Landslide early warning method combined with slope radar visual perception technology

Abstract

The invention discloses a landslide early warning method combined with a side slope radar visual perception technology, and the method comprises the steps: carrying out the periodic monitoring of a target side slope, and obtaining the surface abnormal deformation data and optical images of the target side slope; identifying a local cracking area and a water seepage area in the optical image of the target slope based on a deep learning method, and quantifying feature parameters of the local cracking area and the water seepage area; performing space-time fusion on the surface abnormal deformation data of the target slope and the feature data in the optical image, and constructing a slope landslide monitoring and early warning method based on the fused surface abnormal deformation data and optical image; according to the invention, visual monitoring of the synthetic aperture radar and the video monitoring equipment is combined, so that the accuracy and reliability of slope instability monitoring are comprehensively improved. The optical image is analyzed through deep learning, risk features such as local cracking and water seepage are recognized in time, space-time fusion of deformation and visual features is achieved, the sensitivity of an early warning mechanism is remarkably improved, and the false alarm rate is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of slope landslide early warning, and in particular to a landslide early warning method combined with slope radar visual perception technology. Background Art

[0002] Slope instability monitoring and early warning methods are an important research topic in the field of safe production. The abnormal surface deformation produced before the slope becomes unstable is the most easily captured and monitored feature. Synthetic aperture slope radar (S-SAR) and image recognition technology have been widely used in landslide disaster monitoring. Synthetic aperture slope radar (S-SAR) senses the tiny deformation of the slope surface (along the monitoring line of sight) by emitting microwaves and receiving reflected signals, while image recognition technology is also used to identify cracks and water seepage problems in the slope.

[0003] However, S-SAR can only monitor deformation, and is usually unable to effectively capture other visual potential instability precursor features of the slope, such as local cracking and water seepage. The landslide monitoring and early warning model established based on a single precursor feature (deformation / deformation rate) has limited early warning capabilities, especially for hard rock slopes, which collapse or become unstable suddenly and rapidly, and usually do not show obvious deformation before becoming unstable, making it difficult to reach the set early warning threshold. Monitoring and early warning of such landslides is very difficult. Summary of the invention

[0004] The purpose of the present invention is to provide a landslide early warning method combined with slope radar visual perception technology to solve the technical problem of limited early warning capability of the landslide monitoring and early warning model established by a single precursor feature (deformation amount / deformation rate) in the prior art.

[0005] In order to solve the above technical problems, the present invention specifically provides the following technical solutions: A landslide early warning method combined with slope radar visual perception technology includes the following steps: Step 100: Periodically monitor the target slope using radar and video monitoring equipment respectively, so as to obtain abnormal surface deformation data of the target slope from radar monitoring data, and obtain an optical image of the target slope; Step 200: identifying local cracked areas and water seepage areas in the optical image of the target slope based on a deep learning method, and quantifying characteristic parameters of the local cracked areas and water seepage areas; Step 300: Temporally and spatially fuse the surface abnormal deformation data of the target slope and the characteristic parameters of the local cracking area and the water seepage area, and respectively determine the time coordinate values ​​and space coordinate values ​​of the surface abnormal deformation data and the local cracking area and the water seepage area, and construct a slope landslide monitoring and early warning method based on the surface abnormal deformation data, the time coordinate values ​​and space coordinate values ​​of the local cracking area and the water seepage area.

[0006] As a preferred solution of the present invention, in step 100, the monitoring cycles of the S-SAR radar and the video surveillance equipment are respectively and The monitoring start time points are and ; Obtain radar monitoring data in different time series and slope optical images , the surface abnormal deformation of the target slope is obtained from the radar monitoring data R.

[0007] As a preferred solution of the present invention, in step 200, when implementing the method of identifying the local cracked area and the water seepage area of ​​the slope in the optical image of the target slope based on the deep learning method, the deep learning model is first trained by using historical images with the cracked area and the water seepage area of ​​the slope until the deep learning model can identify the optical image with the cracked area and the water seepage. The specific implementation method is: Collect historical photo samples with slope cracking areas and water seepage areas, manually mark the slope cracking areas and water seepage areas in each image of the historical photo samples, and convert the historical photo samples into binary images that retain the slope cracking areas and water seepage areas; The original historical photo samples and their corresponding binary images were used as the input and output of the convolutional neural network, and a deep learning model that can be used to identify slope cracking areas and seepage areas was obtained through training and optimization. The optical image of the target slope is input into the deep learning model to obtain a binary image dataset of the target slope. , as well as the slope cracking area and water seepage area in each binary image.

