Aerial photography-based geological disaster detection system

Abstract

This invention belongs to the field of geological disaster detection and discloses a geological disaster detection system based on aerial photography. The system includes a SAR image acquisition device, a SAR image processing device, a drone device, and a geological disaster detection device. The SAR image acquisition device acquires a first SAR image and a second SAR image of the geological disaster detection area, with the first SAR image being captured earlier than the second SAR image. The SAR image processing device identifies the shooting area based on the first and second SAR images. The drone device captures images of the shooting area, obtaining visible light images. The geological disaster detection device identifies the visible light images to determine whether a preset type of geological disaster exists. This invention can effectively shorten the average time between the occurrence of all geological disaster events and the time when the responsible department obtains the detection results, facilitating more timely detection of areas where geological disaster events have occurred.

Description

Technical Field

[0001] This invention relates to the field of geological disaster detection, and in particular to a geological disaster detection system based on aerial photography. Background Technology

[0002] Using drone aerial photography for geological hazard detection is an efficient method that can identify areas prone to landslides and other geological hazards relatively quickly. However, current technologies typically divide the entire detection area into multiple smaller zones, then use the drone to photograph all of these zones, and obtain detection results based on the images. However, in some smaller zones photographed later in the sequence, a significant time gap exists between the onset of a geological hazard and the time the detection department receives the results, making it difficult to detect these areas in a timely manner. Summary of the Invention

[0003] The purpose of this invention is to disclose a geological disaster detection system based on aerial photography, thereby solving the technical problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention adopts the following technical solution:

[0005] This invention provides a geological disaster detection system based on aerial photography, including a SAR image acquisition device, a SAR image processing device, an unmanned aerial vehicle (UAV) device, and a geological disaster detection device;

[0006] The SAR image acquisition device is used to acquire a first SAR image and a second SAR image of the geological disaster detection area, wherein the first SAR image was captured earlier than the second SAR image.

[0007] The SAR image processing device is used to obtain the shooting area based on the first SAR image and the second SAR image;

[0008] The drone device is used to photograph the area being photographed and acquire visible light images;

[0009] The geological hazard detection device is used to identify visible light images and determine whether there are geological hazards of a preset type in the visible light images;

[0010] This includes capturing images of the shooting area to obtain visible light images, including:

[0011] Calculate the clustering value for each shooting area separately;

[0012] Based on the clustering values, a clustering algorithm is used to divide all clustering values ​​into two clusters;

[0013] Obtain the average of the cluster values ​​in the two clusters respectively;

[0014] Let CA represent the cluster with the larger average cluster value, and CB represent the other cluster.

[0015] First, take pictures of the areas corresponding to the cluster values ​​in CA to obtain visible light images. Then, take pictures of the areas corresponding to the cluster values ​​in CB to obtain visible light images.

[0016] Preferably, the SAR image acquisition device includes an Earth observation remote sensing satellite carrying a synthetic aperture radar;

[0017] Earth observation remote sensing satellites carrying synthetic aperture radar are used to image geological hazard detection areas using synthetic aperture radar, and to acquire first SAR images and second SAR images of the geological hazard detection areas.

[0018] Preferably, obtaining the shooting area based on the first SAR image and the second SAR image includes:

[0019] The second SAR image is divided into partitions to obtain multiple regions to be judged.

[0020] Based on the first SAR image, each region to be judged is determined to meet the preset judgment conditions, and the region to be judged that meets the preset judgment conditions is taken as the shooting area.

[0021] Preferably, the second SAR image is divided into multiple regions to be determined, including:

[0022] Calculate the zoning control coefficients;

[0023] The second SAR image is partitioned based on the partition control coefficient to obtain multiple regions to be judged.

[0024] Preferably, the formula for calculating the zoning control coefficient is:

[0025]

[0026] The scp represents the partition control coefficient of the second SAR image, scp represents the set of pixels in the second SAR image, and nscp represents the total number of pixels in the scp. This represents the pixel value of pixel i in the SCP. This indicates the preset reference value. This represents the preset baseline value.

