Regional geological disaster prevention management method, device and equipment and storage medium

Abstract

The present application relates to the technical field of geological disaster prevention, and discloses a regional geological disaster prevention management method, device, equipment and storage medium, a reference correlation model of a regional lattice beam is constructed, a mapping relationship is established between reference identification space coordinates, flight parameters and pixel coordinates, in the flight process, based on the difference between the real-time collected identification pixel coordinates and the reference data, the flight trajectory is dynamically corrected, and the data deviation is reduced from the collection source; the corrected flight parameters are fully applied to subsequent image calibration, the consistency of image scale and spatial position is improved, the cooperation of flight correction and image data calibration processing is realized, the consistency of image scale and spatial position is improved, the classification early warning is carried out in combination with crack propagation parameters, deformation characteristic parameters and flight trajectory deviation cumulative amount, the data reliability is quantized, and false positives and false negatives caused by single parameter determination are avoided. Finally, the feature comparison accuracy and early warning reliability of the lattice beam monitoring are significantly improved, and the high-precision requirement of high and steep slope geological disaster prevention is met.

Description

Technical Field

[0001] This invention relates to the field of geological disaster prevention and control technology, and in particular to a regional geological disaster prevention and control management method, device, equipment and storage medium. Background Technology

[0002] Grid beam support structures for steep slopes are a common form of geological disaster protection in mountainous transportation engineering and mining scenarios. Their structural integrity directly affects the safety of surrounding personnel and facilities. Accurately capturing precursor signals such as crack propagation and node deformation in grid beams is crucial for early warning of geological disasters. However, the posture of the grid beam support structure varies at different node locations, increasing the difficulty of geological disaster early warning analysis for grid beam support structures on steep slopes. Drones, due to their advantages of non-contact operation, high efficiency, and adaptability to complex terrain, have become the mainstream tool for grid beam monitoring.

[0003] However, existing UAV monitoring technology has significant limitations: First, steep slopes have complex terrain and variable airflow, which can easily lead to problems such as flight altitude fluctuations, shooting angle shifts, and horizontal / vertical coordinate misalignment between two monitoring sessions. This results in image distortion, inconsistent scale, and spatial misalignment. Furthermore, the different attitudes of the lattice beam support structure at different node positions exacerbate the errors caused by the differences between the two UAV monitoring sessions, directly affecting the accuracy of feature comparison. Second, traditional monitoring methods rely heavily on post-collection data calibration and lack real-time correction mechanisms during flight. Even with subsequent image calibration, it is difficult to completely eliminate errors caused by the original acquisition deviations, leading to inaccuracies in the calculation of crack propagation and deformation. Third, flight trajectory correction and data post-processing are independent of each other. The corrected flight parameters are not fully applied to the subsequent calibration process, further reducing the reliability of early warning. Summary of the Invention

[0004] The purpose of this invention is to provide a regional geological disaster prevention and management method and system to at least solve the problems of data distortion caused by flight trajectory deviation, lack of coordination between flight correction and data calibration, and low reliability of early warning when using existing UAVs to monitor lattice beams.

[0005] To achieve the above objectives, the present invention provides a regional geological disaster prevention and management method, comprising the following steps:

[0006] Acquire benchmark monitoring data of the regional lattice beams and construct a benchmark association model; wherein, the benchmark monitoring data includes benchmark identifier spatial coordinates, benchmark flight parameters, and benchmark identifier pixel coordinates;

[0007] Based on the aforementioned benchmark correlation model, the monitoring drone is controlled to perform the current monitoring task. While the monitoring drone collects current monitoring data including corrected flight parameters, currently acquired images, and currently identified spatial coordinates, the flight trajectory of the drone performing the current monitoring task is simultaneously and dynamically corrected.

[0008] Based on the benchmark correlation model and the corrected flight parameters and current identifier spatial coordinates in the current monitoring data, calibration processing is performed on the currently acquired image in the current monitoring data and its features are compared with the benchmark image to obtain the feature comparison results.

[0009] Based on the feature comparison results, the crack propagation parameters and deformation characteristic parameters of the regional lattice beams are analyzed.

[0010] Based on the crack propagation parameters, the deformation characteristic parameters, and the cumulative flight trajectory deviation determined during the dynamic correction of the flight trajectory, a graded early warning information for regional geological disaster prevention and control is generated.

[0011] Optionally, the steps of acquiring benchmark monitoring data of regional lattice beams and constructing a benchmark correlation model specifically include:

[0012] The monitoring drone is controlled to perform close-to-slope, terrain-following flight on the lattice beam slope in the area marked with a preset benchmark, and collects benchmark images of the lattice beam along the preset benchmark route.

[0013] The RTK module on the monitoring drone is used to record the three-dimensional spatial coordinates of each reference marker as the reference marker spatial coordinates. The attitude sensor on the monitoring drone is used to record the reference flight parameters of the drone. The pixel coordinates of the reference markers in the reference image are extracted as the reference marker pixel coordinates.