[0008] As a preferred solution of the present invention, the implementation method of quantifying the characteristic parameters of the local cracking area and the water seepage area is: Traverse the binary image dataset Detect the pixel points where the slope crack area and the water seepage area appear based on the pixel values ​​in the binary image in , if they exist, it means that the deep learning model has identified the slope crack area and the water seepage area; The morphological analysis method was used to quantify the crack length and maximum crack width of the slope cracking area, and the seepage area of ​​the seepage area was quantified.

[0009] As a preferred solution of the present invention, the method of implementing the morphological analysis method for the cracked area and the seepage area of ​​the slope is as follows: Calculate the area of ​​the water seepage region in the binary image using the contour search and area calculation functions in the OpenCV software library of Python; The skeleton morphology function in Python's skimage software library is used to calculate the single-pixel wide skeleton of the slope cracking area in the binary image. The distance between the two farthest endpoints on the single-pixel wide skeleton line is the crack length. The skeleton morphology function in Python's skimage software library is used to calculate the distance between the two black pixels with the farthest distance in the normal direction of the skeleton line in the binary image, which is the maximum crack width.

[0010] As a preferred solution of the present invention, in step 300, the surface abnormal deformation data of the target slope and the characteristic parameters in the optical image are temporally fused and spatially fused, so that the surface abnormal deformation data of the target slope and the characteristic data in the optical image are mapped to a unified time axis and a three-dimensional space coordinate system. The specific implementation method is: The radar monitoring data and the optical images taken by the video surveillance equipment are mapped to the same fusion time series, and the surface abnormal deformation of the radar monitoring data corresponding to the video surveillance equipment patrol time is calculated by linear interpolation method; A three-dimensional coordinate system is constructed using radar monitoring data, the radar monitoring data in the same slope area is three-dimensionally integrated with the slope crack area and the water seepage area in the optical image, the three-dimensional coordinate values ​​of the slope crack area and the water seepage area in the three-dimensional coordinate system are calculated using a collinear equation, and the three-dimensional coordinate value of each pixel point in the optical image is determined; Determine the abnormal surface deformation in the radar monitoring data and the three-dimensional coordinate values ​​corresponding to the slope cracking area and the water seepage area of ​​the optical image, and spatially fuse the abnormal surface deformation in the radar monitoring data with the slope cracking area and the water seepage area of ​​the optical image having the same three-dimensional coordinate value.

[0011] As a preferred solution of the present invention, when the surface abnormal deformation data of the target slope and the characteristic parameters in the optical image are time-fused, the patrol cycle of the video monitoring device is set to , the radar monitoring cycle is , let the time of the nth patrol of the video surveillance device be t, then: ; where t0 ’ The time when the video surveillance equipment starts patrolling; The monitoring cycles of S-SAR radar and video surveillance equipment are and The monitoring start points are and ; make ; Where t0 is the time point when the S-SAR radar starts monitoring; have ; Then the radar monitoring data at time t is: .

[0012] As a preferred solution of the present invention, the cracked area and the seepage area of ​​the slope in the optical image are a two-dimensional plane coordinate system, and a mapping relationship between the two-dimensional plane coordinate system and the three-dimensional coordinate system is established using a collinear equation, and the collinear equation is established and solved to determine the three-dimensional coordinate values ​​of the cracked area and the seepage area of ​​the slope in the three-dimensional coordinate system; ; ; Where: , is the image plane coordinate value of each pixel in the optical image; , , is the internal orientation element of the optical image; , , are the three exterior orientation line elements of the optical image; , , is the three-dimensional coordinate value of each pixel point of the optical image in the three-dimensional coordinate system; The nine direction cosines are composed of the three exterior azimuth elements of the image.

