Method, apparatus, electronic device and medium for determining landslide risk based on images

Abstract

The present application provides a method, apparatus, electronic device and medium for determining landslide risk based on images. The method includes: obtaining an image of an active landslide to be identified corresponding to a target area; determining identification areas of different levels corresponding to the image of the active landslide to be identified; obtaining a change rate of a first surface fracture rate of a first identification area corresponding to the image of the active landslide to be identified, and obtaining a change rate of a second surface fracture rate of a second identification area corresponding to the image of the active landslide to be identified; determining a landslide risk level of the image of the active landslide to be identified according to the change rate of the first surface fracture rate and the change rate of the second surface fracture rate. By dividing the image of the active landslide to be identified into identification areas of different levels, the present application avoids the misjudgment problem caused by the overall analysis of the image of the active landslide to be identified, improves the accuracy and efficiency of landslide risk determination, reduces the cost in the process of landslide risk determination, and the method involves fewer parameters and is simple and easy to use.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular, to a method, device, electronic device, and medium for determining landslide risk based on images. Background Art

[0002] With the continuous development of artificial intelligence technology, among which, machine learning technology and image recognition technology have also developed rapidly in the field of geological disaster recognition. For example, machine learning technology and image recognition technology have been widely used in geological disaster monitoring.

[0003] For landslide geological disasters, in the related art, the entire landslide image is often identified and analyzed through landslide image recognition technology, which is easily affected by non-landslide features, and quarries or artificial excavation disturbances are identified as landslides, resulting in the problem of landslide misjudgment. Furthermore, the accuracy and efficiency of landslide risk determination are reduced. To avoid the problem of landslide misjudgment, the corresponding model is improved. However, the model involves too many parameters and is too complex to use, increasing the cost of landslide image data acquisition and analysis applications. Therefore, how to improve the accuracy and efficiency of landslide risk determination and reduce the cost in the process of landslide risk determination has become an urgent problem to be solved. Summary of the Invention

[0004] The purpose of this application is to solve at least one of the technical problems in the above technologies to some extent.

[0005] The first aspect of this application provides a method for determining landslide risk based on images, including: obtaining an image of an active landslide to be identified corresponding to a target area; determining different levels of identification areas corresponding to the image of the active landslide to be identified; obtaining a change rate of the first surface fracture rate of the first identification area corresponding to the image of the active landslide to be identified, and obtaining a change rate of the second surface fracture rate of the second identification area corresponding to the image of the active landslide to be identified; determining the landslide risk level of the image of the active landslide to be identified according to the change rate of the first surface fracture rate and the change rate of the second surface fracture rate.

[0006] The method for determining landslide risk based on images provided by the first aspect of this application also has the following technical features, including:

[0007] According to an embodiment of this application, the obtaining of the image of the active landslide to be identified corresponding to the target area includes: determining the active landslide area in the target area through spaceborne synthetic aperture radar interferometry (InSAR) technology; collecting an image of the active landslide area based on an image acquisition device, and using the collected image of the active landslide area as the image of the active landslide to be identified.

[0008] According to an embodiment of the present application, determining different-level recognition regions corresponding to the image of the landslide to be recognized includes: recognizing the image of the landslide to be recognized, obtaining the landslide boundary corresponding to the image of the landslide to be recognized, and determining the landslide body region of the image of the landslide to be recognized from the landslide boundary; determining different-level recognition regions corresponding to the image of the landslide to be recognized according to the landslide boundary, the landslide body region, and the image of the landslide to be recognized.

[0009] According to an embodiment of the present application, determining different-level recognition regions corresponding to the image of the landslide to be recognized according to the landslide boundary, the landslide body region, and the image of the landslide to be recognized includes: obtaining a first sub-recognition region formed by the first preset width outside the landslide boundary and the landslide boundary, and a second sub-recognition region formed by the second preset width inside the landslide boundary and the landslide boundary, and taking the first sub-recognition region and the second sub-recognition region as the first recognition region; taking the region in the landslide body region except the second sub-recognition region as the second recognition region, and taking the region in the image of the landslide to be recognized except the first recognition region and the second recognition region as the third recognition region.

[0010] According to an embodiment of the present application, obtaining the change rate of the first surface crack rate of the first recognition region corresponding to the image of the landslide to be recognized, and obtaining the change rate of the second surface crack rate of the second recognition region corresponding to the image of the landslide to be recognized includes: obtaining the first surface crack rate of the first recognition region and the second surface crack rate of the second recognition region, and obtaining the first initial surface crack rate of the first recognition region and the second initial surface crack rate of the second recognition region; determining the change rate of the first surface crack rate according to the first surface crack rate and the first initial surface crack rate, and determining the change rate of the second surface crack rate according to the second surface crack rate and the second initial surface crack rate.

[0011] According to an embodiment of the present application, obtaining the first surface crack rate of the first recognition region and the second surface crack rate of the second recognition region includes: performing binarization processing on the image of the landslide to be recognized, obtaining the total number of pixels of the binarized image of the landslide to be recognized, the total number of first black pixels of the first recognition region, and the total number of second black pixels of the second recognition region; obtaining the first ratio of the total number of first black pixels to the total number of pixels, and taking the first ratio as the first surface crack rate; obtaining the second ratio of the total number of second black pixels to the total number of pixels, and taking the second ratio as the second surface crack rate.