[0014] Establish the mapping relationship between the reference identifier spatial coordinates, the reference flight parameters and the reference identifier pixel coordinates, and generate the reference relationship model.

[0015] Optionally, based on the aforementioned benchmark correlation model, the monitoring drone is controlled to perform the current monitoring task. While the monitoring drone collects current monitoring data including corrected flight parameters, currently acquired images, and currently identified spatial coordinates, the flight trajectory of the drone performing the current monitoring task is simultaneously and dynamically corrected. Specifically, this includes:

[0016] Using the baseline flight parameters in the baseline association model as initial configuration parameters, the monitoring drone is controlled to start the current monitoring task and collect the current images of the regional lattice beams in real time according to the initial flight path;

[0017] The current spatial coordinates of the marker are obtained by using the RTK module on the monitoring drone, and the real-time flight parameters of the monitoring drone are obtained by using the attitude sensor on the monitoring drone. The pixel coordinates of the reference marker in the currently acquired image are extracted as the real-time marker pixel coordinates.

[0018] The real-time identifier pixel coordinates are compared with the baseline identifier pixel coordinates in the baseline association model. The horizontal and vertical pixel offsets of each identifier are calculated, and the average horizontal and vertical pixel offsets of all identifiers are taken as the corrected flight parameters.

[0019] Combining the baseline flight parameters in the baseline association model, the average level pixel offset and average vertical pixel offset are converted into the drone's altitude adjustment, horizontal position adjustment and angle adjustment through a preset mapping formula, thereby dynamically correcting the drone's flight trajectory for the current monitoring task.

[0020] After completing the current monitoring task, the corrected flight parameters, the currently acquired images, and the current spatial coordinates of the markers will be linked and stored to form the current monitoring data.

[0021] Optionally, the step of performing calibration processing on the currently acquired image in the current monitoring data based on the benchmark correlation model and the corrected flight parameters and current identifier spatial coordinates in the current monitoring data, and comparing its features with the benchmark image to obtain the feature comparison result, specifically includes:

[0022] Based on the physical diameter and reference scale factor of the reference identifier, and combined with the reference flight parameters and corrected flight data in the reference association model, the calibrated scale factor of the currently acquired image is calculated.

[0023] Using the reference spatial coordinates of the reference identifier in the reference association model as the reference, and the horizontal translation in the corrected flight parameters as the initial registration parameter, the iterative nearest point algorithm is used to perform registration operation on the current identifier spatial coordinates, and the coordinate deviation is minimized to obtain the current identifier spatial coordinates after registration.

[0024] Based on the calibrated scale factor and the registered current label spatial coordinates, the currently acquired image and the reference image are adjusted to the same scale and spatial position.

[0025] Edge detection is used to extract crack region features from the baseline image and the calibrated current image. The corresponding crack regions are then compared using a feature point matching algorithm to obtain feature comparison results.

[0026] Optionally, based on the feature comparison results, the steps for analyzing the crack propagation parameters and deformation characteristic parameters of the regional lattice beam specifically include:

[0027] Based on the calibrated scale factor, the width and length of the crack in the reference image and the currently acquired image are calculated to obtain the crack width expansion amount and crack length expansion amount as crack expansion parameters.

[0028] Based on the difference between the current identifier spatial coordinates and the reference identifier spatial coordinates after registration, the actual displacement of the lattice beam node is calculated. Using the preset key area of ​​the lattice beam in the reference image as a template, matching is performed in the currently acquired image to obtain the horizontal and vertical pixel displacements of the preset key area. The pixel displacements are then converted into actual deformations by combining the calibrated size factor.

[0029] The time interval between the current monitoring task and the benchmark monitoring is obtained. The displacement rate of the lattice beam node is obtained by calculating the ratio of the actual displacement to the time interval. The actual displacement, actual deformation, and displacement rate of the node are used as deformation characteristic parameters.

[0030] Optionally, the step of generating graded early warning information for regional geological disaster prevention and control based on the crack propagation parameters, the deformation characteristic parameters, and the cumulative amount of flight trajectory deviation determined during the dynamic correction of the flight trajectory specifically includes:

[0031] The cumulative flight trajectory deviation is calculated by summing the first absolute values ​​of all altitude adjustments and the second absolute values ​​of all angle adjustments during the statistical dynamic correction of the flight trajectory, and combining them with the vertical slope height in the reference flight parameters.

[0032] The crack propagation parameters and deformation characteristic parameters are compared with the judgment conditions of the graded early warning threshold, and combined with the cumulative amount of flight trajectory deviation, graded early warning information for regional geological disaster prevention and control is generated.