[0013] As a preferred solution of the present invention, when the time point corresponding to the appearance of abnormal surface deformation in the radar monitoring data matches the time point at which the slope cracking area and the water seepage area appear in the optical image in the fused time series, and when the three-dimensional coordinate value corresponding to the abnormal surface deformation in the radar monitoring data is the same as the three-dimensional coordinate value corresponding to the slope cracking area and the water seepage area in the optical image, a comprehensive risk index of the three-dimensional coordinate point is set based on the standardized data of the abnormal surface deformation, the slope cracking area and the water seepage area, and a warning value of the three-dimensional coordinate point on the target slope is determined based on the comprehensive risk index; When the time point corresponding to the appearance of abnormal surface deformation in the radar monitoring data does not match the time point at which the slope crack area and the water seepage area appear in the optical image in the fused time series, or when the three-dimensional coordinate value corresponding to the abnormal surface deformation in the radar monitoring data is different from the three-dimensional coordinate value corresponding to the slope crack area and the water seepage area appearing in the optical image, the abnormal surface deformation is used as a single parameter, and the slope crack area and the water seepage area are used as single parameters to independently determine the warning value of the monitoring point where the abnormality occurs.

[0014] As a preferred solution of the present invention, the implementation method of setting the comprehensive risk index of the three-dimensional coordinate point based on the standardized data of the abnormal surface deformation, the slope cracking area and the water seepage area is: Standardize the surface abnormal deformation in the radar monitoring data of the three-dimensional coordinate point, and the quantitative characteristic data of the slope crack area and the water seepage area in the optical image; Assign weights to the abnormal surface deformation, slope cracking area and water seepage area of ​​the three-dimensional coordinate point, multiply the standardized characteristic data by its corresponding weight to obtain weighted characteristic values, and calculate the comprehensive risk index of the three-dimensional coordinate point by adding the weighted characteristic values. Set the threshold of the comprehensive risk index and divide the comprehensive risk index into different monitoring risk levels; Comprehensive risk index ; Among them, R is the comprehensive risk index, D is the standardized surface abnormal deformation, C is the standardized crack length, W is the standardized maximum crack width, S is the standardized seepage area, w1, w2, w3 and w4 are the distribution weights corresponding to the surface abnormal deformation, crack length, maximum crack width and seepage area, respectively.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention combines two slope monitoring methods of synthetic aperture radar and visual monitoring of video monitoring equipment. Through deep learning analysis of optical images, risk features such as local cracking and water seepage are timely identified. The abnormal surface deformation identified by radar monitoring is spatially and temporally fused with the local cracking and water seepage of visual features to determine whether local cracking, water seepage and abnormal surface deformation problems occur simultaneously at the same monitoring point at a certain monitoring time point. Feature fusion is performed on the same monitoring point where local cracking, water seepage and abnormal surface deformation problems occur simultaneously, and the monitoring risk level is set. This can significantly improve the sensitivity of the early warning mechanism and reduce the false alarm rate. This multi-feature fusion method is not only suitable for hard rock slopes, but can also be widely used in other types of slope monitoring, providing effective protection for safe production. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0017] Figure 1 A flow chart of a landslide early warning method according to an embodiment of the present invention; Figure 2 This is an effect diagram of manually annotated cracking areas in the landslide early warning method according to an embodiment of the present invention; Figure 3 It is an effect diagram of manually annotated water seepage area in the landslide early warning method according to an embodiment of the present invention; Figure 4 A flow chart for constructing a convolutional neural network in a landslide early warning method according to an embodiment of the present invention; Figure 5 A schematic diagram of the quantification of cracking areas in the landslide early warning method according to an embodiment of the present invention; Figure 6 It is a quantitative schematic diagram of the seepage area in the landslide early warning method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0019] like Figure 1 As shown, the present invention provides a landslide early warning method combined with slope radar visual perception technology, which combines the slope radar monitoring results with the visual perception parameters formed by optical image recognition technology, so that the slope radar can capture the precursor characteristics of slope instability more comprehensively and accurately, and establish a slope instability monitoring and early warning method considering multi-feature fusion, including the following steps: Step 100: Use radar and video monitoring equipment to periodically monitor the target slope, respectively, to obtain abnormal surface deformation data of the target slope from radar monitoring data, and obtain an optical image of the target slope.

