An unmanned aerial vehicle inspection method and system applied to foundation pit water accumulation monitoring

Abstract

The application discloses an unmanned aerial vehicle inspection method and system applied to foundation pit water accumulation monitoring, and comprises the following steps: determining an optimal route node sequence, and generating an unmanned aerial vehicle control instruction set; acquiring multi-source sensor internal and external parameters, and performing time alignment compensation on image frames and sensor data; acquiring water accumulation area image coordinate sets and attribute data; acquiring water accumulation area three-dimensional projection point sets, and calculating water accumulation area real coverage areas; generating a foundation pit three-dimensional overview map by using multi-view images of the foundation pit area; determining water accumulation area three-dimensional coordinate point sets and area estimation results; and projecting the water accumulation area three-dimensional coordinate point sets to the foundation pit three-dimensional overview map to generate a hidden danger monitoring report. By integrating the unmanned aerial vehicle, sensor data and advanced image processing technology, the application greatly improves the precision, stability and visualization effect of the foundation pit water accumulation monitoring, provides more reliable and comprehensive technical support for the safety management of the foundation pit engineering, and significantly reduces the safety risk in the construction process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle intelligent inspection, and particularly relates to an unmanned aerial vehicle inspection method and system applied to pit water monitoring. BACKGROUND

[0002] As an important part of underground structure construction, pit engineering has complex construction environment and long construction period, and is easily affected by factors such as climate conditions, hydrological changes and surrounding environment disturbances, especially in rainy seasons or areas with abundant groundwater. The pit water problem is particularly prominent. The water not only may cover the construction risk points and weaken the slope stability, but also may cause abnormal stress of the supporting structure, and even lead to slope instability, pit collapse and other major safety accidents. Therefore, real-time monitoring and accurate grasping of the pit area water condition become an important means to ensure the safe operation and scientific management of pit engineering. At present, the water monitoring methods widely used in engineering mainly include manual inspection, ground sensor layout and fixed camera observation. Such methods have obvious limitations. First, manual inspection depends on the experience of operating personnel, is limited by the inspection frequency, weather conditions and site accessibility, and is difficult to achieve comprehensive and continuous monitoring. Second, the liquid level sensor or water immersion alarm laid on the ground can only detect the set point, cannot cover the entire pit area, and the equipment is easily affected by silt accumulation or electrical failure, resulting in data loss. Although the fixed camera can provide continuous image information, its viewing angle is limited and cannot meet the identification needs of a large area, especially hidden corners. In addition, most of the traditional image recognition methods use binary segmentation or simple threshold processing based on single-frame images, which cannot accurately distinguish between water and shadow, wet mud or reflective areas, and are prone to false positives or false negatives, and it is difficult to extract the real spatial position and area information of the water. In the aspect of unmanned aerial vehicle application, although it has the advantages of flexible deployment and wide coverage, the existing inspection strategies are mostly based on rule-based flight routes, and lack of precise control of pit structure boundaries, flight parameters and image overlap, resulting in poor continuity and incomplete coverage of aerial images, affecting the subsequent image processing effect. At the same time, the existing methods often fail to effectively integrate unmanned aerial vehicle attitude data, laser ranging information and image content, making it difficult to accurately project two-dimensional images into three-dimensional space, thereby limiting the physical quantification and spatial positioning of the water area. In summary, the existing technology still has significant deficiencies in the comprehensive perception, automatic identification, spatial positioning and information integration of pit water, and needs to be systematically improved and enhanced in terms of data acquisition accuracy, target detection stability and result visualization presentation capability. SUMMARY

[0003] The present application provides an unmanned aerial vehicle inspection method and system applied to pit water monitoring to solve the above problems of the existing technology.

[0004] The embodiment of the first aspect of the application provides an unmanned aerial vehicle inspection method applied to foundation pit water accumulation monitoring, mainly comprising:

[0005] According to the spatial boundary coordinates of the foundation pit area, the flight operation height, the camera field of view angle and the image resolution parameters, an initial route set is constructed, an optimal route node sequence is determined, and a set of unmanned aerial vehicle control instructions is generated;

[0006] According to the camera calibration board image, the radar ranging residual error and the IMU motion simulation data, multi-source sensor internal and external parameters are obtained, and time alignment compensation of image frames and sensor data is performed;

[0007] Based on historical foundation pit area image frames and corresponding timestamp information, the segmentation mask of the water accumulation area in the foundation pit area image, the corresponding boundary box information and the confidence score are extracted, and the water accumulation area image coordinate set and attribute data are obtained;

[0008] According to the pixel mask coordinates of the foundation pit area image and the camera internal parameters, combined with the rotation matrix constructed by the Euler angle and the unmanned aerial vehicle track position vector, the world coordinate system conversion is performed, and the real coverage area of the water accumulation area is calculated;

[0009] Using the multi-view images of the foundation pit area, SIFT or ORB local feature points are extracted, cross-view corresponding relationship is constructed, and combined with the camera attitude matrix, the track position vector and the dense point cloud surface fitting result, the foundation pit three-dimensional overview map is generated;

[0010] According to the corresponding three-dimensional coordinate point set of the water accumulation area in each image frame, combined with the area coincidence degree of the cross-temporal multi-view segmentation point set, the three-dimensional coordinate point set and the area estimation result of the water accumulation area are determined;

[0011] By projecting the three-dimensional coordinate point set of the water accumulation area to the foundation pit three-dimensional overview map, and combining the water accumulation area boundary box center position and the image frame index, a hidden danger monitoring report is generated.

