Earthquake motion amplification coefficient real-time detection method and device based on unmanned aerial vehicle image recognition technology

Abstract

The invention discloses a seismic oscillation amplification coefficient real-time detection method and device based on an unmanned aerial vehicle image recognition technology. The method comprises the steps that after earthquake early warning information is received, a plurality of unmanned aerial vehicles are controlled to enter a to-be-detected area to collect monitoring images of the earth surface; receiving a monitoring image sent back by the unmanned aerial vehicle in real time through a wireless transmission technology; recognizing a displacement difference value, a speed difference value and an acceleration difference value of the earth surface of the to-be-measured area by using the original image of the earth surface before the earthquake, the monitoring image in the epicenter and the original three-dimensional terrain model; calculating propagation characteristics and seismic oscillation amplification coefficients of seismic waves in different terrains and earth surfaces by combining a seismic engineering principle and utilizing a displacement difference value, a speed difference value and an acceleration difference value of the earth surface of a to-be-measured area; and generating a seismic oscillation amplification coefficient distribution diagram through data analysis and modeling. The technical problem that in the prior art, the timeliness of collecting the seismic oscillation amplification coefficient is poor is solved.

Description

Technical Field

[0001] The present application relates to the field of earthquake detection technology, and more specifically, to a real-time detection method and device for earthquake amplification coefficient based on drone image recognition technology. Background Art

[0002] This section is intended to provide a background or context to what is stated in the claims or specification, and nothing described herein is admitted to be prior art by inclusion in this section.

[0003] Earthquakes, a powerful natural phenomenon with unpredictable explosive power and devastating consequences, have long been a serious challenge facing human society. They can not only instantly destroy buildings and claim lives, but also profoundly impact the balance and recovery of the natural environment. Accurately assessing the propagation characteristics of seismic waves and their energy amplification under varying surface geological conditions—the seismic amplification factor—is crucial in earthquake response and prevention. This parameter is not only an indispensable reference for construction engineers designing earthquake-resistant structures, but also a crucial foundation for geologists to predict and assess geological hazard risks.

[0004] Existing techniques for determining seismic amplification factors rely primarily on data collected by ground-based observation stations, which are then analyzed and calculated using complex physical models. While accurate, this approach has significant limitations. For one thing, ground-based observation stations are expensive to build and maintain, and their geographical location limits their ability to fully cover remote, complex, or inaccessible terrain. Furthermore, the computational complexity of the physical models consumes significant time and computing resources, resulting in slow data updates and a difficulty in responding to changes in seismic activity.

[0005] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0006] The present invention provides a real-time detection method and device for seismic amplification coefficients based on drone image recognition technology. This method employs drone image recognition and segmentation technology based on computer vision. By leveraging high-precision drone-mounted image acquisition equipment, combined with advanced image processing and data analysis techniques, the method aims to rapidly and accurately collect seismic amplification coefficients, providing important data support for earthquake engineering research and disaster prevention and mitigation. This method addresses the existing technical issue of poor timeliness in collecting seismic amplification coefficients.

[0007] According to one aspect of an embodiment of the present application, a real-time detection method for seismic amplification coefficient based on drone image recognition technology is provided, comprising: after receiving earthquake early warning information, controlling multiple drones to enter the area to be tested to collect monitoring images of the surface; receiving monitoring images transmitted back by the drones in real time through wireless transmission technology; using the original image of the surface before the earthquake, the monitoring image of the epicenter, and the original three-dimensional terrain model to identify the displacement difference, velocity difference, and acceleration difference of the surface of the area to be tested; combining the principles of earthquake engineering, using the displacement difference, velocity difference, and acceleration difference of the surface of the area to be tested to calculate the propagation characteristics of seismic waves in different terrains and surfaces and the seismic amplification coefficient; and generating a seismic amplification coefficient distribution map through data analysis and modeling.

[0008] Optionally, before receiving earthquake warning information, the method also includes: preprocessing and enhancing the collected surface images, extracting features, and classifying and identifying them, and constructing an original three-dimensional terrain model by identifying surface morphological features, thereby providing basic data for the calculation of the seismic motion amplification coefficient.

