Geological disaster detection method based on image processing

Abstract

The invention discloses a geological disaster detection method based on image processing, and relates to the technical field of disaster monitoring, and the method comprises the following steps: S1, obtaining the initial road surface image data of a to-be-detected region, and carrying out the geometric correction of the initial road surface image data, and obtaining the road surface feature image data; s2, all spots are screened and removed by using outer edge coefficients and pixel point gray values of the spots in the road surface feature image data, and the remaining spots are used as a re-detection area; and S3, processing the re-detection area to obtain a crack area of the pavement. According to the method, the crack area is accurately positioned, early-stage signs of geological disasters can be found in time, a key basis is provided for follow-up disaster early warning, assessment and prevention, and timely and effective measures can be taken to reduce loss caused by the geological disasters.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster monitoring, and particularly to a geological disaster detection method based on image processing. Background Art

[0002] Geological disasters, as natural disasters that seriously threaten the safety of human life and property and the stability of the natural environment, their monitoring and early warning have always been the research focus in the fields of geology, disaster science, and related engineering. The occurrence of geological disasters is often accompanied by a series of complex geological environment changes, among which the damage of the road surface structure is one of the common early signs. For example, before or during the occurrence of geological disasters such as earthquakes, landslides, and debris flows, the road surface may show abnormal phenomena such as cracks, settlements, and uplifts due to factors such as the movement and deformation of geological bodies. Timely and accurately detecting these road surface abnormalities is of great significance for the early warning and prevention of geological disasters.

[0003] Traditional methods for detecting geological disaster road surfaces mainly rely on manual inspections. Inspectors regularly conduct on-site inspections of areas where geological disasters may occur, and use the naked eye or simple measuring tools to find abnormalities such as cracks on the road surface. However, this method has many limitations. On the one hand, manual inspections are inefficient and it is difficult to conduct real-time and comprehensive monitoring of large areas, easily missing some early and subtle road surface changes. On the other hand, the results of manual detection are greatly affected by subjective factors, and the experience and judgment criteria of different inspectors may vary, resulting in difficulties in ensuring the accuracy and reliability of the detection results.

[0004] With the rapid development of image processing technology, its application in the field of geological disaster detection has gradually attracted attention. Image processing technology can analyze and process the acquired image data, automatically extract the feature information in the image, and thus realize the detection and recognition of the target object. In the detection of geological disaster road surfaces, image processing technology can be used to obtain the road surface image data of the area to be detected and conduct in-depth analysis of these data to discover the abnormalities existing on the road surface.

[0005] In practical applications, the acquired road surface image data often has certain geometric distortions. This is caused by various factors such as lens distortion of imaging devices (such as cameras), shooting angles, and terrain undulations. Geometric distortions will affect the accuracy of subsequent image analysis. In addition, the road surface image data usually contains a large amount of noise and irrelevant information, and these noise and irrelevant information will interfere with the subsequent detection of road surface abnormalities, reducing the accuracy and efficiency of detection. Therefore, an effective method is needed to further accurately detect the crack area of the road surface. Summary of the Invention

[0006] To solve the above problems, the present invention proposes a geological disaster detection method based on image processing.

[0007] The technical solution of the present invention is: a geological disaster detection method based on image processing includes the following steps:

[0008] S1. Obtain the initial road surface image data of the area to be detected, and perform geometric correction on the initial road surface image data to obtain road surface feature image data;

[0009] S2. Use the outer edge coefficient and pixel gray value of the spots in the road surface feature image data to screen and eliminate all spots, and use the remaining spots as the re-detection area;

[0010] S3. Process the re-detection area to obtain the crack area of the road surface.

[0011] Further, S2 includes the following sub-steps:

[0012] S21. Extract several spots from the road surface feature image data;

[0013] S22. Generate an outer edge coefficient for each spot;

[0014] S23. Use the outer edge coefficient of the spot and the gray value of the internal pixel points to screen and eliminate the spots to obtain the re-detection area.