[0027] Preferably, the second SAR image is partitioned based on partition control coefficients to obtain multiple regions to be judged, including:

[0028] Calculate the length of the region to be judged using the following formula:

[0029]

[0030] Calculate the width of the region to be judged using the following formula:

[0031]

[0032] Where Lth and Wth represent the length and width of the region to be judged, respectively, and Lbs and Wbs represent the preset length and width, respectively;

[0033] The second SAR image is divided into multiple regions of length Lth and width Wth to be processed;

[0034] The region to be processed is processed to generate the region to be judged.

[0035] Preferably, the region to be processed is subjected to a region-to-be-judged generation process to obtain the region to be-judged, including:

[0036] The first step is to treat all regions to be processed as elements of the set Udeal;

[0037] The second step is to randomly select a region to be processed from Udeal, use the selected region as the comparison region, use the selected region as an element in the set NU, and delete the selected region from Udeal.

[0038] The third step is to calculate the adjacency value of each region to be processed that is adjacent to the comparison region and belongs to Udeal;

[0039] The fourth step is to determine whether the smallest adjacency value meets the set adjacency value threshold. If it does, the region to be processed with the smallest adjacency value is deleted from Udeal, the region to be processed with the smallest adjacency value is stored in NU, and the region to be processed with the smallest adjacency value is used as the new comparison region. Then proceed to the third step. If not, proceed to the fifth step.

[0040] Fifth step: Treat the regions corresponding to all elements in NU as a region to be judged;

[0041] Step 6: Clear the elements in NU and proceed to step 2.

[0042] Preferably, the adjacency value is obtained as follows:

[0043] Let cmp represent the comparison region, and Ucmp represent the set of all regions to be processed that are adjacent to cmp and belong to Udeal;

[0044] If we use "deal" to represent the region to be processed, then the adjacency value corresponding to "deal" is:

[0045]

[0046] This represents the adjacency value corresponding to the deal. and These are the average pixel values ​​of the pixels in cmp and deal, respectively.

[0047] Preferably, based on the first SAR image, it is determined whether each region to be judged meets the preset judgment conditions, including:

[0048] Let jud2 represent the region to be judged, and let jud1 represent the region where all pixels in the first SAR image have the same coordinates as the pixels in jud2.

[0049] Calculate the judgment value:

[0050]

[0051] This indicates the judgment value corresponding to jud2. This represents the total number of pixels in jud2 that satisfy the following inequality:

[0052]

[0053] This represents the pixel value of pixel j in jud2. pixlm represents the pixel value of the pixel with the same coordinates as pixel j in the first SAR image, and pixel j represents the maximum pixel value of the pixel in the second SAR image. This represents the total number of pixels in jud2;

[0054] like If the value is greater than the preset threshold, it means that jud2 meets the preset judgment condition.

[0055] Preferably, the visible light image is identified to determine whether a predetermined type of geological hazard exists in the visible light image, including:

[0056] The visible light image is input into a pre-trained recognition model for identification, to determine whether there is a preset type of geological disaster in the visible light image.

[0057] Beneficial effects:

[0058] In the process of geological disaster detection using UAV aerial photography technology, this invention acquires the shooting area based on two SAR images taken at different times. Then, the cluster values ​​of the shooting areas are divided into two clusters, and the shooting areas corresponding to the cluster values ​​of the clusters with larger average values ​​are prioritized for shooting. This effectively reduces the number of shooting areas that need to be photographed, while prioritizing the shooting of areas with a higher probability of geological disaster events among all the required shooting areas. This can effectively shorten the average time between the occurrence of all geological disaster events and the time when the responsible department obtains the detection results, which is conducive to more timely detection of areas where geological disaster events have occurred. Attached Figure Description

[0059] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 This is a schematic diagram of a geological disaster detection system based on aerial photography according to the present invention.

[0061] Figure 2 This is a schematic diagram illustrating the process of capturing images of the areas corresponding to the cluster values ​​in CA to obtain visible light images. Detailed Implementation

[0062] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0063] like Figure 1 As shown in one embodiment, the present invention provides a geological disaster detection system based on aerial photography, including a SAR image acquisition device, a SAR image processing device, an unmanned aerial vehicle (UAV) device, and a geological disaster detection device;

[0064] The SAR image acquisition device is used to acquire a first SAR image and a second SAR image of the geological disaster detection area, wherein the first SAR image was captured earlier than the second SAR image.