[0012] According to an embodiment of the present application, determining the landslide risk level of the landslide image to be recognized according to the change rate of the first surface fracture rate and the change rate of the second surface fracture rate includes: obtaining a threshold value of the change rate of the surface fracture rate; in response to the change rate of the first surface fracture rate being greater than the threshold value of the change rate of the surface fracture rate, determining that the landslide risk level of the landslide image to be recognized is high; or, in response to the change rate of the first surface fracture rate being less than or equal to the threshold value of the change rate of the surface fracture rate and the change rate of the second surface fracture rate being greater than the threshold value of the change rate of the surface fracture rate, determining that the landslide risk level of the landslide image to be recognized is medium; or, in response to the change rate of the first surface fracture rate being less than or equal to the threshold value of the change rate of the surface fracture rate and the change rate of the second surface fracture rate being less than or equal to the threshold value of the change rate of the surface fracture rate, determining that the landslide risk level of the landslide image to be recognized is low.

[0013] A device for determining landslide risk based on images according to a second aspect of the present application includes: a first acquisition module for acquiring a landslide image to be recognized corresponding to a target area; a first determination module for determining recognition areas of different levels corresponding to the landslide image to be recognized; a second acquisition module for acquiring a change rate of the first surface fracture rate of the first recognition area corresponding to the landslide image to be recognized and acquiring a change rate of the second surface fracture rate of the second recognition area corresponding to the landslide image to be recognized; a second determination module for determining the landslide risk level of the landslide image to be recognized according to the change rate of the first surface fracture rate and the change rate of the second surface fracture rate.

[0014] A device for determining landslide risk based on images according to a second aspect of the present application further has the following technical features, including:

[0015] According to an embodiment of the present application, the device is further configured to: pre-build a template image database, where the template image database includes various types of images.

[0016] According to an embodiment of the present application, the first acquisition module is further configured to: determine an active landslide area in the target area through spaceborne synthetic aperture radar interferometry (InSAR) technology; collect an image of the active landslide area based on an image acquisition device, and use the collected image of the active landslide area as the landslide image to be recognized.

[0017] According to an embodiment of the present application, the first determination module is further configured to: identify the image of the landslide to be identified, obtain the landslide boundary corresponding to the image of the landslide to be identified, and determine the landslide body area of the image of the landslide to be identified from the landslide boundary; determine different levels of identification areas corresponding to the image of the landslide to be identified according to the landslide boundary, the landslide body area, and the image of the landslide to be identified.

[0018] According to an embodiment of the present application, the first determination module is further configured to: obtain a first sub-identification area formed by a first preset width outside the landslide boundary and the landslide boundary, and a second sub-identification area formed by a second preset width inside the landslide boundary and the landslide boundary, and use the first sub-identification area and the second sub-identification area as the first identification area; use the area within the landslide body area except the second sub-identification area as the second identification area, and use the area in the image of the landslide to be identified except the first identification area and the second identification area as the third identification area.

[0019] According to an embodiment of the present application, the second acquisition module is further configured to: obtain a first surface crack rate of the first identification area and a second surface crack rate of the second identification area, and obtain a first initial surface crack rate of the first identification area and a second initial surface crack rate of the second identification area; determine a first surface crack rate change rate according to the first surface crack rate and the first initial surface crack rate, and determine a second surface crack rate change rate according to the second surface crack rate and the second initial surface crack rate.

[0020] According to an embodiment of the present application, the second acquisition module is further configured to: perform binarization processing on the image of the landslide to be identified, and obtain the total number of pixels of the binarized image of the landslide to be identified, the total number of black pixels of the first identification area, and the total number of black pixels of the second identification area; obtain a first ratio of the total number of black pixels of the first identification area to the total number of pixels, and use the first ratio as the first surface crack rate; obtain a second ratio of the total number of black pixels of the second identification area to the total number of pixels, and use the second ratio as the second surface crack rate.

[0021] According to an embodiment of the present application, the second determination module is further configured to: obtain a threshold value of the surface crack rate change rate; in response to the first surface crack rate change rate being greater than the threshold value of the surface crack rate change rate, determine that the landslide risk level of the landslide image to be recognized is high; or, in response to the first surface crack rate change rate being less than or equal to the threshold value of the surface crack rate change rate and the second surface crack rate change rate being greater than the threshold value of the surface crack rate change rate, determine that the landslide risk level of the landslide image to be recognized is medium; or, in response to the first surface crack rate change rate being less than or equal to the threshold value of the surface crack rate change rate and the second surface crack rate change rate being less than or equal to the threshold value of the surface crack rate change rate, determine that the landslide risk level of the landslide image to be recognized is low.

[0022] An embodiment of the third aspect of the present application provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for determining landslide risk based on images provided in the first aspect of the present application.

[0023] An embodiment of the fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions, and the computer instructions are used to cause the computer to execute the method for determining landslide risk based on images provided in the first aspect of the present application.

[0024] An embodiment of the fifth aspect of the present application provides a computer program product, and when the instruction processor in the computer program product executes, it executes the method for determining landslide risk based on images provided in the first aspect of the present application.