[0015] Further, S22 includes the following sub-steps:

[0016] S221. Generate a minimum circumscribed circle for each spot, and extract four equally spaced edge points on the edge of the minimum circumscribed circle;

[0017] S222. Compose the gray values of the four edge points into a spot outer edge feature matrix;

[0018] S224. Use the maximum eigenvalue of the spot outer edge feature matrix as the outer edge coefficient of the spot.

[0019] The beneficial effect of the above further solution is: in the present invention, in S221, the four points extracted on the edge of the minimum circumscribed circle should be symmetric about the center of the circle in pairs. In S222, the expression of the spot outer edge feature matrix is: ; where represents the gray value of the first edge point, represents the gray value of the second edge point, represents the gray value of the third edge point, Denote the grayscale value of the fourth edge point. In the pavement feature image data, the presence of spots may be caused by various factors, including pavement anomalies caused by geological disasters (such as the blurred area at the edge of a crack, the spot-like features formed in the image due to local protrusions or depressions caused by geological deformation, etc.). By extracting a number of spots, it is possible to comprehensively cover the areas in the image where anomalies may exist, avoid missing potential information related to geological disasters, and lay a foundation for subsequent accurate detection. Extracting the spots in the image is equivalent to structuring the image data. The original continuous image data is decomposed into discrete spot objects, and each spot has its own characteristic information (such as position and shape, etc.). The outer edge coefficient is a quantitative index designed in the present invention to describe the shape characteristics of spots, which can express the shape characteristics of spots in numerical form, facilitating subsequent discrimination and screening using mathematical methods. At the same time, using the outer edge coefficient of the spots and the grayscale values of the internal pixel points for screening and elimination is a screening method that combines multi-dimensional features. The outer edge coefficient reflects the shape characteristics of the spots, while the grayscale values of the internal pixel points reflect the brightness information of the spots. For example, pavement cracks usually have specific grayscale change characteristics in the image, while the grayscale values of spots such as noise and stains may be different from those of cracks. By comprehensively considering these two features, it is possible to more accurately distinguish the spots related to geological disasters from other irrelevant spots and improve the accuracy of screening.

[0020] Further, S23 includes the following sub-steps:

[0021] S231. Extract the grayscale values of each pixel point on the outer edge of the spot, and construct a contour loss function for the spot using the outer edge coefficient;

[0022] S232. Judge whether the grayscale values of the internal pixel points of the spot and the contour loss function meet the set spot screening conditions. If so, retain the spot; otherwise, eliminate the spot.

[0023] The beneficial effects of the above further solution are as follows: In the present invention, extracting the grayscale values of each pixel point on the outer edge of the spot can carefully capture the brightness change information at the edge of the spot. In the pavement images related to geological disasters, the edges of abnormal areas such as cracks often have unique grayscale characteristics. For example, the edge of a crack may show a different grayscale from the surrounding pavement due to material differences or different light reflections. The contour loss function can quantify the degree of difference between the spot contour and an ideal shape (such as the abnormal shape caused by a geological disaster). For example, if the cracks caused by geological disasters usually present a relatively regular or certain trending shape in the image, then the contour loss function can measure the degree of mismatch between the actual spot contour and this ideal shape, thereby more comprehensively describing the characteristics of the spot and improving the accuracy of screening.

[0024] Further, in S231, the contour loss function of the spot has the following expression:

[0025] ;

[0026] In the formula, represents the logarithmic function, represents the exponential function, represents the outer edge coefficient of the spot, represents the average gray value of all pixel points on the outer edge of the spot.

[0027] Further, in S232, the expression of the set spot screening condition is: ; In the formula, represents the average gray value of the internal pixel points on the outer edge of the spot, represents the contour loss function of the spot, represents the set compromise factor, represents the logarithmic function, represents the exponential function.

[0028] The compromise factor is between 0 and 1.

[0029] Further, in S3, perform a dilation operation on each spot in the re-detection area, and use the several spots after the dilation operation as the crack area of the road surface.