[0012] Further, the method according to the spatial boundary coordinates of the foundation pit area, the flight operation height, the camera field of view angle and the image resolution parameters, the initial route set is constructed, the optimal route node sequence is determined, and the set of unmanned aerial vehicle control instructions is generated, comprising:

[0013] According to the spatial boundary coordinates of the foundation pit area, the flight operation height, the camera field of view angle and the image resolution parameters, the image ground projection size and the flight line spacing are calculated; by setting the lateral and longitudinal overlap rate threshold, a heading and lateral coverage matrix is constructed; a regular grid scanning path is generated by using a rotating minimum circumscribed rectangle constraint, and a spiral progressive path starting from the center of the foundation pit is constructed based on a polar coordinate generation function; by taking the regular grid scanning path and the spiral progressive path as an initial flight line set, and constructing a multi-objective optimization model with flight path coverage rate and path overlap degree as objective functions, the genetic algorithm is used to iteratively optimize the flight line node sequence and flight attitude angle parameters, and the optimal flight line node sequence meeting the coverage and energy balance requirements is obtained by combining the distance constraint between flight line nodes and the minimum turning radius limit; according to the optimal flight line node sequence, the latitude, longitude, height and shooting trigger time information of each node are obtained, and the unmanned aerial vehicle control instruction set and the unmanned aerial vehicle flight monitoring route are generated; according to the unmanned aerial vehicle flight monitoring route, the camera and the radar are carried on the unmanned aerial vehicle, and the multi-view images of the foundation pit area are shot in real time and stored in the foundation pit area monitoring database.

[0014] Further, the multi-source sensor internal and external parameters are obtained according to the camera calibration board image, the radar ranging residual error and the IMU motion simulation data, and the time alignment and compensation of the image frame and the sensor data are performed, including:

[0015] By shooting a sequence of calibration board images, the camera internal parameter matrix is calculated by using the Zhang Zhengyou camera calibration method to obtain the focal length parameter, the principal point coordinates and the distortion coefficient; the radar ranging calibration is performed according to the known distance reflection plate, the residual data of the actual distance and the radar ranging output are recorded, the least square regression method is used to establish a ranging error correction model to determine the radar ranging correction coefficient; according to the three-axis angular velocity and linear acceleration data output by the inertial measurement unit, a six-degree-of-freedom motion simulation test is implemented, and the extended Kalman filter algorithm is used to estimate the attitude solution error; by adjusting the off-line parameters of the bias term and the noise covariance matrix, the IMU attitude drift correction model parameters are determined, and the calibrated camera, radar and IMU internal and external parameter data are obtained, the IMU internal parameter data includes zero offset, scale factor and noise characteristics, and the IMU external parameter data includes the pose transformation matrix relative to the camera and the radar; according to the calibrated camera, radar and IMU internal and external parameter data, the unmanned aerial vehicle autonomous flight task is executed, and the spatial position, attitude parameter and shooting trigger timestamp of the unmanned aerial vehicle are obtained, the spatial position includes the flight path position and the radar height information, the attitude parameter includes the attitude angle and the flight speed, and the attitude angle includes the roll angle, the pitch angle and the yaw angle; by comparing the shooting trigger timestamp with the timestamp recorded by other sensors, the multi-source data time compensation is performed by using the linear interpolation alignment method to obtain the spatial position and attitude parameter set at the corresponding image frame time.

[0016] Further, based on the historical foundation pit area image frames and corresponding timestamp information, the segmentation mask of the water accumulation area in the foundation pit area image, the corresponding bounding box information and the confidence score are extracted to obtain the image coordinate set and attribute data of the water accumulation area, including:

[0017] Through the foundation pit area monitoring database, the historical foundation pit area image frames and corresponding timestamp information are obtained. An image enhancement processing method of random cropping, rotation, multi-scale scaling and brightness contrast adjustment is used to generate an extended image sample set containing multiple perspectives, different lighting conditions and different scale changes. A rectangular bounding box is drawn on the water accumulation area of the historical foundation pit area image and the extended image sample set using the box selection labeling method. The yolov11 target detection algorithm is used for model training to extract the segmentation mask of the water accumulation area in the foundation pit area image, the corresponding bounding box information and the confidence score. The pixel mask coordinate point set of the water accumulation area in the image coordinate system is obtained by decoding the extracted water accumulation area image. The pixel-level boundary contour of the water accumulation area is calculated by counting the area pixel number and the boundary polygon vertex coordinates of each water accumulation area. The image frame index, mask coordinates, confidence and timestamp information are stored in the foundation pit area monitoring database to obtain the image coordinate set and attribute information of the water accumulation area. By pre-setting the confidence threshold and mask integrity screening conditions, false detection areas and boundary damaged targets are removed, and the target mask set meeting the spatial continuity requirement is retained, and the pixel mask coordinate point set and image frame index information are recorded.

[0018] Further, according to the pixel mask coordinates of the foundation pit area image and the camera intrinsic parameters, the rotation matrix constructed by the Euler angle and the UAV flight path position vector are combined to perform world coordinate system conversion and calculate the real coverage area of the water accumulation area, including:

[0019] According to the pixel mask coordinates of the foundation pit area image and the camera intrinsic parameters, the water accumulation area boundary points in the image coordinate system are mapped to the space rays in the camera coordinate system using the pinhole imaging model, and the formula is wherein, is the space ray in the camera coordinate system, is the scale factor, is the camera intrinsic parameter matrix, , is the focal length, , is the principal point coordinate, is the image pixel point coordinate; According to the roll angle, pitch angle and yaw angle recorded during the flight of the UAV, the Euler angle split shaft rotation method is used to calculate the rotation matrix around the X axis, Y axis and Z axis in turn, and a 3×3 space rotation matrix is formed by matrix multiplication combination; based on the rotation matrix and the flight path position vector Convert the camera coordinate system ray to the world coordinate system, the formula is, wherein, is the coordinate in the world coordinate system, is the attitude matrix, is the track position vector; project the two-dimensional pixel mask to three-dimensional coordinates, calculate the real coverage area of the water accumulation area by triangulation or gridding method wherein, is the projected area grid of a single water accumulation segmentation mask, and N is the number of grid points of the mask.

