Monitoring object deformation monitoring method and system

Abstract

The invention relates to a monitoring object deformation monitoring method and system. The monitoring object deformation monitoring method comprises the following steps: acquiring more than two stages of image data of a monitoring object; based on the image data of each period, generating a corresponding orthoimage and a DEM model, and determining a monitoring point from the orthoimage; and generating a deformation monitoring result of the monitored object according to the monitoring point determined in each period in combination with the DEM model. Monitoring data are intelligently processed by fusing oblique photogrammetry and an AI intelligent interpretation technology, and the accuracy of a deformation monitoring result is effectively improved.

Description

Technical Field

[0001] The present disclosure relates to the field of deformation monitoring, and in particular to a method and system for monitoring deformation of a monitoring object. Background Art

[0002] In recent years, intelligent monitoring technology has been widely used in deformation monitoring and measurement of deformable bodies. Its advantages such as high efficiency and low cost of data acquisition and no need to set up monitoring points in advance have been effectively verified in actual deformation monitoring. At present, the research on slope deformation monitoring methods based on uncontrolled photogrammetry is more relevant to this proposal at home and abroad. Usually, the deformation monitoring is carried out based on the data of the manually selected feature points through manual analysis and selection of feature points on the three-dimensional model. However, the human interference factor is large in the process of monitoring data selection, and the accuracy is low. Summary of the invention

[0003] In view of this, the present disclosure proposes a deformation monitoring method and system for a monitoring object, which can effectively improve the accuracy of deformation monitoring data results.

[0004] According to one aspect of the present application, a deformation monitoring method of a monitoring object is provided, comprising: Obtaining imaging data of the monitored object for more than two periods; Generate corresponding orthophotos and DEM models based on the image data of each period, and determine monitoring points from the orthophotos; The deformation monitoring result of the monitored object is generated according to the monitoring points determined in each period in combination with the DEM model.

[0005] In one possible implementation method, when generating corresponding orthophotos and DEM models based on the image data of each period, the coordinates of the control points determined in the orthophotos of the initial period are used as a reference to generate the orthophotos and the DEM models for the image data of each subsequent period of the initial period.

[0006] In a possible implementation method, when determining the monitoring point from the orthophoto, the method includes: Identifying identification features of the monitored object from the orthophoto; The center point of the identified identification feature is extracted, and the extracted center point of the identification feature is used as a monitoring point.

[0007] In a possible implementation method, when extracting the center point of the identified identification feature, an external circle algorithm is used.

[0008] In a possible implementation method, the deformation monitoring result of the monitored object is characterized by at least one of a horizontal displacement change result and a vertical displacement change result of the monitored object.

[0009] In a possible implementation method, when the deformation monitoring result is characterized by the horizontal displacement change result of the monitored object, it includes: Obtaining the coordinates of the monitoring points determined in each period; According to the coordinates of the monitoring points of each period, respectively calculating the horizontal displacement of the monitoring points of each period and the monitoring points corresponding to the initial period, and obtaining the cumulative horizontal displacement results of the monitoring points; According to the coordinates of the monitoring points of each period, respectively calculating the horizontal displacement of the same monitoring point between different periods in each period, and obtaining the relative horizontal displacement result of the monitoring point; The horizontal displacement change result of the monitored object is characterized by the accumulated horizontal displacement result and the relative horizontal displacement result of the monitoring point.

[0010] In a possible implementation method, when the deformation monitoring result is characterized by the vertical displacement change result of the monitored object, it includes: Obtaining the coordinates of the monitoring points determined in each period, and locating the triangle where the monitoring points are located in the corresponding DEM model; According to the monitoring point coordinates of each period and the three-dimensional coordinates of the triangle vertices, respectively calculate the vertical displacement of the monitoring point of each period and the monitoring point corresponding to the initial period, and obtain the cumulative vertical displacement result of the monitoring point; According to the monitoring point coordinates of each period and the three-dimensional coordinates of the triangle vertices, respectively calculate the vertical displacement of the same monitoring point between different periods in each period to obtain the relative vertical displacement result of the monitoring point; The vertical displacement change result of the monitored object is characterized by the accumulated vertical displacement result and the relative vertical displacement result of the monitoring point.