[0025] The method and device for determining landslide risk based on images provided by the present application obtain a landslide image to be recognized corresponding to a target area; determine different-level recognition areas corresponding to the landslide image to be recognized; obtain a first surface crack rate change rate of a first recognition area corresponding to the landslide image to be recognized, and obtain a second surface crack rate change rate of a second recognition area corresponding to the landslide image to be recognized; determine the landslide risk level of the landslide image to be recognized according to the first surface crack rate change rate and the second surface crack rate change rate. By dividing the landslide image to be recognized into different-level recognition areas, the present application avoids the misjudgment problem caused by the overall analysis of the landslide image to be recognized, improves the accuracy and efficiency of landslide risk determination, reduces the cost in the process of landslide risk determination, and the method involves fewer parameters and is simple and easy to use.

[0026] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Description of the Drawings

[0027] The above-mentioned and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, wherein:

[0028] Figure 1 is a schematic flowchart of a method for determining landslide risk based on images according to an embodiment of the present application;

[0029] Figure 2 is a schematic diagram of identification areas of different grades for an active landslide image to be identified in the present application;

[0030] Figure 3 is a schematic flowchart of a method for determining landslide risk based on images according to another embodiment of the present application;

[0031] Figure 4 is a schematic flowchart of the landslide boundary corresponding to an active landslide image to be identified in the present application;

[0032] Figure 5 is a schematic diagram of dividing identification areas of different grades for an active landslide image to be identified in the present application;

[0033] Figure 6 is a schematic flowchart of a method for determining landslide risk based on images according to another embodiment of the present application;

[0034] Figure 7 is a schematic flowchart of a method for determining landslide risk based on images according to another embodiment of the present application;

[0035] Figure 8 is a schematic flowchart of a method for determining landslide risk based on images according to another embodiment of the present application;

[0036] Figure 9 is a schematic structural diagram of a device for determining landslide risk based on images according to an embodiment of the present application;

[0037] Figure 10 is a block diagram of an electronic device according to an embodiment of the present application. Detailed Description of the Embodiments

[0038] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0039] The method, device, electronic device, and medium for determining landslide risk based on images according to the embodiments of the present application will be described below with reference to the accompanying drawings.

[0040] Figure 1 It is a flowchart of the method for determining landslide risk based on images according to an embodiment of the present application. As Figure 1 shown, the method includes:

[0041] S101. Obtain the to-be-identified active landslide image corresponding to the target area.

[0042] Among them, the target area can be any area where landslide identification is required.

[0043] It should be noted that in order to improve the efficiency of determining landslide risk, the target area can be analyzed to determine the active landslide area in the target area. Further, images of the active landslide area are collected to obtain the to-be-identified active landslide image.

[0044] It should be noted that the present application does not limit the specific method for obtaining the to-be-identified active landslide image corresponding to the target area, which can be selected according to the actual situation.

[0045] Optionally, the spaceborne synthetic aperture radar interferometry (InSAR) technology can be used to determine the active landslide area in the target area, and based on the image acquisition device, images of the active landslide area are collected, and the collected images of the active landslide area are used as the to-be-identified active landslide images.

[0046] For example, through the spaceborne synthetic aperture radar interferometry InSAR technology, an SAR complex image pair of the same target area can be obtained, and the SAR complex image is analyzed to calculate the terrain, landform, and minute changes on the surface of the target area, and the area with landslides in the high-deformation area of the target area is used as the active landslide area. An unmanned aerial vehicle aerial photography device is used to collect images of the active landslide area, and then the to-be-identified active landslide images are obtained.

[0047] S102. Determine different levels of identification areas corresponding to the to-be-identified active landslide image.

[0048] It should be noted that in the related art, the landslide image recognition technology is often used to recognize and analyze the entire landslide image. It is easily affected by non-landslide features, and quarries or artificial excavation disturbances are recognized as landslides, resulting in the problem of landslide misjudgment. The method for determining the landslide risk based on images proposed in this application, after obtaining the image of the active landslide to be recognized, divides the image of the active landslide to be recognized into different levels of recognition areas, avoiding the misjudgment problem caused by the overall analysis of the image of the active landslide to be recognized.

[0049] In the embodiment of the present application, the image of the active landslide to be recognized is recognized to obtain the landslide boundary corresponding to the image of the active landslide to be recognized. The landslide body area of the image of the active landslide to be recognized is determined from the landslide boundary, and different levels of recognition areas corresponding to the image of the active landslide to be recognized are determined according to the landslide boundary, the landslide body area, and the image of the active landslide to be recognized.

[0050] Optionally, the areas that are prone to landslide phenomena such as crack water gushing (the rear edge of the landslide, both sides of the landslide boundary, and the toe of the slope) can be divided into the first recognition area. Since the boundary crack ranges of landslides of different scales are also different, the middle area of the sliding mass where the image will change but not significantly when there is a trend of sliding failure can be divided into the second recognition area, and the mountain part outside the landslide that does not show obvious changes during the landslide can be divided into the third recognition area.

[0051] For example, as Figure 2 shown, the image of the active landslide to be recognized can be divided into the first recognition area (main recognition area), the second recognition area (secondary recognition area), and the third recognition area (non-recognition area).

[0052] S103, obtain the change rate of the first surface crack rate of the first recognition area corresponding to the image of the active landslide to be recognized, and obtain the change rate of the second surface crack rate of the second recognition area corresponding to the image of the active landslide to be recognized.

