizontal displacement of pixels , get the The initial leakage area in the frame image is Predicted position in the frame image , Indicates the The centroid coordinates of the initial leakage area in the frame image, displacement The calculation formula is ;in, The conversion coefficient of pixel displacement corresponding to the actual unit distance; is the focal length of the infrared thermal imaging device; is the distance between the infrared thermal imaging device and the tunnel wall. Considering the uncertainty of the prediction, the size of the search window is set to twice the bounding box of the initial leakage area to ensure that the tracked object is within the search window.

[0060] In this embodiment, the vehicle equipped with the infrared thermal imaging device travels at a speed of 20 km / h to 30 km / h, and the sampling frequency of the infrared thermal imaging device is 25 Hz.

[0061] By assigning a unique identifier to each initial leakage area and extracting characterizing features, the position of the area in subsequent frames is predicted by combining vehicle motion parameters and image acquisition parameters. A search window is set and feature matching is calculated for tracking matching. The relative motion characteristics in the vehicle scene are taken into account, effectively solving the image displacement problem caused by vehicle movement, so that the same leakage area can maintain a consistent identification in continuous image sequences, providing a basis for subsequent spatial variation characteristic analysis.

[0062] Furthermore, for each initial leakage area, the spatial gradient characteristic value is calculated based on the regional spatial sequence, and the calculation formula is:

[0063] ;

[0064] in, Initial leakage area The spatial gradient eigenvalue of Initial leakage area The length of the regional spatial sequence; is the serial number of the regional spatial sequence; For the The weight coefficient of each serial number; and Initial leakage area In the Hedi The average temperature value in the enhanced infrared image corresponding to the serial number; Enhance the spatial distance of infrared images for two adjacent frames.

[0065] By calculating spatial gradient eigenvalues, the relationship between temperature variations and spatial distances between adjacent frames in a regional spatial sequence is analyzed. This quantifies the spatial temperature variation trend in the leaking area, reflecting the spatial diffusion characteristics of the leak phenomenon and helping to distinguish between real leaks and surface temperature anomalies. Real leaks often exhibit certain spatial gradient eigenvalue distribution characteristics, while ordinary temperature anomalies lack this characteristic. By introducing spatial gradient eigenvalues, the system's ability to identify leaks is significantly improved.

[0066] Furthermore, the pixel point with the highest comprehensive leakage index in the initial leakage area is used as the seed point, and the region growing algorithm is applied to the initial leakage area to obtain the leakage area. The calculation formula of the comprehensive leakage index is:

[0067] ;

[0068] in, Initial leakage area Medium pixel Comprehensive leakage index; 、 and are the weight coefficients of outlier eigenvalue, gradient eigenvalue and spatial gradient eigenvalue respectively; is the outlier eigenvalue; is the gradient eigenvalue; Initial leakage area The maximum value of the gradient eigenvalue in the enhanced infrared image; Initial leakage area The spatial gradient eigenvalue of Initial leakage area The maximum value of the spatial gradient eigenvalue of all initial leakage areas in the enhanced infrared image.

[0069] By comprehensively considering the outlier eigenvalue, gradient eigenvalue and spatial gradient eigenvalue, a comprehensive leakage index was constructed. The region segmentation method based on multi-feature fusion can more accurately determine the boundary of the leakage area, avoiding the over-segmentation or under-segmentation problem caused by a single feature. At the same time, it can adapt to different leakage detection scenarios and improve the accuracy and robustness of the segmentation results.

[0070] Furthermore, the process of feature extraction and severity assessment of the leakage area includes: obtaining the regional spatial sequence of the leakage area according to the mapping relationship between each leakage area and the initial leakage area, extracting the regional multidimensional features to obtain a regional multidimensional feature sequence; the regional multidimensional features include regional morphological features, regional temperature features and regional permeability features; inputting the regional multidimensional feature sequence into the leakage severity assessment model, and outputting the leakage severity index.

[0071] By extracting multidimensional regional features and constructing feature sequences, which are then input into a leakage severity assessment model, all aspects of leakage are comprehensively considered. This model can not only detect the presence of leakage but also assess its severity, providing a more specific quantitative basis for tunnel maintenance decisions. This is crucial for timely identifying dangerous tunnel conditions, determining repair priorities, and developing preventive maintenance strategies.