[0011] According to another aspect of the present application, there is also provided a monitoring object deformation monitoring system, comprising a data acquisition module, a data processing module, and a data calculation module; The data acquisition module is configured to acquire more than two periods of image data of the currently monitored object; The data processing module is configured to generate corresponding orthophotos and DEM models based on the image data of each period, and determine monitoring points from the orthophotos; The data calculation module is configured to generate deformation monitoring results of the monitored object according to the monitoring points determined in each period in combination with the DEM model.

[0012] According to another aspect of the present application, there is also provided a deformation monitoring device for a monitoring object, comprising: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement any of the above methods when executing the executable instructions.

[0013] According to another aspect of the present application, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, characterized in that when the computer program instructions are executed by a processor, any one of the above-mentioned methods is implemented.

[0014] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0016] Figure 1 A flow chart showing a method for monitoring deformation of a monitoring object according to an embodiment of the present application; Figure 2 A technical flow chart showing an embodiment of the present application; Figure 3 A schematic diagram of a DEM grid is shown in an embodiment of the present application; Figure 4 A schematic diagram of an inclined flight route according to an embodiment of the present application is shown; Figure 5 An orthophoto of a monitoring object according to an embodiment of the present application is shown; Figure 6 A schematic diagram of extracting monitoring points according to an embodiment of the present application is shown; Figure 7 A schematic block diagram showing a deformation monitoring device for a monitoring object according to an embodiment of the present application; Figure 8 A schematic diagram showing the horizontal deformation monitoring result of an embodiment of the present application; Fig. 9 A schematic diagram showing the vertical deformation monitoring results of an embodiment of the present application. DETAILED DESCRIPTION

[0017] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0018] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0019] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0020] This application is applicable to monitoring deformation of monitored objects. By integrating oblique photogrammetry and AI intelligent interpretation technology, the intelligent collection and processing of deformation monitoring data is realized, and the accuracy of deformation monitoring results is improved; the shortcomings of traditional monitoring methods, which select feature points through manual analysis, have large interference factors and low accuracy, are overcome.

[0021] Figure 1 FIG. 1 is a flow chart showing a method for monitoring deformation of a monitoring object according to an embodiment of the present application. Figure 1 As shown, the method includes: step S100, obtaining image data of more than two periods of the currently monitored object. Step S200, generating corresponding orthophotos and DEM models based on the image data of each period, and determining monitoring points from the orthophotos. Step S300, generating deformation monitoring results of the monitored object based on the monitoring points determined in each period combined with the DEM model.

[0022] It should be pointed out that in the method of the embodiment of the present application, the image data obtained is the oblique image data of the monitored object. That is, when collecting image data of the monitored object, the oblique image data covering the current monitored object (such as: the current monitored object is a rockfill dam) can be obtained through oblique photogrammetry technology. Specifically, the camera inclination angle of the drone during tilted flight can be set within a preset inclination range to collect and obtain the oblique image data of the rockfill dam. All image data captured by the drone during one flight is used as one period of oblique image data, and the image of the monitored object will be captured multiple times during a single flight. One period of image data contains the oblique image data obtained by multiple shots.

[0023] Among them, in a possible implementation, the preset tilt angle should be set at 45°. It should be noted here that the camera tilt angle refers to the angle formed by the main optical axis of the inclined camera and the main optical axis of the vertically placed camera in the determined plane.

