A mountainous power transmission and transformation project slope sliding slag detection method based on tower base three-dimensional area change

Abstract

The application discloses a mountainous power transmission and transformation project slope-sliding slag detection method based on tower base three-dimensional area change, obtains satellite images of a target region at an initial stage and a current stage of tower base construction and target region digital elevation model data, and then carries out pretreatment; a tower base region is segmented from the satellite image at the current stage, and a current three-dimensional area is calculated according to the digital elevation model data; an area change rate is calculated according to a reference three-dimensional area and the current three-dimensional area; if the area change rate is not less than a preset threshold value, the satellite images at the initial stage and the current stage are compared to obtain a new area, and the diffusion direction and slope direction consistency of the new area and the slag soil spectrum characteristics are verified; if all the verifications are passed, the slope-sliding slag event is determined, and a corresponding risk level is output. The application reduces the measurement error of steep slope terrain, improves the accuracy of tower base region slope-sliding slag judgment, and provides stable and reliable technical support for water and environmental protection monitoring in the field of mountainous power transmission and transformation.

Description

Technical Field

[0001] This invention relates to environmental monitoring technology for power engineering, specifically to a method for detecting slag discharge along slopes in mountainous power transmission and transformation projects based on the three-dimensional area change of the tower base. Background Technology

[0002] In power transmission and transformation engineering construction, tower foundation construction often involves complex terrains such as mountainous and hilly areas, requiring foundation treatment through methods such as excavation and blasting, which easily generates a large amount of waste. This can lead to slope slippage (i.e., waste soil sliding down the slope), causing soil erosion, tower foundation instability, and even inducing secondary geological disasters (such as landslides and debris flows), threatening power grid safety and affecting ecological acceptance. Traditional manual inspection is inefficient and relies on experience; UAV imagery and satellite remote sensing imagery both use single image recognition, failing to consider the impact of factors such as terrain elevation differences, resulting in low recognition accuracy and high recognition difficulty.

[0003] Patent application CN113280764A discloses a method and system for quantitative monitoring of disturbance range in power transmission and transformation projects based on multi-satellite collaborative technology, including the following steps: S1: Acquire satellite remote sensing image img1 before construction of the power transmission and transformation line project and satellite remote sensing image img2 during construction, and preprocess the two satellite remote sensing images to obtain satellite remote sensing images img1-pre and img2-pre after error correction; S2: Crop img2-pre and img2-pre with a buffer zone at a set distance outside the power transmission and transformation line as the search range to obtain satellite remote sensing images at a set distance outside the power transmission and transformation line; S3: Overlay the coordinates of the power transmission and transformation line tower points with the satellite remote sensing images at the set distance outside the power transmission and transformation line to find tower point #a in the satellite remote sensing images; S4: For tower point #a, identify the disturbance range of tower base and road construction using spectral features; S5: Calculate the area of ​​the disturbance range of tower base construction; S6: Calculate the area of ​​the disturbance range of road construction. Therefore, the above technical solution has the following problems: satellite imagery only provides two-dimensional planar data and does not consider three-dimensional terrain factors, resulting in large errors in the calculation results if there are significant terrain differences in the disturbed area. Secondly, the lack of verification of the determination results of the disturbed area leads to problems such as low accuracy and difficulty in judgment. Summary of the Invention

[0004] The technical problem to be solved by this invention is to provide a method for detecting slag chutes on slopes in mountainous power transmission and transformation projects based on the three-dimensional area change of the tower base, which takes the three-dimensional area change of the tower base as the core criterion and combines it with terrain slope analysis to achieve efficient identification of slag chutes on slopes.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0006] A method for detecting slag chutes on slopes in mountainous power transmission and transformation projects based on the three-dimensional area variation of the tower base includes the following steps:

[0007] Acquire satellite images of the initial and current stages of tower foundation construction in the target area, and acquire digital elevation model data of the target area. Preprocess the satellite images and digital elevation model data.

[0008] The tower base region is segmented from current satellite imagery, and the current three-dimensional area of ​​the tower base region is calculated based on digital elevation model data;

[0009] Calculate the area change rate based on the baseline three-dimensional area and the current three-dimensional area of ​​the tower base region;

[0010] If the area change rate is greater than or equal to a preset threshold, the initial satellite imagery is compared with the current satellite imagery to obtain the newly added area. The consistency between the diffusion direction and slope aspect of the newly added area is verified, and the spectral characteristics of the slag in the newly added area are verified.