[0009] Optionally, the collected surface images are preprocessed and enhanced, feature extracted and classified, and the original three-dimensional terrain model is constructed by identifying the surface morphological features, including: image preprocessing of the surface image: using a filtering algorithm to denoise the collected surface image to eliminate random noise and interference signals in the surface image to improve the image signal-to-noise ratio; then using histogram equalization and Laplace sharpening to enhance the contrast of the surface image to make the surface features more prominent; according to the distortion characteristics of the camera lens, the surface image is geometrically corrected to eliminate image distortion and deformation caused by lens distortion; obtaining a point cloud dataset: importing the preprocessed surface image, and The SIFT algorithm in the Open3D library is used to match the feature points of each surface image to obtain the point cloud data and corresponding three-dimensional spatial coordinates required for model construction; the model is constructed using the point cloud dataset: the alpha shape algorithm in the Open3D library or the Delaunay algorithm in the scipy library is used to triangulate the point cloud data in the point cloud dataset, and then the triangulated dataset is visualized using the matplotlib library or the plotly library to generate a three-dimensional terrain model; the generated three-dimensional terrain model is optimized: redundant data is removed and the surface is smoothed to improve the model's accuracy and rendering efficiency, ultimately forming the original three-dimensional terrain model for subsequent analysis.

[0010] Optionally, using original pre-earthquake surface images, monitoring images of the epicenter, and the original three-dimensional terrain model, the displacement differences, velocity differences, and acceleration differences of the surface in the area to be measured are identified. This includes preprocessing and enhancing the acquired monitoring images, extracting features, and classifying and identifying them to construct a three-dimensional terrain model by identifying surface morphological features; sorting the three-dimensional terrain model by the acquisition time of the monitoring images, converting the three-dimensional terrain into node information, calculating the phase differences of the corresponding nodes, and then using the finite difference method to calculate the displacement differences, velocity differences, and acceleration differences at different nodes.

[0011] Optionally, the phase difference of the corresponding nodes is obtained by calculation, and then the finite difference method is used to calculate the displacement difference, velocity difference and acceleration difference of different nodes, including: using the KNN algorithm or the FLANN algorithm to perform local similarity matching of feature descriptors, and establishing the correspondence between the monitoring image of the drone at different times and the original three-dimensional terrain model; aligning the local coordinate system of the monitoring image of the drone with the global coordinate system of the original three-dimensional terrain model, and determining the displacement difference, velocity difference and acceleration difference of each feature point according to the three-dimensional coordinates of the feature point at different times.

[0012] Optionally, after converting the three-dimensional terrain into node information, the method further includes: calculating and obtaining local features of the terrain based on the node information within the area.

[0013] Optionally, the method further includes: visually displaying the distribution map of the seismic amplification coefficient; and outputting calculation reports and data files to provide a basis for the seismic design of building structures and the prediction and assessment of geological disasters.

[0014] According to another aspect of an embodiment of the present application, a real-time detection device for seismic amplification coefficient based on drone image recognition technology is also provided, including: an acquisition unit, which is used to control multiple drones to enter the area to be tested to collect monitoring images of the surface after receiving earthquake early warning information; a receiving unit, which is used to receive monitoring images transmitted back by the drone in real time through wireless transmission technology; an identification unit, which is used to use the original image of the surface before the earthquake, the monitoring image of the epicenter and the original three-dimensional terrain model to identify the displacement difference, velocity difference and acceleration difference of the surface of the area to be tested; a calculation unit, which is used to combine the principles of earthquake engineering and use the displacement difference, velocity difference and acceleration difference of the surface of the area to be tested to calculate the propagation characteristics of seismic waves in different terrains and surfaces and the seismic amplification coefficient; a generation unit, which is used to generate a seismic amplification coefficient distribution map through data analysis and modeling.

[0015] According to another aspect of an embodiment of the present application, a computer-readable storage medium is further provided, which includes a stored program, and the above method is executed when the program is run.

[0016] According to another aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above method through the computer program.

[0017] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of any of the above-described method embodiments.

[0018] In an embodiment of the present application, after receiving earthquake warning information, multiple drones are controlled to enter the area to be tested to collect monitoring images of the ground surface; the monitoring images transmitted back by the drones in real time via wireless transmission technology are received; the original image of the ground surface before the earthquake, the monitoring image of the epicenter, and the original three-dimensional terrain model are used to identify the displacement difference, velocity difference, and acceleration difference of the ground surface in the area to be tested; in combination with the principles of earthquake engineering, the displacement difference, velocity difference, and acceleration difference of the ground surface in the area to be tested are used to calculate the propagation characteristics of seismic waves in different terrains and surfaces and the seismic amplification coefficient; through data analysis and modeling, a distribution map of the seismic amplification coefficient is generated. This solution uses high-precision image acquisition equipment carried by drones, combined with advanced image processing and data analysis technologies, to quickly and accurately collect seismic amplification coefficients, thereby solving the technical problem of poor timeliness in collecting seismic amplification coefficients in the existing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 This is a flowchart of an optional real-time detection method for earthquake amplification coefficient based on drone image recognition technology according to an embodiment of the present application; Figure 2 is a schematic diagram of an optional real-time detection device for earthquake amplification coefficient based on drone image recognition technology according to an embodiment of the present application; Figure 3 This is a structural block diagram of a terminal according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] The rapid development of drone technology and the increasing sophistication of image recognition techniques have revolutionized the collection of seismic amplification factors. As a prominent representative of modern science and technology, drones, with their unique advantages, have shone brightly in diverse fields such as geological mapping and environmental monitoring. They can overcome terrestrial obstacles, freely traversing mountains, rivers, and oceans. Their exceptional flexibility and wide coverage enable rapid scanning and data collection in complex terrain.