[0024] Furthermore, five images of the monitored object are obtained each time, including four oblique images and one downward image. The information obtained from all the images is the information of the front, back, left, right and bottom of a certain area of ​​the monitored object, so that the main structure of the monitored object and all the information in the surrounding stable zone of the monitored object can be obtained. Among them, the main structure of the monitored object corresponds to the main body of the monitored object. For example, when the monitored object is a rockfill dam, the main structure of the monitored object refers to the entire dam body of the rockfill dam; the stable zone refers to an area far away from the main structure of the monitored object, with good geological conditions and not affected by the main load. At the same time, during the image acquisition process, the heading overlap and lateral overlap of the image data should be controlled to be no less than 85%. In a possible implementation method, for the determination of the surrounding stable zone, the area outside the range of three times the main body height can be used as the surrounding stable zone according to the straight-line distance from the edge contour of the main structure of the monitored object.

[0025] It should also be noted that deformation monitoring of the monitored object is a continuous monitoring process. Therefore, when collecting oblique image data of the monitored object, image data are generally collected more than twice, and deformation monitoring is performed based on more than two image data.

[0026] That is to say, in the monitoring method of the present application, the collection of image data of the monitored object includes more than two phases of collection. The oblique image data covering the monitored object obtained for the first time through the oblique photogrammetry technology is recorded as the initial phase (TH1) image data, the image data collected for the second time is the second phase (TH2) image data, ..., the image data collected for the Nth time is the Nth phase (THN) image data, and so on.

[0027] When collecting multiple periods of image data, the time interval between each two adjacent periods can be flexibly adjusted according to actual conditions, and the time interval between each two adjacent periods can be the same or different, which is not specifically limited in this application.

[0028] After the image data of the monitored object is collected in the above manner, an orthophoto and a DEM model can be generated based on the collected image data.

[0029] Among them, when generating orthophotos, it can be achieved in the following ways. First, in the process of generating orthophotos of a period, all downward images in the oblique image data are selected, and aerial triangulation is performed on multiple downward images in this period, and the external orientation elements and internal orientation elements of each of the multiple downward images are calculated respectively, so as to determine the relative position and posture of each downward image; then, the multiple downward images are corrected and projected onto a horizontal plane to eliminate the inclination and projection difference, and obtain multiple horizontal orthophotos; finally, the corrected multiple orthophotos are mosaicked and joined to generate a complete orthophoto map of the monitoring area of ​​this period.

[0030] For the generated complete orthophoto, it is necessary to modify it, mainly to remove noise, enhance the contrast and tilt of the image, and adjust the tone and color of the image to improve the quality and accuracy of the orthophoto.

[0031] The modification method of the orthophoto image can adopt conventional image processing technology in the art, so it will not be explained in detail in this application.

[0032] Furthermore, when generating a DEM model based on the collected image data, based on multiple images of the monitored object from the front, back, left, right, and bottom, the ground points and non-ground points are screened and distinguished for each image, and the screened ground points are used to build an irregular triangulated network (TIN) model, and the TIN model is converted into DEM data of a regular triangular grid, thereby obtaining a DEM model, such as Figure 3 shown.

[0033] The process of generating orthophotos and DEM models can be generated using conventional techniques in the art, and will not be described in detail in this application.

[0034] After obtaining the orthophoto and DEM model of the image data in the above manner, the monitoring points can be determined based on the obtained orthophoto, and the deformation monitoring results of the monitored object can be obtained in combination with the DEM model.

[0035] Among them, when determining the monitoring points, AI intelligent interpretation technology can be used to identify the monitoring points. That is, the generated orthophoto is used as the input data of the monitoring point recognition model. It should be noted that the monitoring point refers to the center point of the characteristic object in the monitoring object that serves as an identifier. For example, when the monitoring object is a rockfill dam, the monitoring point can be the center point of the stone in the rockfill dam. Among them, the number of monitoring points can be multiple. After identifying the monitoring point of the monitoring object, the coordinates of the monitoring point are extracted as the monitoring identifier for later deformation monitoring.