[0020] Further, the multi-view image of the foundation pit area is used to extract SIFT or ORB local feature points, to construct the corresponding relationship across the view angle, and to generate a three-dimensional overview map of the foundation pit by combining the camera attitude matrix, the track position vector and the dense point cloud surface fitting result, including:

[0021] Using multi-view images of the foundation pit area, SIFT or ORB local feature points are extracted, and the feature correspondence between multi-view images is established; the structure self-motion method is used to solve the attitude matrix and the track position vector of the image frame in the world coordinate system, and to restore the sparse three-dimensional point cloud , the formula is wherein, represents a pinhole projection function that maps three-dimensional points to an image plane, is the number of feature points of the th image, is the number of image frames; according to the laser radar height ranging value recorded simultaneously during flight, the Z-axis coordinates of the three-dimensional sparse point cloud are aligned with the radar ground height reference, and the formula is used to correct the Z-axis of the three-dimensional sparse point cloud, wherein, is the average height of the sparse point cloud; according to the camera pose parameters solved by the structure self-motion method and the three-dimensional sparse point cloud result, a multi-view stereo matching algorithm is used to estimate the disparity and inverse depth of each pixel in the image, to construct a high-density three-dimensional dense point cloud, and the pose parameters include spatial position and attitude parameters; by Poisson reconstruction or Delaunay triangulation algorithm, the surface fitting and topological modeling of the dense point cloud are performed, to generate a three-dimensional overview map of the foundation pit.

[0022] Further, according to the three-dimensional coordinate point set of the water accumulation area in each image frame, and the area coincidence degree of the cross-temporal multi-view segmentation point set, the three-dimensional coordinate point set and the area estimation result of the water accumulation area are determined, including:

[0023] According to all the pixel points in the real coverage area of the water accumulation area of each acquisition frame, the corresponding three-dimensional coordinate points are converted by the radar position information at the corresponding moment; the segmentation coordinate point set of multi-view and multi-time in time sequence is expressed as , the area coincidence degree of different detection results on the reference plane is calculated by formula , and it is not difficult to remove low confidence detection results less than the preset coincidence degree threshold based on the preset coincidence degree threshold, wherein represents the coincidence ratio of the detection result and on the projection plane, , respectively, the three-dimensional coordinate point set of two detection results; according to the remaining high confidence detection result, the three-dimensional coordinate point set of the water accumulation area is determined by formula , and the area estimation result , wherein is the weight, which is obtained by comprehensive calculation of segmentation confidence, area coincidence degree or multi-view coverage, is the area of the i-th detection area.

[0024] Further, the hidden danger monitoring report is generated by projecting the three-dimensional coordinate point set of the water accumulation area to the three-dimensional overview map of the foundation pit, and combining the center position of the water accumulation area bounding box and the image frame index, including:

[0025] According to the three-dimensional coordinate point set of the water accumulation area, the grid structure, the facet normal vector and the positional relationship of the three-dimensional overview map of the foundation pit, the most adjacent surface area corresponding to each water accumulation point is determined, and the projection position of the water accumulation area in the three-dimensional overview map of the foundation pit is determined using the vertical projection, the normal projection or the shortest distance matching strategy. The three-dimensional coordinate point set of the water accumulation area is projected into the three-dimensional overview map of the foundation pit; according to the projection position of the water accumulation area in the three-dimensional overview map of the foundation pit, the number of water accumulation targets in the current task period is determined, and each target is assigned a unique number identification; based on the center position of the bounding box of the three-dimensional coordinate point set of the water accumulation area, the three-dimensional position coordinates of the water accumulation area in the world coordinate system are determined, and the original image frame index corresponding to the water accumulation area is obtained. The image cropping area containing the segmentation mask of the water accumulation area is extracted as image evidence; according to the number, number, three-dimensional position coordinates, area and corresponding image evidence of the water accumulation area, a hidden danger monitoring report of the foundation pit area is generated and stored in the foundation pit area monitoring database.

[0026] The second aspect embodiment of the application provides an unmanned aerial vehicle inspection system applied to foundation pit water accumulation monitoring, mainly comprising:

[0027] An optimal flight monitoring route generation module is used to construct an initial route set according to the spatial boundary coordinates of the foundation pit area, the flight operation height, the camera field of view angle and the image resolution parameters, determine the optimal route node sequence, and generate the unmanned aerial vehicle control instruction set.

[0028] A multi-source sensor calibration and timing alignment module is configured to obtain multi-source sensor internal and external parameters based on camera calibration board images, radar ranging residuals and IMU motion simulation data, and to perform time alignment compensation of image frames and sensor data.

[0029] A water accumulation area identification module is configured to extract a segmentation mask, corresponding bounding box information and confidence score of a water accumulation area in a foundation pit area image based on historical foundation pit area image frames and corresponding timestamp information, to obtain a water accumulation area image coordinate set and attribute data.

[0030] A three-dimensional projection area estimation module is configured to perform world coordinate system conversion based on pixel mask coordinates of the foundation pit area image and camera internal parameters, in combination with a rotation matrix constructed based on Euler angles and a UAV track position vector, and to calculate a real water accumulation area coverage.