[0072] This embodiment adopts the gradient boosting tree model as the basic model for leakage severity assessment, and adjusts and optimizes it in combination with expert knowledge. The model training uses 300 sets of leakage case data evaluated by experts. During the training process, the tree depth is set to 6, the learning rate is 0.05, the number of iterations is 500, and a five-fold cross validation is used to ensure the stability of the model. In order to improve the sensitivity of the model to samples of different severity, a weighted loss function is introduced to give higher weights to high severity samples. The regional multidimensional feature sequence is used as the input of the leakage severity assessment model, the features are normalized to eliminate the dimensional effect, and principal component analysis is used to reduce the redundancy between features. The model output is a leakage severity index from 0 to 100, and the original output of the model is mapped to the interval [0,100] through the activation function. The leakage severity index ranges from [0, 20] for slight leakage, [21, 40] for relatively mild leakage, [41, 60] for moderate leakage, [61, 80] for relatively severe leakage, and [81, 100] for severe leakage requiring immediate attention.

[0073] The present invention first uses infrared thermal imaging technology for non-contact detection, achieving high-efficiency, all-round monitoring of tunnel leakage, and avoiding the shortcomings of traditional manual detection such as low efficiency, high risk and strong subjectivity. Secondly, through image preprocessing and feature enhancement, the recognizability of the leakage area in the image is significantly improved. Third, the initial leakage area is divided by combining the gradient eigenvalue and outlier eigenvalue features, which improves the reliability of the preliminary detection. The introduction of regional tracking and spatial gradient feature analysis solves the problem of target tracking in a vehicle-mounted environment, achieves consistent identification of the same leakage area in continuous images, and effectively distinguishes between real leakage and surface temperature anomalies by analyzing its spatial temperature change characteristics. The comprehensive leakage index and the region growing algorithm based on the index further improve the accuracy of leakage area segmentation. Finally, through regional multidimensional feature extraction and severity assessment model, a quantitative assessment of the degree of leakage is achieved, providing a scientific basis for tunnel maintenance decision-making.

[0074] Example 2:

[0075] A tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology. The data flow is shown in Figure 3 , the specific steps include:

[0076] Acquire an infrared image frame sequence of the tunnel detection area and perform preprocessing and feature enhancement processing on each frame of the infrared image to obtain an enhanced infrared image frame sequence;

[0077] Furthermore, the process of preprocessing and feature enhancement of each frame of the infrared image specifically includes: performing Gaussian filtering denoising, geometric correction and temperature calibration on the infrared image to obtain a preprocessed infrared image; and performing feature enhancement on the preprocessed infrared image through adaptive nonlinear mapping, the formula is:

[0078] ;

[0079] in, and Pixels before and after enhancement The temperature value at is the average temperature of the preprocessed infrared image; is the adaptive enhancement coefficient; is the gradient sensitivity coefficient; is the pixel point in the preprocessed infrared image The gradient at .

[0080] Extracting the gradient eigenvalue and the outlier eigenvalue of each pixel from each frame of enhanced infrared image, and identifying the initial leakage area by combining the gradient eigenvalue and the outlier eigenvalue;

[0081] Furthermore, the process of identifying the initial leakage area specifically includes: extracting the temperature gradient of each pixel point in the enhanced infrared image to obtain the gradient eigenvalue; dividing the enhanced infrared image into uniform local areas, calculating the temperature deviation of each pixel point and the temperature of the local area in which it is located, and obtaining the outlier eigenvalue; calculating the potential leakage index of each pixel point based on the gradient eigenvalue and the outlier eigenvalue; processing the pixels whose potential leakage index is greater than the potential leakage threshold through the connected component algorithm to obtain the initial leakage area set.

[0082] Table 1 Initial leakage area identification results

[0083] Detection area number Number of initial leakage areas Average gradient eigenvalue Average outlier eigenvalue False alarm rate (%) 1 12 0.38 2.7 8.3 2 9 0.42 3.1 6.7 3 15 0.51 3.5 9.8

[0084] Table 1 shows an example of the initial leakage area identification results. The initial leakage area division algorithm based on gradient eigenvalue and outlier degree achieves an average false alarm rate of ≤10% in a complex tunnel environment.