[0036] According to the above, when using AI intelligent interpretation technology to identify monitoring points in orthophotos, it is necessary to train the monitoring point recognition model. In the embodiment of the present application, the image data collected in the same period can be directly used as sample data to realize the training of the monitoring point recognition model.

[0037] Specifically, after obtaining the image data of the monitored object, it also includes the step of generating a sample library. That is, the image data of the monitored object is obtained by oblique photogrammetry, and representative feature areas (such as stone areas) are selected from the image data as samples. Then, the selected samples are annotated using a sample annotation tool (such as Supervisely), and the annotated samples are classified according to the type of feature area (such as color, texture, shape, and size, etc.). At the same time, data enhancement processing can also be performed on the annotated and classified samples, such as flipping, rotating, scaling, and other operations, to increase the diversity of samples. After constructing and generating a sample library in the above manner, the constructed sample library can be used to train the recognition model to identify the identification features in the orthophoto, and obtain the center point of the identification feature as the monitoring point.

[0038] The sample annotation tool Supervisely can be replaced by other sample annotation tools, which is not specifically limited in this application.

[0039] Among them, after identifying the identification features in the orthophoto (such as rocks in a rockfill dam), the circumscribed circle algorithm can be used to extract the center point of the identification feature. The unique center point of the identification feature is obtained through the circumscribed circle algorithm, and the position coordinates of the center points of these feature objects (i.e., monitoring points) in the orthophoto are determined through further image processing and calculation.

[0040] It should be noted that orthophotos contain geographic reference information and coordinate information. The coordinates can be obtained by determining the center point. The acquisition of coordinates is a consensus in this field and will not be elaborated here.

[0041] Therefore, in an embodiment of the present application, after the recognition model is trained through the above-mentioned training process, the AI ​​intelligent interpretation technology can be used to automatically identify the identification features of the monitored object based on the orthophoto and sample library generated above; wherein, the AI ​​intelligent interpretation technology is a conventional processing method for interpreting remote sensing data in this field and will not be described in detail in this application.

[0042] Specifically, when identifying the identification features of the monitored object, the logical process is as follows: match and compare the input image with the previously learned pattern; the trained model can automatically classify the samples in the image and determine the position of the feature object in the image, and then obtain the coordinates of the center point of the feature object (i.e., the monitoring point).

[0043] Furthermore, after the monitoring points are acquired, the deformation monitoring results of the monitored object can be determined based on the determined monitoring points combined with the DEM model. Here, since the process of deformation monitoring of the monitored object is a continuous and long-term monitoring process, when the deformation monitoring results are determined based on the identified monitoring points, it is necessary to identify the monitoring points based on the image data of the monitored object collected at least two times, and then determine the final deformation monitoring results based on the monitoring points identified at least two times.

[0044] Therefore, in a possible implementation, when the monitoring point is identified for each period of image data collected after the initial period, it is also necessary to generate the corresponding orthophoto and DEM model according to the image data of each period. Among them, when generating the corresponding orthophoto and DEM model for each period of image data after the initial period, it is mainly achieved by the following methods: Based on the image data of each period, the control points determined by the orthophoto of the initial period are used as the reference to perform aerial triangulation calculations, determine the image position, and generate the corresponding orthophotos and DEM models of the subsequent periods for calculating the subsequent displacement change results. Here, it should be explained that the control points refer to the pixel points determined as the reference in the orthophoto generated by the initial period when the orthophotos of each period of image data after the initial period are generated. When the orthophotos and DEM models are generated in the subsequent periods, the control points determined in the initial period are used for aerial triangulation calculations to unify the image reference.

[0045] The coordinates of the control points are determined based on the orthophotos generated in the initial phase, and a number of feature points are identified in the orthophotos generated in the initial phase that are outside the main body of the monitored object and within a straight line distance of three times the main body height from the edge contour of the main structure of the monitored object, and the coordinates of each identified feature point are extracted. Here, the identified feature points are the control points.