[0031] A foundation pit three-dimensional overview map construction module is configured to extract SIFT or ORB local feature points based on multi-view images of the foundation pit area, to construct a cross-view correspondence relationship, and to generate a foundation pit three-dimensional overview map in combination with a camera pose matrix, a track position vector and a dense point cloud surface fitting result.

[0032] A multi-view water accumulation point set fusion module is configured to determine a three-dimensional coordinate point set and area estimation result of a water accumulation area based on corresponding three-dimensional coordinate point sets of the water accumulation area in each image frame, in combination with an area overlap degree of cross-temporal multi-view segmentation point sets.

[0033] A hidden danger monitoring report generation module is configured to project the three-dimensional coordinate point set of the water accumulation area to the foundation pit three-dimensional overview map, in combination with a water accumulation area bounding box center position and an image frame index, to generate a hidden danger monitoring report.

[0034] The technical scheme provided by the embodiments of the present application can include the following beneficial effects:

[0035] This invention provides a UAV inspection method and system for monitoring water accumulation in foundation pits. By combining parameters such as the spatial boundary of the foundation pit area, flight altitude, camera field of view, and resolution, this invention can automatically generate an optimal flight path sequence, ensuring coverage of the entire foundation pit area and overcoming the limitations of traditional monitoring methods in terms of limited coverage and numerous blind spots. Secondly, based on time alignment and compensation of multi-source sensor data, high-precision image and sensor data fusion is achieved, significantly improving the accuracy and stability of monitoring data. Through processing historical image data and precise segmentation and attribute extraction of the water accumulation area, this invention can identify water accumulation areas in real time and generate corresponding spatial coordinate data, ensuring accurate positioning of water accumulation information. Combining the three-dimensional spatial information of the foundation pit area and multi-view images, this invention can achieve three-dimensional projection of the water accumulation area and physical quantification of its coverage area, enhancing the spatial representation and visualization capabilities of the monitoring results. Furthermore, by using an overlap threshold to eliminate low-confidence detection results, the accuracy and reliability of water accumulation area detection are improved. This invention generates a hazard monitoring report by spatially projecting the water accumulation area onto a 3D overview of the foundation pit, achieving comprehensive perception, accurate identification, and real-time monitoring of foundation pit water accumulation, effectively ensuring the safety and stability of foundation pit projects. By integrating drones, sensor data, and advanced image processing technology, this invention significantly improves the accuracy, stability, and visualization of foundation pit water accumulation monitoring, providing more reliable and comprehensive technical support for the safety management of foundation pit projects and significantly reducing safety risks during construction. Attached Figure Description

[0036] Figure 1 This is a flowchart of a drone inspection method for monitoring water accumulation in foundation pits, according to the present invention.

[0037] Figure 2 This is a schematic diagram of a drone inspection method for monitoring water accumulation in foundation pits according to the present invention;

[0038] Figure 3 This is a schematic diagram of an unmanned aerial vehicle (UAV) inspection system for monitoring water accumulation in foundation pits, according to the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0040] like Figure 1 The diagram shown is an overall flowchart of a UAV inspection method for monitoring water accumulation in foundation pits, as described in this application. It illustrates the execution sequence and logical relationship of the core processing steps. Further, as... Figure 2As shown, it is a structural schematic diagram of the system of the present application, which details the composition of each functional module and the data flow and calculation relationship between them, including image instance segmentation processing, three-dimensional space mapping, time sequence fusion and report generation, and other key links, thus fully embodying the technical implementation path of the present application.

[0041] In the embodiment of the present application, before flight operation, the flight operator needs to understand the whole area of the monitored foundation pit and set the operation boundary range. According to the two-dimensional coordinate point set of the foundation pit boundary, the preset flight height, the camera field of view angle and the image resolution parameters, the projection size of a single frame image on the ground is calculated. By setting the lateral and longitudinal overlap rate threshold, the flight line spacing is calculated and the coverage matrix is constructed to form the image overlap relationship model of heading and lateral. Based on the foundation pit boundary profile, the regular grid scanning path is generated by using the rotating minimum circumscribed rectangle method, and the spiral progressive path with the geometric center of the foundation pit as the starting point is constructed by using the polar coordinate generation function. The regular grid scanning path and the spiral progressive path are used as the initial flight line set, a multi-objective optimization model is constructed with the maximum flight path coverage rate and the minimum path overlap rate as the objective function, the genetic algorithm is used to iteratively solve the flight line node sequence and the flight attitude angle parameters, and the optimal flight monitoring flight line node sequence meeting the coverage and energy balance requirements is obtained by combining the distance constraint between nodes, the minimum turning radius and the path continuity constraint. According to the optimized flight line sequence, the unmanned aerial vehicle flight control instruction set containing latitude, longitude, height, heading angle, flight speed and shooting trigger time is generated for each node, and the flight monitoring flight line is automatically constructed. During the flight task execution process, the task instructions are issued to the unmanned aerial vehicle to control the unmanned aerial vehicle to automatically fly along the planned path and simultaneously perform image acquisition. The unmanned aerial vehicle platform needs to carry a high-definition image acquisition module, a laser radar and an inertial measurement unit. The camera acquires the camera intrinsic matrix including focal length , principal point coordinates and radial distortion coefficient by shooting a standard calibration board image sequence using Zhang Zhengyou calibration method, which is used for subsequent projection conversion of image pixel coordinates to space rays. The laser radar is used to provide height ranging , and the IMU records attitude angle and acceleration / angle velocity information, auxiliary flight solution, by setting multiple groups of different known distance reflector plates, comparing the residual error of ranging output and actual distance, using least square method to construct one-dimensional fitting regression model, determining the ranging error correction coefficient, and applying it to the height correction during flight. The IMU records the output of three-axis angular velocity and linear acceleration through six-degree-of-freedom motion simulation experiment, estimates the attitude solution error by using extended Kalman filtering method, optimizes the noise covariance matrix and zero offset model parameters offline, and obtains the IMU attitude drift correction model. Finally, the camera, radar and IMU are calibrated, the IMU internal parameters include zero offset, scale factor and measurement noise characteristics, and the external parameters include the relative pose transformation matrix of camera and radar. When the unmanned aerial vehicle executes the task according to the flight route, the image , track position , attitude matrix and radar ranging value are collected in real time, the timestamp generated by the image acquisition trigger signal is compared with the timestamp in the sensor data stream, the linear interpolation method is used to complete the time sequence alignment and synchronization compensation of multi-source data of image, IMU and radar, the spatial pose data set at image frame level is constructed, and the data set is uploaded to the unmanned aerial vehicle inspection platform through the communication link. The platform is the core node of the whole platform, integrates communication access, data scheduling, processing control and result uploading functions, is responsible for coordinating the operation of each module, ensures the real-time receiving, processing and storage of flight data, image segmentation results and three-dimensional projection and area estimation information, and realizes the unified management and visual presentation of the whole process of foundation pit water monitoring.

