Dam bank deformation patrol method and system based on unmanned aerial vehicle

Abstract

The invention discloses a dam bank deformation patrol method and system based on an unmanned aerial vehicle, and the method comprises the steps: obtaining a dam bank image containing a mark body when the unmanned aerial vehicle flies to a set observation point, and enabling the mark body to be disposed on the surface of a dam bank; extracting a marker body from the dam bank image; calculating the similarity between the marker body and the initial marker body; wherein the initial mark body is a mark body extracted from a dam bank initial image, and the dam bank initial image is a dam bank image obtained when the dam bank does not deform and the unmanned aerial vehicle flies to a set observation point; when the similarity between the mark body and the initial mark body is larger than a set threshold value, it is judged that the dam bank does not deform; when the similarity between the mark body and the initial mark body is smaller than or equal to a set threshold value, it is judged that the dam bank deforms. Rapid and accurate detection of dam bank deformation is realized, and manpower and material resources are greatly saved.

Description

Technical Field

[0001] The present invention relates to the technical field of dam bank deformation monitoring, and in particular to a dam bank deformation inspection method and system based on an unmanned aerial vehicle. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In order to ensure the safety of rivers, lakes, etc., it is necessary to conduct regular inspections of the dam banks of rivers, lakes, etc. so as to promptly understand whether there are any engineering problems such as deformation or collapse of the dam banks.

[0004] Currently, the dam bank is mainly inspected by drones, and images of the dam bank are obtained during the inspection process. The images are then identified through image recognition technology to determine whether the dam bank is deformed or displaced. Since the color of dry-laid or mortar-laid stones on the dam bank slope is relatively dark, and the color of the stones does not change much after deformation and displacement, the accuracy and efficiency of computer-processed image identification to detect problems such as stone displacement and deformation on the engineering slope are low, and identification errors often occur. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a dam bank deformation inspection method and system based on unmanned aerial vehicle, which improves the timeliness, accuracy and efficiency of dam bank deformation judgment.

[0006] To achieve the above object, the present invention adopts the following technical solution:

[0007] First, a dam bank deformation inspection method based on UAV is proposed, including:

[0008] When the UAV flies to the set observation point, an image of the dam bank including the marker is obtained, wherein the marker is set on the surface of the dam bank;

[0009] Extracting landmarks from dam bank images;

[0010] Calculate the similarity between the marker and the initial marker; the initial marker is the marker extracted from the initial image of the dam bank, and the initial image of the dam bank is the image of the dam bank obtained when the drone flies to the set observation point at the initial stage of setting the marker on the dam bank;

[0011] When the similarity between the marker and the initial marker is greater than the set threshold, it is determined that the dam bank has not deformed;

[0012] When the similarity between the marker and the initial marker is less than or equal to the set threshold, it is determined that the dam bank is deformed.

[0013] Furthermore, the marking body includes marking lines and marking points;

[0014] Calculate the similarity between the marking line and the initial marking line, and the similarity between the marking point connection figure and the marking point connection figure;

[0015] When the similarity between the marking line and the initial marking line is less than or equal to the set threshold, or / and the similarity between the marking point connection figure and the marking point connection initial figure is less than or equal to the set threshold, it indicates that the similarity between the marking body and the initial marking body is less than or equal to the set threshold, and it is determined that the dam bank is deformed;

[0016] When the similarity between the marking line and the initial marking line, and the similarity between the marking point connection figure and the marking point connection figure are both greater than the set threshold, it indicates that the similarity between the marking body and the initial marking body is greater than the set threshold, and it is determined that the dam bank has not been deformed.

[0017] Further, the landmark points in the dam bank image are identified, and the pixel coordinates of the identified landmark points are determined;

[0018] When there are unrecognizable landmarks in the dam bank image, it is determined that the dam bank is deformed;

[0019] For the dam bank image that can identify all the landmarks, the dam bank image is corrected according to the pixel coordinates of the identified landmarks to obtain a corrected dam bank image;

[0020] Extract the landmark lines and landmark points from the corrected dam bank image.

[0021] Furthermore, the correction of the dam bank image includes correcting the scale and direction of the dam bank image, so that the scale and direction of the corrected dam bank image are consistent with the scale and direction of the initial dam bank image.

