Landslide deformation identification method and device based on image difference

Abstract

The invention provides a landslide deformation identification method and device based on image difference, and relates to the technical field of landslide deformation identification. The method comprises the following steps: building a landslide test model, and collecting a plurality of side slope images; preprocessing the collected slope image, wherein the preprocessing comprises calculation parameter setting, displacement noise filtering and displacement numerical value interpolation; the preprocessed slope image sequence data are analyzed and calculated through the LSPIV technology, and a displacement vector field or a velocity vector field of the surface of a landslide mass in the slope image is obtained; and deformation and movement of the landslide mass are identified through a python-based writing algorithm. According to the invention, through processing the image in the landslide test model video, identification and measurement of landslide deformation and movement in the image sequence are realized, and precision and feasibility are compared with actual deformation. The landslide deformation identification method based on image difference is enriched, and favorable technical support is provided for high-precision and low-cost landslide deformation identification.

Description

Technical Field

[0001] The invention relates to the technical field of landslide deformation recognition, and in particular to a landslide deformation recognition method and device based on image difference. Background Art

[0002] A large number of landslide disasters occur every year around the world, and there are a large number of potential hazards. The deformation displacement of the landslide body is an important early warning indicator of landslides. Traditional landslide deformation displacement monitoring methods have shortcomings such as point measurement and difficulty in equipment installation and maintenance. Although ground-based synthetic aperture radar, ground-based lidar and other methods can achieve surface monitoring, they are expensive and difficult to carry out long-term automated monitoring.

[0003] The image-based landslide monitoring method has the advantages of surface monitoring, remote non-contact, easy implementation, and strong economy. Therefore, it is of high research value to explore the technical method of deformation recognition of landslide images. Summary of the invention

[0004] In view of the limitations of existing landslide deformation recognition technologies, the present invention provides a landslide deformation recognition method and device based on image difference. The technical solution is as follows:

[0005] On the one hand, a landslide deformation identification method based on image difference is provided, and the method comprises the following steps:

[0006] S1. Build a landslide test model and collect multiple slope images;

[0007] S2, preprocessing the collected slope image, including: calculation parameter setting, displacement noise filtering and displacement numerical interpolation;

[0008] S3, analyzing and calculating the pre-processed slope image sequence data by LSPIV technology to obtain the displacement vector field or velocity vector field of the landslide surface in the slope image;

[0009] S4. The deformation and movement of the landslide body are identified through a python-based algorithm.

[0010] Optionally, in step S1, the landslide test model includes a main body, a water flow system and a monitoring system; the main body includes a container box, a base, and a landslide body; the water flow system includes a water source, a water pump, a water inlet, a water outlet, a water inlet valve, a water outlet valve, and a drain; and the monitoring system includes an image acquisition device and a pull-rope displacement meter;

[0011] The container box is a rectangular organic glass open box, which is erected on the base, and the landslide body is contained in the container box; a water inlet and a water outlet are respectively provided at the bottom of both sides of the container box, and the water level in the container box is controlled to rise and fall through the water pump, the water inlet valve and the water outlet valve during the test, so as to provide the power for the landslide body in the landslide test model to slide;

[0012] Three of the pull-rope displacement meters are used, and the measuring ends are respectively buried at three measuring points at the upper part, the middle part and the lower part of the landslide body, to obtain the measuring results as comparison data.

[0013] Optionally, the image acquisition device uses an infrared camera with a fixed position, angle and focal length, and captures no less than two slope images.

[0014] Optionally, the infrared camera is calibrated using Zhang's plane calibration method, and a calibration plate uses a checkerboard calibration plate, and the checkerboard calibration plate is made of a glass plate coated with aluminum oxide.

[0015] Optionally, the step S2 specifically includes:

[0016] S21, calculation parameter setting, including: performing image segmentation on the acquired slope image, and setting the calculation window size, search area size, window pane overlap distance, and iteration step number according to the segmented image;

[0017] S22, displacement noise filtering, including: performing noise filtering on the slope image by a median filtering method, the calculation formula is:

[0018] (1)

[0019] In formula (1), x[n] is the original image signal, y[n] is the filtered image signal, n is the current position, k is the window size, and median represents median filtering;

[0020] S23, displacement numerical interpolation, including: performing displacement numerical interpolation on the slope image by a nearest neighbor interpolation method.