[0033] Optionally, by combining the cumulative flight trajectory deviation, a graded early warning information for regional geological disaster prevention and control can be generated, specifically including:

[0034] When the cumulative deviation of the flight trajectory is less than or equal to the first preset value and any one of the crack propagation parameter or deformation characteristic parameter triggers the threshold, it is determined to be a level one warning.

[0035] When the cumulative deviation of the flight trajectory is less than or equal to the second preset value and at least two of the crack propagation parameters and deformation characteristic parameters trigger the threshold, it is determined to be a level two warning.

[0036] When the cumulative deviation of the flight trajectory is less than or equal to the third preset value and at least three of the crack propagation parameters and deformation characteristic parameters trigger the threshold, it is determined to be a level three warning.

[0037] Furthermore, to achieve the above objectives, the present invention also provides a regional geological disaster prevention and management device, comprising:

[0038] A construction module is used to acquire benchmark monitoring data of regional lattice beams and construct a benchmark association model; wherein, the benchmark monitoring data includes benchmark identifier spatial coordinates, benchmark flight parameters, and benchmark identifier pixel coordinates;

[0039] The correction module is used to control the monitoring drone to perform the current monitoring task based on the benchmark association model. While the monitoring drone collects current monitoring data including corrected flight parameters, currently acquired images and currently identified spatial coordinates, the module simultaneously and dynamically corrects the flight trajectory of the drone to perform the current monitoring task.

[0040] The comparison module is used to perform calibration processing on the currently acquired image in the current monitoring data based on the benchmark association model and the corrected flight parameters and current identifier spatial coordinates in the current monitoring data, and compare the features with the benchmark image to obtain the feature comparison result;

[0041] The analysis module is used to analyze the crack propagation parameters and deformation characteristic parameters of the regional lattice beam based on the feature comparison results.

[0042] The early warning module is used to generate graded early warning information for regional geological disaster prevention and control based on the crack propagation parameters, the deformation characteristic parameters, and the cumulative amount of flight trajectory deviation determined during the dynamic correction of the flight trajectory.

[0043] In addition, to achieve the above objectives, the present invention also provides a regional geological disaster prevention and management device, which includes: a memory, a processor, and a regional geological disaster prevention and management program stored in the memory and executable on the processor. When the regional geological disaster prevention and management program is executed by the processor, it implements the steps of the regional geological disaster prevention and management method as described above.

[0044] In addition, to achieve the above objectives, the present invention also provides a storage medium storing a regional geological disaster prevention and control management program, which, when executed by a processor, implements the steps of the above-described regional geological disaster prevention and control management method.

[0045] The beneficial effects of this invention are as follows: It proposes a regional geological disaster prevention and management method, device, equipment, and storage medium. By constructing a benchmark association model of regional lattice beams, a mapping relationship is established between the spatial coordinates of benchmark markers, flight parameters, and pixel coordinates, providing a unified reference benchmark for subsequent flight correction and image calibration. During flight, the flight trajectory is dynamically corrected based on the difference between the real-time collected marker pixel coordinates and the benchmark data, reducing data deviation from the source of data acquisition. The corrected flight parameters are fully applied to subsequent image calibration, achieving synergy between flight correction and image data calibration processing, improving the consistency of image scale and spatial position. A graded early warning system is implemented by combining crack propagation parameters, deformation characteristic parameters, and cumulative flight trajectory deviation, quantifying data reliability and avoiding false alarms and missed alarms caused by single-parameter judgments. Ultimately, the feature comparison accuracy and early warning reliability of lattice beam monitoring are significantly improved, meeting the high-precision requirements for geological disaster prevention and control on steep slopes. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention;

[0047] Figure 2 This is a flowchart illustrating an embodiment of the regional geological disaster prevention and management method of the present invention;

[0048] Figure 3 This is a structural block diagram of a regional geological disaster prevention and management device according to an embodiment of the present invention. Detailed Implementation

[0049] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0050] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0051] like Figure 1 As shown, Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention.

[0052] like Figure 1As shown, the device may include: a processor 1001, such as a CPU; a communication bus 1002; a user interface 1003; a network interface 1004; and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0053] Those skilled in the art will understand that Figure 1 The structure of the device shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0054] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a regional geological disaster prevention and management program.

[0055] exist Figure 1 In the terminal shown, network interface 1004 is mainly used to connect to the backend server and communicate data with it; user interface 1003 is mainly used to connect to the client (user terminal) and communicate data with it; while processor 1001 can be used to call the regional geological disaster prevention and control management program stored in memory 1005 and perform the following operations:

[0056] Acquire benchmark monitoring data of the regional lattice beams and construct a benchmark association model; wherein, the benchmark monitoring data includes benchmark identifier spatial coordinates, benchmark flight parameters, and benchmark identifier pixel coordinates;

[0057] Based on the aforementioned benchmark correlation model, the monitoring drone is controlled to perform the current monitoring task. While the monitoring drone collects current monitoring data including corrected flight parameters, currently acquired images, and currently identified spatial coordinates, the flight trajectory of the drone performing the current monitoring task is simultaneously and dynamically corrected.