[0023] More importantly, when drones are combined with advanced image recognition technology, their potential is further unlocked. High-resolution cameras and other sensors onboard drones can capture subtle changes in surface texture and transmit this information back to ground processing centers in real time via wireless transmission. Subsequently, image recognition algorithms are used to process and analyze this massive amount of data, automatically extracting key information about surface morphological changes caused by earthquakes, providing a rich data source for constructing various real-time 3D terrain models.

[0024] These 3D terrain models not only intuitively demonstrate the complex and diverse surface morphology but also reveal the propagation patterns of seismic waves under different geological conditions. Based on these models, the seismic amplification factor can be accurately calculated. Compared with traditional physical models, this method not only improves computational efficiency and accuracy but also significantly increases the amount of surface seismic data obtained.

[0025] Based on this, according to one aspect of the present application, a method embodiment is provided for real-time detection of seismic amplification factors using drone image recognition technology. The core of this application lies in combining drone image recognition technology with earthquake engineering to achieve rapid, non-contact collection of seismic amplification factors. Compared to traditional manual measurement and ground observation methods, this application offers greater efficiency and accuracy, can cover a wider geographic area, and update data in real time, while also acquiring a larger amount of data, providing a scientific basis for earthquake risk assessment, seismic design, and post-disaster reconstruction. Furthermore, this application emphasizes real-time data processing and visualization. By constructing a seismic amplification factor database and a geographic information system (GIS) platform, rapid data query, analysis, and sharing are achieved, providing convenient data support for earthquake science research and engineering applications. With advantages such as high efficiency, accuracy, real-time performance, visualization, and the acquisition of a large amount of data, this method is of great significance for improving earthquake engineering research and disaster prevention and mitigation capabilities.

[0026] Figure 1 This is a flow chart of an optional real-time detection method for earthquake amplification coefficient based on drone image recognition technology according to an embodiment of the present application, such as Figure 1 As shown, the method may include the following steps: Step S102: After receiving the earthquake warning information, control multiple drones to enter the area to be tested to collect monitoring images of the surface.

[0027] Step S104: receiving the monitoring image transmitted back in real time by the drone via wireless transmission technology.

[0028] Step S106 , using the original image of the ground surface before the earthquake, the monitoring image of the epicenter, and the original three-dimensional terrain model, the displacement difference, velocity difference, and acceleration difference of the ground surface in the area to be measured are identified.

[0029] Step S108 , combining earthquake engineering principles, uses displacement differences, velocity differences, and acceleration differences on the surface of the area to be measured to calculate the propagation characteristics of seismic waves in different terrains and surfaces and the ground motion amplification coefficient.

[0030] The propagation characteristics of seismic waves refer to the physical characteristics and behavioral laws exhibited by seismic waves during their propagation inside the earth or on the surface, such as: wave type (body waves, longitudinal waves P waves, transverse waves S waves, surface waves, Rayleigh waves, Love waves), propagation speed, etc.

[0031] The value of the seismic amplification coefficient is the ratio of the measured point to the point with the weakest movement inside the model, such as the displacement ratio, velocity ratio, and acceleration ratio.

[0032] Step S110 : generating a seismic amplification coefficient distribution map through data analysis and modeling.

[0033] According to the technical solution of the present application, first, after receiving earthquake warning information, multiple drones carrying high-resolution cameras or video cameras take off and enter a preset area to take photos and videos, obtaining detailed surface images and three-dimensional model data before and during the earthquake; secondly, through image recognition technology, the displacement difference, velocity difference and acceleration difference of the complex terrain surface in the area to be measured during the earthquake are automatically identified and extracted; then, combined with the principles of earthquake engineering, these data are used to calculate the propagation characteristics and amplification effect of seismic waves on different terrain surfaces; finally, through data analysis and modeling, the seismic motion amplification coefficient is obtained, and a detailed seismic motion amplification coefficient distribution map is generated. This solution uses high-precision image acquisition equipment carried by drones, combined with advanced image processing and data analysis technologies, to quickly and accurately collect seismic motion amplification coefficients, thereby solving the technical problem of poor timeliness in collecting seismic motion amplification coefficients in the existing technology.