[0011] If the diffusion direction and slope aspect of the newly added area are consistent with the spectral characteristics of the slag soil, it is determined to be a downslope slag dumping event and the corresponding risk level is output.

[0012] Furthermore, when segmenting the tower base area from current satellite imagery, the following steps are included:

[0013] The current satellite imagery is input into the deep learning model to obtain a probability map. The probability of each pixel in the probability map is compared with a preset probability threshold. If it is less than the preset probability threshold, the value of the pixel is updated to 0. If it is greater than the preset probability threshold, the value of the pixel is updated to 1, thereby converting the probability map into a binary mask image.

[0014] Morphological operations are performed on the binarized mask image to obtain an optimized binarized mask image. Boundaries are extracted from the optimized binarized mask image and vector polygons are constructed. The vector polygons correspond one-to-one with the base region of the tower.

[0015] Furthermore, when calculating the current three-dimensional area of ​​the tower base region based on digital elevation model data, the following steps are included:

[0016] Obtain the planar coordinates of all boundary points of the vector polygon corresponding to the current tower base region;

[0017] The elevation value of the boundary point is calculated as the height coordinate based on the vertex coordinates of the grid into which the boundary point falls in the digital elevation model data.

[0018] Calculate the average of the planar coordinates and the average of the height coordinates of all boundary points of the vector polygon to obtain the three-dimensional coordinates of the centroid point O of the vector polygon;

[0019] Using centroid O as a common vertex, connect adjacent boundary points on the vector polygon boundary to centroid O in sequence to form corresponding triangles. Calculate the three-dimensional area of ​​each triangle and sum the three-dimensional areas of all triangles to obtain the current three-dimensional area of ​​the current tower base region.

[0020] Furthermore, the formula for calculating the elevation value of the boundary point is as follows:

[0021]

[0022] in, This indicates the lower left vertex of the grid into which the boundary point falls. The elevation value, and the lower left vertex The plane coordinates are , ), This represents the top-left vertex of the grid into which the boundary point falls. The elevation value, and the top left vertex The plane coordinates are , ), This indicates the bottom right vertex of the grid into which the boundary point falls. The elevation value, and the lower right vertex The plane coordinates are , ), This represents the top right vertex of the grid into which the boundary point falls. The elevation value, and the upper right vertex The plane coordinates are , ).

[0023] Furthermore, when calculating the area of ​​each triangle separately, the following steps are included:

[0024] Obtain the 3D coordinates of vertices O, A, and B of the current triangle △OAB, and calculate the vector based on the 3D coordinates of vertices O, A, and B. and Then calculate the vector and cross product , where A and B are adjacent boundary points on the boundary of the vector polygon;

[0025] Calculate the cross product Length of the module , mold length Multiply This gives us the three-dimensional area of ​​the current triangle △OAB.

[0026] Furthermore, the reference three-dimensional area of ​​the tower base region is specifically the product of the designed area of ​​the tower base region and the terrain correction coefficient corresponding to the target region.

[0027] Furthermore, verifying the consistency between the diffusion direction and slope aspect of the newly added area specifically includes the following steps:

[0028] Extract the minimum bounding rectangle of the newly added region, and calculate the major axis direction angle α of the minimum bounding rectangle;

[0029] Obtain digital elevation model data for the newly added area, and calculate the dominant slope aspect β of the newly added area based on the digital elevation model data;

[0030] Calculate the angle γ between the major axis direction angle α and the dominant slope aspect β. If the value of the angle γ is less than the angle threshold, the consistency between the diffusion direction and the slope aspect of the newly added area is verified.

[0031] Furthermore, when verifying the spectral characteristics of the newly added area's slag, specifically, if optical imagery is available, spectral verification is performed on the newly added area; if optical imagery is unavailable, SAR image coherence change detection is used as an alternative to spectral verification. After obtaining the spectral verification results or the SAR image coherence change detection results, if the near-infrared band reflectance... 0.3 and Normalized Difference Vegetation Index (NDVI) If the value is 0.2, the spectral characteristics of the slag in the newly added area are verified.