[0065] The SAR image processing device is used to obtain the shooting area based on the first SAR image and the second SAR image;

[0066] The drone device is used to photograph the area being photographed and acquire visible light images;

[0067] The geological hazard detection device is used to identify visible light images and determine whether there are geological hazards of a preset type in the visible light images;

[0068] This includes capturing images of the shooting area to obtain visible light images, including:

[0069] Calculate the clustering value for each shooting area separately;

[0070] Based on the clustering values, a clustering algorithm is used to divide all clustering values ​​into two clusters;

[0071] Obtain the average of the cluster values ​​in the two clusters respectively;

[0072] Let CA represent the cluster with the larger average cluster value, and CB represent the other cluster.

[0073] First, take pictures of the areas corresponding to the cluster values ​​in CA to obtain visible light images. Then, take pictures of the areas corresponding to the cluster values ​​in CB to obtain visible light images.

[0074] In the process of using drone aerial photography for geological disaster detection, the area to be photographed is obtained based on two SAR images taken at different times. Then, the cluster values ​​of the photographed areas are divided into two clusters, and the areas corresponding to the cluster values ​​with larger average values ​​are photographed first. This can effectively reduce the number of areas that need to be photographed, while prioritizing the areas with a higher probability of geological disaster events among all the areas that need to be photographed. This can effectively shorten the average time between the occurrence of all geological disaster events and the time when the department responsible for detection obtains the detection results, which is conducive to more timely detection of areas where geological disaster events have occurred.

[0075] Furthermore, the reason this invention does not directly rely on SAR images for geological hazard detection is that the pixel values ​​(including amplitude and phase) of pixels in SAR images are easily affected by various factors, which may lead to changes in image quality and thus affect the accuracy of applications such as geological hazard monitoring and change detection. For example:

[0076] (1) Atmospheric factors:

[0077] Atmospheric humidity: The water vapor content in the atmosphere affects the propagation of SAR signals, leading to phase delay and amplitude attenuation, thus affecting the accuracy of pixel values. Especially in cloudy or humid areas, the propagation of radar signals can be significantly affected.

[0078] Changes in air pressure and temperature: These atmospheric factors can affect the speed of signal propagation and attenuation, especially in the processing of image data over long time scales, and may lead to systematic errors.

[0079] (2) Weather factors:

[0080] Precipitation (rain, snow, fog): Precipitation is a significant factor affecting SAR image quality. Heavy precipitation causes radar signal scattering and absorption, thus affecting pixel intensity. Snow, fog, and other weather conditions also attenuate radar signals, leading to a decrease in image quality.

[0081] Clouds: Although SAR has the ability to penetrate clouds, under certain extreme weather conditions, the thickness and type of clouds may have a certain impact on the signal, especially on the reflection intensity of ground objects.

[0082] Therefore, after acquiring SAR images, the present invention uses drones for secondary confirmation, which can significantly reduce the probability of misidentification.

[0083] Preferably, the SAR image acquisition device includes an Earth observation remote sensing satellite carrying a synthetic aperture radar;

[0084] Earth observation remote sensing satellites carrying synthetic aperture radar are used to image geological hazard detection areas using synthetic aperture radar, and to acquire first SAR images and second SAR images of the geological hazard detection areas.

[0085] The SAR image acquisition device of the present invention can image the geological disaster detection area at a fixed period, for example, once every week. Each imaging session is identical except for the shooting time. Therefore, the second SAR image of the present invention can be the most recently acquired SAR image, while the first SAR image is the SAR image whose shooting time is closest to that of the second SAR image. In this case, the shooting time between the two SAR images is equal to the fixed period.

[0086] Preferably, obtaining the shooting area based on the first SAR image and the second SAR image includes:

[0087] The second SAR image is divided into partitions to obtain multiple regions to be judged.

[0088] Based on the first SAR image, each region to be judged is determined to meet the preset judgment conditions, and the region to be judged that meets the preset judgment conditions is taken as the shooting area.