[0034] This application aims to provide a method for collecting seismic amplification factors based on drone image recognition. This method uses a high-definition camera mounted on a drone to capture surface images before and after an earthquake, extracts surface deformation information using image recognition technology, and then calculates and collects seismic amplification factors by combining seismological theory with data processing algorithms. As an optional embodiment, the following further details the technical solution of this application in conjunction with specific implementation methods: This solution aims to provide a method for collecting seismic amplification factors based on drone image recognition technology. By combining drone remote sensing imagery with advanced image processing and data analysis techniques, this method enables rapid and accurate collection of seismic amplification factors in complex terrain. From a functional perspective, the solution can be divided into the following modules: 3D modeling, image acquisition, data analysis, and data collection.

[0035] 3D Modeling Module: Utilizes advanced image recognition algorithms to pre-process, extract features, and classify captured images. By identifying features such as surface morphology, a real-time 3D terrain model is constructed, providing basic data for calculating the seismic amplification factor.

[0036] The UAV monitoring module captures real-time surface images during flight and transmits these images back to a ground processing center via wireless transmission technology. The system supports multiple image formats and resolutions to accommodate different geological characteristics and accuracy requirements.

[0037] Data Analysis Module: This module arranges the 3D terrain model in time sequence and converts it into node information. Phase differences between corresponding nodes are calculated, and the finite difference method is used to calculate the displacement, velocity, and acceleration amplification factor of each node. Furthermore, local terrain features such as height, longitudinal slope, and transverse slope can be calculated based on the node information within the region.

[0038] Data Collection Module: This module visualizes calculation results in the form of charts and images, allowing users to intuitively understand the distribution of seismic amplification coefficients. It also outputs detailed calculation reports and data files, providing a scientific basis for seismic design of building structures and prediction and assessment of geological hazards.

[0039] The steps to achieve this are as follows: 1) Drone aerial photography 1.1) Data Collection and Analysis: First, basic data such as topographic maps, satellite images, and weather forecasts of the exploration area are collected, and factors such as terrain undulations, vegetation cover, and climate characteristics in the area are analyzed.

[0040] 1.2) Equipment Inspection and Calibration: Before flight, conduct a comprehensive inspection of the cameras, laser scanners, and other image acquisition equipment onboard multiple drones to ensure proper operation and correct parameter settings. Perform necessary calibrations, such as correcting camera lens distortion and verifying laser scanner accuracy.

[0041] 1.3) Flight Path Planning: Based on the target area's terrain complexity, combined with terrain data and drone performance parameters (such as maximum altitude, speed, and endurance), an optimal flight path (primarily using a circular approach) is planned. This path ensures that it fully covers the target area while avoiding potential risks such as no-fly zones and obstacles.

[0042] 1.4) Calculation of real terrain height: The shooting angle is downward. Angle, where a is the short frame and f is the focal length. When the height direction of the mountain completely fills the photo, the flight altitude of the drone becomes the actual height of the mountain.

[0043] 1.5) Altitude and Speed ​​Setting: Set the appropriate flight altitude and speed based on the target area's resolution requirements, 3D model accuracy requirements, image overlap ratio, and the drone's performance limitations.

[0044] Heading and lateral overlap rate and Can be set to 75%-80%.

[0045] The image acquisition time interval is approximately:

[0046] in, is the speed of the drone around the terrain, b is the long frame, The height at which the drone orbits the first layer, determined according to the model accuracy.

[0047] The surrounding rise height of each layer is .

[0048] 2) 3D model construction 2.1) Image Preprocessing: Filtering algorithms are used to denoise the captured images, eliminating random noise and interfering signals, and improving the signal-to-noise ratio. Histogram equalization and Laplace sharpening are used to enhance image contrast, making surface features more prominent and facilitating subsequent identification and analysis. Geometric correction is performed on the images based on the distortion characteristics of the camera lens to eliminate image distortion and deformation caused by lens distortion.

[0049] 2.2) Point cloud acquisition: Import the carefully processed image data and use the SIFT algorithm of the OpenCV library to match the feature points of each image to obtain the constructed point cloud data and the corresponding 3D space coordinates.

[0050] 2.3) Model construction: Use the alpha shape algorithm in the Open3D library or the Delaunay algorithm in scipy to triangulate the point cloud dataset, and further use the matplotlib or plotly library to visualize the triangulated dataset.

[0051] 2.4) Model Optimization: The generated 3D model is optimized to remove redundant data, smooth the surface, and improve model accuracy and rendering efficiency. The final 3D model is generated and passed to the analysis module.

[0052] 3) Drone monitoring 3.1) Determine the monitoring area: Determine the number of drones based on the area requirements for seismic data collection, and preset flight positions and shooting parameters for each drone. Ensure that the overlapping rate of shooting in the area to be measured reaches 100% at the same time. 3.2) Real-time monitoring: Upon receiving an earthquake warning, the drone will quickly take off, arrive at the predetermined location, and start photographing the preset area. The shooting interval ts must be less than 0.02s until the earthquake ends and the monitoring is completed.