[0032] Furthermore, after calculating the area change rate based on the designed area and the current three-dimensional area of ​​the tower base region, the process also includes:

[0033] If the area change rate is less than the preset threshold but greater than the first threshold, the initial satellite imagery is compared with the current satellite imagery to obtain the newly added area, and the spectral characteristics of the slag in the newly added area are verified.

[0034] If the spectral characteristics of the construction waste in the newly added area pass the verification, the corresponding risk level will be output.

[0035] The present invention also proposes a slope sludge chute detection system for mountain power transmission and transformation projects based on the three-dimensional area change of the tower base, comprising a processor and a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the slope sludge chute detection method for mountain power transmission and transformation projects based on the three-dimensional area change of the tower base.

[0036] Compared with the prior art, the advantages of the present invention are as follows:

[0037] This invention combines satellite imagery and digital elevation model data and uses a triangulation algorithm to calculate the three-dimensional area of ​​the tower base region, reducing the measurement error of traditional planar methods on steep slope terrain and solving the error problem of planar measurement on steep slope terrain.

[0038] When performing risk warning, this invention combines three criteria: three-dimensional area change, direction verification, and spectral verification. If the area change rate is greater than the threshold, it indicates that there is additional accumulation in the tower base area. If the direction verification is passed, it indicates that there is a downslope flow condition. If the spectral verification is passed, it confirms the presence of slag. This eliminates false alarms and achieves efficient and accurate identification of slag flow in the tower base area. Attached Figure Description

[0039] Figure 1 This is a flowchart of a method according to an embodiment of the present invention.

[0040] Figure 2 This is a flowchart illustrating the process of calculating the three-dimensional area of ​​the tower base region in step S2 of an embodiment of the present invention.

[0041] Figure 3 This is a schematic diagram of the direction verification and spectral verification principle in step S4 of this embodiment of the invention. Detailed Implementation

[0042] The present invention will be further described below with reference to the accompanying drawings and specific preferred embodiments, but this does not limit the scope of protection of the present invention.

[0043] This embodiment proposes a method for detecting slope sludge chutes in mountainous power transmission and transformation projects based on the three-dimensional area change of the tower base. By combining satellite imagery and digital elevation model (DEM) data, the three-dimensional area of ​​the tower base region is calculated, thereby eliminating measurement errors caused by topographic elevation differences. The three-dimensional area change of the tower base region is used as the core criterion for slope sludge chutes. By combining DeepLabV3+ segmentation with accurate three-dimensional area calculation, the method solves the problem of accuracy and efficiency in identifying sludge chutes at the tower base of power transmission and transformation projects in mountainous areas.

[0044] like Figure 1 As shown, the method includes the following steps:

[0045] S1) Obtain satellite images of the initial and current phases of tower foundation construction in the target area, and obtain digital elevation model data of the target area, and preprocess the satellite images and digital elevation model data;

[0046] S2) Segment the tower base region from the current satellite imagery and calculate the current three-dimensional area S of the tower base region based on digital elevation model data. t ;

[0047] S3) Based on the reference three-dimensional area S0 of the tower base region and the current three-dimensional area S... tCalculate the rate of change of area ;

[0048] S4) If the area change rate If the value is greater than or equal to a preset threshold, the initial satellite imagery is compared with the current satellite imagery to obtain the newly added area. The consistency between the diffusion direction and slope aspect of the newly added area is verified, and the spectral characteristics of the slag in the newly added area are also verified.

[0049] S5) If the diffusion direction and slope aspect of the newly added area are consistent with the spectral characteristics of the slag soil, the event is determined to be a downslope slag dumping event and the corresponding risk level is output.

[0050] The above steps, utilizing satellite imagery and DEM elevation data, significantly reduce measurement errors on steep slopes. Through a triple criterion of "three-dimensional area change + direction verification + spectral verification," the accuracy of judging slope and debris flow in the tower base area is greatly improved. This provides stable and reliable technical support for environmental and water conservation monitoring in mountainous power transmission and transformation areas.

[0051] Taking a 110kV transmission line project in Hunan Province as an example, this paper provides a detailed explanation of each step. The example is located in a typical mountainous and hilly area, with a total length of approximately 26km and a maximum slope of 39°. During the rainy season, multiple incidents of slag runoff occurred at the tower base area.