[0022] Furthermore, the viewing angle at which the drone obtains the dam bank image is the same as the viewing angle at which the drone obtains the initial image of the dam bank.

[0023] Furthermore, when it is determined that the dam bank is deformed, an alarm message is issued.

[0024] Secondly, a dam bank deformation inspection system based on UAV is proposed, including:

[0025] An image acquisition unit is used to acquire an image of the dam bank including a marker when the UAV flies to a set observation point, wherein the marker is set on the surface of the dam bank;

[0026] Curve extraction module, used to extract landmarks from dam bank images;

[0027] The similarity calculation module is used to calculate the similarity between the marker and the initial marker; wherein the initial marker is a marker extracted from the initial image of the dam bank, and the initial image of the dam bank is an image of the dam bank obtained when the drone flies to the set observation point when the dam bank is not deformed;

[0028] The dam bank deformation judgment module is used to determine that the dam bank has not been deformed when the similarity between the marker and the initial marker is greater than a set threshold; when the similarity between the marker and the initial marker is less than or equal to the set threshold, determine that the dam bank has been deformed.

[0029] In a third aspect, a computer device is provided, the device comprising:

[0030] a processor adapted to execute a computer program;

[0031] A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, a dam bank deformation inspection method based on a drone proposed in the first aspect is implemented.

[0032] In a fourth aspect, a computer-readable storage medium is proposed, wherein the computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing a drone-based dam bank deformation inspection method proposed in the first aspect.

[0033] In a fifth aspect, a computer program product is proposed, which includes a computer program. When the computer program is executed by a processor, it implements the drone-based dam bank deformation inspection method proposed in the first aspect.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention provides a method and system for inspecting dam bank deformation based on an unmanned aerial vehicle. The method inspects the dam bank through an unmanned aerial vehicle, and during the inspection of the dam bank, when the unmanned aerial vehicle flies along a fixed track line to a set observation point, an image of the dam bank is obtained, and a marker is extracted from the image of the dam bank, and the similarity between the marker and the initial marker is calculated, and whether the dam bank is deformed is judged by the similarity. For the dam bank determined to be deformed, manual background review and on-site inspection are carried out to confirm whether the dam bank is deformed, the degree of deformation and its impact on the safety of the project dam bank, and finally it is determined whether it is necessary to take treatment measures and report the dangerous situation, thereby improving the accuracy and efficiency of judging the deformation of the dam bank, and being able to discover engineering dangerous situations earlier and more efficiently, saving a lot of manpower and material resources.

[0036] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings in the specification, which constitute a part of the present application, are used to provide further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0038] Figure 1 A method for inspecting dam bank deformation based on a drone is disclosed in an embodiment;

[0039] Figure 2 The process of preprocessing the dam bank image disclosed in the embodiment;

[0040] Figure 3 The process of identifying the marker disclosed in the embodiment;

[0041] Figure 4 This is a state diagram of the UAV disclosed in the embodiment when acquiring the dam bank image.

[0042] Among them, 1. Drone, 2. Marking line, 3. Marking point. DETAILED DESCRIPTION

[0043] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0044] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0045] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0046] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0047] Example 1

[0048] With the maturity of drone technology, it has been applied in more and more fields, and it is not uncommon to use drones to carry out related work in the engineering field. However, as an emerging technology, the application of drones is inevitably incompatible with the traditional problem-solving ideas and technical solutions in the engineering field. Therefore, it is necessary to combine the characteristics of emerging technologies and innovate or improve technical routes and technical solutions according to the needs of solving problems. For example, in the application of drones and image recognition technology in dam bank engineering inspections, drones are used to inspect the dam bank, and dam bank images are obtained during the inspection process. Then, the dam bank images are identified through image recognition technology to determine whether the dam bank is deformed or displaced. Because the color of dry masonry or mortar masonry on the dam bank slope is relatively dark, and the color of the stone does not change much after deformation and displacement, the accuracy and efficiency of using computers to process and identify images to find problems such as displacement and deformation of engineering slope stones are low, and recognition errors often occur.

[0049] In order to realize accurate and rapid identification of dam bank deformation, this embodiment proposes a dam bank deformation inspection method based on drones. This method sets markers on the dam bank in advance, and then uses drones to observe whether the markers are deformed to determine whether the dam bank is deformed, thereby realizing accurate and rapid prediction of dam bank deformation.