[0053] Among them, the first surface crack rate refers to the proportion of cracks (fissures) in the first recognition area, and the second surface crack rate refers to the proportion of cracks (fissures) in the second recognition area.

[0054] It should be noted that the present application does not limit the specific method for obtaining the change rate of the first surface crack rate of the first recognition area corresponding to the image of the active landslide to be recognized, and it can be selected according to the actual situation.

[0055] Optionally, the first surface crack rate of the first recognition area and the first initial surface crack rate of the first recognition area can be obtained, and the change rate of the first surface crack rate can be obtained according to the first surface crack rate and the first initial surface crack rate.

[0056] For example, after obtaining the first surface crack rate δ1 and the first initial surface crack rate δ0, the following formula can be used to obtain the change rate P of the first surface crack rate:

[0057] P = [(δ1 - δ0) / δ0] × 100%

[0058] Where P is the change rate of the first surface crack rate, δ1 is the first surface crack rate, and δ0 is the first initial surface crack rate.

[0059] It should be noted that this application does not limit the specific method for obtaining the change rate of the first surface crack rate of the first recognition area corresponding to the image of the landslide to be identified, and it can be selected according to the actual situation.

[0060] Optionally, the second surface crack rate and the second initial surface crack rate of the second recognition area can be obtained, and based on the second surface crack rate and the second initial surface crack rate, the change rate of the second surface crack rate can be obtained.

[0061] For example, after obtaining the second surface crack rate ζ1 and the second initial surface crack rate ζ0, the following formula can be used to obtain the change rate Q of the second surface crack rate:

[0062] Q = [(ζ1 - ζ0) / ζ0] × 100%

[0063] Where Q is the change rate of the first surface crack rate, ζ1 is the second surface crack rate, and ζ0 is the second initial surface crack rate.

[0064] S104. Determine the landslide risk level of the image of the landslide to be identified based on the change rate of the first surface crack rate and the change rate of the second surface crack rate.

[0065] Optionally, a threshold for the change rate of the surface crack rate can be obtained, and the change rate of the first surface crack rate and the change rate of the second surface crack rate are compared with the threshold for the change rate of the surface crack rate. Based on the comparison results, the landslide risk level of the image of the landslide to be identified is determined.

[0066] It should be noted that this application does not limit the setting of the threshold for the change rate of the surface crack rate, and it can be set according to the actual situation.

[0067] Optionally, the threshold for the change rate of the surface crack rate can be set to 5%.

[0068] For example, when the change rate of the first surface crack rate is greater than the threshold for the change rate of the surface crack rate, it is determined that the landslide risk level of the image of the landslide to be identified is high.

[0069] Further, when the landslide risk level of the active landslide image to be recognized is determined to be high, relevant personnel can be reminded to take corresponding emergency measures to avoid adverse consequences caused by the occurrence of the landslide.

[0070] The method for determining the landslide risk based on images proposed in this application obtains the active landslide image to be recognized corresponding to the target area, determines the recognition areas of different levels corresponding to the active landslide image to be recognized, obtains the change rate of the first surface crack rate of the first recognition area corresponding to the active landslide image to be recognized, and obtains the change rate of the second surface crack rate of the second recognition area corresponding to the active landslide image to be recognized. According to the change rate of the first surface crack rate and the change rate of the second surface crack rate, the landslide risk level of the active landslide image to be recognized is determined. By dividing the active landslide image to be recognized into recognition areas of different levels, this application avoids the misjudgment problem caused by the overall analysis of the active landslide image to be recognized, improves the accuracy and efficiency of landslide risk determination, reduces the cost in the process of landslide risk determination, involves fewer parameters, and is simple and easy to use.

[0071] In the above-mentioned embodiment, regarding the specific process of determining the recognition areas of different levels corresponding to the active landslide image to be recognized, it can be combined with Figure 3 for further understanding. Figure 3 is a schematic flowchart of the method for determining the landslide risk based on images according to another embodiment of this application. As Figure 3 shown, the method includes:

[0072] S301, recognize the active landslide image to be recognized, obtain the landslide boundary corresponding to the active landslide image to be recognized, and determine the landslide body area of the active landslide image to be recognized from the landslide boundary.

[0073] For example, as Figure 4 shown, based on image recognition technology, the active landslide image to be recognized can be recognized to obtain the landslide boundary corresponding to the active landslide image to be recognized.

[0074] Further, after obtaining the landslide boundary, the area composed of the landslide boundary is the landslide body area of the active landslide image to be recognized.

[0075] S202, determine the recognition areas of different levels corresponding to the active landslide image to be recognized according to the landslide boundary, the landslide body area, and the active landslide image to be recognized.

[0076] Optionally, a first sub-recognition area composed of the first preset width outside the landslide boundary and the landslide boundary and a second sub-recognition area composed of the second preset width inside the landslide boundary and the landslide boundary can be obtained, and the first sub-recognition area and the second sub-recognition area are used as the first recognition area.

[0077] Optionally, the area within the landslide body except the second sub-identification area can be used as the second identification area, and the area within the image of the active landslide to be identified except the first identification area and the second identification area can be used as the third identification area.

[0078] It should be noted that the present application does not limit the specific settings of the first preset width and the second preset width, and they can be set according to the actual situation.

[0079] Optionally, the major axis length L of the landslide body area of the image of the active landslide to be identified can be obtained, and L / 10 can be used as the first preset width, and L / 15 can be used as the second preset width.