[0021] Optionally, in step S3, analyzing and calculating the pre-processed slope image sequence data by using the LSPIV technology specifically includes:

[0022] The normalized cross-correlation method is used to analyze and calculate the preprocessed slope image sequence data. The calculation formula is as follows:

[0023] (2)

[0024] In formula (2), T(x', y') is the pixel value at the point (x', y') in the slope image to be matched, I(x, y) is the pixel value at the point (x, y) in the original slope image, and R ccorr_normed (x,y) represents the cross-correlation calculation result;

[0025] According to the calculation results, the displacement vector field or velocity vector field of the landslide surface in the slope image is obtained.

[0026] Optionally, in step S4, a rectangular frame of the same size as the calculation window is drawn with the pixel point as the center point of the rectangular area through a python-based algorithm, and the calculation result of LSPIV is processed to obtain the deformation and movement range of the landslide body.

[0027] On the other hand, a landslide deformation identification device based on image difference is provided, which is used to implement any of the above methods, and the device includes:

[0028] Image acquisition module, used to build a landslide test model and collect multiple slope images;

[0029] The image processing module is used to pre-process the collected slope images, including: calculation parameter setting, displacement noise filtering and displacement numerical interpolation;

[0030] An analysis and calculation module is used to analyze and calculate the pre-processed slope image sequence data through the LSPIV technology to obtain the displacement vector field or velocity vector field of the landslide surface in the slope image;

[0031] The recognition module is used to identify the deformation and movement of landslides through a Python-based algorithm.

[0032] In another aspect, an electronic device is provided, the electronic device comprising:

[0033] processor;

[0034] A memory having computer-readable instructions stored therein, wherein when the computer-readable instructions are loaded and executed by the processor, the steps of the above-mentioned landslide deformation identification method are implemented.

[0035] On the other hand, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores program codes, and the program codes can be called by a processor to execute the steps of the above-mentioned landslide deformation identification method.

[0036] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0037] The present invention collects multiple slope images and performs preprocessing, including calculation parameter setting, displacement noise filtering and displacement numerical interpolation, analyzes and calculates the image sequence data through the LSPIV technology, comprehensively and accurately measures the displacement vector field or velocity vector field of the landslide surface in the slope image, and identifies the deformation and movement of the landslide through a python-based algorithm based on the obtained vector field. The present invention processes the images in the indoor landslide test model video to achieve the identification and measurement of the landslide deformation and movement in the image sequence, and compares the accuracy and feasibility with the actual deformation. The method can also be used for image processing in real landslide videos. The present invention enriches the landslide deformation identification method based on image difference, and provides favorable technical support for high-precision and low-cost landslide deformation identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 It is a flow chart of a landslide deformation identification method based on image difference provided by an embodiment of the present invention;

[0040] Figure 2 is a schematic diagram of a landslide test model provided by an embodiment of the present invention;

[0041] Figure 3 is a bar graph of indoor test calibration errors provided by an embodiment of the present invention;

[0042] Figure 4 Schematic diagram of a two-dimensional normalized cross-correlation calculation process provided by an embodiment of the present invention;

[0043] FIG. 5 (a) and FIG. 5 (b) are the displacement vector diagram and cloud diagram of the landslide body at a certain moment in the indoor test provided by the embodiment of the present invention;

[0044] Figure 6 It is a scatter plot of the x- and y-direction components of the landslide displacement at a certain moment in an indoor test provided by an embodiment of the present invention;

[0045] Figure 7 is a schematic diagram of a landslide deformation identification process provided by an embodiment of the present invention;

[0046] FIG8 (a) and FIG8 (b) are schematic diagrams of LSPIV velocity measurement results and displacement results of point No. 1 provided in an embodiment of the present invention;

[0047] FIG9 (a) and FIG9 (b) are schematic diagrams of LSPIV velocity measurement results and displacement results of point No. 2 provided by an embodiment of the present invention;

[0048] FIG. 10 (a) and FIG. 10 (b) are schematic diagrams of LSPIV velocity measurement results and displacement results at point 3 provided by an embodiment of the present invention;

[0049] Fig.11 It is a structural schematic diagram of a landslide deformation identification device based on image difference provided by an embodiment of the present invention;

[0050] Fig.12 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a concrete way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two. In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the distinction between them is not emphasized, the meanings to be expressed are consistent.

[0053] The embodiment of the present invention provides a landslide deformation recognition method based on image difference, which can be implemented by an electronic device, and the electronic device can be a terminal or a server. Figure 1 As shown, the processing flow of the method may include the following steps:

[0054] S1. Build a landslide test model and collect multiple slope images.