[0030] The beneficial effects of the present invention are as follows: The present invention performs geometric correction on the acquired image data, eliminating geometric distortions caused by factors such as imaging devices, shooting angles, and terrain; uses the outer edge coefficient and pixel gray value of spots in the road surface feature image data to screen and eliminate spots. The outer edge coefficient can reflect the shape characteristics of the spots, and the gray value reflects the brightness information of the spots. By comprehensively considering these two factors, it is possible to effectively distinguish irrelevant spots such as noise on the road surface from areas that may have abnormalities, avoiding interference from this irrelevant information to subsequent detections; using the remaining spots after screening as the re-detection area to accurately locate the crack area, which helps to timely detect early signs of geological disasters, providing key basis for subsequent disaster warning, assessment, and prevention, and helping to take timely and effective measures to reduce losses caused by geological disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a flowchart of a geological disaster detection method based on image processing. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] The following further describes the embodiments of the present invention with reference to the drawings.

[0033] As Figure 1As shown in the figure, the present invention provides a geological disaster detection method based on image processing, including the following steps:

[0034] S1. Obtain the initial road surface image data of the area to be detected, and perform geometric correction on the initial road surface image data to obtain the road surface feature image data;

[0035] S2. Use the outer edge coefficient and pixel gray value of the spots in the road surface feature image data to screen and eliminate all spots, and use the remaining spots as the re-detection area;

[0036] S3. Process the re-detection area to obtain the crack area of the road surface.

[0037] In the embodiment of the present invention, S2 includes the following sub-steps:

[0038] S21. Extract several spots from the road surface feature image data;

[0039] S22. Generate an outer edge coefficient for each spot;

[0040] S23. Use the outer edge coefficient of the spot and the gray value of the internal pixel points to screen and eliminate the spots to obtain the re-detection area.

[0041] In the embodiment of the present invention, S22 includes the following sub-steps:

[0042] S221. Generate a minimum circumscribed circle for each spot, and extract four equally spaced edge points on the edge of the minimum circumscribed circle;

[0043] S222. Form a spot outer edge feature matrix with the gray values of the four edge points;

[0044] S224. Use the maximum eigenvalue of the spot outer edge feature matrix as the outer edge coefficient of the spot.

[0045] In the present invention, in S221, the four points extracted on the edge of the minimum circumscribed circle should be symmetric about the center of the circle in pairs. In S222, the expression of the spot outer edge feature matrix is: ; In the formula, represents the gray value of the first edge point, represents the gray value of the second edge point, represents the gray value of the third edge point, Denote the grayscale value of the fourth edge point. In the pavement feature image data, the presence of spots may be caused by various factors, including pavement anomalies caused by geological disasters (such as the blurred area at the edge of a crack, the spot-like features formed in the image due to local protrusions or depressions caused by geological deformation, etc.). By extracting a number of spots, it is possible to comprehensively cover the areas in the image where anomalies may exist, avoiding the omission of potential information related to geological disasters and laying a foundation for subsequent accurate detection. Extracting the spots in the image is equivalent to structuring the image data. The originally continuous image data is decomposed into discrete spot objects, and each spot has its own characteristic information (such as position and shape, etc.). The outer edge coefficient is a quantitative index designed in the present invention to describe the shape characteristics of spots, which can express the shape characteristics of spots in numerical form, facilitating subsequent discrimination and screening using mathematical methods. At the same time, using the outer edge coefficient of spots and the grayscale values of internal pixel points for screening and elimination is a screening method that combines multi-dimensional features. The outer edge coefficient reflects the shape characteristics of spots, while the grayscale values of internal pixel points reflect the brightness information of spots. For example, pavement cracks usually have specific grayscale change characteristics in the image, while the grayscale values of spots such as noise and stains may be different from those of cracks. By comprehensively considering these two characteristics, it is possible to more accurately distinguish spots related to geological disasters from other irrelevant spots and improve the accuracy of screening.

[0046] In the embodiment of the present invention, S23 includes the following sub-steps:

[0047] S231. Extract the grayscale values of each pixel point on the outer edge of the spot, and construct a contour loss function for the spot using the outer edge coefficient;

[0048] S232. Determine whether the grayscale values of the internal pixel points of the spot and the contour loss function meet the set spot screening conditions. If so, retain the spot; otherwise, eliminate the spot.