[0080] For example, as Figure 5 shown, the first sub-identification area formed by the first preset width (L / 10) outside the landslide boundary and the landslide boundary, the second sub-identification area formed by the second preset width (L / 10) inside the landslide boundary and the landslide boundary. The first sub-identification area and the second sub-identification area are used as the first identification area (main identification area), the area within the landslide body except the second sub-identification area is used as the second identification area (secondary identification area), and the area within the image of the active landslide to be identified except the first identification area and the second identification area is used as the third identification area (non-identification area).

[0081] The method for determining the landslide risk based on images proposed in the present application divides the image of the active landslide to be identified into identification areas of different levels, avoiding the misjudgment problem caused by the overall analysis of the image of the active landslide to be identified, and laying a foundation for improving the accuracy and efficiency of landslide risk determination in the subsequent process.

[0082] In the above-mentioned embodiment, regarding the specific process of obtaining the change rate of the first surface crack rate of the first identification area corresponding to the image of the active landslide to be identified and obtaining the change rate of the second surface crack rate of the second identification area corresponding to the image of the active landslide to be identified, it can be combined with Figure 6 for further understanding. Figure 6 This is a schematic flowchart of the method for determining the landslide risk based on images according to another embodiment of the present application. As Figure 6 shown, the method includes:

[0083] S601, obtain the first surface crack rate of the first identification area and the second surface crack rate of the second identification area, and obtain the first initial surface crack rate of the first identification area and the second initial surface crack rate of the second identification area.

[0084] Optionally, images of the active landslide area can be collected by a drone aerial photography device at a first preset time, and then the active landslide images can be obtained to acquire the first initial surface fracture rate of the first identification area and the second initial surface fracture rate of the second identification area. Correspondingly, images of the active landslide area can be collected by the drone aerial photography device at a second preset time to obtain the active landslide images to be identified, so as to acquire the first surface fracture rate of the first identification area and the second surface fracture rate of the second identification area. It can be understood that the first surface fracture rate and the first initial surface fracture rate are the fracture rates of the active landslide images to be identified with a certain time interval, and the second surface fracture rate and the second initial surface fracture rate are the fracture rates of the active landslide images to be identified with a certain time interval.

[0085] For example, the time interval between the first preset time and the second preset time can be set to 15 days. Within the preset time, images of the same active landslide area can be collected by the drone aerial photography device. Among them, the position and shooting angle of the drone aerial photography device should be relatively close, which can be achieved by setting position control points on the ground.

[0086] It should be noted that the present application does not limit the specific method for the first initial surface fracture rate and the second initial surface fracture rate, which can be selected according to the actual situation.

[0087] Optionally, the active landslide images collected at the first preset time can be binarized to obtain the total number of pixels of the binarized active landslide images, the total number of first initial black pixels in the first identification area, and the total number of second initial black pixels in the second identification area. Based on the total number of pixels of the active landslide images, the total number of first initial black pixels in the first identification area, and the total number of second initial black pixels in the second identification area, the first initial surface fracture rate and the second initial surface fracture rate can be obtained.

[0088] For example, after obtaining the total number of first initial black pixels a1, the total number of second initial black pixels a2, and the total number of pixels a, the first initial surface fracture rate δ0 = a1 / a, and the second surface fracture rate ζ0 = a2 / a.

[0089] As a possible implementation, as Figure 7 shown, on the basis of the above embodiment, the specific process of obtaining the first surface fracture rate of the first identification area and the second surface fracture rate of the second identification area in the above step S601 includes the following steps:

[0090] S701, binarize the active landslide images to be identified to obtain the total number of pixels of the binarized active landslide images to be identified, the total number of first black pixels in the first identification area, and the total number of second black pixels in the second identification area.

[0091] Optionally, image analysis technology can be used to obtain the total number of pixels A of the active landslide image to be recognized after binarization processing, the total number of first black pixels A1 in the first recognition area, and the total number of second black pixels A2 in the second recognition area.

[0092] S702, obtain the first ratio of the total number of first black pixels to the total number of pixels, and use the first ratio as the first surface fracture rate.

[0093] In the embodiment of the present application, after obtaining the first ratio of the total number of first black pixels A1 to the total number of pixels A, the first surface fracture rate δ1 = A1 / A.

[0094] S703, obtain the second ratio of the total number of second black pixels to the total number of pixels, and use the second ratio as the second surface fracture rate.

[0095] In the embodiment of the present application, after obtaining the first ratio of the total number of first black pixels A2 to the total number of pixels A, the first surface fracture rate ζ1 = A2 / A.

[0096] S602, determine the change rate of the first surface fracture rate according to the first surface fracture rate and the first initial surface fracture rate, and determine the change rate of the second surface fracture rate according to the second surface fracture rate and the second initial surface fracture rate.

[0097] For example, after obtaining the first surface fracture rate δ1 and the first initial surface fracture rate δ0, the following formula can be used to obtain the change rate P of the first surface fracture rate:

[0098] P = [(δ1 - δ0) / δ0] × 100%

[0099] Wherein, P is the change rate of the first surface fracture rate, δ1 is the first surface fracture rate, and δ0 is the first initial surface fracture rate.