[0046] It should be noted that the feature points include at least one of: obvious local extreme value points, corner points, points with local maximum or minimum curvature on edges, texture feature points, and color mutation points.

[0047] Furthermore, the deformation monitoring result of the monitored object can be obtained by calculating the displacement of the monitoring point coordinates, wherein the displacement change result of the monitoring point coordinates includes: a horizontal displacement change result and a vertical displacement change result.

[0048] That is to say, the deformation monitoring result of the monitored object can be characterized by at least one of a horizontal displacement change result and a vertical displacement change result.

[0049] In a possible implementation, the coordinates of the monitoring points determined in each period are obtained, and the horizontal displacements of the monitoring points of each period and the monitoring points corresponding to the initial period are calculated respectively to obtain the cumulative horizontal displacement results of the monitoring points; according to the coordinates of the monitoring points of each period, the horizontal displacements of the same monitoring points between different periods in each period are calculated respectively to obtain the relative horizontal displacement results of the monitoring points. That is, the cumulative horizontal displacement results and relative horizontal displacement results of the monitoring points are used to characterize the horizontal displacement change results of the rockfill dam.

[0050] Similarly, the coordinates of the monitoring points determined in each period are obtained, and the triangle where the monitoring points are located in the corresponding DEM model is located is located. According to the coordinates of the monitoring points in each period and the three-dimensional coordinates of the triangle vertices, the vertical displacement of the monitoring points in each period and the monitoring points corresponding to the initial period is calculated, and the cumulative vertical displacement results of the monitoring points are obtained; according to the coordinates of the monitoring points in each period and the three-dimensional coordinates of the triangle vertices, the vertical displacement of the same monitoring point between different periods in each period is calculated, and the relative vertical displacement results of the monitoring points are obtained. That is, the cumulative vertical displacement results and relative vertical displacement results of the monitoring points are used to characterize the vertical displacement change results of the rockfill dam.

[0051] The deformation monitoring result of the monitored object is to analyze the displacement and trend of the average distributed monitoring points through the horizontal displacement change and vertical displacement change of the monitoring points, so as to determine the deformation of the monitored object. Figure 8 and Fig. 9 It is a schematic diagram of the deformation monitoring result of the embodiment of the present application, where P3-P22 are 20 monitoring points monitored in the specific embodiment, indicating the coordinate changes of different monitoring points over time.

[0052] It should also be noted that the calculation formula for the cumulative and relative horizontal displacement of the above monitoring points is as follows: (1) The coordinates of the monitoring points identified and extracted during TH2 to THN are calculated with the coordinates of TH1. According to the coordinates of the i-th monitoring point in the orthophoto of TH1 (X iTH1 ,Y iTH1 ), where TH1 is the initial period, and the cumulative horizontal displacement of the ith monitoring point in period A is calculated as follows:

[0053] The coordinates of the monitoring points identified and extracted in the TH2 to THN periods are calculated mutually. As above, according to the coordinates of the monitoring points of different subsequent periods in the orthophoto, the relative horizontal displacement of the i-th monitoring point between the A-th period and the B-th period is calculated as follows:

[0054] The calculation formula for the cumulative and relative vertical displacement of the above monitoring points is as follows: According to the coordinates of the DEM grid nodes and the coordinates of the monitoring points, locate the triangle ABC where a monitoring point (denoted as P) is located. According to the three-dimensional coordinates of the three vertices of ABC and the plane coordinates of point P, calculate the elevation of P according to the following formula (where a 0 , a 1 , a 2 The three-dimensional coordinates of the three vertices ABC are obtained by linear interpolation, and the calculation process is common knowledge in the art and will not be elaborated here).