[0020] In step 100, the target slope is periodically monitored using S-SAR radar and video monitoring equipment, wherein the monitoring periods of the S-SAR radar and video monitoring equipment are respectively and The monitoring start points are and ; Obtain radar monitoring data in different time series and slope optical images , the surface abnormal deformation of the target slope is obtained from the radar monitoring data R.

[0021] Step 200: Identify local cracked areas and water seepage areas in the optical image of the target slope based on a deep learning method, and quantify characteristic parameters of the local cracked areas and water seepage areas.

[0022] In step 200, when implementing the method of identifying the local cracked area and the water seepage area of ​​the slope in the optical image of the target slope based on the deep learning method, the deep learning model is first trained by using historical images with slope cracks and water seepage until the deep learning model can identify the optical image with slope cracks and water seepage. The specific implementation method is: (1) Collect historical photo samples with slope cracks and seepage areas, and manually mark the slope cracks and seepage areas in each image of the historical photo samples. Convert the historical photo samples into binary images that retain the slope cracks and seepage areas, wherein a binary image (black and white image) of the photo samples is generated, with the cracks and seepage areas as the foreground (black) and other areas as the background (white). That is, convert the historical photo samples into binary images that retain the slope cracks and seepage areas, set the pixel values ​​of the slope cracks and seepage areas to 0, and set the pixel values ​​of the non-slope cracks and seepage areas to 255.

[0023] like Figure 2 As shown, Figure 2 (a) is a local cracking image of the rock mass in a historical photo sample. Figure 2 (b) is a binary image of the local cracking map of the rock mass, with the cracked area of ​​the slope manually marked.

[0024] like Figure 3 As shown, Figure 3 (a) is a local seepage map of the rock mass in the historical photo sample. Figure 3 (b) is a binary image of the local seepage map of the rock mass, with the seepage area manually marked.

[0025] (2) The original historical photo samples and their corresponding binary images are used as the input and output of the convolutional neural network. Through training and tuning, a deep learning model that can be used to identify slope cracking areas and seepage areas is obtained.

[0026] (3) Input the optical image of the target slope into the deep learning model to obtain a binary image dataset of the target slope. , as well as the slope cracking area and water seepage area in each binary image, the training process of the deep learning model, and the binarization process of the optical image of the target slope are shown in Figure 3 shown.

[0027] The implementation method for quantifying the characteristic parameters of local cracking areas and water seepage areas is as follows: Traversing the binary image dataset The pixel values ​​in the binary image in are used to detect whether there are any pixels with a pixel value of 0. If so, it means that the deep learning model has identified the cracked area and the seepage area of ​​the slope.

[0028] The morphological analysis method was used to quantify the crack length and maximum crack width of the slope cracking area, and the seepage area of ​​the seepage area was quantified.

[0029] The implementation method of using morphological analysis method for slope cracking area and seepage area is as follows: Use the contour search and area calculation functions in Python's OpenCV software library to calculate the area of ​​the water seepage area in the binary image, such as Figure 6 As shown; The skeleton morphology function in Python's skimage software library is used to calculate the single-pixel wide skeleton of the slope cracking area in the binary image. The distance between the two farthest endpoints on the single-pixel wide skeleton line is the crack length. The skeleton morphology function in Python's skimage software library is used to calculate the distance between the two black pixels with the farthest distance in the normal direction of the skeleton line in the binary image, which is the maximum crack width, such as Figure 5 shown.

[0030] Step 300: Temporally and spatially fuse the surface abnormal deformation data of the target slope and the characteristic parameters of the local cracking area and the water seepage area, and respectively determine the time coordinate values ​​and space coordinate values ​​of the surface abnormal deformation data and the local cracking area and the water seepage area, and construct a slope landslide monitoring and early warning method based on the surface abnormal deformation data, the time coordinate values ​​and space coordinate values ​​of the local cracking area and the water seepage area.

[0031] In step 300, the surface abnormal deformation data of the target slope and the characteristic parameters in the optical image are temporally fused and spatially fused, so that the surface abnormal deformation data of the target slope and the characteristic data in the optical image are mapped to a unified time axis and a three-dimensional space coordinate system. The specific implementation method is as follows: Time fusion: The radar monitoring data and the optical images taken by the video surveillance equipment are mapped to the same fusion time series, and the linear interpolation method is used to calculate the surface abnormal deformation of the radar monitoring data corresponding to the video surveillance equipment patrol time.