[0085] Tracking each of the initial leakage regions in the enhanced infrared image frame sequence to obtain a region space sequence, and extracting spatial gradient feature values ​​of the initial leakage region;

[0086] Furthermore, the process of tracking each of the initial leakage areas in the enhanced infrared image frame sequence specifically includes: assigning a different identifier to each of the initial leakage areas in the enhanced infrared image frame sequence and extracting characterization features; calculating the first leakage area in combination with vehicle motion parameters and image acquisition parameters; The predicted position of the initial leakage area in the frame image in the subsequent frame image; in the subsequent frame image, a search window is set with the predicted position as the center, and the representation matching degree between the initial leakage area to be matched in the search window and the initial leakage area is calculated according to the representation feature, and the initial leakage area to be matched with the largest representation matching degree in the search window is marked as the tracking object of the initial leakage area, if the representation matching degree of the tracking object is greater than or equal to the matching degree threshold, the identifier of the tracking object is changed to the identifier of the initial leakage area, if the representation matching degree of the tracking object is less than the matching degree threshold, the tracking of the initial leakage area is ended; the initial leakage areas to be matched with the same identifier as the initial leakage area in the enhanced infrared image frame sequence are summarized as the regional spatial sequence of the initial leakage area.

[0087] Table 2 Initial leakage area tracking results

[0088] Vehicle speed (km / h) Tracking success rate (%) Search window size (pixels) Average matching threshold 10 98.5 40×40 0.92 20 95.2 60×60 0.88 30 89.7 80×80 0.85

[0089] Table 2 shows the initial leakage area tracking results obtained at different vehicle speeds and search window sizes. By dynamically adjusting the search window size based on vehicle motion parameters, the tracking success rate remains above 85% at a speed of 30 km / h, meeting the requirements of on-board dynamic detection.

[0090] Furthermore, for each initial leakage area, the spatial gradient characteristic value is calculated based on the regional spatial sequence, and the calculation formula is:

[0091] ;

[0092] in, Initial leakage area The spatial gradient eigenvalue of Initial leakage area The length of the regional spatial sequence; is the serial number of the regional spatial sequence; For the The weight coefficient of each serial number; and Initial leakage area In the Hedi The average temperature value in the enhanced infrared image corresponding to the serial number; Enhance the spatial distance of infrared images for two adjacent frames.

[0093] Calculating a comprehensive leakage index of the initial leakage area according to the gradient eigenvalue, the outlier eigenvalue, and the spatial gradient eigenvalue;

[0094] According to the comprehensive leakage index, the initial leakage area is processed by a region growing algorithm to obtain a leakage area;

[0095] Furthermore, the pixel point with the highest comprehensive leakage index in the initial leakage area is used as the seed point, and the region growing algorithm is applied to the initial leakage area to obtain the leakage area. The calculation formula of the comprehensive leakage index is:

[0096] ;

[0097] in, Initial leakage area Medium pixel Comprehensive leakage index; 、 and are the weight coefficients of outlier eigenvalue, gradient eigenvalue and spatial gradient eigenvalue respectively; is the outlier eigenvalue; is the gradient eigenvalue; Initial leakage area The maximum value of the gradient eigenvalue in the enhanced infrared image; Initial leakage area The spatial gradient eigenvalue of Initial leakage area The maximum value of the spatial gradient eigenvalue of all initial leakage areas in the enhanced infrared image.

[0098] Performing feature analysis on each leakage area to obtain regional multidimensional features, and evaluating the severity of the leakage area based on the regional multidimensional features;

[0099] Furthermore, the process of feature extraction and severity assessment of the leakage area includes: obtaining the regional spatial sequence of the leakage area according to the mapping relationship between each leakage area and the initial leakage area, extracting the regional multidimensional features to obtain a regional multidimensional feature sequence; the regional multidimensional features include regional morphological features, regional temperature features and regional permeability features; inputting the regional multidimensional feature sequence into the leakage severity assessment model, and outputting the leakage severity index.

[0100] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology, characterized in that: include: Acquire an infrared image frame sequence of the tunnel detection area and perform preprocessing and feature enhancement processing on each frame of the infrared image to obtain an enhanced infrared image frame sequence; The gradient eigenvalue and outlier eigenvalue of each pixel are extracted from each frame of enhanced infrared image, and the initial leakage area is identified by combining the gradient eigenvalue and outlier eigenvalue; In the enhanced infrared image frame sequence, each initial leakage area is tracked to obtain a regional spatial sequence, including: assigning an identifier to the initial leakage area and extracting characterization features; combining vehicle motion parameters and image acquisition parameters to calculate the predicted position of the initial leakage area in the subsequent frame image; identifying the initial leakage area to be matched based on the characterization features and the predicted position to obtain the tracking object of the initial leakage area; if the characterization matching degree of the tracking object is greater than or equal to the matching degree threshold, the identifier of the tracking object is changed to the identifier of the initial leakage area, otherwise the tracking of the initial leakage area is terminated; the initial leakage areas to be matched with the same identifier are summarized to obtain a regional spatial sequence of the initial leakage area; based on the regional spatial sequence, the spatial gradient feature value of the initial leakage area is extracted, and the calculation formula is: ； in, Initial leakage area The spatial gradient eigenvalue of Initial leakage area The length of the regional spatial sequence; is the serial number of the regional space sequence; For the The weight coefficient of each serial number; and Initial leakage area In the Hedi The average temperature value in the enhanced infrared image corresponding to the serial number; Enhance the spatial distance of infrared images between two adjacent frames; The comprehensive leakage index of the initial leakage area is calculated based on the gradient eigenvalue, outlier eigenvalue and spatial gradient eigenvalue; According to the comprehensive leakage index, the initial leakage area is processed by the region growing algorithm to obtain the leakage area; Feature analysis is performed on each leakage area to obtain regional multidimensional features, and the severity of the leakage area is evaluated based on the regional multidimensional features.