[0100] For example, after obtaining the second surface fracture rate δ1 and the second initial surface fracture rate δ0, the following formula can be used to obtain the change rate Q of the second surface fracture rate:

[0101] Q = [(ζ1 - ζ0) / ζ0] × 100%

[0102] Wherein, Q is the change rate of the first surface fracture rate, ζ1 is the second surface fracture rate, and ζ0 is the second initial surface fracture rate.

[0103] The method for determining landslide risk based on images proposed in the present application lays a foundation for subsequent judgment of landslide risk levels by obtaining the change rate of the first surface fracture rate corresponding to the first recognition area and the change rate of the second surface fracture rate corresponding to the second recognition area.

[0104] In the above embodiments, regarding the specific process of determining the landslide risk level of the landslide image to be identified according to the change rate of the first surface fracture rate and the change rate of the second surface fracture rate, it can be combined with Figure 8 for further understanding. Figure 8 As shown in Figure 8 the flowchart of the method for determining the landslide risk based on an image according to another embodiment of the present application.

[0105] S801, obtain the threshold value of the change rate of the surface fracture rate.

[0106] It should be noted that the present application does not limit the setting of the threshold value of the change rate of the surface fracture rate, and it can be selected according to the actual situation.

[0107] Optionally, the threshold value of the change rate of the surface fracture rate can be set to 0.5%.

[0108] S802, in response to the change rate of the first surface fracture rate being greater than the threshold value of the change rate of the surface fracture rate, determine that the landslide risk level of the landslide image to be identified is high.

[0109] It should be noted that when the change rate of the first surface fracture rate is greater than the threshold value of the change rate of the surface fracture rate, that is, Q > 0.5%, it indicates that relatively obvious new cracks have occurred near the landslide boundary of the landslide image to be identified, and the trend of sliding is relatively obvious, and the landslide risk level is high.

[0110] S803, in response to the change rate of the first surface fracture rate being less than or equal to the threshold value of the change rate of the surface fracture rate, and the change rate of the second surface fracture rate being greater than the threshold value of the change rate of the surface fracture rate, determine that the landslide risk level of the landslide image to be identified is medium.

[0111] It should be noted that when the change rate of the first surface fracture rate is less than or equal to the threshold value of the change rate of the surface fracture rate and the change rate of the second surface fracture rate is greater than the threshold value of the change rate of the surface fracture rate, that is, Q ≤ 0.5% and P > 0.5%, it indicates that debris movement or human engineering activities may have occurred, and the landslide risk level is medium.

[0112] S804, in response to the change rate of the first surface fracture rate being less than or equal to the threshold value of the change rate of the surface fracture rate, and the change rate of the second surface fracture rate being less than or equal to the threshold value of the change rate of the surface fracture rate, determine that the landslide risk level of the landslide image to be identified is low.

[0113] It should be noted that when the change rate of the first surface fracture rate is less than or equal to the threshold value of the change rate of the surface fracture rate, and the change rate of the second surface fracture rate is less than or equal to the threshold value of the change rate of the surface fracture rate, that is, Q ≤ 0.5% and P ≤ 0.5%, it indicates that the debris is in a stable state, and the landslide risk level is low.

[0114] It should be noted that geological disasters have an important impact on the safe operation of hydropower stations. In areas with drastic topographical changes, frequent earthquake disasters, and complex stratum conditions, there are many slopes, especially high and steep slopes, where it is extremely easy to form loose surfaces, and there are a large number of loose debris and accumulations inside. Such loose soil slopes in the reservoir area are washed and transported during heavy rain in the rainy season, and are in a continuous process of instability and convergence. They are high-incidence areas of landslides. Under the influence of landslide disasters, there are generally safety risks in the hydropower project buildings and reservoirs. Therefore, in order to avoid adverse consequences such as damage to the buildings and surges caused by landslides, combined with image recognition technology, a method for determining landslide risk based on images is proposed, which can be applied to landslide monitoring in the reservoir area of hydropower stations with complex geological conditions where it is difficult to carry out manual monitoring and investigation of geological disasters, and is of great significance to the safe operation of hydropower stations.

[0115] The method for determining landslide risk based on images proposed in this application divides the image of the active landslide to be recognized into different levels of recognition areas, avoiding the misjudgment problem caused by the overall analysis of the image of the active landslide to be recognized, improving the accuracy and efficiency of landslide risk determination, reducing the cost in the process of landslide risk determination, and involving fewer parameters and being simple and easy to use.

[0116] Figure 9 It is a schematic structural diagram of a device for determining landslide risk based on images according to an embodiment of this application. As Figure 9 shown, the device 900 for determining landslide risk based on images includes a first acquisition module 91, a first determination module 92, a second acquisition module 93, and a second determination module 94, where:

[0117] The first acquisition module 91 is used to acquire the image of the active landslide to be recognized corresponding to the target area;

[0118] The first determination module 92 is used to determine different levels of recognition areas corresponding to the image of the active landslide to be recognized;

[0119] The second acquisition module 93 is used to acquire the change rate of the first surface crack ratio of the first recognition area corresponding to the image of the active landslide to be recognized, and acquire the change rate of the second surface crack ratio of the second recognition area corresponding to the image of the active landslide to be recognized;

[0120] The second determination module 94 is used to determine the landslide risk level of the image of the active landslide to be recognized according to the change rate of the first surface crack ratio and the change rate of the second surface crack ratio.