[0032] When the abnormal surface deformation data of the target slope and the characteristic parameters in the optical image are temporally fused, the patrol cycle of the video monitoring equipment is set to , the radar monitoring cycle is , let the time of the nth patrol of the video surveillance device be t, then: ; where t0 ’The time when the video surveillance equipment starts patrolling; The monitoring cycles of S-SAR radar and video surveillance equipment are and The monitoring start points are and ; make ; Where t0 is the time point when the S-SAR radar starts monitoring; have ; Then the radar monitoring data at time t is: .

[0033] In this embodiment, each time the S-SAR radar scans the target slope once, the video monitoring device collects an image of the target slope once, and a virtual fusion time series is constructed. As a reference value, establish a patrol cycle for video surveillance equipment , radar monitoring cycle The matching relationship between them is obtained, and based on the matching relationship, the optical image captured by the video surveillance device at time t and the radar monitoring data corresponding to time t' matching the time t are determined. By integrating the optical image corresponding to each shooting time point and the radar monitoring data formed by the radar scanning time point matching the shooting time point into the same fused time series, the slope areas with abnormal surface deformation, cracks and water seepage at the same time can be marked.

[0034] Spatial fusion: Construct a three-dimensional coordinate system using radar monitoring data, and perform three-dimensional fusion of the radar monitoring data in the same slope area with the slope cracking area and water seepage area in the optical image. Use the collinear equation to calculate the three-dimensional coordinate values ​​of the slope cracking area and water seepage area in the three-dimensional coordinate system, and determine the three-dimensional coordinate value of each pixel point in the optical image.

[0035] The abnormal surface deformation in the radar monitoring data and the three-dimensional coordinate values ​​corresponding to the slope cracking area and the water seepage area in the optical image are determined, and the abnormal surface deformation in the radar monitoring data with the same three-dimensional coordinate values ​​are spatially fused with the slope cracking area and the water seepage area in the optical image.

[0036] The cracked area and water seepage area of ​​the slope in the optical image are two-dimensional plane coordinate systems. The mapping relationship between the two-dimensional plane coordinate system and the three-dimensional coordinate system is established using the collinear equation. The collinear equation is established and solved to determine the three-dimensional coordinate values ​​of the cracked area and water seepage area of ​​the slope in the three-dimensional coordinate system. ; ; Where: , is the image plane coordinate value of each pixel in the optical image; , , is the internal orientation element of the optical image; , , are the three exterior orientation line elements of the optical image; , , is the three-dimensional coordinate value of each pixel in the optical image; The nine direction cosines are composed of the three exterior azimuth elements of the image.

[0037] In order to understand this equation, we need to introduce the three internal orientation elements of the image. f is the focal length of the camera. During the production process of the camera, the center of its optical axis cannot be completely opposite to the center of the photo (that is, the center of the sensor). There will be a slight deviation. This deviation is represented by x0 and y0, which is generally sub-millimeter. x0, y0 and f can be easily obtained through the camera calibration program, which means that these three parameters are also known values ​​in the collinearity equation. Observing the equation, we can find that in order to solve X, Y, Z, we also need to know the three external orientation line elements , , and the three exterior azimuth elements The line element represents the position of the camera relative to the earth coordinate system, and the angle element represents the spatial posture of the camera. When drones on the market take photos, the photos will have POS information, which automatically stores the exterior orientation line element and angle element values. Therefore, the three exterior orientation line elements , , and the three exterior azimuth elements Is a known number.

[0038] The purpose of spatial fusion is to test whether the abnormal surface deformation of radar monitoring data and the slope cracking and water seepage characteristics identified in the optical image can correspond to the same area. According to the model of video surveillance equipment and the position sensor information of the video surveillance equipment, the internal and external orientation elements of each photo can be determined. By taking at least two photos taken at different angles of the same slope cracking area and water seepage area, the collinear equation can be established and solved to determine the position of the slope cracking area and water seepage area in three-dimensional space.