[0049] In the present invention, by extracting the grayscale values of each pixel point on the outer edge of the spot, the brightness change information at the edge of the spot is carefully captured. In pavement images related to geological disasters, the edges of abnormal areas such as cracks often have unique grayscale characteristics. For example, the edge of a crack may exhibit a different grayscale from the surrounding pavement due to material differences or different light reflections. The contour loss function can quantify the degree of difference between the spot contour and an ideal shape (such as the abnormal shape caused by a geological disaster). For example, if the cracks caused by geological disasters usually present a relatively regular or certain trending shape in the image, then the contour loss function can measure the degree of mismatch between the actual spot contour and this ideal shape, thereby more comprehensively describing the characteristics of the spot and improving the accuracy of screening.

[0050] In the embodiment of the present invention, in S231, the contour loss function of the spot The expression of

[0051] ;

[0052] In the formula, represents the logarithmic function, represents the exponential function, represents the outer edge coefficient of the spot, represents the average gray value of all pixel points on the outer edge of the spot.

[0053] In the embodiment of the present invention, in S232, the expression of the set spot screening condition is: ; In the formula, represents the average gray value of the internal pixel points on the outer edge of the spot, represents the contour loss function of the spot, represents the set compromise factor, represents the logarithmic function, represents the exponential function. The compromise factor is between 0 and 1.

[0054] In the embodiment of the present invention, in S3, perform a dilation operation on each spot in the re-detection area, and use the several spots after the dilation operation as the crack area of the road surface.

[0055] Those of ordinary skill in the art will realize that the embodiments described here are to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific deformations and combinations without departing from the essence of the present invention according to the technical revelations disclosed in the present invention, and these deformations and combinations are still within the protection scope of the present invention.

Claims

1. A geological disaster detection method based on image processing, characterized in that, It includes the following steps: S1. Obtain the initial road surface image data of the area to be detected, and perform geometric correction on the initial road surface image data to obtain the road surface feature image data; S2. Use the outer edge coefficient and pixel gray value of the spots in the road surface feature image data to screen and eliminate all spots, and regard the remaining spots as the re-detection area; S3. Process the re-detection area to obtain the crack area of the road surface.

2. The geological disaster detection method based on image processing according to claim 1, wherein The S2 includes the following sub-steps: S21. Extract several spots from the road surface feature image data; S22. Generate an outer edge coefficient for each spot; S23. Use the outer edge coefficient and the gray value of the internal pixels of the spot to screen and eliminate the spot to obtain the re-detection area.

3. The geological disaster detection method based on image processing according to claim 2, characterized in that The S22 includes the following sub-steps: S221. Generate a minimum circumscribed circle for each spot, and extract four equally spaced edge points on the edge of the minimum circumscribed circle; S222. Compose the gray values of the four edge points into a spot outer edge feature matrix; S224. Take the maximum eigenvalue of the spot outer edge feature matrix as the outer edge coefficient of the spot.

4. The geological disaster detection method based on image processing according to claim 2, wherein, The S23 includes the following sub-steps: S231. Extract the gray values of each pixel point on the outer edge of the spot, and use the outer edge coefficient to construct a contour loss function for the spot; S232. Judge whether the gray value of the internal pixel points of the spot and the contour loss function meet the set spot screening conditions. If so, retain the spot, otherwise eliminate the spot.

5. The geological disaster detection method based on image processing according to claim 4, wherein In S231, the contour loss function of the speckles has the following expression: ； In the formula, represents the logarithmic function, represents the exponential function, represents the outer edge coefficient of the spot, represents the average gray value of all pixel points on the outer edge of the spot.

6. The geological disaster detection method based on image processing according to claim 4, characterized in that In the S232, the expression of the set spot screening condition is: ; In the formula, represents the average gray value of the internal pixel points on the outer edge of the spot, represents the contour loss function of the spot, represents the set compromise factor, represents the logarithmic function, represents the exponential function.

7. The geological disaster detection method based on image processing according to claim 1, wherein, In the S3, perform a dilation operation on each spot in the re-detection area, and regard the several spots after the dilation operation as the crack area of the road surface.

Images