[0053] 3.3) Real-time data transmission and processing: The drone will transmit the captured earthquake information to the data analysis module in real time.

[0054] 4) Data analysis (feature point matching) 4.1) Data Preprocessing and Enhancement: Distortion correction (radial and tangential) and projection distortion caused by flight attitude changes are performed on monitoring images to ensure that the image geometric accuracy meets feature extraction requirements. Histogram equalization or radiometric correction is used to eliminate interference such as shadows and reflections, improving the robustness of feature point detection.

[0055] 4.2) Feature Point Extraction: Use SIFT, SURF, or ORB algorithms to extract high-resolution feature points from drone imagery, preserving key points that are scale- and rotation-invariant. Based on an existing 3D model (such as a mesh or point cloud) and the drone's viewing angle, normal analysis and curvature calculation are used to extract geometrically significant feature points (such as terrain turning points) and a surface map of the three-modal model region corresponding to the drone's viewing angle.

[0056] 4.3) Cross-modal feature matching: Use the KNN (k-nearest neighbor) algorithm or FLANN (Fast Approximate Nearest Neighbor) algorithm to perform local similarity matching of feature descriptors and establish a preliminary correspondence between the drone image and the original 3D model at different times. The feature point of the original 3D model is at time M0, and the site node P to be analyzed is determined. M0 , extract the three-dimensional coordinate information of the initial moment (x M0 ,y M0 ,z M0 ), where the x direction is the horizontal propagation direction of seismic waves, the y direction is the horizontal direction perpendicular to the x direction, and the z direction is the vertical direction.

[0057] 4.4) Calculation of feature point motion at different times: Align the local coordinate system of the drone image with the global coordinate system of the 3D model. The 3D coordinates (x Mi ,y Mi ,z Mi ). Then the displacement difference of this point can be expressed as: Dx Mi =x Mi -x Mi-1 Dy Mi =y Mi -y Mi-1 Dz Mi =z Mi -z Mi-1 The velocity difference and acceleration difference of the node can be further obtained: Vx Mi =V Mi -V Mi-1 =((Dx Mi- Dx Mi-1 )-(Dx Mi-1- Dx Mi-2 )) / ts Vy Mi =V Mi -V Mi-1 =((Dy Mi- Dy Mi-1 )-(Dy Mi-1- Dy Mi-2 )) / ts VZ Mi =V Mi -V Mi-1 =((Dz Mi- Dz Mi-1 )-(Dz Mi-1- Dz Mi-2 )) / ts Ax Mi =A Mi -A Mi-1 =((Vx Mi- Vx Mi-1 )-(Vx Mi-1- Vx Mi-2 )) / ts Ay Mi =A Mi -A Mi-1 =((Vy Mi- Vy Mi-1 )-(Vy Mi-1- Vy Mi-2 )) / ts Az Mi =A Mi -A Mi-1 =((Vz Mi- VZ Mi-1 )-(Vz Mi-1- VZ Mi-2 )) / ts ts is the shooting interval, and the acceleration time history dataset of each feature point is: x direction: [Ax M0 ,Ax M1 ,Ax M2 ,Ax M2 ,Ax M3 ,Ax M4 ,Ax M5 ,.....] y direction: [Ay M0 ,Ay M1 ,Ay M2 ,Ay M2 ,Ay M3 ,Ay M4 ,Ay M5 ,.....] z direction: [Az M0 ,Az M1 ,AzM2 ,Az M2 ,Az M3 ,Az M4 ,Az M5 ,.....] 4.5) Data transmission: The acceleration time history data set of each feature point is transmitted to the data collection module.

[0058] 5) Data collection and visualization 5.1) The seismic amplification coefficients at different locations are calculated based on the obtained seismic amplification coefficients. The calculation formula for the seismic amplification coefficients is as follows:

[0059] Where, and They are the seismic response of the site point (including displacement, velocity and acceleration) and the minimum seismic response in the corresponding area.

[0060] 5.2) Calculate the local characteristics of each site point based on the established original 3D model, such as terrain height, slope and other important information. The slope is calculated as follows:

[0061]

[0062]

[0063] Where g is the unit width, For the venue height.

[0064] 5.3) Finally, the seismic amplification factor and corresponding terrain features of each feature point are established, and visualization is used to color-code the seismic amplification factor of each feature point in the original 3D model.