[0121] A device for determining landslide risk based on images provided in the second aspect of this application also has the following technical features, including:

[0122] According to an embodiment of the present application, the first acquisition module 91 is further configured to: determine the active landslide area in the target area through spaceborne synthetic aperture radar interferometry (InSAR) technology; collect an image of the active landslide area based on an image acquisition device, and use the collected image of the active landslide area as the to-be-identified active landslide image.

[0123] According to an embodiment of the present application, the first determination module 92 is further configured to: identify the to-be-identified active landslide image to obtain the landslide boundary corresponding to the to-be-identified active landslide image, and determine the landslide body area of the to-be-identified active landslide image from the landslide boundary; determine different levels of identification areas corresponding to the to-be-identified active landslide image according to the landslide boundary, the landslide body area, and the to-be-identified active landslide image.

[0124] According to an embodiment of the present application, the first determination module 92 is further configured to: obtain a first sub-identification area formed by a first preset width outside the landslide boundary and the landslide boundary, and a second sub-identification area formed by a second preset width inside the landslide boundary and the landslide boundary, and use the first sub-identification area and the second sub-identification area as the first identification area; use the area in the landslide body area except the second sub-identification area as the second identification area, and use the area in the to-be-identified active landslide image except the first identification area and the second identification area as the third identification area.

[0125] According to an embodiment of the present application, the second acquisition module 93 is further configured to: obtain a first surface crack rate of the first identification area and a second surface crack rate of the second identification area, and obtain a first initial surface crack rate of the first identification area and a second initial surface crack rate of the second identification area; determine a first surface crack rate change rate according to the first surface crack rate and the first initial surface crack rate, and determine a second surface crack rate change rate according to the second surface crack rate and the second initial surface crack rate.

[0126] According to an embodiment of the present application, the second acquisition module 93 is further configured to: perform binarization processing on the to-be-identified active landslide image to obtain the total number of pixels of the binarized to-be-identified active landslide image, the total number of black pixels of the first identification area, and the total number of black pixels of the second identification area; obtain a first ratio of the total number of black pixels of the first identification area to the total number of pixels, and use the first ratio as the first surface crack rate; obtain a second ratio of the total number of black pixels of the second identification area to the total number of pixels, and use the second ratio as the second surface crack rate.

[0127] According to an embodiment of the present application, the second determination module 94 is further configured to: obtain a threshold value of the surface crack rate change rate; in response to the first surface crack rate change rate being greater than the threshold value of the surface crack rate change rate, determine that the landslide risk level of the landslide image to be recognized is high; or, in response to the first surface crack rate change rate being less than or equal to the threshold value of the surface crack rate change rate and the second surface crack rate change rate being greater than the threshold value of the surface crack rate change rate, determine that the landslide risk level of the landslide image to be recognized is medium; or, in response to the first surface crack rate change rate being less than or equal to the threshold value of the surface crack rate change rate and the second surface crack rate change rate being less than or equal to the threshold value of the surface crack rate change rate, determine that the landslide risk level of the landslide image to be recognized is low.

[0128] The apparatus for determining landslide risk based on images proposed in the present application obtains a landslide image to be recognized corresponding to a target area, determines different levels of recognition areas corresponding to the landslide image to be recognized, obtains a first surface crack rate change rate of a first recognition area corresponding to the landslide image to be recognized, and obtains a second surface crack rate change rate of a second recognition area corresponding to the landslide image to be recognized. According to the first surface crack rate change rate and the second surface crack rate change rate, the landslide risk level of the landslide image to be recognized is determined. By dividing the landslide image to be recognized into different levels of recognition areas, the present application avoids the misjudgment problem caused by the overall analysis of the landslide image to be recognized, improves the accuracy and efficiency of landslide risk determination, reduces the cost in the process of landslide risk determination, and involves fewer parameters and is simple and easy to use.

[0129] To achieve the above embodiments, the present application further provides an electronic device, a computer-readable storage medium, and a computer program product.

[0130] Figure 10 For the block diagram of the electronic device according to an embodiment of the present application, as Figure 10 shown, the device 1000 includes a memory 101, a processor 102, and a computer program stored on the memory 101 and executable on the processor 102. When the processor 102 executes the program instructions, it implements the method for determining landslide risk based on images according to the Figures 1 to 8 embodiment.

[0131] To implement the above embodiments, the present application further provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the Figures 1 to 8 method for determining landslide risk based on images according to the

[0132] To implement the above embodiments, the present application further provides a computer program product, which, when executed by an instruction processor in the computer program product, executes Figures 1 to 8 the method for determining landslide risk based on images in the embodiments of

[0133] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0134] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically and clearly defined.