[0042] The instance segmentation framework accessed in the platform is used for automatic identification processing of the foundation pit water accumulation image. The framework takes YOLOv11 model as the core detection algorithm, and can realize target segmentation, boundary box extraction and confidence score output of the water accumulation area in the unmanned aerial vehicle collected image. In order to improve the generalization ability and positioning accuracy of the model, the training data set is derived from the historical image frames stored in the foundation pit area monitoring database and the corresponding collection timestamp information. The historical image frames are labeled and expanded to form a sample set for model training. Before training, first, perform enhancement processing operation on the historical image frames, specifically including applying random cropping, affine rotation, multi-scale scaling and brightness contrast adjustment strategy to the original image to generate image expansion samples containing multi-view, lighting conditions and size changes. The artificial auxiliary frame selection labeling method is used to draw the rectangular boundary box of the water accumulation area in the original image and the enhanced image, and the annotation file is generated according to the YOLO input format. During the training process, the model backbone network adopts CSPDarknet architecture to extract multi-scale spatial features, introduces FPN+PAN pyramid structure in the Neck part for feature fusion, and the Head module adopts a multi-head prediction mechanism to output boundary boxes, masks and classification confidence at different down-sampling rates. The model training adopts a combined loss function strategy, which jointly uses GIoU Loss, Focal Loss, Dice Loss and BCE Loss to optimize the boundary, class and mask accuracy. The optimizer adopts Adam structure, cooperates with learning rate preheating and cosine annealing scheduling mechanism to improve the model convergence rate and stability. After training, the model is deployed in the platform inference engine to perform prediction on the unmanned aerial vehicle collected image. The platform performs post-processing operation on the segmentation mask output by each image, extracts the pixel coordinate point set of the mask boundary polygon, calculates the pixel area, boundary contour and confidence score of each mask, and writes the image frame index, mask coordinate point set, boundary box position information and timestamp field into the foundation pit area monitoring database. According to the dynamic water level and soil type of each mask area, the pre-set confidence threshold of the area is adaptively adjusted. Through the pre-set confidence threshold and the mask connectivity judgment condition, the abnormal detection results with low confidence prediction and boundary structure damage are removed, and only the target mask set with continuous boundary and area greater than the minimum area threshold is retained. The actual deployment results show that under the condition of 1280x1280 resolution image input, the average prediction time of a single image can be controlled within hundreds of milliseconds, and the GPU accelerated deployment environment can realize multi-channel image parallel inference. In multiple foundation pit scene tests, the target segmentation accuracy reaches more than 90%, and the platform can stably output water accumulation area mask image, boundary coordinates, confidence and image frame number and other key information, meeting the comprehensive requirements of accuracy, speed and traceability in foundation pit inspection tasks.

[0043] The specific steps for adaptively adjusting the preset confidence threshold for each masked area of ​​the foundation pit, based on the dynamic water level and soil type, are as follows: The images acquired by the UAV are converted from RGB to HSV color space. The mean, variance, and spatial continuity indices of chromaticity are statistically analyzed to obtain the color feature vectors of each area of ​​the foundation pit. The boundaries and color gradient fields of each foundation pit area are extracted through sub-pixel edge detection. The gray-level co-occurrence matrix, local binary mode, and histogram of directional gradients are calculated to obtain the texture feature vectors of each foundation pit area, which are then stored in the foundation pit area monitoring database. Through the foundation pit area monitoring database, historical color feature vectors and texture feature vectors of the foundation pit areas are obtained, and the soil type of each area is labeled. A random forest algorithm is used for model training to construct a soil type recognition model for foundation pit areas, identifying the soil type of each masked area within the foundation pit, thereby determining the soil type of each masked area. The water accumulation area within the foundation pit changes dynamically with the groundwater level, and the soil type has a significant impact on the water's reflectivity. Real-time water level changes within the foundation pit are obtained using radar ranging data. The radar ranging system measures the distance between the water surface and the radar by emitting electromagnetic waves and receiving their reflected signals, thus providing accurate water level data. The water level change Zt over time t can be expressed as... ,in, This represents the initial water level of the foundation pit. The change in water level over time t represents the dynamic fluctuation of the water depth in the foundation pit. Meanwhile, soil type significantly affects the reflectivity of the masking area; different soil types, such as clay, sandy soil, and loam, result in varying degrees of light reflection. A soil influence coefficient is defined based on soil type s. To correct the reflection characteristics of the masked region, an adaptive confidence threshold correction formula is used. Adaptively adjust the preset confidence threshold for the mask region. This makes the detection of the masked area more accurate, among which, This is the initial detection threshold. This is a correction factor for the detection threshold based on soil type. Based on the adjusted preset confidence threshold, waterlogged areas are identified. If the confidence level of the currently extracted waterlogged area is greater than the adjusted preset confidence threshold, the area is classified as a waterlogged area; otherwise, it is considered a background area.