[0055] refer to Figure 2As shown, the landslide test model includes a main body, a water flow system and a monitoring system. The main body includes a container box 1, a base, and a landslide body 2. The container box 1 is a rectangular organic glass open box, which is erected on the base. The container box 1 contains the landslide body 2. The container box 1 is 2.2 meters long, 1 meter wide, and 1.2 meters high, and is not covered. The soil of the landslide body 2 contained therein is about 2.2 meters long, 1 meter wide, and 0.8 meters high, with a surface slope of about 40°.

[0056] The water flow system includes a water source, a water pump, a water inlet, a water outlet, a water inlet valve, a water outlet valve, and a water drain. A water inlet and a water outlet are provided at the bottom of both sides of the container box 1. During the test, the water level in the container box 1 is controlled by the water pump, the water inlet valve, and the water outlet valve to slowly rise to a height of about 400 mm in about 15 hours, and then drop to the bottom of the container box 1 at the same speed, thereby providing the power for the landslide body 2 in the landslide test model to slide.

[0057] The monitoring system includes an image acquisition device 3 and a pull-wire displacement meter 4. The measuring ends of the three pull-wire displacement meters 4 are respectively buried at three measuring points at the upper part, the middle part and the lower part of the landslide body 2 to obtain the measurement results as comparison data.

[0058] In the embodiment of the present invention, the image acquisition device 1 uses an infrared camera with a fixed position, angle and focal length, and takes no less than two slope images.

[0059] The infrared camera is calibrated using Zhang's plane calibration method, and the calibration plate uses a checkerboard calibration plate, which is made of a glass plate coated with aluminum oxide, has the characteristics of diffuse light, opacity, and non-deformation. The model is GP200, with an overall size of 200×200mm, a checkerboard pattern array of 12×9, a pattern size of 180×135mm, a single color block side length of 15mm, and an accuracy of ±0.01mm.

[0060] Through Zhang's plane calibration method, the average calibration error calculated by feature point remapping is only 0.06 pixels, and the maximum error value is only 0.09 pixels. Figure 3 shown.

[0061] S2. Preprocessing the collected slope image, including: setting calculation parameters, displacement noise filtering and displacement numerical interpolation. The preprocessing specifically includes:

[0062] S21, calculation parameter setting, including: performing image segmentation on the acquired slope image, and setting the calculation window size, search area size, window pane overlap distance and iteration step number according to the segmented image.

[0063] S22, displacement noise filtering, including: performing noise filtering on the slope image by a median filtering method, the calculation formula is:

[0064] (1)

[0065] In formula (1), x[n] is the original image signal, y[n] is the filtered image signal, n is the current position, k is the window size, and median represents median filtering.

[0066] It should be noted that, by comparing different filtering methods, including standard deviation filtering, median filtering, correlation coefficient threshold filtering, etc., the present invention selects the median filtering method with the best filtering effect to perform noise filtering on the slope image.

[0067] S23, displacement numerical interpolation, including: performing displacement numerical interpolation on the slope image by a nearest neighbor interpolation method.

[0068] S3, analyzing and calculating the preprocessed slope image sequence data by LSPIV technology to obtain the displacement vector field or velocity vector field of the landslide surface in the slope image. In the embodiment of the present invention, the displacement vector field or velocity vector field is represented by a vector diagram, also called a displacement vector diagram or a velocity vector diagram.

[0069] Among them, the normalized cross-correlation method is used to analyze and calculate the preprocessed slope image sequence data, such as Figure 4 As shown, the calculation formula is as follows:

[0070] (2)

[0071] In formula (2), T(x', y') is the pixel value at the point (x', y') in the slope image to be matched, I(x, y) is the pixel value at the point (x, y) in the original slope image, and R ccorr_normed (x, y) represents the cross-correlation calculation result. The slope image to be matched refers to the slope image collected during the landslide test, and the original slope image refers to the slope image before the landslide test.

[0072] According to the calculation results, the displacement vector field or velocity vector field of the landslide surface in the slope image is obtained.

[0073] Refer to Figure 5 (a) and Figure 5 (b), which are the displacement vector diagram and cloud diagram of the landslide body at a certain moment in the indoor test. Figure 6 It is a scatter plot of the x and y direction components of the landslide displacement at a certain moment in the indoor test. Select the landslide displacement vector diagram at a certain moment. The smallest component unit of the vector diagram is the calculation window in the last round of iterative calculation. The arrow represents the direction of the displacement vector at the window, and the number represents the displacement of the window in meters.

[0074] S4. The deformation and movement of the landslide body are identified through a python-based algorithm.