[0135] Any process or method description shown in a flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0136] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definitional sequence list of executable instructions for implementing logical functions, which can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in conjunction with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion having one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0137] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0138] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by a program instructing relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0139] In addition, each functional unit in various embodiments of the present application may be integrated into one processing module, may exist independently physically for each unit, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0140] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for determining landslide risk based on images, characterized in that, The method includes: Obtaining an active landslide image to be recognized corresponding to a target area; Determining different-level recognition areas corresponding to the active landslide image to be recognized; Obtaining a change rate of the first surface crack rate of a first recognition area corresponding to the active landslide image to be recognized, and obtaining a change rate of the second surface crack rate of a second recognition area corresponding to the active landslide image to be recognized; Determining a landslide risk level of the active landslide image to be recognized according to the change rate of the first surface crack rate and the change rate of the second surface crack rate; The determining different-level recognition areas corresponding to the active landslide image to be recognized includes: Recognizing the active landslide image to be recognized, obtaining a landslide boundary corresponding to the active landslide image to be recognized, and determining a landslide body area of the active landslide image to be recognized from the landslide boundary; Determining different-level recognition areas corresponding to the active landslide image to be recognized according to the landslide boundary, the landslide body area, and the active landslide image to be recognized; The determining different-level recognition areas corresponding to the active landslide image to be recognized according to the landslide boundary, the landslide body area, and the active landslide image to be recognized includes: Obtaining a first sub-recognition area formed by a first preset width outside the landslide boundary and the landslide boundary, and a second sub-recognition area formed by a second preset width inside the landslide boundary and the landslide boundary, and taking the first sub-recognition area and the second sub-recognition area as a first recognition area; Taking the area in the landslide body area except the second sub-recognition area as a second recognition area, and taking the area in the active landslide image to be recognized except the first recognition area and the second recognition area as a third recognition area.

2. The method according to claim 1, wherein The obtaining an active landslide image to be recognized corresponding to a target area includes: Determining an active landslide area in the target area by using spaceborne synthetic aperture radar interferometry (InSAR) technology; Collecting an image of the active landslide area based on an image acquisition device, and taking the collected image of the active landslide area as the active landslide image to be recognized.

3. The method according to claim 1, characterized in that, The obtaining a change rate of the first surface crack rate of a first recognition area corresponding to the active landslide image to be recognized, and obtaining a change rate of the second surface crack rate of a second recognition area corresponding to the active landslide image to be recognized includes: Obtaining a first surface crack rate of the first recognition area and a second surface crack rate of the second recognition area, and obtaining a first initial surface crack rate of the first recognition area and a second initial surface crack rate of the second recognition area; Determining a change rate of the first surface crack rate according to the first surface crack rate and the first initial surface crack rate, and determining a change rate of the second surface crack rate according to the second surface crack rate and the second initial surface crack rate.

4. The method according to claim 3, wherein The obtaining a first surface crack rate of the first recognition area and a second surface crack rate of the second recognition area includes: Perform binarization processing on the image of the active landslide to be recognized, and obtain the total number of pixels of the image of the active landslide to be recognized after binarization processing, the total number of black pixels in the first recognition area, and the total number of black pixels in the second recognition area; Obtain a first ratio of the total number of the black pixels to the total number of pixels, and use the first ratio as the first surface crack rate; Obtain a second ratio of the total number of the black pixels to the total number of pixels, and use the second ratio as the second surface crack rate.

5. The method according to claim 1, wherein Determining the landslide risk level of the image of the active landslide to be recognized according to the change rate of the first surface crack rate and the change rate of the second surface crack rate includes: Obtain a threshold for the change rate of the surface crack rate; In response to the change rate of the first surface crack rate being greater than the threshold for the change rate of the surface crack rate, determine that the landslide risk level of the image of the active landslide to be recognized is high; or, In response to the change rate of the first surface crack rate being less than or equal to the threshold for the change rate of the surface crack rate and the change rate of the second surface crack rate being greater than the threshold for the change rate of the surface crack rate, determine that the landslide risk level of the image of the active landslide to be recognized is medium; or, In response to the change rate of the first surface crack rate being less than or equal to the threshold for the change rate of the surface crack rate and the change rate of the second surface crack rate being less than or equal to the threshold for the change rate of the surface crack rate, determine that the landslide risk level of the image of the active landslide to be recognized is low.

6. An apparatus for determining landslide risk based on images, characterized in that, The device includes: A first acquisition module for acquiring an image of an active landslide to be recognized corresponding to a target area; A first determination module for determining recognition areas of different levels corresponding to the image of the active landslide to be recognized; A second acquisition module for acquiring a change rate of the first surface crack rate corresponding to the first recognition area of the image of the active landslide to be recognized, and acquiring a change rate of the second surface crack rate corresponding to the second recognition area of the image of the active landslide to be recognized; A second determination module for determining the landslide risk level of the image of the active landslide to be recognized according to the change rate of the first surface crack rate and the change rate of the second surface crack rate; The first determination module is further configured to recognize the image of the active landslide to be recognized, obtain a landslide boundary corresponding to the image of the active landslide to be recognized, and determine a landslide body area of the image of the active landslide to be recognized from the landslide boundary; Determine recognition areas of different levels corresponding to the image of the active landslide to be recognized according to the landslide boundary, the landslide body area, and the image of the active landslide to be recognized; The first determination module is further configured to obtain a first sub-recognition area formed by a first preset width outside the landslide boundary and the landslide boundary and a second sub-recognition area formed by a second preset width inside the landslide boundary and the landslide boundary, and use the first sub-recognition area and the second sub-recognition area as the first recognition area; Use the area within the landslide body area except the second sub-recognition area as the second recognition area, and use the area of the image of the active landslide to be recognized except the first recognition area and the second recognition area as the third recognition area.

7. An electronic device, characterized in that, Includes: At least one processor; And A memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method according to any one of claims 1-5.

8. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are for causing the computer to execute the method according to any one of claims 1-5.

Images