[0065] The technical solution of this application can improve collection efficiency: using drones to carry out large-scale and high-efficiency surface image collection, greatly shortening the collection time of seismic amplification coefficients, while greatly increasing the amount of measured data obtained; reducing costs: compared with traditional ground observation stations or manual measurement methods, this application reduces equipment costs and labor costs; improving accuracy: combining advanced image recognition technology and data processing algorithms, the calculation accuracy and reliability of seismic amplification coefficients are improved; wide application: this application can be widely used in earthquake risk assessment, disaster prevention and mitigation planning, building seismic performance assessment and other fields, with significant social and economic benefits.

[0066] This application provides a solution for collecting seismic amplification factors based on drone image recognition. By using drones equipped with high-definition cameras to capture surface images and combining image recognition technology with data processing algorithms, this system enables rapid and accurate collection of seismic amplification factors. This system boasts high efficiency, low cost, and high precision, and is widely applicable to earthquake risk assessment, disaster prevention and mitigation planning, and other fields, possessing significant practical value and social significance.

[0067] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0068] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus the necessary general hardware platform. 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 application, or the part that contributes to the existing technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0069] According to another aspect of the embodiments of the present application, a real-time detection device for seismic amplification coefficient based on drone image recognition technology is provided for implementing the above-mentioned real-time detection method for seismic amplification coefficient based on drone image recognition technology. Figure 2 is a schematic diagram of an optional real-time detection device for earthquake amplification coefficient based on drone image recognition technology according to an embodiment of the present application, such as Figure 2 As shown, the device may include: The acquisition unit 21 is used to control multiple drones to enter the area to be monitored to collect monitoring images of the ground surface after receiving earthquake warning information; The receiving unit 23 is used to receive the monitoring image transmitted back by the drone in real time via wireless transmission technology; an identification unit 25 for identifying displacement differences, velocity differences, and acceleration differences of the surface of the area to be measured using the original image of the surface before the earthquake, the monitoring image of the epicenter, and the original three-dimensional terrain model; A calculation unit 27 is configured to calculate the propagation characteristics of seismic waves on different terrains and surfaces and the ground motion amplification coefficient using displacement differences, velocity differences, and acceleration differences of the surface of the measured area in accordance with earthquake engineering principles; The generating unit 29 is used to generate a distribution map of the seismic amplification coefficient through data analysis and modeling.

[0070] Through the above module, after receiving earthquake warning information, multiple drones are controlled to enter the area to be tested to collect monitoring images of the surface; the monitoring images transmitted back by the drones in real time via wireless transmission technology are received; the original images of the surface before the earthquake, the monitoring images of the epicenter, and the original three-dimensional terrain model are used to identify the displacement difference, velocity difference, and acceleration difference of the surface of the area to be tested; combined with the principles of earthquake engineering, the displacement difference, velocity difference, and acceleration difference of the surface of the area to be tested are used to calculate the propagation characteristics of seismic waves in different terrains and surfaces and the seismic amplification coefficient; through data analysis and modeling, a seismic amplification coefficient distribution map is generated. This solution uses high-precision image acquisition equipment carried by drones, combined with advanced image processing and data analysis technologies, to quickly and accurately collect seismic amplification coefficients, thereby solving the technical problem of poor timeliness in collecting seismic amplification coefficients in the existing technology.

[0071] Optionally, the device may also include: a modeling module, which is used to: pre-process and enhance, extract features and classify the collected surface images before receiving earthquake warning information, and construct an original three-dimensional terrain model by identifying surface morphological features, thereby providing basic data for the calculation of the seismic motion amplification coefficient.

[0072] Optionally, the modeling module is also used to: perform image preprocessing on the surface image: use a filtering algorithm to perform denoising on the collected surface image to eliminate random noise and interference signals in the surface image to improve the image signal-to-noise ratio; then enhance the contrast of the surface image through histogram equalization and Laplace sharpening to make the surface features more prominent; perform geometric correction on the surface image according to the distortion characteristics of the camera lens to eliminate image distortion and deformation caused by lens distortion; obtain point cloud data set: import the preprocessed surface image, match the feature points of each surface image through the SIFT algorithm of the opencv library, and obtain Obtain the point cloud data and corresponding 3D spatial coordinates required for model construction; construct the model using the point cloud dataset: triangulate the point cloud data in the point cloud dataset using the alpha shape algorithm in the Open3D library or the Delaunay algorithm in the scipy library, and then use the matplotlib library or plotly library to visualize the triangulated dataset to generate a 3D terrain model; optimize the generated 3D terrain model: remove redundant data and perform surface smoothing to improve the model's accuracy and rendering efficiency, ultimately forming the original 3D terrain model for subsequent analysis.

[0073] Optionally, the recognition unit is further configured to perform preprocessing and enhancement, feature extraction, and classification on the collected surveillance images, thereby constructing a three-dimensional terrain model by identifying surface morphological features; sorting the three-dimensional terrain models by the acquisition time of the surveillance images, converting the three-dimensional terrain into node information, calculating the phase difference between corresponding nodes, and then using the finite difference method to calculate the displacement difference, velocity difference, and acceleration difference between different nodes.