[0052] In step S1 of this embodiment, the higher the resolution of the acquired satellite imagery and digital elevation model data, the better the recognition effect. To obtain better recognition results, after multiple tests, the satellite imagery and digital elevation model data should meet the following conditions:

[0053]

[0054] Therefore, in this embodiment, when acquiring satellite images of the initial and current stages of tower foundation construction in the target area, and acquiring digital elevation model data of the target area, the following data is specifically acquired:

[0055]

[0056] In step S1 of this embodiment, when preprocessing the satellite imagery and digital elevation model data, one or more preprocessing steps are performed, such as spatial registration and topographic radiometric correction. Specifically, in this embodiment, spatial registration uses SIFT feature matching, and topographic radiometric correction uses the Minnaert model to eliminate the influence of topographic shadows.

[0057] In step S2 of this embodiment, when segmenting the base region from the current satellite image, a deep learning model such as DeepLabV3+ is used to segment the base region in the current satellite image. Then, the segmentation result is morphologically optimized, and the boundary points are vectorized. This includes the following steps:

[0058] First, the current satellite imagery is input into the DeepLabV3+ model to obtain a probability map. The probability of each pixel in the probability map is compared with a preset probability threshold. If the probability is less than the preset probability threshold, the value of the pixel is updated to 0; if the probability is greater than the preset probability threshold, the value of the pixel is updated to 1. This converts the probability map into a binary mask image. In this embodiment, the probability threshold is 0.5, but the probability threshold can also be adjusted according to the actual situation.

[0059] Then, morphological operations are performed on the binarized mask image to optimize its quality, resulting in an optimized binarized mask image, which lays the foundation for subsequent vectorization. The morphological operations mainly include closing operations (dilation followed by erosion, used to fill small holes and short breaks inside the mask) and opening operations (erosion followed by dilation, used to eliminate small isolated noise points and smooth boundaries).

[0060] Finally, the boundaries are extracted from the optimized binarized mask image and vector polygons are constructed. Each vector polygon corresponds one-to-one with the base region of the tower, and the boundary points of each vector polygon are obtained.

[0061] In this embodiment, a contour-finding algorithm is used to extract boundaries from the optimized binary image. This algorithm finds the contours of all connected regions and represents each contour as a set of points. Subsequently, the obtained point sets are used to construct vector polygons, which are then simplified using a vector simplification algorithm (such as the Douglas-Peucker algorithm). Each contour (polygon) obtained after vectorization is itself formed by the ordered connection of boundary points. Each vector polygon feature represents a segmented base region.

[0062] In step S2 of this embodiment, the current three-dimensional area S of the tower base region is calculated based on the digital elevation model data. t At that time, the triangular mesh partitioning algorithm is used for calculation, such as Figure 2 As shown, it includes the following steps:

[0063] S201) Obtain the planar coordinates of all boundary points of the vector polygon corresponding to the current tower base area; specifically, obtain the set of boundary points of the vector polygon corresponding to the current tower base area obtained after segmenting the tower base area from the current satellite image, arrange the boundary points in clockwise or counterclockwise order, and establish a two-dimensional coordinate sequence of the boundary points: P i ( (i=1, 2, ..., n);

[0064] S202) Calculate the elevation value of the boundary point as the height coordinate based on the vertex coordinates of the grid into which the boundary point falls in the digital elevation model data;

[0065] In this embodiment, for each boundary point P i The DEM data is used to interpolate elevation values ​​to form a three-dimensional point set: =( , , ), During interpolation, let boundary point P be... i Four points falling on the DEM data grid , ), , ), , ), , If the elevation interpolation value is between ), then the elevation interpolation value is:

[0066]

[0067] in, This indicates the lower left vertex of the grid into which the boundary point falls. The elevation value, and the lower left vertex The plane coordinates are , ), This represents the top-left vertex of the grid into which the boundary point falls. The elevation value, and the top left vertex The plane coordinates are , ), This indicates the bottom right vertex of the grid into which the boundary point falls. The elevation value, and the lower right vertex The plane coordinates are , ), This represents the top right vertex of the grid into which the boundary point falls. The elevation value, and the upper right vertex The plane coordinates are , );