[0089] By dividing the area into zones, it is easier to select areas with a high probability of geological disasters as filming areas, thereby reducing the probability of filming in areas where there are no geological disasters and facilitating the more timely detection of areas with potential geological disasters.

[0090] Preferably, the second SAR image is divided into multiple regions to be determined, including:

[0091] Calculate the zoning control coefficients;

[0092] The second SAR image is partitioned based on the partition control coefficient to obtain multiple regions to be judged.

[0093] The partitioning process of this invention is not based on a fixed length and width, because such a partitioning method is not applicable to SAR images in different states. It is easy to cause the area to be judged after partitioning to be too large or too small. If the area to be judged is too large, the results obtained by the subsequent judgment process of the shooting area will not be accurate enough; if the area to be judged is too small, the number of shooting areas will be too large, which will affect the efficiency of geological hazard identification in the geological hazard detection area and will not be conducive to timely detection of existing geological hazards.

[0094] Preferably, the formula for calculating the zoning control coefficient is:

[0095]

[0096] The scp represents the partition control coefficient of the second SAR image, scp represents the set of pixels in the second SAR image, and nscp represents the total number of pixels in the scp. This represents the pixel value of pixel i in the SCP. This indicates the preset reference value. This represents the preset baseline value.

[0097] The partition control coefficient of this invention is calculated based on the degree of difference in pixel values ​​of all pixels in the second SAR image. The greater the difference, the greater the probability of a geological disaster event in the second SAR image, and the larger the partition control coefficient. This results in a smaller length and width of the subsequently calculated region to be judged, which is beneficial for obtaining more accurate partitioning results and for more comprehensive identification of areas with geological disaster events. Conversely, a smaller difference results in a smaller partition control coefficient, which results in a larger length and width of the subsequently calculated region to be judged, which is beneficial for reducing the number of regions to be judged, thereby reducing the number of shooting areas and improving the efficiency of acquiring visible light images.

[0098] In some embodiments, the preset reference value can be 128.

[0099] In some embodiments, the preset baseline value can be 10.

[0100] In some embodiments, a pixel value may be a grayscale value or a phase value.

[0101] Grayscale value:

[0102] Type: Grayscale images typically represent gray levels of amplitude information. SAR images, after conversion, can be displayed as visually understandable grayscale images. Grayscale values ​​reflect signal strength and are usually processed through logarithmic transformation of amplitude (e.g., expressed in dB after taking the logarithm).

[0103] Value range: If a logarithmic transformation is performed (e.g., in dB), the grayscale value range is generally 0 to 255 (8-bit image).

[0104] Phase value:

[0105] Type: The pixel values ​​of a phase image represent the phase information of the echo signal, typically a complex phase component. Phase values ​​are used in interferometric measurements (such as differential interferometric SAR, InSAR) to obtain information about surface deformation.

[0106] Value range: The range of phase values ​​is -π to π (i.e. -180° to 180°). Because the phase is periodic, values ​​outside this range will be treated as wrapping.

[0107] Preferably, the second SAR image is partitioned based on partition control coefficients to obtain multiple regions to be judged, including:

[0108] Calculate the length of the region to be judged using the following formula:

[0109]

[0110] Calculate the width of the region to be judged using the following formula:

[0111]

[0112] Where Lth and Wth represent the length and width of the region to be judged, respectively, and Lbs and Wbs represent the preset length and width, respectively;

[0113] The second SAR image is divided into multiple regions of length Lth and width Wth to be processed;

[0114] The region to be processed is processed to generate the region to be judged.

[0115] In the above formula, This is the floor symbol.

[0116] The length and width of the judgment area of ​​the present invention can be adaptively changed based on the change of the partition control coefficient, thereby enabling the present invention to obtain a shooting area with a length and width that better meets the actual shooting requirements.

[0117] In some embodiments, the preset length is one-fifth of the length of the image obtained when the drone takes pictures at its maximum flight altitude; the preset width is one-fifth of the width of the image obtained when the drone takes pictures at its maximum flight altitude.