[0044] Next, the pixel mask data of the water accumulation area needs to be processed by the spatial projection and area estimation module to achieve the mapping transformation from image coordinates to real three-dimensional space. The UAV inspection platform uses the boundary point coordinates of the water accumulation target pixel mask in each frame of the image and the calibrated camera intrinsic parameters, including focal length, to perform the mapping. Principal point coordinates and radial distortion coefficient Using a pinhole imaging model to capture image pixels Mapped to a spatial ray in the camera coordinate system The mapping is expressed as ,in, The scale factor is determined by depth information or radar ranging. Subsequently, based on the timestamp of the image acquisition time, the platform aligns the IMU output with the flight track record using linear interpolation to obtain the UAV flight attitude data corresponding to the current frame image, including three-axis attitude angles. Using angular velocity data, rotation matrices around the X, Y, and Z axes are constructed sequentially using Euler angle-separated rotation. These matrices are then combined through matrix multiplication to generate the rotation matrix from the camera to the world coordinate system. Combined with real-time recorded track position vectors The spatial transformation process is completed, converting the spatial ray from the camera coordinate system to the world coordinate system. The mapping relationship is as follows: ,in, The coordinates are in the world coordinate system. After the projection transformation, the platform extends the spatial rays generated by the projection of each mask boundary point to the plane where the target is located. Based on the radar altitude ranging information or the terrain surface Z-value provided by the 3D overview model of the foundation pit, the coordinates of the intersection points of the rays and the ground are extracted to form a 3D point set of the water accumulation area. The platform uses a triangular meshing method to construct the contour according to the point set order, converting the mask boundary into a closed 3D projected boundary, forming an area estimation mesh structure. The projected area corresponding to a single mask area is calculated using the formula: ,in, The projected area grid of a single water accumulation mask is divided, where N is the number of grid points of the mask. The area is obtained by accumulating grid points one by one. Finally, the platform obtains the coverage area data of each water accumulation target at the real scale.

[0045] In this embodiment, to present the monitoring results in a more concrete and unified manner, the platform generates a 3D overview of the foundation pit based on multi-view aerial images from UAVs, flight path positions, attitude parameters, and radar altitude ranging information. Firstly, multi-view images are used... Extract local feature points from SIFT or ORB. ,in This represents the j-th feature point in the i-th image, and cross-view correspondence is determined through feature matching. The camera pose was calculated using the Structure Self-Motion (SfM) method. And recover sparse 3D point clouds The formula is ,in This represents the pinhole projection function, which maps 3D points onto the image plane. For the first The number of feature points in the image. To eliminate scale uncertainty in SfM, radar altitude ranging is introduced. The Z-axis of the point cloud is corrected using the following formula: ,in The average height of the sparse point cloud is given. Subsequently, dense matching algorithms, such as multi-view stereo matching, are used to analyze the sparse point cloud. Expanding into a dense point cloud Furthermore, by employing surface reconstruction algorithms such as Poisson reconstruction or Delaunay triangulation, a 3D overview map of the foundation pit with both topographical height and structural continuity is generated. The formula is The three-dimensional overview of the foundation pit truly reflects its geometric structure and spatial morphology. It can serve as a unified reference plane for subsequent three-dimensional projection of the water accumulation area, area calculation, and time series result fusion.

[0046] In this embodiment, segmentation prediction is performed on temporally discrete images, therefore the results contain repetitions from multiple views or misjudgments from certain views. A related temporal multi-view fusion framework is deployed on the platform. The predicted area of ​​each previously acquired frame... All pixels The radar and pose information at the corresponding moment has been converted into corresponding three-dimensional coordinates. At this point, the multi-view, multi-timescale segmented coordinate point set can be described as follows: For overlapping areas between different detection results, calculate their area overlap on the reference plane. ,in, Indicates the test results and The overlap ratio on the projection plane. This process is expanded and paired in time sequence, and multiple [various values] exist. These can be identified as low-confidence, sporadic detections and discarded. For the remaining high-confidence detection results, the platform uses a weighted fusion method to obtain the final accurate target location and area estimate. ,in The weights can be calculated by combining segment confidence, area overlap, or multi-view coverage. For the first The area of ​​each detection region. Finally, through the surface projection function. The fused results are then precisely projected onto the 3D overview map of the foundation pit. This approach enables unified display and analysis of results from multiple perspectives and time series. Through this process, the application can maintain the consistency and robustness of detection results in complex environments, providing accurate three-dimensional positioning and area assessment for water accumulation monitoring.