[0039] When the time point corresponding to the appearance of abnormal surface deformation in the radar monitoring data matches the time point at which the slope cracking area and the water seepage area appear in the optical image in the fused time series, and when the three-dimensional coordinate value corresponding to the abnormal surface deformation in the radar monitoring data is the same as the three-dimensional coordinate value corresponding to the slope cracking area and the water seepage area in the optical image, a comprehensive risk index of the three-dimensional coordinate point is set based on the standardized data of the abnormal surface deformation, the slope cracking area and the water seepage area, and the warning value of the three-dimensional coordinate point on the target slope is determined based on the comprehensive risk index.

[0040] When the time point corresponding to the appearance of abnormal surface deformation in the radar monitoring data does not match the time point when the slope cracking area and the water seepage area appear in the optical image in the fused time series, or when the three-dimensional coordinate value corresponding to the abnormal surface deformation in the radar monitoring data is different from the three-dimensional coordinate value corresponding to the slope cracking area and the water seepage area in the optical image, the abnormal surface deformation is taken as a single parameter, and the slope cracking area and the water seepage area are taken as single parameters to independently determine the warning value of the monitoring point where the abnormality occurs.

[0041] The implementation method of setting the comprehensive risk index of the three-dimensional coordinate point based on the standardized data of surface abnormal deformation, slope cracking area and seepage area is as follows: The abnormal surface deformation in the radar monitoring data of the three-dimensional coordinate point, and the quantitative characteristic data of the slope crack area and the water seepage area in the optical image are standardized. In this embodiment, the quantitative characteristic data of the abnormal surface deformation, the slope crack area and the water seepage area are subjected to Z-score standardization to form quantity-free tempered data.

[0042] Assign weights to the abnormal surface deformation, slope cracking area and water seepage area of ​​the three-dimensional coordinate point, multiply the standardized characteristic data by its corresponding weight to obtain weighted characteristic values, and calculate the comprehensive risk index of the three-dimensional coordinate point by adding the weighted characteristic values. Set the threshold of the comprehensive risk index and divide the comprehensive risk index into different monitoring risk levels; Comprehensive risk index ; Among them, R is the comprehensive risk index, D is the standardized surface abnormal deformation, C is the standardized crack length, W is the standardized maximum crack width, S is the standardized seepage area, w1, w2, w3 and w4 are the distribution weights corresponding to the surface abnormal deformation, crack length, maximum crack width and seepage area, respectively.

[0043] In actual monitoring, when abnormal surface deformation, cracking and water seepage appear at the same monitoring point at the same time, it means that the danger level of the monitoring point is relatively high. The existing method of separately warning multiple monitoring results has the following defects: when the abnormal surface deformation, cracking and water seepage appearing at the same monitoring point at the same time do not reach the warning value, no warning warning will be issued. In addition, the radar principle only monitors the displacement of the slope by emitting electromagnetic waves. In addition to the displacement data, it cannot obtain any other precursor features of the slope instability. If there is a relatively dangerous situation, that is, the slope has cracked / seeped, but the radar has not or cannot provide an early warning.

[0044] The processing method of this embodiment can give the slope radar visual perception ability. When abnormal surface deformation, cracking and water seepage appear at the same monitoring point at the same time, the comprehensive risk index is reconstructed for graded warning. Even if the abnormal surface deformation, cracking and water seepage do not reach the warning value respectively, the comprehensive risk index formed by their fusion will alarm according to the specific value. By calculating the comprehensive risk index in real time, it is ensured that potential risks can be discovered in time, and the weights and thresholds are adjusted regularly according to new monitoring data and actual events to improve the accuracy of the warning.

[0045] This implementation combines two slope monitoring methods, synthetic aperture radar and visual monitoring by video surveillance equipment. Through deep learning analysis of optical images, risk features such as local cracking and water seepage are timely identified. The abnormal surface deformation identified by radar monitoring is spatially and temporally fused with the local cracking and water seepage of visual features to determine whether local cracking, water seepage and abnormal surface deformation problems occur simultaneously at the same monitoring point at a certain monitoring time point. Feature fusion is performed on the same monitoring point where local cracking, water seepage and abnormal surface deformation problems occur simultaneously, and the monitoring risk level is set. This can significantly improve the sensitivity of the early warning mechanism and reduce the false alarm rate. This multi-feature fusion method is not only applicable to hard rock slopes, but can also be widely used in other types of slope monitoring, providing effective protection for safe production.