[0075] In this step, a rectangular box of the same size as the calculation window is drawn with the pixel point as the center point of the rectangular area by a Python-based algorithm, and the calculation results of LSPIV are processed to obtain the deformation and movement range of the landslide body. Specifically, referring to Figure 5 (a), the windows with displacement greater than the threshold are marked with rectangular boxes, and all rectangular boxes are combined into the moving shape detected by the algorithm. The above recognition process is as follows Figure 7 shown.

[0076] In order to verify the accuracy of the method of the present invention, the calculation results of three measuring points with the same buried positions of the measuring ends of the three pull-wire displacement meters at the upper, middle and lower parts of the landslide body were selected and compared with the measurement results of the pull-wire displacement meters. Figure 2 As shown, the calculation error and accuracy of LSPIV are verified.

[0077] In the embodiment of the present invention, the test lasts for dozens of hours and the landslide develops slowly, so frame extraction processing is adopted. After processing, the overall displacement of the landslide model is calculated through the algorithm flow written based on Python and PIVlab. The LSPIV velocity measurement results of the upper (No. 1), middle (No. 2), and lower (No. 3) points are accumulated to obtain the displacement data at each time point, which are compared with the measurement results of the rope displacement meter. The results of the three points are shown in Figures 8 (a) and 8 (b), Figures 9 (a) and 9 (b), and Figures 10 (a) and 10 (b).

[0078] Through analysis, it can be found that the LSPIV displacement calculation result of point 3 is quite different from the data measured by the pull-rope displacement meter. The average absolute error of the cumulative displacement during the whole test is 12.75mm, corresponding to 13.42 pixels, and the relative error is 11%. In addition to this group of data, the errors of point 1 and point 2 are relatively small. The average absolute errors of the cumulative displacement during the whole test are 1.86mm and 13.44mm, corresponding to about 1.96 pixels and 14.15 pixels, respectively. The final relative errors are 4.4% and 6.3%, respectively, indicating that the displacement measurement algorithm based on LSPIV technology used in the present invention has high accuracy and has certain application value for actual landslide displacement monitoring.

[0079] Accordingly, an embodiment of the present invention further provides a landslide deformation identification device based on image difference, Fig.11 FIG. 1 is a structural block diagram of a landslide deformation identification device based on image difference according to an exemplary embodiment. Fig.11 As shown, the device comprises:

[0080] An image acquisition module 201 is used to build a landslide test model and collect multiple slope images;

[0081] The image processing module 202 is used to pre-process the collected slope image, including: calculation parameter setting, displacement noise filtering and displacement numerical interpolation;

[0082] The analysis and calculation module 203 is used to analyze and calculate the pre-processed slope image sequence data by using the LSPIV technology to obtain the displacement vector field or velocity vector field of the landslide surface in the slope image;

[0083] The identification module 204 is used to identify the deformation and movement of the landslide body through a Python-based algorithm.

[0084] For ease of explanation, Fig.11 Only the main components of the device are shown. The device of this embodiment can be used to perform Figure 1 The technical solution of the method embodiment shown has similar implementation principles and technical effects, which will not be repeated here.

[0085] In an exemplary embodiment, the present invention further provides an electronic device, the electronic device comprising:

[0086] processor;

[0087] A memory having computer-readable instructions stored therein, wherein when the computer-readable instructions are loaded and executed by the processor, the steps of the above-mentioned landslide deformation identification method are implemented.

[0088] Fig.12 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Fig.12 As shown, the electronic device 300 may include a processor 3001 and a memory 3002. Optionally, the electronic device 300 may further include a transceiver 3003. The processor 3001, the memory 3002 and the transceiver 3003 may be connected, for example, via a communication bus. The memory 3002 stores computer-readable instructions, and when the computer-readable instructions are executed by the processor 3001, the steps of the landslide deformation identification method described above are implemented.

[0089] In a specific implementation, as an embodiment, the processor 3001 may include one or more CPUs, such as Fig.12 CPU0 and CPU1 are shown in FIG.

[0090] In a specific implementation, as an embodiment, the electronic device 300 may also include multiple processors, such as Fig.123001 and processor 3004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0091] The memory 3002 is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor 3001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0092] The transceiver 3003 is used to communicate with a network device or a terminal device.

[0093] Optionally, the transceiver 3003 may include a receiver and a transmitter, wherein the receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0094] Optionally, the transceiver 3003 may be integrated with the processor 3001 , or may exist independently and be coupled to the processor 3001 via an interface circuit of the electronic device 300 , which is not specifically limited in the embodiment of the present invention.

[0095] It should be noted that Fig.12 The structure of the electronic device 300 shown in the figure does not constitute a limitation on the electronic device. The actual electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. In addition, the technical effects of the electronic device 300 can refer to the technical effects of the above-mentioned method embodiment, which will not be repeated here.