[0068] S203) Calculate the average of the planar coordinates and the average of the height coordinates of all boundary points of the vector polygon to obtain the three-dimensional coordinates of the centroid O of the vector polygon. The calculation formula is as follows:

[0069]

[0070] in, These are the x-coordinates of the plane containing the centroid O. These are the y-coordinates of the centroid O in the plane. It is the z-coordinate value of the height of the center of gravity O. P is the i-th boundary point in the vector polygon. i The x-coordinate value of the plane. P is the i-th boundary point in the vector polygon. i The y-coordinate value of the plane. P is the i-th boundary point in the vector polygon. i The height z-coordinate value, where n is the total number of boundary points of the vector polygon;

[0071] S204) Construct a triangulation with centroid O as the common vertex, and connect adjacent boundary points on the boundary of the vector polygon to centroid O in sequence to form corresponding triangles;

[0072] For a polygon with n boundary points, n triangles can be constructed (the last triangle consists of the nth point, the first point, and point O). The set of triangles is: (O,P i , ), where i ranges from 1 to n, and when i = n, That is, P1;

[0073] S205) Calculate the three-dimensional area of ​​each triangle, including the following steps:

[0074] Obtain the 3D coordinates of vertices O, A, and B of the current triangle △OAB, where A and B are adjacent boundary points on the boundary of the vector polygon. The 3D coordinates of vertices O, A, and B are: A( , ), B ( , ), O ( , );

[0075] Calculate the vector based on the three-dimensional coordinates of vertices O, A, and B. and The formula is as follows:

[0076]

[0077]

[0078] in, These are the x, y, and z coordinates of vertex A, respectively. These are the x, y, and z coordinates of vertex B, respectively. These are the x, y, and z coordinates of vertex O, respectively.

[0079] Then calculate the vector. and cross product The formula is as follows:

[0080]

[0081] Right now:

[0082]

[0083]

[0084]

[0085] in, These are the components in the x, y, and z directions, respectively;

[0086] Calculate the cross product Length of the module The formula is as follows:

[0087]

[0088] mold length Multiply This gives us the three-dimensional area of ​​the current triangle △OAB, i.e.:

[0089]

[0090] in, Represent the three-dimensional area of ​​triangle △OAB;

[0091] (S206) Accumulate the three-dimensional areas of all triangles in the vector polygon corresponding to the current base region to obtain the total accumulated area of ​​the vector polygon, and use this as the current three-dimensional area of ​​the current base region, i.e.:

[0092]

[0093] in, This represents the three-dimensional area of ​​the k-th triangle in the vector polygon.

[0094] In step S3 of this embodiment, the reference three-dimensional area S0 of the tower base region is the projected area of ​​the tower base design boundary, specifically the product of the design area of ​​the tower base region and the terrain correction coefficient corresponding to the target region, that is:

[0095] .

[0096] In step S3 of this embodiment, the area change rate of the tower base region The reference three-dimensional area S0 and the current three-dimensional area S of the same tower base region t The calculation yields the following formula:

[0097]

[0098] For the example above, some of the calculation results from step S3 are shown in the table below, where the station number indicates the station number of the tower base area obtained by segmentation in step S2.

[0099]

[0100] In this embodiment, step S4 is used to measure the area change rate. For tower base areas not less than a preset threshold, directional verification (calculating the direction of the minimum bounding rectangle of the newly added area and comparing it with the slope direction calculated by the DEM) and spectral verification (calculating the average NDVI and near-infrared reflectance within the newly added area) are performed to obtain more accurate results.

[0101] In step S4 of this embodiment, when comparing the initial satellite image with the current satellite image to obtain the newly added area, the preliminary changed area is determined by calculating the spectral difference between two images of the same area at two different time points (time phase T1, i.e., the initial stage of construction) and (time phase T2, i.e., the current stage of construction). Vegetation indices (such as NDVI) are typically used to highlight the changes (areas with vegetation destruction and exposed soil will show significantly negative ΔNDVI values). Then, morphological operations (closing operations to fill small holes and opening operations to remove small noise points) are performed on the extracted preliminary changed area to obtain a final connected and smooth binary mask of the newly added area.