[0118] Preferably, the region to be processed is subjected to a region-to-be-judged generation process to obtain the region to be-judged, including:

[0119] The first step is to treat all regions to be processed as elements of the set Udeal;

[0120] The second step is to randomly select a region to be processed from Udeal, use the selected region as the comparison region, use the selected region as an element in the set NU, and delete the selected region from Udeal.

[0121] The third step is to calculate the adjacency value of each region to be processed that is adjacent to the comparison region and belongs to Udeal;

[0122] The fourth step is to determine whether the smallest adjacency value meets the set adjacency value threshold. If it does, the region to be processed with the smallest adjacency value is deleted from Udeal, the region to be processed with the smallest adjacency value is stored in NU, and the region to be processed with the smallest adjacency value is used as the new comparison region. Then proceed to the third step. If not, proceed to the fifth step.

[0123] Fifth step: Treat the regions corresponding to all elements in NU as a region to be judged;

[0124] Step 6: Clear the elements in NU and proceed to step 2.

[0125] The above calculation process of the present invention mainly involves stitching together regions with similar pixel value features. This amplifies the differences in pixel value features between the regions to be judged and improves the integrity of the areas where geological disasters have occurred. This allows for more accurate identification of areas with geological disasters, which is beneficial to the accuracy of the identification results in the subsequent process of using image recognition algorithms to identify whether a preset type of geological disaster exists.

[0126] Preferably, the adjacency value is obtained as follows:

[0127] Let cmp represent the comparison region, and Ucmp represent the set of all regions to be processed that are adjacent to cmp and belong to Udeal;

[0128] If we use "deal" to represent the region to be processed, then the adjacency value corresponding to "deal" is:

[0129]

[0130] This represents the adjacency value corresponding to the deal. and These are the average pixel values ​​of the pixels in cmp and deal, respectively.

[0131] In some embodiments, the adjacency threshold is set to one-tenth of the average pixel value of the pixels in the second SAR image.

[0132] Preferably, based on the first SAR image, it is determined whether each region to be judged meets the preset judgment conditions, including:

[0133] Let jud2 represent the region to be judged, and let jud1 represent the region where all pixels in the first SAR image have the same coordinates as the pixels in jud2.

[0134] Calculate the judgment value:

[0135]

[0136] This indicates the judgment value corresponding to jud2. This represents the total number of pixels in jud2 that satisfy the following inequality:

[0137]

[0138] This represents the pixel value of pixel j in jud2. pixlm represents the pixel value of the pixel with the same coordinates as pixel j in the first SAR image, and pixel j represents the maximum pixel value of the pixel in the second SAR image. This represents the total number of pixels in jud2;

[0139] like If the value is greater than the preset threshold, it means that jud2 meets the preset judgment condition.

[0140] In the process of determining whether the area to be judged meets the preset judgment conditions, the present invention filters the pixels in jud2 by setting inequalities. This allows the judgment value to be larger when the range of pixels in the second SAR image with more changes in pixel value compared to the pixel value in the first SAR image is larger, thereby identifying areas with a high probability of geological disaster events as the shooting area.

[0141] In some embodiments, the preset judgment threshold can be 0.05.

[0142] Preferably, the visible light image is identified to determine whether a predetermined type of geological hazard exists in the visible light image, including:

[0143] The visible light image is input into a pre-trained recognition model for identification, to determine whether there is a preset type of geological disaster in the visible light image.

[0144] In some embodiments, the pre-trained recognition model can be a CNN or an FCN.

[0145] CNNs excel at automatically extracting features from images, and are particularly well-suited for complex pattern recognition in SAR images. By training a deep convolutional network, a CNN can learn high-level features of disaster areas (such as texture and morphological changes) and perform disaster area identification and segmentation.

[0146] FCN is a network designed for pixel-level segmentation tasks, suitable for pixel-level segmentation of disaster areas in SAR images. It can accurately identify the boundaries of geological disaster areas and is widely used in the detection of geological disasters such as floods and landslides.

[0147] In some embodiments, the preset type of geological hazard includes landslides, fissures, etc.