[0046] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A landslide early warning method combined with slope radar visual perception technology, characterized in that: The following steps are involved: Step 100: Periodically monitor the target slope using radar and video monitoring equipment respectively, so as to obtain abnormal surface deformation data of the target slope from radar monitoring data, and obtain an optical image of the target slope; Step 200: identifying local cracked areas and water seepage areas in the optical image of the target slope based on a deep learning method, and quantifying characteristic parameters of the local cracked areas and water seepage areas; Step 300: Temporally and spatially fuse the surface abnormal deformation data of the target slope and the characteristic parameters of the local cracking area and the water seepage area, and respectively determine the time coordinate values ​​and space coordinate values ​​of the surface abnormal deformation data and the local cracking area and the water seepage area, and construct a slope landslide monitoring and early warning method based on the surface abnormal deformation data, the time coordinate values ​​and space coordinate values ​​of the local cracking area and the water seepage area.

2. The landslide early warning method combined with slope radar visual perception technology according to claim 1 is characterized in that: In step 100, the monitoring cycles of the S-SAR radar and the video surveillance equipment are respectively and The monitoring start time points are and ; Obtain radar monitoring data in different time series and slope optical images , the surface abnormal deformation of the target slope is obtained from the radar monitoring data R.

3. The landslide early warning method combined with slope radar visual perception technology according to claim 1 is characterized in that: In step 200, when implementing the method of identifying the local cracked area and the water seepage area of ​​the slope in the optical image of the target slope based on the deep learning method, the deep learning model is first trained by using historical images with the cracked area and the water seepage area of ​​the slope until the deep learning model can identify the optical image with the cracked area and the water seepage of the slope. The specific implementation method is: Collect historical photo samples with slope cracking areas and water seepage areas, manually mark the slope cracking areas and water seepage areas in each image of the historical photo samples, and convert the historical photo samples into binary images that retain the slope cracking areas and water seepage areas; The original historical photo samples and their corresponding binary images were used as the input and output of the convolutional neural network, and a deep learning model that can be used to identify slope cracking areas and seepage areas was obtained through training and optimization. The optical image of the target slope is input into the deep learning model to obtain a binary image dataset of the target slope. , as well as the slope cracking area and water seepage area in each binary image.

4. The landslide early warning method combined with slope radar visual perception technology according to claim 3 is characterized in that: The implementation method of quantifying the characteristic parameters of the local cracking area and the water seepage area is: Traverse the binary image dataset Detect the pixel points where the slope crack area and the water seepage area appear based on the pixel values ​​in the binary image in , if they exist, it means that the deep learning model has identified the slope crack area and the water seepage area; The morphological analysis method was used to quantify the crack length and maximum crack width of the slope cracking area, and the seepage area of ​​the seepage area was quantified.

5. The landslide early warning method combined with slope radar visual perception technology according to claim 4 is characterized in that: The implementation method of using morphological analysis method for slope cracking area and seepage area is as follows: Calculate the area of ​​the water seepage region in the binary image using the contour search and area calculation functions in the OpenCV software library of Python; The skeleton morphology function in Python's skimage software library is used to calculate the single-pixel wide skeleton of the slope cracking area in the binary image. The distance between the two farthest endpoints on the single-pixel wide skeleton line is the crack length. The skeleton morphology function in Python's skimage software library is used to calculate the distance between the two black pixels with the farthest distance in the normal direction of the skeleton line in the binary image, which is the maximum crack width.

6. The landslide early warning method combined with slope radar visual perception technology according to claim 2 is characterized in that: In step 300, the abnormal surface deformation data of the target slope and the characteristic parameters in the optical image are temporally fused and spatially fused, so that the abnormal surface deformation data of the target slope and the characteristic data in the optical image are mapped to a unified time axis and a three-dimensional space coordinate system. The specific implementation method is: The radar monitoring data and the optical images taken by the video surveillance equipment are mapped to the same fusion time series, and the surface abnormal deformation of the radar monitoring data corresponding to the video surveillance equipment patrol time is calculated by linear interpolation method; A three-dimensional coordinate system is constructed using radar monitoring data, the radar monitoring data in the same slope area is three-dimensionally integrated with the slope crack area and the water seepage area in the optical image, the three-dimensional coordinate values ​​of the slope crack area and the water seepage area in the three-dimensional coordinate system are calculated using a collinear equation, and the three-dimensional coordinate value of each pixel point in the optical image is determined; Determine the abnormal surface deformation in the radar monitoring data and the three-dimensional coordinate values ​​corresponding to the slope cracking area and the water seepage area of ​​the optical image, and spatially fuse the abnormal surface deformation in the radar monitoring data with the slope cracking area and the water seepage area of ​​the optical image having the same three-dimensional coordinate value.