[0055]

[0056] (1) The elevation values ​​of the monitoring points obtained by interpolating the DEM models generated in periods TH2 to THN are interpolated and the difference between the elevation values ​​in period TH1 is calculated, where TH1 is the initial period. The cumulative vertical displacements of each period from TH2 to THN are obtained. The cumulative vertical displacement of the i-th feature point in period A is calculated as follows:

[0057] (2) The DEM model generated during the TH2 to THN periods is interpolated to obtain the elevation values ​​of the monitoring points in different periods and the relative vertical displacement of the i-th feature point between the A-th period and the B-th period is calculated as follows:

[0058] Example 1 The main structure of this example is a rockfill dam, and the main task is to monitor the deformation of the rockfill dam during its construction. Therefore, a deformation monitoring method for monitoring objects that integrates oblique photogrammetry and AI intelligent interpretation technology was implemented to grasp its deformation characteristics in real time, providing a basis for subsequent construction. The detailed steps are as follows: Figure 2 1 is a flow chart showing a technique according to an embodiment of the present disclosure. Figure 2 As shown, the implementation process steps include: Step 1: The project uses a drone smart nest to acquire data every 3 days. Figure 4 The first tilt flight was carried out along the route shown in the figure, and 8860 images with a certain degree of overlap were obtained, including the location information and attitude information of the drone when taking the photo. Step 2: Use conventional aerial triangulation software such as PIX4D and Inpho, and use the data taken by oblique aerial flight in January 2024 to generate orthophotos, DEM models, and stone sample libraries covering the rockfill dam.

[0059] Step 3: Based on the generated orthophoto, AI intelligent interpretation technology is used to automatically identify several feature points in the relatively stable area outside the monitored object and extract their coordinates as control points for subsequent data processing.

[0060] Step 4: Based on the orthophoto of the rockfill dam, AI intelligent interpretation is used to identify several stone feature points inside the deformation zone of the dam body and extract the coordinate information of its center point on January 18, 2024, such as Figure 6 The red circle point in the middle serves as the monitoring point benchmark data for subsequent deformation analysis.

[0061] Step 5: Generate a DEM model based on the image data acquired on January 18, 2024.

[0062] Step 6: Based on the same aerial photography route and the same drone as on January 18, 2024, obtain image data for January 21, 2024 and other subsequent periods. The same aerial photography route and the same tilted drone are used here mainly to reduce the corresponding errors and ensure data consistency.

[0063] Step 7: Using the peripheral feature points of the rockfill dam on January 18, 2024 extracted in step 4 as known control points, perform aerial triangulation and other steps on the image data acquired on January 21, 2024 and other subsequent periods to generate orthophotos, DEM model results and stone sample libraries.

[0064] Step 8: Combine orthophotos from different periods with the stone sample library, and use AI intelligent interpretation to identify and extract the coordinates of the same monitoring points as in step 4.

[0065] Step 9: Generate DEM model data of different periods based on the image data obtained on January 21, 2024 and other subsequent periods.

[0066] Step 10: The monitoring points of the rockfill dam obtained on January 21, 2024 and other subsequent periods are compared with the monitoring points on January 18, 2024 for the above-mentioned cumulative horizontal displacement calculation. The same method is applied to calculate the relative horizontal displacement in different periods.

[0067] Step 11: Interpolate the DEM model generated on January 21, 2024 and other subsequent periods with the DEM model on January 18, 2024 to obtain the cumulative vertical displacement. Alternatively, the same method can be used to interpolate the DEM models of different periods to obtain the relative vertical displacement.

[0068] Through the above steps, the deformation monitoring method that integrates oblique photogrammetry and AI intelligent interpretation technology can grasp the deformation characteristics in real time and obtain more accurate monitoring results.

[0069] Figure 7 A deformation monitoring device for monitoring an object according to an embodiment of the present disclosure is shown. Figure 7 As shown, it includes: a processor 120 and a memory 110 for storing processor executable instructions. The processor 120 is configured to implement any of the above-mentioned monitoring methods for deformation monitoring of monitoring objects when executing the executable instructions.