[0074] Optionally, the recognition unit is also used to: use the KNN algorithm or the FLANN algorithm to perform local similarity matching of feature descriptors, establish a correspondence between the monitoring image of the drone at different times and the original three-dimensional terrain model; align the local coordinate system of the monitoring image of the drone with the global coordinate system of the original three-dimensional terrain model, and determine the displacement difference, velocity difference and acceleration difference of each feature point according to the three-dimensional coordinates of the feature point at different times.

[0075] Optionally, the recognition unit is further configured to: after converting the three-dimensional terrain into node information, calculate and obtain local features of the terrain according to the node information within the area.

[0076] Optionally, the device may further include: an interactive unit for visually displaying the distribution map of the seismic amplification coefficient; and outputting calculation reports and data files to provide a basis for the seismic design of building structures and the prediction and evaluation of geological disasters.

[0077] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in a corresponding hardware environment and can be implemented by software or hardware, wherein the hardware environment includes a network environment.

[0078] According to another aspect of the embodiments of the present application, a server or terminal is provided for implementing the above-mentioned real-time detection method of the seismic amplification factor based on drone image recognition technology.

[0079] Figure 3 is a structural block diagram of a terminal according to an embodiment of the present application, such as Figure 3 As shown, the terminal may include: one or more (only one is shown in the figure) processors 301, a memory 303, and a transmission device 305, as shown in FIG. Figure 3 As shown, the terminal may further include an input and output device 307 .

[0080] Memory 303 can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and apparatus for real-time detection of seismic amplification factors based on drone image recognition technology in the embodiments of the present application. Processor 301 executes the software programs and modules stored in memory 303 to perform various functional applications and data processing, thereby implementing the aforementioned method for real-time detection of seismic amplification factors based on drone image recognition technology. Memory 303 can include high-speed random access memory (RAM) and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 303 may further include memory remotely located from processor 301, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0081] The transmission device 305 is used to receive or send data via a network, and can also be used for data transmission between the processor and the memory. Specific examples of the network may include wired networks and wireless networks. In one embodiment, the transmission device 305 includes a network interface controller (NIC), which can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network. In one embodiment, the transmission device 305 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0082] Specifically, the memory 303 is used to store application programs.

[0083] The processor 301 may call the application stored in the memory 303 through the transmission device 305 to perform the following steps: After receiving earthquake early warning information, multiple drones are controlled to enter the area to be tested to collect monitoring images of the surface; the monitoring images transmitted back by the drones in real time via wireless transmission technology are received; the displacement difference, velocity difference and acceleration difference of the surface of the area to be tested are identified using the original image of the surface before the earthquake, the monitoring image of the epicenter and the original three-dimensional terrain model; in combination with the principles of earthquake engineering, the displacement difference, velocity difference and acceleration difference of the surface of the area to be tested are used to calculate the propagation characteristics of seismic waves in different terrains and surfaces and the seismic amplification coefficient; and through data analysis and modeling, a seismic amplification coefficient distribution map is generated.

[0084] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0085] It can be understood by those skilled in the art that Figure 3 The structure shown is for illustration only. The terminal may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, or other terminal devices. Figure 3 It does not limit the structure of the above electronic device. For example, the terminal may also include Figure 3 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 3 Different configurations shown.

[0086] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0087] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to execute program code of a real-time detection method for earthquake amplification factor based on drone image recognition technology.

[0088] Optionally, in this embodiment, the above-mentioned storage medium may be located on at least one network device among the multiple network devices in the network shown in the above-mentioned embodiment.

[0089] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: After receiving earthquake early warning information, multiple drones are controlled to enter the area to be tested to collect monitoring images of the surface; the monitoring images transmitted back by the drones in real time via wireless transmission technology are received; the displacement difference, velocity difference and acceleration difference of the surface of the area to be tested are identified using the original image of the surface before the earthquake, the monitoring image of the epicenter and the original three-dimensional terrain model; in combination with the principles of earthquake engineering, the displacement difference, velocity difference and acceleration difference of the surface of the area to be tested are used to calculate the propagation characteristics of seismic waves in different terrains and surfaces and the seismic amplification coefficient; and through data analysis and modeling, a seismic amplification coefficient distribution map is generated.

[0090] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0091] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0092] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0093] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above-mentioned computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application.

[0094] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, and can be electrical or other forms.