[0058] Based on the benchmark correlation model and the corrected flight parameters and current identifier spatial coordinates in the current monitoring data, calibration processing is performed on the currently acquired image in the current monitoring data and its features are compared with the benchmark image to obtain the feature comparison results.

[0059] Based on the feature comparison results, the crack propagation parameters and deformation characteristic parameters of the regional lattice beams are analyzed.

[0060] Based on the crack propagation parameters, the deformation characteristic parameters, and the cumulative flight trajectory deviation determined during the dynamic correction of the flight trajectory, a graded early warning information for regional geological disaster prevention and control is generated.

[0061] The specific embodiments of the present invention applied to the device are basically the same as the embodiments of the application area geological disaster prevention and management methods described below, and will not be repeated here.

[0062] This invention provides a regional geological disaster prevention and management method, referring to... Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of the regional geological disaster prevention and management method of the present invention.

[0063] In this embodiment, a regional geological disaster prevention and management method includes the following steps:

[0064] S100: Obtain the benchmark monitoring data of the regional lattice beam and construct the benchmark association model; wherein, the benchmark monitoring data includes the benchmark identifier spatial coordinates, benchmark flight parameters and benchmark identifier pixel coordinates.

[0065] Specifically, the monitoring drone is controlled to perform terrain-following flight close to the slope of the lattice beam in the area with preset benchmark markers, and collect benchmark images of the lattice beam along the preset benchmark flight path; the RTK module on the monitoring drone is used to record the three-dimensional spatial coordinates of each benchmark marker as benchmark marker spatial coordinates, and the attitude sensor on the monitoring drone is used to record the drone's benchmark flight parameters, and the benchmark marker pixel coordinates in the benchmark images are extracted as benchmark marker pixel coordinates; a mapping relationship between benchmark marker spatial coordinates, benchmark flight parameters and benchmark marker pixel coordinates is established to generate a benchmark relationship model.

[0066] In this embodiment of the invention, the placement of reference markers is fundamental to obtaining reliable reference data. At the intersections and critical stress locations in the mid-span of the regional lattice beams, several circular reference markers with unique numbers are uniformly pre-set. Each marker has a uniform physical diameter of 20cm and employs a high-contrast red and white design to ensure clear identification by drones in complex slope environments. At least three markers are used, covering different heights and lateral positions of the lattice beams to prevent marker failure due to partial obstruction.

[0067] In the baseline image acquisition phase, the monitoring drone is controlled to fly along a preset baseline flight path in a slope-following, terrain-mimicking flight mode. Before flight, the flight path is planned according to the slope gradient of the lattice beam to ensure that the drone maintains a stable vertical distance from the slope (the vertical slope height in the baseline flight parameters is preset to 5-8m). During flight, the high-definition visible light camera on the drone acquires baseline images at fixed sampling intervals. Simultaneously, the RTK module records the three-dimensional spatial coordinates of each baseline marker, and the attitude sensor records the drone's baseline flight parameters, including vertical slope height, camera-to-slope angle, roll angle, and yaw angle. All data is timestamped to ensure time synchronization.

[0068] Extracting the pixel coordinates of the reference markers requires image preprocessing. First, radial distortion correction is performed on the acquired reference image to eliminate the influence of lens optical distortion on the marker shape. After correction, a threshold segmentation algorithm (based on red-white color contrast) is used to extract candidate regions for the markers, and then a contour detection algorithm is used to filter out circular contours, determining the pixel coordinates of each reference marker (with the top-left corner of the image as the origin). Finally, a mapping relationship is established based on the pinhole imaging principle of a camera, constructing a reference association model. Through fitting operations, a one-to-one correspondence between spatial coordinates, flight parameters, and pixel coordinates is achieved, providing a unified reference benchmark for subsequent flight trajectory correction and image calibration.

[0069] S200: Based on the aforementioned benchmark association model, control the monitoring drone to execute the current monitoring task. While the monitoring drone collects current monitoring data including corrected flight parameters, currently acquired images, and currently identified spatial coordinates, simultaneously and dynamically correct the flight trajectory of the drone executing the current monitoring task.

[0070] Specifically, step S200 includes the following sub-steps:

[0071] Step S210: Using the baseline flight parameters in the baseline association model as initial configuration parameters, control the monitoring UAV to start the current monitoring task and collect the current images of the regional lattice beams in real time according to the initial flight path.

[0072] In this embodiment of the invention, when the current monitoring task is started, the baseline flight parameters (vertical slope height, camera-slope angle, etc.) in the baseline association model are first called as the initial configuration parameters of the UAV to ensure that the initial flight path is consistent with the baseline flight path. The UAV flies along the initial flight path, and the onboard high-definition camera collects the currently acquired images in real time at the same sampling interval as the baseline acquisition. The image resolution and imaging parameters are consistent with the baseline acquisition, avoiding changes in image features due to differences in imaging parameters.