[0102] In step S4 of this embodiment, direction verification, that is, verifying the consistency between the diffusion direction of the newly added area and the slope aspect, specifically includes the following steps:

[0103] S401) Extract the minimum bounding rectangle of the newly added region and calculate the major axis direction angle α of the minimum bounding rectangle. Specifically, the cv2.minAreaRect() function in OpenCV software is used to extract the outer contour of the newly added region from the binary mask, and then the minimum bounding rectangle and the major axis direction angle α of the minimum bounding rectangle are calculated.

[0104] (S402) Obtain the digital elevation model data of the newly added area, and calculate the dominant slope aspect β of the newly added area based on the digital elevation model data. Specifically, use a binary mask of the newly added area as a raster calculation mask to crop out the portion containing only the newly added area from the digital elevation model data to obtain the digital elevation model data of the newly added area. Then, use a GIS library to calculate the slope aspect raster map of the digital elevation model data of the newly added area, convert each angle value in the slope aspect raster into a unit vector; calculate the average value of all unit vectors to obtain the average vector, and calculate the average angle as the dominant slope aspect β based on the average vector.

[0105] S403) Calculate the angle γ between the major axis direction angle α and the dominant slope aspect β, using the following formula:

[0106] γ=min(|α-β|, 360-|α-β|)

[0107] S404) If the value of the included angle γ is less than the angle threshold, the consistency between the diffusion direction and the slope direction of the newly added area is verified.

[0108] For the example above, the partial calculation results of the direction verification through step S4 are shown in the table below. The station number in the table represents the station number of the tower base area obtained by segmentation through step S2.

[0109]

[0110] In step S4 of this embodiment, spectral verification is performed, specifically verifying the spectral characteristics of the newly added area's slag. If optical images are available, spectral verification is performed on the newly added area; if optical images are unavailable, SAR image coherence change detection is used instead of spectral verification. For the aforementioned example, some calculation results of the spectral verification performed in step S4 are shown in the table below, where the station number indicates the station number of the tower base area obtained through segmentation in step S2.

[0111]

[0112] After multiple experimental verifications, the consistency of the diffusion direction and slope aspect of the newly added area, as well as the spectral characteristics of the slag soil, all passed the verification. Figure 3 As shown, the following conditions must be met:

[0113]

[0114] Among the above conditions, near-infrared reflectance is set. The core reason why >0.3 and NDVI<0.2 are used as criteria for judging construction waste is that the spectral characteristics of construction waste are fundamentally different from those of natural ground surfaces. The specific scientific mechanism is as follows:

[0115] The physical mechanisms underlying near-infrared reflectance > 0.3 are shown in the table below:

[0116]

[0117] In this embodiment, it was verified that the near-infrared reflectance of sandstone slag is 0.35-0.45 (dry state), which is significantly higher than that of surrounding vegetation (0.1-0.25) and moist soil (0.15-0.25). A threshold of 0.3 can effectively distinguish slag from natural ground surface.

[0118] The biological mechanisms of NDVI < 0.2 are shown in the table below:

[0119]

[0120] In this embodiment, it was verified that the chlorophyll absorption rate of healthy vegetation in the red light band is >90%, while the near-infrared reflectance can reach 40-60%, resulting in an NDVI value often greater than 0.6. In slag heap areas, due to the lack of vegetation cover, the calculated value is typically negative to between 0.2.

[0121] In this embodiment, step S5 determines whether a slope-side muck dredging event is occurring and outputs the corresponding risk level. If both directional and spectral verifications are passed, it is determined to be a slope-side muck dredging event, and slope muck dredging information is generated and calculated based on the area change rate. The numerical range output corresponds to the risk level. When the area change rate... If the area is less than a preset threshold, then the area change rate will be used as the criterion. The numerical range determines whether there is a risk of a slope-side muck sluice event and outputs the corresponding risk level. This includes the following steps:

[0122] If the rate of change of area If the value is less than or equal to the first threshold, it is considered a safe state.

[0123] If the rate of change of area If the value is less than a preset threshold but greater than a first threshold, the initial satellite imagery is compared with the current satellite imagery to obtain the newly added area, and the spectral characteristics of the slag in the newly added area are verified. If the spectral characteristics of the slag in the newly added area pass the verification, it is determined that there is a risk of slag descent incidents, and the corresponding risk level is output as a yellow warning.