[0047] In the implementation of the above method, the platform, based on the constructed 3D overview map of the foundation pit and the 3D coordinate point set of the water accumulation area, uses a spatial geometric projection module to align and uniquely identify the monitoring targets in the 3D model. Specifically, based on the 3D point set coordinates of the water accumulation area and the established mesh structure, surface normal vectors, and spatial positional relationships in the 3D model of the foundation pit, the platform sequentially determines the nearest neighbor surface region corresponding to each water accumulation point in the 3D terrain surface. It prioritizes the normal projection strategy to project the 3D point set onto the mesh surface. When the normal direction does not converge or the surface tilt angle exceeds a set threshold, it automatically switches to vertical projection or the shortest distance matching strategy to complete the alignment of the point set in the 3D overview map. After completing the point set mapping, the water accumulation targets are spatially clustered according to the surface assignment results, and the number of valid clusters for all water accumulation targets in the current monitoring period is counted, generating a corresponding number of potential hazard target entities. The platform automatically assigns a unique identifier to each cluster region and records the 3D projection area range corresponding to the identifier, forming an identifier-coordinate mapping relationship. During coordinate annotation, the platform extracts the geometric center of each cluster region based on its 3D bounding box structure, serving as the spatial positioning information of the waterlogged area in the world coordinate system. Simultaneously, the platform combines the original image frame index associated with the cluster number to retrieve the corresponding image frame from the image database. It then uses boundary index cropping to obtain the local image region containing the target and overlays a segmentation mask as image evidence, enhancing the verifiability and image reproducibility of the monitoring results. Finally, the platform unifies the identification numbers, 3D coordinates, coverage area data, and image evidence of each waterlogged target into a standardized data structure, automatically generating a structured hazard monitoring report and uploading it to the foundation pit area monitoring database. This enables unified archiving, historical retrospection, and horizontal comparison of monitoring data.

[0048] like Figure 3 This embodiment describes a drone inspection system for monitoring water accumulation in foundation pits, which may specifically include:

[0049] The optimal flight monitoring route generation module is used to construct an initial route set based on the spatial boundary coordinates of the pit area, flight operation altitude, camera field of view and image resolution parameters, and determine the optimal flight monitoring route node sequence by combining the route node sequence and flight attitude angle parameters, and generate a UAV control command set.

[0050] The multi-source sensor calibration and timing alignment module is used to obtain the intrinsic and extrinsic parameters of the multi-source sensors based on the camera calibration board image, radar ranging residual and IMU motion simulation data, and to perform time alignment compensation between image frames and sensor data.

[0051] The water accumulation area identification module is configured to perform image enhancement and boundary box labeling based on historical foundation pit area images and corresponding timestamp information in a foundation pit area monitoring database, extract a segmentation mask of a water accumulation area in the foundation pit area image, corresponding boundary box information and a confidence score, and obtain a water accumulation area image coordinate set and attribute data;

[0052] The three-dimensional projection area estimation module is configured to perform world coordinate system conversion based on pixel mask coordinates of the foundation pit area image and camera intrinsic parameters, in combination with a rotation matrix constructed based on Euler angles and a UAV flight path position vector, to generate a water accumulation area three-dimensional projection point set and calculate a real coverage area of the water accumulation area.

[0053] The foundation pit three-dimensional overview map construction module is configured to extract SIFT or ORB local feature points based on multi-view images of the foundation pit area, construct a cross-view correspondence relationship, and generate a foundation pit three-dimensional overview map in combination with a camera pose matrix, a flight path position vector and a dense point cloud surface fitting result.

[0054] The multi-view water accumulation point set fusion module is configured to perform overlap threshold elimination on low-confidence detection results based on an area overlap degree of cross-temporal multi-view segmentation point sets, and determine a three-dimensional coordinate point set and an area estimation result of the water accumulation area.

[0055] The hidden danger monitoring report generation module is configured to project the three-dimensional coordinate point set of the water accumulation area to the foundation pit three-dimensional overview map based on a spatial correspondence relationship between the three-dimensional coordinate point set of the water accumulation area and a normal vector of a mesh patch of the foundation pit three-dimensional overview map, and generate a hidden danger monitoring report in combination with a boundary box center position of the water accumulation area and an image frame index.

[0056] The above description is merely preferred embodiments of the present application and a description of the principles of the technology used. Those skilled in the art should understand that the scope of the application disclosed in the present application is not limited to the technical solutions formed by the specific combinations of the technical features described above, and should also cover other technical solutions formed by any combinations of the technical features described above or equivalent features without departing from the concept of the present application. For example, the technical solutions formed by replacing the above-described features with technical features disclosed in the present application (but not limited to) having similar functions.

Claims

1. A method for unmanned aerial vehicle inspection applied to foundation water accumulation monitoring, characterized in that, The method comprises: According to the spatial boundary coordinates of the foundation pit area, the flight operation height, the camera field of view angle and the image resolution parameters, an initial flight path set is constructed, the optimal flight path node sequence is determined, and a set of unmanned aerial vehicle control instructions is generated; According to the camera calibration board image, the radar ranging residual error and the IMU motion simulation data, the multi-source sensor internal and external parameters are obtained, and the time alignment compensation of the image frame and the sensor data is performed; Based on the historical foundation pit area image frame and the corresponding timestamp information, the segmentation mask of the water accumulation area in the foundation pit area image, the corresponding boundary box information and the confidence score are extracted, and the water accumulation area image coordinate set and the attribute data are obtained; According to the pixel mask coordinates of the foundation pit area image and the camera internal parameters, the rotation matrix constructed based on the Euler angle and the unmanned aerial vehicle track position vector are combined to perform world coordinate system conversion, and the real coverage area of the water accumulation area is calculated; Using the multi-view images of the foundation pit area, SIFT or ORB local feature points are extracted, a cross-view correspondence relationship is constructed, and a foundation pit three-dimensional overview map is generated in combination with the camera attitude matrix, the track position vector and the dense point cloud surface fitting result; According to the corresponding three-dimensional coordinate point set of the water accumulation area in each image frame, in combination with the area coincidence degree of the cross-temporal multi-view segmentation point set, the three-dimensional coordinate point set and the area estimation result of the water accumulation area are determined; By projecting the three-dimensional coordinate point set of the water accumulation area to the foundation pit three-dimensional overview map, and in combination with the water accumulation area boundary box center position and the image frame index, a hidden danger monitoring report is generated.