7. The landslide early warning method combined with slope radar visual perception technology according to claim 6 is characterized in that: When the surface abnormal deformation data of the target slope and the characteristic parameters in the optical image are time-fused, the patrol cycle of the video monitoring device is set to , the radar monitoring cycle is , let the time of the nth patrol of the video surveillance device be t, then: ;in The time when the video surveillance equipment starts patrolling; The monitoring cycles of S-SAR radar and video surveillance equipment are and The monitoring start points are and ; make ; Where t0 is the time point when the S-SAR radar starts monitoring; have ; Then the radar monitoring data at time t is: .

8. The landslide early warning method combined with slope radar visual perception technology according to claim 6 is characterized in that: The cracked area and water seepage area of ​​the slope in the optical image are two-dimensional plane coordinate systems. The mapping relationship between the two-dimensional plane coordinate system and the three-dimensional coordinate system is established using the collinear equation. The collinear equation is established and solved to determine the three-dimensional coordinate values ​​of the cracked area and water seepage area of ​​the slope in the three-dimensional coordinate system. ； ； Where: , is the image plane coordinate value of each pixel in the optical image; , , is the internal orientation element of the optical image; , , are the three exterior orientation line elements of the optical image; , , is the three-dimensional coordinate value of each pixel point of the optical image in the three-dimensional coordinate system; The nine direction cosines are composed of the three exterior azimuth elements of the image.

9. The landslide early warning method combined with slope radar visual perception technology according to claim 6 is characterized in that: When the time point corresponding to the appearance of abnormal surface deformation in the radar monitoring data matches the time point at which the slope cracking area and the water seepage area appear in the optical image in the fused time series, and the three-dimensional coordinate value corresponding to the abnormal surface deformation in the radar monitoring data is the same as the three-dimensional coordinate value corresponding to the slope cracking area and the water seepage area in the optical image, a comprehensive risk index of the three-dimensional coordinate point is set based on the standardized data of the abnormal surface deformation, the slope cracking area and the water seepage area, and a warning value of the three-dimensional coordinate point on the target slope is determined based on the comprehensive risk index; When the time point corresponding to the appearance of abnormal surface deformation in the radar monitoring data does not match the time point at which the slope crack area and the water seepage area appear in the optical image in the fused time series, or when the three-dimensional coordinate value corresponding to the abnormal surface deformation in the radar monitoring data is different from the three-dimensional coordinate value corresponding to the slope crack area and the water seepage area appearing in the optical image, the abnormal surface deformation is used as a single parameter, and the slope crack area and the water seepage area are used as single parameters to independently determine the warning value of the monitoring point where the abnormality occurs.

10. The landslide early warning method combined with slope radar visual perception technology according to claim 9 is characterized in that: The implementation method of setting the comprehensive risk index of the three-dimensional coordinate point based on the standardized data of surface abnormal deformation, slope cracking area and seepage area is as follows: Standardize the surface abnormal deformation in the radar monitoring data of the three-dimensional coordinate point, and the quantitative characteristic data of the slope crack area and the water seepage area in the optical image; Assign weights to the abnormal surface deformation, slope cracking area and water seepage area of ​​the three-dimensional coordinate point, multiply the standardized characteristic data by its corresponding weight to obtain weighted characteristic values, and calculate the comprehensive risk index of the three-dimensional coordinate point by adding the weighted characteristic values. Set the threshold of the comprehensive risk index and divide the comprehensive risk index into different monitoring risk levels; Comprehensive risk index ; Among them, R is the comprehensive risk index, D is the standardized surface abnormal deformation, C is the standardized crack length, W is the standardized maximum crack width, S is the standardized seepage area, w1, w2, w3 and w4 are the distribution weights corresponding to the surface abnormal deformation, crack length, maximum crack width and seepage area, respectively.

Images