[0148] Preferably, the formula for calculating the cluster value is:

[0149]

[0150] The clustering value of the shooting region s, The judgment value corresponding to s. This represents the maximum value of the judgment values ​​corresponding to all shooting areas. Let s represent the area. This represents the maximum area of ​​all shooting areas. numl represents the total number of other shooting areas adjacent to s, and numl represents the total number of all shooting areas. , and These are the weights for the influence of the judgment value, the area, and the quantity, respectively.

[0151] Since the judgment of whether the area to be judged meets the preset judgment conditions is based on the judgment value, the present invention uses the area to be judged that meets the judgment value greater than the preset judgment value threshold as the shooting area. Therefore, each shooting area has a corresponding area to be judged, and the judgment value of the area to be judged is the judgment value of the corresponding shooting area.

[0152] The clustering value of this invention comprehensively considers several aspects, including the judgment value, area, and the state of adjacent regions. Therefore, if the judgment value of s is larger, the area is smaller, and the number of adjacent shooting areas is greater, the corresponding clustering value is larger. In this way, it can increase the probability of prioritizing shooting areas with a high probability of geological disaster events, while avoiding the shooting areas corresponding to the clustering values ​​in the clusters being too scattered during subsequent clustering, shortening the total flight distance, and further improving the efficiency of the shooting process.

[0153] This invention further classifies the shooting area through clustering values. Therefore, while maximizing shooting efficiency, it prioritizes shooting areas with a high probability of geological disasters.

[0154] In some embodiments, the weights of the judgment value, area, and quantity can be 0.5, 0.3, and 0.2, respectively.

[0155] Preferably, such as Figure 2 The image is captured by photographing the area corresponding to the clustering value in CA, and a visible light image is obtained, including:

[0156] Store the shooting areas corresponding to the cluster values ​​in CA into set SA;

[0157] Find the shortest path PA that traverses all shooting areas in PA;

[0158] Based on PA, all shooting areas in SA are captured to obtain visible light images corresponding to all shooting areas in SA.

[0159] The shortest path can be found using Dijkstra's algorithm.

[0160] In some embodiments, during shooting, the drone device flies to the center of the area corresponding to the shooting area in actual space and shoots vertically downwards to obtain a visible light image.

[0161] In addition, the method for capturing images of the areas corresponding to the cluster values ​​in CB to obtain visible light images is the same as the method for capturing images of the areas corresponding to the cluster values ​​in CA to obtain visible light images.

[0162] In some embodiments, images are taken of all shooting areas in the SA based on the PA to obtain visible light images corresponding to all shooting areas in the SA, including:

[0163] The PA flies sequentially to each shooting area in the SA to take pictures, and acquires the visible light image corresponding to each shooting area in the SA.