[0050] A dam bank deformation inspection method based on an unmanned aerial vehicle disclosed in this embodiment is described in detail.

[0051] This embodiment discloses a method for inspecting dam bank deformation based on an unmanned aerial vehicle. Figure 1 As shown, including:

[0052] S1: When the UAV flies to the set observation point, an image of the dam bank including the marker is obtained, wherein the marker is set on the surface of the dam bank;

[0053] S2: Extract landmarks from dam bank images;

[0054] S3: Calculate the similarity between the marker and the initial marker; wherein the initial marker is a marker extracted from the initial image of the dam bank, and the initial image of the dam bank is an image of the dam bank obtained when the UAV flies to the set observation point when the dam bank is not deformed;

[0055] S4: When the similarity between the marker and the initial marker is greater than the set threshold, it is determined that the dam bank has not been deformed;

[0056] When the similarity between the marker and the initial marker is less than or equal to the set threshold, it is determined that the dam bank is deformed.

[0057] The marking body includes marking lines and marking points;

[0058] Calculate the similarity between the marking line and the initial marking line, and the similarity between the marking point connection figure and the marking point connection figure;

[0059] When the similarity between the marking line and the initial marking line is less than or equal to the set threshold, or / and the similarity between the marking point connection figure and the marking point connection initial figure is less than or equal to the set threshold, it indicates that the similarity between the marking body and the initial marking body is less than or equal to the set threshold, and it is determined that the dam bank is deformed;

[0060] When the similarity between the marking line and the initial marking line, and the similarity between the marking point connection figure and the marking point connection figure are both greater than the set threshold, it indicates that the similarity between the marking body and the initial marking body is greater than the set threshold, and it is determined that the dam bank has not been deformed.

[0061] like Figure 4 As shown, in this embodiment, when the dam bank is not deformed, a marker is set on the surface of the dam bank, and the set marker includes a marker line 2 and a marker point 3; the color of the marker line and the marker point is a color that is greatly different from the image grayscale value of the dam bank surface material, so as to improve the accuracy of marker extraction when the marker is extracted from the dam bank image later.

[0062] Preferably, in this embodiment, by applying paint or other dyes, a special color of smooth curve or straight line marking line and relatively fixed marking points are set on the surface of the dam bank slope; the color of the paint is selected to have a large difference in the image grayscale of the slope material, and usually a color with strong reflectivity and strong visual penetration in foggy weather is considered. The marking line is set as a smooth curve or a straight line, which can be parallel to the foot line or form a certain angle with the foot line. The bending direction of the smooth curve should be consistent with the arc direction of the dam slope as much as possible. The marking line parallel to the foot line should be continuous and uninterrupted. The inclined marking line and the foot line should be set at intervals. The interval distance is set according to the height and slope of the dam slope, and is flexibly set according to the curvature of the slope surface, so as to avoid the failure to detect small deformation of the slope surface due to excessive spacing. The inclined marking line should be connected to the shoulder line and the foot line up and down. The marking points are set on the slope. The marking points should be set alternately in two or more rows along the slope. The marking points on the slope are connected in sequence to form a triangle and are continuously arranged according to the length of the slope. In addition, in order to facilitate the UAV to focus and clearly observe the slope marking line, some marking points can be selected or set as the focus target points for the UAV fixed-point observation. The marking points can be set in the form of circle + cross + origin.

[0063] When there is a night patrol mission, markers are set up on the dam bank by painting with fluorescent or night-reflective paint.

[0064] After the marker is set on the dam bank, the embodiment first uses the drone 1 to inspect the dam bank that has not been deformed according to the set cruise route. When the inspection reaches the set observation point, the dam bank image is obtained, and the dam bank image is set as the dam bank initial image; the marker is extracted from the dam bank initial image, and the marker is the initial marker. The initial marker is used as a standard for the dam bank not to be deformed, and is used in the subsequent judgment of dam bank deformation monitoring. Correspondingly, the initial marker includes an initial marker line and an initial marker point; the marker points identified in the dam bank initial image are connected according to the set rules to obtain the marker point connection line initial graph.