[0073] Step S220: Use the RTK module on the monitoring drone to obtain the current spatial coordinates of the marker, use the attitude sensor on the monitoring drone to obtain the real-time flight parameters of the monitoring drone, and extract the pixel coordinates of the reference marker in the currently acquired image as the real-time marker pixel coordinates.

[0074] The RTK module outputs the current marker spatial coordinates in real time, with an update frequency synchronized with the image acquisition frequency, ensuring that each currently acquired image has corresponding marker spatial coordinates. The attitude sensor synchronously acquires the UAV's real-time flight parameters, including real-time vertical slope height, real-time camera-to-slope angle, real-time roll angle, and yaw angle. Using threshold segmentation and contour detection algorithms consistent with the baseline marker extraction, the real-time marker pixel coordinates are quickly extracted, ensuring timely feedback of marker position information during UAV flight.

[0075] Step S230: Compare the real-time identifier pixel coordinates with the reference identifier pixel coordinates in the reference association model, calculate the horizontal and vertical pixel offsets of each identifier, and take the average horizontal and vertical pixel offsets of all identifiers as the corrected flight parameters. Horizontal pixel offset Vertical pixel offset ,in , Let be the reference pixel coordinates of the i-th identifier in the baseline association model. To avoid the influence of individual identifier extraction errors, calculate the average pixel offset of all valid identifiers (unoccluded and with complete outlines). Average vertical pixel offset (n is the number of valid identifiers) and As a core correction flight parameter, it reflects the overall deviation between the current flight trajectory and the reference route.

[0076] Step S24: Combining the baseline flight parameters in the baseline association model, the average level pixel offset and average vertical pixel offset are converted into the drone's altitude adjustment, horizontal position adjustment and angle adjustment through a preset mapping formula, so as to dynamically correct the drone's flight trajectory when performing the current monitoring task.

[0077] In this embodiment, the preset mapping formula is constructed based on the inverse mapping relationship of the benchmark correlation model, and derived by combining the camera imaging principle and geometric relationship:

[0078] (1) Height adjustment amount: ;in, The vertical ramp height is the reference flight parameter. The angle between the reference camera and the slope. The x-coordinate of the principal point A positive value indicates that the drone needs to ascend, while a negative value indicates that it needs to descend.

[0079] (2) Horizontal position adjustment amount: ;in, A positive value indicates that the drone needs to be adjusted in the horizontal direction along the slope, while a negative value indicates that it needs to be adjusted in the opposite direction.

[0080] (3) Angle adjustment amount: ;in, This is the adjustment amount for the angle between the camera and the slope, used to correct image distortion caused by viewpoint shift.

[0081] Therefore, the UAV flight control system receives the above adjustments in real time, dynamically updates flight parameters, corrects flight trajectory, and ensures that the current flight is as close as possible to the reference route, reducing the difficulty of subsequent image calibration.

[0082] Step S25: After completing the current monitoring task, the corrected flight parameters, the currently acquired images, and the current marker spatial coordinates are associated and stored to form the current monitoring data.

[0083] In this embodiment, the associated storage rule is as follows: file names are based on acquisition timestamp-identifier number-parameter type to ensure that each currently acquired image corresponds to a unique corrected flight parameter and current identifier spatial coordinates. The timestamp enables a one-to-one correspondence between the current monitoring data and the baseline monitoring data, and the identifier number ensures that the parameters of the same physical identifier are traceable, providing complete data support for subsequent image calibration and feature comparison.

[0084] S300: Based on the reference correlation model and the corrected flight parameters and current marker spatial coordinates in the current monitoring data, perform calibration processing on the currently acquired image in the current monitoring data and compare its features with the reference image to obtain the feature comparison result. Specifically, firstly, based on the physical diameter and reference scale factor of the reference marker, combined with the reference flight parameters and corrected flight data, calculate the calibrated scale factor of the currently acquired image. Reference scale factor Where D is the physical diameter of the reference mark. The diameter of the pixels identified in the reference image. Scale factor after calibration. The calculation formula is: ;in, To correct the vertical ramp height in the flight parameters, To correct the angle between the camera and the slope in the flight parameters, this formula eliminates the image scale differences caused by changes in flight altitude and angle.

[0085] Subsequently, using the reference marker spatial coordinates in the reference association model as the reference, and taking the horizontal translation in the corrected flight parameters as the initial registration parameter, the iterative nearest-point algorithm is used to perform registration operations on the current marker spatial coordinates. A reference marker spatial coordinate set is then established. Current identifier space coordinate set Initial translation vector ( For the corrected horizontal coordinates of the UAV, (Using the baseline UAV's horizontal coordinates), construct the error function: Where R is the rotation matrix, To fine-tune the translation vector, the error function is solved iteratively. Minimize to obtain the current identifier space coordinate set after registration. This enables precise alignment of spatial coordinates.