[0124] If the rate of change of area If the value is greater than or equal to the preset threshold and less than or equal to the second threshold, and the diffusion direction of the newly added area is consistent with the slope aspect and the spectral characteristics of the slag soil are verified, then it is determined to be a downslope slag dumping event and the corresponding risk level is output as orange medium risk.

[0125] If the rate of change of area If the new area's diffusion direction is greater than or equal to the second threshold, and the consistency between the diffusion direction and slope aspect, as well as the spectral characteristics of the slag soil, are verified, then it is determined to be a serious downslope slag dumping event, and the corresponding risk level is output as red high risk.

[0126] In this embodiment, the first threshold is set to 30%, the second threshold is set to 100%, and the preset threshold is set to 50%. The risk classification standard is as follows:

[0127]

[0128] After determining the risk level, an early warning message is generated and pushed to relevant units. Corresponding measures are then taken, as follows:

[0129]

[0130] For the example above, some of the judgment results made by step S5 are shown in the table below. The station number in the table represents the station number of the tower base area obtained by segmentation in step S2.

[0131]

[0132] After verification by drone, a small-scale landslide event was confirmed in the corresponding area. Timely measures, including earthwork containment, were implemented to prevent a large-scale landslide. This demonstrates that the method described in this embodiment provides a stable and reliable technical guarantee for environmental and water conservation monitoring in mountainous power transmission and transformation areas.

[0133] Furthermore, this embodiment also proposes a slope sludge chute detection system for mountain power transmission and transformation projects based on the three-dimensional area change of the tower base, including a processor and a computer-readable storage medium. The computer-readable storage medium stores a computer program, which is executed by the processor to implement the steps of the slope sludge chute detection method for mountain power transmission and transformation projects based on the three-dimensional area change of the tower base described in this embodiment.

[0134] In summary, this invention proposes a method for detecting slope runoff in mountainous power transmission and transformation projects based on the three-dimensional area change of the tower base. The core innovation lies in the integration of satellite remote sensing images and digital elevation models (DEMs) with a multi-criteria system to judge slope runoff events. Compared with traditional methods, it has the following advantages: (1) It combines satellite images and DEM elevation data and pioneers a triangulation algorithm to calculate the three-dimensional area, reducing the measurement error of traditional planar methods on steep slope terrain and solving the error problem of planar measurement on steep slope terrain. (2) The proposed triple criteria of "three-dimensional area change + direction verification + spectral verification" greatly improves the accuracy of judging slope runoff in the tower base area. (3) It supports multi-cloud and multi-source data collaborative processing, ensuring monitoring continuity and providing stable and reliable technical support for the field of environmental and water conservation monitoring of power transmission and transformation in mountainous areas.

[0135] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0136] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A method for detecting downhill sliding of slag in mountain power transmission and transformation engineering based on three-dimensional area change of tower foundation, characterized in that, The method comprises the following steps: Obtaining satellite images of initial and current periods of tower foundation construction in a target area, and obtaining digital elevation model data of the target area, and preprocessing the satellite images and the digital elevation model data; Segmenting a tower foundation area from the satellite image of the current period, and calculating a current three-dimensional area of the tower foundation area according to the digital elevation model data; Calculating an area change rate according to a reference three-dimensional area and the current three-dimensional area of the tower foundation area; If the area change rate is greater than or equal to a preset threshold, comparing the satellite image of the initial period with the satellite image of the current period to obtain a new area, verifying consistency of a diffusion direction and a slope direction of the new area, and verifying a slag soil spectral feature of the new area; If the diffusion direction and the slope direction of the new area are consistent and the slag soil spectral feature of the new area are verified, it is determined that a slope-sliding event occurs and a corresponding risk level is output; When verifying the consistency of the diffusion direction and the slope direction of the new area, the following steps are included: Extracting a minimum circumscribed rectangle of the new area, and calculating a long axis direction angle α of the minimum circumscribed rectangle; Obtaining digital elevation model data of the new area, and calculating a dominant slope direction β of the new area according to the digital elevation model data; Calculating an included angle γ between the long axis direction angle α and the dominant slope direction β, and if the value of the included angle γ is less than an angle threshold, the consistency of the diffusion direction and the slope direction of the new area is verified; When verifying the slag spectrum characteristics of the added area, if the optical image is available, the spectrum verification is performed on the added area, and after obtaining the spectrum verification result, if the near-infrared band reflectivity 0.3 and the normalized vegetation index NDVI 0.2, the slag spectrum characteristics of the added area pass the verification.