[0065] The setting rule is explained by taking the setting of three marking points as an example. The setting rule can connect the marking points end to end to form a triangle; the marking points can also be connected in pairs to form a five-pointed star, etc.

[0066] When the dam bank is inspected regularly in the later stage, the dam bank is inspected by drone according to the set cruise route. When the drone flies to the set observation point, the dam bank image including the marker is obtained, wherein the marker is set on the surface of the dam bank; and the marker is extracted from the dam bank image; then, the similarity between the extracted marker and the initial marker is calculated; based on the similarity, it is determined whether the dam bank has been deformed.

[0067] It should be noted that the cruise route is a pre-set route. When the drone cruises along the cruise route, it can reach all inspection points on the dam bank, thereby achieving all-round inspection of the dam bank.

[0068] The observation point where the UAV obtains the initial image of the dam bank is the same as the observation point where the UAV obtains the image of the dam bank during the later inspection of the dam bank. The viewing angle of the UAV to obtain the image of the dam bank is the same as the viewing angle when the UAV obtains the initial image of the dam bank. In this way, the images of the dam bank obtained by the UAV at the same position and with the same viewing angle are basically consistent. Then, by analyzing the landmarks extracted from the dam bank images, it is possible to accurately judge whether the dam bank has collapsed, slid, sank, or other deformations.

[0069] When the UAV acquires the dam bank image, firstly, a point is selected from the landmark points set on the dam bank as the focus point for the UAV to acquire the dam bank image, the UAV is focused, and the dam bank image is acquired using the focused UAV to ensure the clarity of the acquired dam bank image.

[0070] In this embodiment, after the drone acquires the dam bank image, the landmark points in the dam bank image are identified, and the pixel coordinates of the identified landmark points are determined;

[0071] When there are unrecognizable landmarks in the dam bank image, it is determined that the dam bank is deformed;

[0072] For the dam bank image that can identify all the landmarks, the dam bank image is corrected according to the pixel coordinates of the identified landmarks to obtain a corrected dam bank image;

[0073] Extract the landmark lines and landmark points from the corrected dam bank image.

[0074] The correction of the dam bank image includes correcting the scale and direction of the dam bank image, so that the scale and direction of the corrected dam bank image are consistent with the scale and direction of the initial dam bank image.

[0075] The process of extracting the landmark from the dam bank image in this embodiment is as follows:

[0076] Preprocessing the dam bank image to obtain a preprocessed image;

[0077] The preprocessed image is recognized to obtain the landmark.

[0078] like Figure 2 As shown in the figure, the process of preprocessing the dam bank image includes: graying, enhancing and denoising the acquired dam bank image. Graying can reduce the space occupied by the image without losing the main information of the image and increase the speed of subsequent image processing. Image enhancement makes the main information in the image more prominent. Image denoising is used to remove Gaussian noise and salt and pepper noise in the image to obtain a clear target image, which is convenient for subsequent image processing operations.

[0079] After obtaining the preprocessed image, the preprocessed image is segmented to obtain the marker area, and the mathematical morphological operation is performed on the marker area to make the edge of the marker area smoother; then, the marker points are identified, and the image angle and proportion of the preprocessed image are corrected according to the identified marker points, such as Figure 3 As shown, edge detection is performed on the marker lines and marker points in the corrected dam bank image to obtain the edges of each marker body, and the least squares curve fitting algorithm is used to perform least squares curve fitting on the edge of each marker body to obtain the final marker lines and marker points, and the pixel coordinates of the center point of the marker point and the pixel coordinates of the marker line can be obtained to complete the marker body pixel coordinate positioning.

[0080] After acquiring the marker, this embodiment establishes the marker in MATLAB according to the pixel coordinates of the extracted marker points and marker lines, and then calculates the similarity between the marker and the initial marker. The similarity between the marker and the initial marker includes: the similarity between the marker line and the initial marker line, and the similarity between the marker point connection line figure and the marker point connection line initial figure.

[0081] The correlation coefficient between the marker line and the initial marker line is calculated by the Pearson correlation coefficient, and the similarity between the two marker lines is judged by the correlation coefficient.

[0082] Calculate the length error between each line segment in the landmark point connection figure and the corresponding line segment in the landmark point connection initial figure, and use the largest length error in the landmark point connection figure to judge the similarity between the landmark point connection figure and the landmark point connection initial figure; and the larger the length error, the smaller the similarity between the two figures.