[0086] Based on calibrated scale factor and the current identifier space coordinates after registration The scale and spatial position of the currently acquired image are adjusted to ensure that it is on the same scale and in the same spatial coordinate system as the reference image. The Canny edge detection algorithm is used to extract crack region features from both the reference image and the calibrated currently acquired image. The high and low thresholds of the Canny algorithm are determined adaptively (based on the image grayscale histogram). The extracted crack features include the pixel coordinates, contour shape, and endpoint positions of the cracks. A feature point matching algorithm (such as SIFT) is used to compare the crack regions in the two images to determine the positional correspondence of the same crack, thus obtaining the feature comparison results.

[0087] S400: Based on feature comparison results, analyze the crack propagation parameters and deformation characteristic parameters of the regional lattice beam. Specifically, based on the calibrated scale factor... Calculate the crack propagation parameters. Crack width in the reference image. Crack width in the currently acquired image ,in , These represent the number of pixels in the vertical direction of the crack in the reference image and the current image, respectively; similarly, the crack length... , ,in , These represent the pixel distances between the beginning and end points of the crack. Length expansion The analysis of deformation feature parameters includes three parts: first, based on the current identifier space coordinates after registration. The actual displacement of the lattice beam node is calculated based on the difference between the coordinates of the lattice beam node and the coordinates of the reference point A. ;

[0088] Secondly, using the key areas of the lattice beam (mid-span and node connections) in the reference image as templates, a sub-pixel template matching algorithm is used to match them in the currently acquired image to obtain the horizontal pixel displacement. and vertical pixel displacement , combined Converted into actual deformation: Third, obtain the time interval between the current monitoring and the baseline monitoring. (Calculated from the acquisition timestamp), the nodal displacement rate is obtained: Ultimately, the actual displacement of the node Actual deformation and displacement rate Together they constitute the deformation characteristic parameters.

[0089] S500: Based on the crack propagation parameters, the deformation characteristic parameters, and the cumulative flight trajectory deviation determined during the dynamic correction of the flight trajectory, generate graded early warning information for regional geological disaster prevention and control.

[0090] Specifically, first, the cumulative flight trajectory deviation S is calculated. Then, the sum of the absolute values ​​of all altitude adjustments during the dynamic correction process is calculated. The sum of the first absolute values ​​and the sum of the absolute values ​​of all angle adjustments. (the second absolute sum), combined with the vertical ramp height in the baseline flight parameters. The calculation formula is: The angle adjustment amount is multiplied by... It is converted into an equivalent distance deviation to ensure dimensional uniformity. S quantifies the overall consistency of the two flight trajectories. The smaller S is, the higher the data reliability.

[0091] Set graded early warning thresholds: daily crack width expansion threshold Daily crack length expansion threshold Node displacement rate threshold Local actual deformation threshold The first preset value is 2m, the second preset value is 1m, and the third preset value is 0.5m.

[0092] The rules for determining the warning level are as follows: If (First preset value) and , , , If any one of the following conditions is met, it is determined to be a Level 1 warning (yellow warning); if (Second preset value) and at least two of the above four conditions are met, it is determined to be a Level II warning (orange warning); if (Third preset value) If at least three of the above four conditions are met, it is determined to be a Level 3 warning (red warning).

[0093] Ultimately, the generated tiered early warning information includes the early warning level, details of indicators exceeding the threshold, cumulative deviation of flight trajectory (data reliability), and the specific location of the affected lattice beam (based on the spatial coordinate positioning of the benchmark). This information is then pushed to relevant personnel through preset channels (such as management platforms and mobile terminal apps) to provide accurate decision-making basis for geological disaster prevention and control.

[0094] Reference Figure 3 , Figure 3 This is a structural block diagram of an embodiment of the regional geological disaster prevention and management device of the present invention.

[0095] like Figure 3 As shown, the regional geological disaster prevention and management device proposed in this embodiment of the invention includes:

[0096] Module 10 is used to acquire benchmark monitoring data of regional lattice beams and construct a benchmark association model; wherein, the benchmark monitoring data includes benchmark identifier spatial coordinates, benchmark flight parameters, and benchmark identifier pixel coordinates;

[0097] The correction module 20 is used to control the monitoring drone to perform the current monitoring task based on the benchmark association model. While the monitoring drone collects current monitoring data including corrected flight parameters, currently acquired images and current identifier spatial coordinates, the module dynamically corrects the flight trajectory of the drone to perform the current monitoring task.