[0164] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A geological disaster detection system based on aerial photography, characterized in that, This includes SAR image acquisition devices, SAR image processing devices, unmanned aerial vehicle (UAV) devices, and geological disaster detection devices; The SAR image acquisition device is used to acquire a first SAR image and a second SAR image of the geological disaster detection area, wherein the first SAR image was captured earlier than the second SAR image. The SAR image processing device is used to obtain the shooting area based on the first SAR image and the second SAR image; The drone device is used to photograph the area being photographed and acquire visible light images; The geological hazard detection device is used to identify visible light images and determine whether there are geological hazards of a preset type in the visible light images; This includes capturing images of the shooting area to obtain visible light images, including: Calculate the clustering value for each shooting area separately; Based on the clustering values, a clustering algorithm is used to divide all clustering values ​​into two clusters; Obtain the average of the cluster values ​​in the two clusters respectively; Let CA represent the cluster with the larger average cluster value, and CB represent the other cluster. First, take pictures of the shooting areas corresponding to the cluster values ​​in CA to obtain visible light images, and then take pictures of the shooting areas corresponding to the cluster values ​​in CB to obtain visible light images; The captured area is obtained based on the first SAR image and the second SAR image, including: The second SAR image is divided into partitions to obtain multiple regions to be judged. Based on the first SAR image, determine whether each region to be judged meets the preset judgment conditions, and take the region to be judged that meets the preset judgment conditions as the shooting area. The second SAR image is partitioned to obtain multiple regions to be judged, including: Calculate the zoning control coefficients; The second SAR image is partitioned based on the partition control coefficient to obtain multiple regions to be judged. The formula for calculating the zoning control coefficient is: The scp represents the partition control coefficient of the second SAR image, scp represents the set of pixels in the second SAR image, and nscp represents the total number of pixels in the scp. This represents the pixel value of pixel i in the SCP. This indicates the preset reference value. This represents the preset baseline value; The second SAR image is partitioned based on the partition control coefficient to obtain multiple regions to be judged, including: Calculate the length of the region to be judged using the following formula: Calculate the width of the region to be judged using the following formula: Where Lth and Wth represent the length and width of the region to be judged, respectively, and Lbs and Wbs represent the preset length and width, respectively; The second SAR image is divided into multiple regions of length Lth and width Wth to be processed; The region to be processed is processed to generate the region to be judged, thus obtaining the region to be judged. The formula for calculating cluster values ​​is: The clustering value of the shooting region s, The judgment value corresponding to s. This represents the maximum value of the judgment values ​​corresponding to all shooting areas. Let s represent the area. This represents the maximum area of ​​all shooting areas. numl represents the total number of other shooting areas adjacent to s, and numl represents the total number of all shooting areas. , and These are the weights influenced by the judgment value, the area, and the quantity, respectively. Based on the first SAR image, each region to be judged is determined to meet the preset judgment conditions, including: Let jud2 represent the region to be judged, and let jud1 represent the region where all pixels in the first SAR image have the same coordinates as the pixels in jud2. Calculate the judgment value: This indicates the judgment value corresponding to jud2. This represents the total number of pixels in jud2 that satisfy the following inequality: This represents the pixel value of pixel j in jud2. pixlm represents the pixel value of the pixel with the same coordinates as pixel j in the first SAR image, and pixel j represents the maximum pixel value of the pixel in the second SAR image. This represents the total number of pixels in jud2; like If the value is greater than the preset threshold, it means that jud2 meets the preset judgment condition.

2. The geological disaster detection system based on aerial photography according to claim 1, characterized in that, SAR image acquisition devices include Earth observation remote sensing satellites carrying synthetic aperture radar; Earth observation remote sensing satellites carrying synthetic aperture radar are used to image geological hazard detection areas using synthetic aperture radar, and to acquire first SAR images and second SAR images of the geological hazard detection areas.

3. The geological disaster detection system based on aerial photography according to claim 1, characterized in that, The region to be processed is subjected to a region-to-be-determined generation process to obtain the region to be-determined, including: The first step is to treat all regions to be processed as elements of the set Udeal; The second step is to randomly select a region to be processed from Udeal, use the selected region as the comparison region, use the selected region as an element in the set NU, and delete the selected region from Udeal. The third step is to calculate the adjacency value of each region to be processed that is adjacent to the comparison region and belongs to Udeal; The fourth step is to determine whether the smallest adjacency value meets the set adjacency value threshold. If it does, the region to be processed with the smallest adjacency value is deleted from Udeal, the region to be processed with the smallest adjacency value is stored in NU, and the region to be processed with the smallest adjacency value is used as the new comparison region. Then proceed to the third step. If not, proceed to the fifth step. Fifth step: Treat the regions corresponding to all elements in NU as a region to be judged; Step 6: Clear the elements in NU and proceed to step 2.

4. The geological disaster detection system based on aerial photography according to claim 3, characterized in that, The adjacency value is obtained as follows: Let cmp represent the comparison region, and Ucmp represent the set of all regions to be processed that are adjacent to cmp and belong to Udeal; If we use "deal" to represent the region to be processed, then the adjacency value corresponding to "deal" is: This represents the adjacency value corresponding to the deal. and These are the average pixel values ​​of the pixels in cmp and deal, respectively.

5. The geological disaster detection system based on aerial photography according to claim 1, characterized in that, The visible light image is identified to determine whether a pre-defined type of geological hazard exists in the image, including: The visible light image is input into a pre-trained recognition model for identification, to determine whether there is a preset type of geological disaster in the visible light image.

Images