[0083] When the similarity between the marking line and the initial marking line is less than or equal to the set threshold, or / and the similarity between the marking point connection figure and the marking point connection initial figure is less than or equal to the set threshold, it indicates that the similarity between the marking body and the initial marking body is less than or equal to the set threshold, and it is determined that the dam bank is deformed;

[0084] When the similarity between the marking line and the initial marking line, and the similarity between the marking point connection figure and the marking point connection figure are both greater than the set threshold, it indicates that the similarity between the marking body and the initial marking body is greater than the set threshold, and it is determined that the dam bank has not been deformed.

[0085] When determining whether the dam bank has deformed, it is also determined whether the dam bank has deformed locally or as a whole based on the similarity; specifically, when the similarity between the marking line and the initial marking line is less than or equal to the set threshold, it means that the position of the marking line demarcated by the dam bank has been locally deformed; when the similarity between the marking point connection line figure and the marking point connection line initial figure is less than or equal to the set threshold, it means that the dam bank has been deformed as a whole; when the similarity between the marking line and the initial marking line is less than or equal to the set threshold, and the similarity between the marking line and the initial marking line is less than or equal to the set threshold, it means that the position of the marking line demarcated by the dam bank has been locally deformed, and the dam bank has also been deformed as a whole.

[0086] The threshold value can be set according to actual conditions, such as 0.9, 0.8 or 0.85.

[0087] This embodiment also obtains the dam bank number based on the dam bank image; determines the deformed dam bank based on the dam bank number; when it is determined that the dam bank is deformed, an alarm message is issued to remind engineering personnel that the dam bank is deformed, there are engineering hazards or dangerous situations, and manual confirmation is required; after receiving the alarm message, the engineering personnel determine the similarity between the marker and the initial marker to determine whether the marker has undergone a large deformation, and go to the dam bank where the sound is determined to have changed for on-site inspection, so as to finally confirm whether the dam bank has engineering hazards or risks such as deformation; when the engineering personnel confirm that the dam bank has engineering hazards or risks such as deformation, the engineering hazards or risks are reported and handled to eliminate the engineering hazards or risks.

[0088] Preferably, this embodiment issues different alarm messages according to different locations where the dam bank is deformed.

[0089] The present embodiment discloses a dam bank deformation inspection method based on a drone. The method inspects the dam bank through a drone. During the inspection of the dam bank, when the drone flies along a fixed track line to a set observation point, an image of the dam bank is acquired, and a marker is extracted from the image of the dam bank. The similarity between the marker and the initial marker is calculated, and whether the dam bank is deformed is judged by the similarity, thereby improving the accuracy and efficiency of judging the deformation of the dam bank. When it is judged that the dam bank is deformed, the engineering personnel are notified to go to the dam bank site for reconfirmation, thereby further improving the timeliness and accuracy of discovering the deformation of the dam bank, and being able to promptly deal with the deformation of the dam bank to ensure the safety of the dam bank.

[0090] In addition, the present embodiment discloses a dam bank deformation inspection method based on a drone. When judging whether the dam bank is deformed, the evaluation is based on the overall appearance of the marker, which further improves the accuracy of dam bank deformation detection.

[0091] Example 2

[0092] In this embodiment, a dam bank deformation inspection system based on a drone is disclosed, comprising:

[0093] An image acquisition unit is used to acquire an image of the dam bank including a marker when the UAV flies to a set observation point, wherein the marker is set on the surface of the dam bank;

[0094] Curve extraction module, used to extract landmarks from dam bank images;

[0095] The similarity calculation module is used to calculate the similarity between the marker and the initial marker; wherein the initial marker is a marker extracted from the initial image of the dam bank, and the initial image of the dam bank is an image of the dam bank obtained when the drone flies to the set observation point when the dam bank is not deformed;

[0096] The dam bank deformation judgment module is used to determine that the dam bank has not been deformed when the similarity between the marker and the initial marker is greater than a set threshold; when the similarity between the marker and the initial marker is less than or equal to the set threshold, determine that the dam bank has been deformed.

[0097] The present invention also discloses a computer device, which includes:

[0098] a processor adapted to execute a computer program;

[0099] A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, a dam bank deformation inspection method based on a drone disclosed in Example 1 is implemented.