2. The method according to claim 1, wherein the method is characterized by, When segmenting the tower foundation area from the satellite image of the current period, the following steps are included: Inputting the satellite image of the current period into a deep learning model to obtain a probability map, comparing a probability of each pixel point in the probability map with a preset probability threshold, if the probability is less than the preset probability threshold, updating a value of the pixel point to 0, if the probability is greater than the preset probability threshold, updating the value of the pixel point to 1, thereby converting the probability map into a binary mask image; Performing morphological operation on the binary mask image to obtain an optimized binary mask image, extracting a boundary from the optimized binary mask image, and constructing a vector polygon, the vector polygon corresponding to the tower foundation area one by one.

3. The method according to claim 2, wherein the method is characterized by, When calculating the current three-dimensional area of the tower foundation area according to the digital elevation model data, the following steps are included: Obtaining plane coordinates of all boundary points of a vector polygon corresponding to the current tower foundation area; Calculating an elevation value of the boundary point as a height coordinate according to vertex coordinates of a grid in which the boundary point falls in the digital elevation model data; Calculating an average value of the plane coordinates of all boundary points of the vector polygon and an average value of the height coordinates to obtain three-dimensional coordinates of a gravity center point O of the vector polygon; Connecting adjacent boundary points on the boundary of the vector polygon and the gravity center point O in turn to form corresponding triangles with the gravity center point O as a common vertex, calculating a three-dimensional area of each triangle respectively, and accumulating the three-dimensional areas of all the triangles to obtain the current three-dimensional area of the current tower foundation area.

4. The mountainous power transmission and transformation project slope sliding detection method based on tower base three-dimensional area change according to claim 3, characterized in that, The calculation formula of the elevation value of the boundary point is as follows: wherein represents the elevation value of the lower left corner of the grid in which the boundary point falls, and the planar coordinates of the lower left corner are , ), represents the elevation value of the upper left corner of the grid in which the boundary point falls, and the planar coordinates of the upper left corner are , ), represents the elevation value of the lower right corner of the grid in which the boundary point falls, and the planar coordinates of the lower right corner are , ), represents the elevation value of the upper right corner of the grid in which the boundary point falls, and the planar coordinates of the upper right corner are , ).​​​​ 5. The mountainous power transmission and distribution project slope sliding detection method based on tower base three-dimensional area change according to claim 3, characterized in that, When calculating the area of each triangle respectively, the following steps are included: Obtain the three-dimensional coordinates of each vertex O, A, B of the current triangle △OAB, calculate the vectors and Then calculate the cross product of the vectors and where A, B are adjacent boundary points on the boundary of the vector polygon;​ The cross product is calculated The length of the module The length of the module is multiplied by to obtain the three-dimensional area of the current triangle △OAB.

6. The mountainous power transmission and distribution project slope sliding detection method based on tower base three-dimensional area change according to claim 1, characterized in that, The reference three-dimensional area of the tower foundation area is specifically a product of a design area of the tower foundation area and a terrain correction coefficient corresponding to the target area.

7. The method according to claim 1, wherein the method is characterized by, When the optical image is unavailable, the SAR image coherent change detection is used to replace the spectral verification in the verification of the slag spectrum characteristics of the new added area. After obtaining the SAR image coherent change detection result, if the near-infrared band reflectivity 0.3 and the normalized vegetation index NDVI 0.2, the slag spectrum characteristics of the new added area pass the verification.

8. The mountainous power transmission and distribution project slope sliding detection method based on tower base three-dimensional area change according to claim 1, characterized in that, After calculating the area change rate according to the design area and the current three-dimensional area of the tower foundation area, the following steps are included: If the area change rate is less than the preset threshold but greater than the first threshold, the initial satellite image is compared with the current satellite image to obtain a new area, and the spectrum feature of the slag in the new area is verified; If the spectrum feature of the slag in the new area is verified, the corresponding risk level is output.

9. A mountainous power transmission and transformation project slope sliding slag detection system based on tower base three-dimensional area change, characterized in that, The method comprises a processor and a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the steps of the mountainous power transmission and transformation project slope sliding slag detection method based on tower foundation three-dimensional area change.

Images