[0098] The comparison module 30 is used to perform calibration processing on the currently acquired image in the current monitoring data based on the benchmark association model and the corrected flight parameters and current identifier spatial coordinates in the current monitoring data, and compare the features with the benchmark image to obtain the feature comparison result;

[0099] Analysis module 40 is used to analyze the crack propagation parameters and deformation characteristic parameters of the regional lattice beam based on the feature comparison results;

[0100] The early warning module 50 is used to generate graded early warning information for regional geological disaster prevention and control based on the crack propagation parameters, the deformation characteristic parameters, and the cumulative amount of flight trajectory deviation determined during the dynamic correction of the flight trajectory.

[0101] Other embodiments or specific implementations of the regional geological disaster prevention and management device of the present invention can be referred to the above-described method embodiments, and will not be repeated here.

[0102] Furthermore, the present invention also proposes a regional geological disaster prevention and management device, which includes: a memory, a processor, and a regional geological disaster prevention and management program stored in the memory and executable on the processor. When the regional geological disaster prevention and management program is executed by the processor, it implements the steps of the regional geological disaster prevention and management method described above.

[0103] The specific implementation method of the regional geological disaster prevention and control management equipment in this application is basically the same as the various embodiments of the above-mentioned regional geological disaster prevention and control management methods, and will not be repeated here.

[0104] Furthermore, this invention also proposes a readable storage medium, which includes a computer-readable storage medium storing a regional geological disaster prevention and management program thereon. The readable storage medium may be... Figure 1 The memory 1005 in the terminal can also be at least one of ROM (Read-Only Memory) / RAM (Random Access Memory), magnetic disk, optical disk, etc. The readable storage medium includes several instructions to cause a regional geological disaster prevention and management device with a processor to execute the regional geological disaster prevention and management method described in the various embodiments of the present invention.

[0105] The specific implementation methods in the readable storage medium of this application are basically the same as those in the above-described embodiments of the regional geological disaster prevention and management methods, and will not be repeated here.

[0106] It is understood that in the description of this specification, references to terms such as "one embodiment," "another embodiment," "other embodiments," or "first embodiment to Nth embodiment," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0107] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0108] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0109] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0110] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for regional geological disaster prevention and management, characterized in that, Includes the following steps: Acquire benchmark monitoring data of the regional lattice beams and construct a benchmark association model; wherein, the benchmark monitoring data includes benchmark identifier spatial coordinates, benchmark flight parameters, and benchmark identifier pixel coordinates; Specifically, this includes: controlling a monitoring drone to perform terrain-following flight close to the slope of a lattice beam in an area with preset benchmark markers, and collecting benchmark images of the lattice beam along a preset benchmark flight path; using the RTK module on the monitoring drone to record the three-dimensional spatial coordinates of each benchmark marker as benchmark marker spatial coordinates, using the attitude sensor on the monitoring drone to record the drone's benchmark flight parameters, and extracting the benchmark marker pixel coordinates from the benchmark images as benchmark marker pixel coordinates; establishing a mapping relationship between benchmark marker spatial coordinates, benchmark flight parameters, and benchmark marker pixel coordinates to generate a benchmark relationship model; Based on the aforementioned benchmark correlation model, the monitoring drone is controlled to perform the current monitoring task. While the monitoring drone collects current monitoring data including corrected flight parameters, currently acquired images, and currently identified spatial coordinates, the flight trajectory of the drone performing the current monitoring task is simultaneously and dynamically corrected. Specifically, this includes: using the baseline flight parameters in the baseline association model as initial configuration parameters, controlling the monitoring drone to start the current monitoring task, and collecting current images of the regional lattice beams in real time according to the initial flight path; using the RTK module on the monitoring drone to obtain the current marker spatial coordinates, using the attitude sensor on the monitoring drone to obtain the real-time flight parameters of the monitoring drone, and extracting the pixel coordinates of the baseline markers in the currently collected images as the real-time marker pixel coordinates; comparing the real-time marker pixel coordinates with the baseline marker pixel coordinates in the baseline association model, calculating the horizontal and vertical pixel offsets of each marker, and taking the average horizontal and vertical pixel offsets of all markers as the corrected flight parameters; combining the baseline flight parameters in the baseline association model, converting the average horizontal and vertical pixel offsets into the drone's altitude adjustment, horizontal position adjustment, and angle adjustment through a preset mapping formula, dynamically correcting the drone's flight trajectory for the current monitoring task; after completing the current monitoring task, associating and storing the corrected flight parameters, the currently collected images, and the current marker spatial coordinates to form the current monitoring data; Based on the benchmark correlation model and the corrected flight parameters and current identifier spatial coordinates in the current monitoring data, calibration processing is performed on the currently acquired image in the current monitoring data and its features are compared with the benchmark image to obtain the feature comparison results. Specifically, this includes: calculating the calibrated scale factor of the currently acquired image based on the physical diameter and scale factor of the reference marker, combined with the reference flight parameters and corrected flight data in the reference association model; using the spatial coordinates of the reference marker in the reference association model as a reference, taking the horizontal translation in the corrected flight parameters as the initial registration parameter, and using the iterative nearest point algorithm to perform registration operations on the spatial coordinates of the current marker, minimizing the coordinate deviation to obtain the registered spatial coordinates of the current marker; adjusting the currently acquired image and the reference image to the same scale and spatial position based on the calibrated scale factor and the registered spatial coordinates of the current marker; extracting crack region features in the reference image and the calibrated currently acquired image using edge detection, and comparing the corresponding crack regions using a feature point matching algorithm to obtain feature comparison results; Based on the feature comparison results, the crack propagation parameters and deformation characteristic parameters of the regional lattice beams are analyzed. Based on the crack propagation parameters, the deformation characteristic parameters, and the cumulative flight trajectory deviation determined during the dynamic correction flight trajectory process, a graded early warning information for regional geological disaster prevention and control is generated. Specifically, this includes: summing the first absolute value of all altitude adjustments and summing the second absolute value of all angle adjustments during the dynamic correction of the flight trajectory, and combining this with the vertical slope height in the baseline flight parameters to calculate the cumulative flight trajectory deviation; comparing the crack expansion parameters and deformation characteristic parameters with the judgment conditions of the graded early warning threshold, and combining this with the cumulative flight trajectory deviation to generate graded early warning information for regional geological disaster prevention and control. Specifically, based on the cumulative flight trajectory deviation, a graded early warning information for regional geological disaster prevention and control is generated. This includes: a Level 1 early warning is generated when the cumulative flight trajectory deviation is less than or equal to a first preset value and any one of the crack propagation parameter or deformation characteristic parameter triggers a threshold; a Level 2 early warning is generated when the cumulative flight trajectory deviation is less than or equal to a second preset value and at least two of the crack propagation parameter or deformation characteristic parameter triggers a threshold; and a Level 3 early warning is generated when the cumulative flight trajectory deviation is less than or equal to a third preset value and at least three of the crack propagation parameter or deformation characteristic parameter triggers a threshold.