[0100] The present invention also discloses a computer-readable storage medium, which stores a computer program. The computer program is suitable for being loaded by a processor and executing a dam bank deformation inspection method based on a drone disclosed in Example 1.

[0101] The present invention also discloses a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements a dam bank deformation inspection method based on an unmanned aerial vehicle disclosed in Example 1.

[0102] The method disclosed in Example 1 can be directly embodied as a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0103] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0104] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A dam bank deformation inspection method based on drone, characterized in that: include: When the UAV flies to the set observation point, an image of the dam bank including the marker is obtained, wherein the marker is set on the surface of the dam bank; Extracting landmarks from dam bank images; Calculate the similarity between the marker and the initial marker; the initial marker is the marker extracted from the initial image of the dam bank, and the initial image of the dam bank is the image of the dam bank obtained when the drone flies to the set observation point when the dam bank is not deformed; When the similarity between the marker and the initial marker is greater than the set threshold, it is determined that the dam bank has not deformed; When the similarity between the marker and the initial marker is less than or equal to the set threshold, it is determined that the dam bank is deformed.

2. The method for inspecting dam bank deformation based on an unmanned aerial vehicle according to claim 1, characterized in that: The sign body includes a sign line and a sign point; Calculate the similarity between the marking line and the initial marking line, and the similarity between the marking point connection figure and the marking point connection figure; When the similarity between the marking line and the initial marking line is less than or equal to the set threshold, or / and the similarity between the marking point connection figure and the marking point connection initial figure is less than or equal to the set threshold, it indicates that the similarity between the marking body and the initial marking body is less than or equal to the set threshold, and it is determined that the dam bank is deformed; When the similarity between the marking line and the initial marking line, and the similarity between the marking point connection figure and the marking point connection figure are both greater than the set threshold, it indicates that the similarity between the marking body and the initial marking body is greater than the set threshold, and it is determined that the dam bank has not been deformed.

3. The method for inspecting dam bank deformation based on an unmanned aerial vehicle according to claim 2, characterized in that: Identify the landmark points in the dam bank image and determine the pixel coordinates of the identified landmark points; When there are unrecognizable landmarks in the dam bank image, it is determined that the dam bank is deformed; For the dam bank image that can identify all the landmarks, the dam bank image is corrected according to the pixel coordinates of the identified landmarks to obtain a corrected dam bank image; Extract the landmark lines and landmark points from the corrected dam bank image.

4. The method for inspecting dam bank deformation based on an unmanned aerial vehicle according to claim 3, characterized in that: The correction of the dam bank image includes correcting the scale and direction of the dam bank image, so that the scale and direction of the corrected dam bank image are consistent with the scale and direction of the initial dam bank image.

5. The method for inspecting dam bank deformation based on an unmanned aerial vehicle according to claim 1, characterized in that: When it is determined that the dam bank is deformed, an alarm message is issued.

6. The method for inspecting dam bank deformation based on an unmanned aerial vehicle according to claim 1, characterized in that: The viewing angle of the drone to obtain the dam bank image is the same as the viewing angle of the drone to obtain the initial image of the dam bank.

7. A dam bank deformation inspection system based on drones, characterized in that: include: An image acquisition unit is used to acquire an image of the dam bank including a marker when the UAV flies to a set observation point, wherein the marker is set on the surface of the dam bank; Curve extraction module, used to extract landmarks from dam bank images; The similarity calculation module is used to calculate the similarity between the marker and the initial marker; wherein the initial marker is a marker extracted from the initial image of the dam bank, and the initial image of the dam bank is an image of the dam bank obtained when the drone flies to the set observation point when the dam bank is not deformed; The dam bank deformation judgment module is used to determine that the dam bank has not been deformed when the similarity between the marker and the initial marker is greater than a set threshold; when the similarity between the marker and the initial marker is less than or equal to the set threshold, determine that the dam bank has been deformed.

8. An electronic device, characterized in that: The device comprises: a processor adapted to execute a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the method for inspecting dam bank deformation based on a drone as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing a dam bank deformation inspection method based on a drone as described in any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the dam bank deformation inspection method based on a drone as described in any one of claims 1 to 6.

Images