[0070] The memory 110 is a computer-readable storage medium that can be used to store software programs, computer executable programs, and various modules, such as the program or module corresponding to the method for monitoring deformation of a monitored object in the embodiment of the present disclosure. The processor 120 executes various functional applications and data processing of monitoring deformation of a monitored object by running the software programs or modules stored in the memory 110.

[0071] Those skilled in the art will understand that Figure 7 What is shown in the figure is only a partial result block diagram related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0072] This embodiment also provides a non-volatile computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, any of the above-mentioned methods for monitoring deformation of a monitoring object is implemented.

[0073] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for monitoring deformation of a monitoring object, characterized in that: include: Obtaining imaging data of the monitored object for more than two periods; Generate corresponding orthophotos and DEM models based on the image data of each period, and determine monitoring points from the orthophotos; The deformation monitoring result of the monitored object is generated according to the monitoring points determined in each period in combination with the DEM model.

2. The method according to claim 1, characterized in that When generating corresponding orthophotos and DEM models based on the image data of each period, the coordinates of the control points determined in the orthophotos of the initial period are used as a reference to generate the orthophotos and DEM models for the image data of each subsequent period of the initial period.

3. The method according to claim 1, characterized in that When the monitoring points are determined from the orthophoto, it includes: Identifying identification features of the monitored object from the orthophoto; The center point of the identified identification feature is extracted, and the extracted center point of the identification feature is used as a monitoring point.

4. The method according to claim 3, characterized in that When extracting the center point of the identified identification feature, an circumscribed circle algorithm is used.

5. The method according to any one of claims 1 to 4, characterized in that: The deformation monitoring result of the monitored object is characterized by at least one of a horizontal displacement change result and a vertical displacement change result of the monitored object.

6. The method according to claim 5, characterized in that When the deformation monitoring result is characterized by the horizontal displacement change result of the monitored object, it includes: Obtaining the coordinates of the monitoring points determined in each period; According to the coordinates of the monitoring points of each period, respectively calculating the horizontal displacement of the monitoring points of each period and the monitoring points corresponding to the initial period, and obtaining the cumulative horizontal displacement results of the monitoring points; According to the coordinates of the monitoring points of each period, respectively calculating the horizontal displacement of the same monitoring point between different periods in each period, and obtaining the relative horizontal displacement result of the monitoring point; The horizontal displacement change result of the monitored object is characterized by the accumulated horizontal displacement result and the relative horizontal displacement result of the monitoring point.

7. The method according to claim 5, characterized in that When the deformation monitoring result is characterized by the vertical displacement change result of the monitored object, it includes: Obtaining the coordinates of the monitoring points determined in each period, and locating the triangles of the monitoring points in the corresponding DEM model; According to the coordinates of the monitoring points of each period and the three-dimensional coordinates of the triangle vertices, respectively calculate the vertical displacement of the monitoring points of each period and the corresponding monitoring points in the initial period to obtain the cumulative vertical displacement results of the monitoring points; According to the monitoring point coordinates of each period and the three-dimensional coordinates of the triangle vertices, respectively calculate the vertical displacement of the same monitoring point between different periods in each period to obtain the relative vertical displacement result of the monitoring point; The vertical displacement change result of the monitored object is characterized by the accumulated vertical displacement result and the relative vertical displacement result of the monitoring point.

8. A system for monitoring deformation of a monitoring object, characterized in that: It includes a data acquisition module, a data processing module and a data calculation module; The data acquisition module is configured to acquire more than two periods of image data of the currently monitored object; The data processing module is configured to generate corresponding orthophotos and DEM models based on the image data of each period, and determine monitoring points from the orthophotos; The data calculation module is configured to generate deformation monitoring results of the monitored object according to the monitoring points determined in each period in combination with the DEM model.

9. A deformation monitoring device for a monitoring object, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method described in any one of claims 1 to 7 when executing the executable instructions.

10. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images