[0096] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0097] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0098] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A real-time detection method for earthquake amplification coefficient based on drone image recognition technology, characterized in that: include: After receiving earthquake warning information, control multiple drones to enter the area to be tested to collect monitoring images of the surface; Receiving the monitoring images transmitted back in real time by the drone via wireless transmission technology; Using the original image of the ground surface before the earthquake, the monitoring image of the epicenter, and the original three-dimensional terrain model, the displacement difference, velocity difference, and acceleration difference of the ground surface in the area to be measured are identified; In combination with earthquake engineering principles, the displacement difference, velocity difference and acceleration difference of the surface of the measured area are used to calculate the propagation characteristics of seismic waves in different terrains and surfaces and the ground motion amplification coefficient; Through data analysis and modeling, a distribution map of seismic amplification coefficients is generated.

2. The method according to claim 1, characterized in that Before receiving the earthquake early warning information, the method further includes: The collected surface images are pre-processed and enhanced, features are extracted, and classified. By identifying the surface morphological features, the original three-dimensional terrain model is constructed, thus providing basic data for the calculation of the seismic amplification factor.

3. The method according to claim 2, characterized in that The collected surface images are pre-processed and enhanced, and feature extracted and classified. By identifying the surface morphological features, the original three-dimensional terrain model is constructed, including: Image preprocessing of surface images: Filtering algorithms are used to denoise the collected surface images, eliminating random noise and interference signals in the surface images to improve the image signal-to-noise ratio. Histogram equalization and Laplace sharpening are then used to enhance the contrast of the surface images to highlight surface features. Based on the distortion characteristics of the camera lens, geometric correction is performed on the surface images to eliminate image distortion and deformation caused by lens distortion. Obtaining point cloud datasets: Import pre-processed surface images and use the SIFT algorithm of the OpenCV library to match the feature points of each surface image to obtain the point cloud data and corresponding 3D spatial coordinates required for model construction; Build a model using a point cloud dataset: Use the alpha shape algorithm in the Open3D library or the Delaunay algorithm in the scipy library to triangulate the point cloud data in the point cloud dataset, and then use the matplotlib library or plotly library to visualize the triangulated dataset to generate a 3D terrain model; The generated 3D terrain model is optimized by removing redundant data and performing surface smoothing to improve the accuracy and rendering efficiency of the model, ultimately forming the original 3D terrain model for subsequent analysis.

4. The method according to claim 1, wherein Using the original image of the ground surface before the earthquake, the monitoring image of the epicenter, and the original three-dimensional terrain model, the displacement difference, velocity difference, and acceleration difference of the ground surface in the area to be measured are identified, including: The collected monitoring images are pre-processed and enhanced, and feature extracted and classified to construct a three-dimensional terrain model by identifying surface morphological features; The three-dimensional terrain models are sorted according to the acquisition time of the monitoring images, and the three-dimensional terrain is converted into node information. The phase difference of the corresponding nodes is obtained by calculation. Then, the finite difference method is used to calculate the displacement difference, velocity difference and acceleration difference of different nodes.

5. The method according to claim 4, characterized in that The phase difference of the corresponding nodes is obtained by calculation, and then the displacement difference, velocity difference and acceleration difference of different nodes are calculated using the finite difference method, including: Use the KNN algorithm or FLANN algorithm to perform local similarity matching of feature descriptors and establish the correspondence between the UAV monitoring images at different times and the original 3D terrain model; The local coordinate system of the UAV's monitoring image is aligned with the global coordinate system of the original 3D terrain model, and the displacement difference, velocity difference, and acceleration difference of each feature point are determined according to the 3D coordinates of the feature point at different times.

6. The method according to claim 4, characterized in that After converting the three-dimensional terrain into node information, the method further includes: Based on the node information in the area, the local features of the terrain are calculated and obtained.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Visualize the distribution map of seismic amplification coefficient; Output calculation reports and data files to provide a basis for the seismic design of building structures and the prediction and assessment of geological disasters.

8. A real-time detection device for earthquake amplification coefficient based on drone image recognition technology, characterized in that: include: The acquisition unit is used to control multiple drones to enter the test area to collect surface monitoring images after receiving earthquake warning information; A receiving unit, configured to receive the monitoring image transmitted back in real time by the drone via wireless transmission technology; an identification unit, configured to identify displacement differences, velocity differences, and acceleration differences of the surface of the area to be measured using the original image of the surface before the earthquake, the monitoring image of the epicenter, and the original three-dimensional terrain model; a calculation unit for calculating the propagation characteristics of seismic waves on different terrains and surfaces and the seismic amplification coefficient using displacement differences, velocity differences, and acceleration differences of the surface of the measured area in accordance with earthquake engineering principles; The generating unit is used to generate a distribution map of earthquake amplification coefficients through data analysis and modeling.

9. A computer-readable storage medium, characterized in that: The storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor executes the method according to any one of claims 1 to 7 through the computer program.

Images