[0096] In an exemplary embodiment, the present invention further provides a computer-readable storage medium, wherein at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is loaded and executed by a processor to implement the steps of the landslide deformation identification method as described above. For example, the computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0097] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0098] References in the specification to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments", etc. indicate that the described embodiments may include a particular feature, structure, or characteristic, but not every embodiment may include the particular feature, structure, or characteristic. In addition, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the relevant art to implement such feature, structure, or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0099] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0100] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0101] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0102] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0105] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0106] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0107] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A landslide deformation identification method based on image difference, characterized in that: The following steps are involved: S1. Build a landslide test model and collect multiple slope images; S2, preprocessing the collected slope image, including: calculation parameter setting, displacement noise filtering and displacement numerical interpolation; S3, analyzing and calculating the pre-processed slope image sequence data by LSPIV technology to obtain the displacement vector field or velocity vector field of the landslide surface in the slope image; S4. The deformation and movement of the landslide body are identified through a python-based algorithm.

2. The landslide deformation identification method according to claim 1, characterized in that: In step S1, the landslide test model includes a main body, a water flow system and a monitoring system; the main body includes a container box, a base, and a landslide body; the water flow system includes a water source, a water pump, a water inlet, a water outlet, a water inlet valve, a water outlet, and a drain; and the monitoring system includes an image acquisition device and a pull-rope displacement meter; The container box is a rectangular organic glass open box, which is erected on the base, and the landslide body is contained in the container box; a water inlet and a water outlet are respectively provided at the bottom of both sides of the container box, and the water level in the container box is controlled to rise and fall through the water pump, the water inlet valve and the water outlet valve during the test, so as to provide the power for the landslide body in the landslide test model to slide; Three of the pull-rope displacement meters are used, and the measuring ends are respectively buried at three measuring points at the upper part, the middle part and the lower part of the landslide body, to obtain the measuring results as comparison data.

3. The landslide deformation identification method according to claim 2, characterized in that: The image acquisition device uses an infrared camera with a fixed position, angle and focal length, and takes no less than two slope images.

4. The landslide deformation identification method according to claim 3, characterized in that: The infrared camera is calibrated by Zhang's plane calibration method, and the calibration plate adopts a checkerboard calibration plate, and the material of the checkerboard calibration plate is a glass plate coated with aluminum oxide.

5. The landslide deformation identification method according to claim 1, characterized in that: The step S2 specifically includes: S21, calculation parameter setting, including: performing image segmentation on the acquired slope image, and setting the calculation window size, search area size, window pane overlap distance, and iteration step number according to the segmented image; S22, displacement noise filtering, including: performing noise filtering on the slope image by a median filtering method, the calculation formula is: (1) In formula (1), x[n] is the original image signal, y[n] is the filtered image signal, n is the current position, k is the window size, and median represents median filtering; S23, displacement numerical interpolation, including: performing displacement numerical interpolation on the slope image by using a nearest neighbor interpolation method.

6. The landslide deformation identification method according to claim 1, characterized in that: In step S3, analyzing and calculating the pre-processed slope image sequence data by LSPIV technology specifically includes: The normalized cross-correlation method is used to analyze and calculate the preprocessed slope image sequence data. The calculation formula is as follows: (2) In formula (2), T(x', y') is the pixel value at the point (x', y') in the slope image to be matched, I(x, y) is the pixel value at the point (x, y) in the original slope image, and R ccorr_normed (x,y) represents the cross-correlation calculation result; According to the calculation results, the displacement vector field or velocity vector field of the landslide surface in the slope image is obtained.

7. The landslide deformation identification method according to claim 1, characterized in that: In step S4, a rectangular frame of the same size as the calculation window is drawn with the pixel point as the center point of the rectangular area through a python-based algorithm, and the calculation result of LSPIV is processed to obtain the deformation and movement range of the landslide body.

8. A landslide deformation identification device based on image difference, the device is used to implement the method according to any one of claims 1 to 7, characterized in that: The device comprises: Image acquisition module, used to build a landslide test model and collect multiple slope images; The image processing module is used to pre-process the collected slope images, including: calculation parameter setting, displacement noise filtering and displacement numerical interpolation; An analysis and calculation module is used to analyze and calculate the pre-processed slope image sequence data through the LSPIV technology to obtain the displacement vector field or velocity vector field of the landslide surface in the slope image; The recognition module is used to identify the deformation and movement of landslides through a Python-based algorithm.

9. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are loaded and executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, which can be called by a processor to execute the method according to any one of claims 1 to 7.

Images