2. The tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology according to claim 1 is characterized in that: The process of preprocessing and feature enhancement of each frame of the infrared image specifically includes: performing Gaussian filtering denoising, geometric correction and temperature calibration on the infrared image to obtain a preprocessed infrared image; and performing feature enhancement on the preprocessed infrared image through adaptive nonlinear mapping, the formula is: ； in, and Pixels before and after enhancement The temperature value at is the average temperature of the preprocessed infrared image; is the adaptive enhancement coefficient; is the gradient sensitivity coefficient; is the pixel point in the preprocessed infrared image The gradient at .

3. The tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology according to claim 1 is characterized in that: The process of identifying the initial leakage area specifically includes: extracting the temperature gradient of each pixel point in the enhanced infrared image to obtain the gradient eigenvalue; dividing the enhanced infrared image into uniform local areas, calculating the temperature deviation of each pixel point from the temperature of the local area in which it is located, and obtaining the outlier eigenvalue; calculating the potential leakage index of each pixel point based on the gradient eigenvalue and the outlier eigenvalue; processing the pixels whose potential leakage index is greater than the potential leakage threshold through the connected component algorithm to obtain the initial leakage area set.

4. The tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology according to claim 1 is characterized in that: The process of tracking each of the initial leakage areas in the enhanced infrared image frame sequence specifically includes: assigning a different identifier to each of the initial leakage areas in the enhanced infrared image frame sequence and extracting characterization features; calculating the first leakage area in combination with vehicle motion parameters and image acquisition parameters; The predicted position of the initial leakage area in the frame image in the subsequent frame image; in the subsequent frame image, a search window is set with the predicted position as the center, and the representation matching degree between the initial leakage area to be matched in the search window and the initial leakage area is calculated according to the representation feature, and the initial leakage area to be matched with the largest representation matching degree in the search window is marked as the tracking object of the initial leakage area, if the representation matching degree of the tracking object is greater than or equal to the matching degree threshold, the identifier of the tracking object is changed to the identifier of the initial leakage area, if the representation matching degree of the tracking object is less than the matching degree threshold, the tracking of the initial leakage area is ended; the initial leakage areas to be matched with the same identifier as the initial leakage area in the enhanced infrared image frame sequence are summarized as the regional spatial sequence of the initial leakage area.

5. The tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology according to claim 1 is characterized in that: The pixel point with the highest comprehensive leakage index in the initial leakage area is used as the seed point, and the region growing algorithm is applied to the initial leakage area to obtain the leakage area. The calculation formula of the comprehensive leakage index is: ； in, Initial leakage area Medium pixel Comprehensive leakage index; 、 and are the weight coefficients of outlier eigenvalue, gradient eigenvalue and spatial gradient eigenvalue respectively; is the outlier eigenvalue; is the gradient eigenvalue; Initial leakage area The maximum value of the gradient eigenvalue in the enhanced infrared image; Initial leakage area The spatial gradient eigenvalue of Initial leakage area The maximum value of the spatial gradient eigenvalue of all initial leakage areas in the enhanced infrared image.

6. The tunnel vehicle-mounted leakage detection method based on infrared thermal imaging technology according to claim 1 is characterized in that: The process of feature extraction and severity assessment of the leakage area includes: obtaining the regional spatial sequence of the leakage area according to the mapping relationship between each leakage area and the initial leakage area, extracting the regional multidimensional features to obtain a regional multidimensional feature sequence; the regional multidimensional features include regional morphological features, regional temperature features and regional permeability features; inputting the regional multidimensional feature sequence into the leakage severity assessment model, and outputting the leakage severity index.

Images