2. The regional geological disaster prevention and management method as described in claim 1, characterized in that, Based on the feature comparison results, the steps for analyzing the crack propagation parameters and deformation characteristic parameters of the regional lattice beam include: Based on the calibrated scale factor, the width and length of the crack in the reference image and the currently acquired image are calculated to obtain the crack width expansion amount and crack length expansion amount as crack expansion parameters. Based on the difference between the current identifier spatial coordinates and the reference identifier spatial coordinates after registration, the actual displacement of the lattice beam node is calculated. Using the preset key area of ​​the lattice beam in the reference image as a template, matching is performed in the currently acquired image to obtain the horizontal and vertical pixel displacements of the preset key area. The pixel displacements are then converted into actual deformations by combining the calibrated size factor. The time interval between the current monitoring task and the benchmark monitoring is obtained. The displacement rate of the lattice beam node is obtained by calculating the ratio of the actual displacement to the time interval. The actual displacement, actual deformation, and displacement rate of the node are used as deformation characteristic parameters.

3. A regional geological disaster prevention and management device, used to execute the regional geological disaster prevention and management method as described in any one of claims 1-2, characterized in that, include: A construction module is used to acquire benchmark monitoring data of regional lattice beams and construct a benchmark association model; wherein, the benchmark monitoring data includes benchmark identifier spatial coordinates, benchmark flight parameters, and benchmark identifier pixel coordinates; The correction module is used to control the monitoring drone to perform the current monitoring task based on the benchmark association model. While the monitoring drone collects current monitoring data including corrected flight parameters, currently acquired images and currently identified spatial coordinates, the module simultaneously and dynamically corrects the flight trajectory of the drone to perform the current monitoring task. The comparison module is used to perform calibration processing on the currently acquired image in the current monitoring data based on the benchmark association model and the corrected flight parameters and current identifier spatial coordinates in the current monitoring data, and compare the features with the benchmark image to obtain the feature comparison result; The analysis module is used to analyze the crack propagation parameters and deformation characteristic parameters of the regional lattice beam based on the feature comparison results. The early warning module is used to generate graded early warning information for regional geological disaster prevention and control based on the crack propagation parameters, the deformation characteristic parameters, and the cumulative amount of flight trajectory deviation determined during the dynamic correction of the flight trajectory.

4. A regional geological disaster prevention and management device, characterized in that, The regional geological disaster prevention and management equipment includes: a memory, a processor, and a regional geological disaster prevention and management program stored in the memory and executable on the processor. When the regional geological disaster prevention and management program is executed by the processor, it implements the steps of the regional geological disaster prevention and management method as described in any one of claims 1 to 2.

5. A storage medium, characterized in that, The storage medium stores a regional geological disaster prevention and control management program, which, when executed by a processor, implements the steps of the regional geological disaster prevention and control management method as described in any one of claims 1 to 2.

Images