2. The method of claim 1, wherein, The method comprises: According to the spatial boundary coordinates of the foundation pit area, the flight operation height, the camera field of view angle and the image resolution parameters, the image ground projection size and the flight path distance are calculated; by setting the lateral and longitudinal overlap rate threshold, a heading and lateral coverage matrix is constructed; a regular grid scanning path is generated by adopting a rotating minimum circumscribed rectangle constraint; a spiral progressive path starting from the center of the foundation pit is constructed based on a polar coordinate generation function; the regular grid scanning path and the spiral progressive path are taken as the initial flight path set, a multi-objective optimization model with the track coverage rate and the path overlap degree as the objective functions is constructed, the genetic algorithm is adopted to iteratively optimize the flight path node sequence and the flight attitude angle parameters, the optimal flight monitoring path node sequence meeting the coverage and energy balance requirements is obtained in combination with the distance constraint between the flight path nodes and the minimum turning radius limit; according to the optimal flight monitoring path node sequence, the latitude, longitude and height of each node and the shooting trigger time information are obtained, a set of unmanned aerial vehicle control instructions and an unmanned aerial vehicle flight monitoring path are generated; according to the unmanned aerial vehicle flight monitoring path, the camera and the radar are carried on the unmanned aerial vehicle, the multi-view images of the foundation pit area are shot in real time, and are stored in the foundation pit area monitoring database.

3. The method of claim 1, wherein, The method comprises: The camera intrinsic matrix is calculated by shooting the calibration board sequence image, the focal length parameter, the principal point coordinates and the distortion coefficient are obtained by using the camera calibration method of Zhang Zhengyou, the residual data of the actual distance and the radar ranging output are recorded by the radar ranging calibration of the known distance reflection plate, the least square regression method is used to establish the ranging error correction model, and the radar ranging correction coefficient is determined; according to the three-axis angular velocity and linear acceleration data output by the inertial measurement unit, the six-degree-of-freedom motion simulation test is carried out, and the extended Kalman filter algorithm is used to estimate the attitude solution error; the IMU attitude drift correction model parameters are determined by offline adjustment of the bias term and noise covariance matrix parameters, and the calibrated camera, radar and IMU internal and external parameter data are obtained, the IMU internal parameter data includes zero offset, scale factor and noise characteristics, and the IMU external parameter data includes the pose transformation matrix relative to the camera and radar; according to the calibrated camera, radar and IMU internal and external parameter data, the unmanned aerial vehicle autonomous flight task is executed, and the spatial position, attitude parameter and shooting trigger timestamp of the unmanned aerial vehicle are obtained, the spatial position includes the track position and radar height information, the attitude parameter includes the attitude angle and flight speed, and the attitude angle includes the roll angle, pitch angle and yaw angle; by comparing the shooting trigger timestamp with the timestamp recorded by other sensors, the multi-source data time compensation is carried out by using the linear interpolation alignment method, and the spatial position and attitude parameter set at the corresponding image frame time are obtained.

4. The method of claim 1, wherein, Based on the historical foundation pit region image frames and corresponding timestamp information, the segmentation mask, corresponding bounding box information and confidence score of the water accumulation region in the foundation pit region image are extracted, and the water accumulation region image coordinate set and attribute data are obtained, including: Through the foundation pit region monitoring database, the historical foundation pit region image frames and corresponding timestamp information are obtained, the image enhancement processing method of random cropping, rotation, multi-scale scaling and brightness contrast adjustment is used to generate an extended image sample set containing multiple views, different lighting conditions and different scale changes; the rectangular boundary box of the water accumulation region in the historical foundation pit region image and the extended image sample set is drawn by using the frame selection labeling method, the yolov11 target detection algorithm is used for model training, the segmentation mask, corresponding bounding box information and confidence score of the water accumulation region in the foundation pit region image are extracted; the pixel mask coordinate point set of the water accumulation region in the image coordinate system is obtained by decoding the extracted water accumulation region image; the pixel-level boundary contour of the water accumulation region is calculated by counting the area pixel number and boundary polygon vertex coordinates of each water accumulation region, the image frame index, mask coordinates, confidence and timestamp information are stored in the foundation pit region monitoring database, and the image coordinate set and attribute information of the water accumulation region are obtained; by pre-setting the confidence threshold and mask integrity screening conditions, the pseudo-detection region and boundary damaged target are removed, the target mask set meeting the spatial continuity requirement is retained, and the pixel mask coordinate point set and image frame index information are recorded.

5. The method of claim 1, wherein, The world coordinate system conversion is performed by combining the rotation matrix constructed according to the Euler angle and the flight path position vector of the unmanned aerial vehicle, and the real coverage area of the water accumulation region is calculated. According to the pixel mask coordinates of the foundation pit area image and the camera intrinsic parameters, the water accumulation area boundary points in the image coordinate system are mapped into the space rays in the camera coordinate system by using the pinhole imaging model, and the formula is wherein, is the space ray in the camera coordinate system, is the scale factor, is the camera intrinsic parameter matrix, , is the focal length, , is the principal point coordinate, is the image pixel point coordinate; according to the roll angle, the pitch angle and the yaw angle recorded in the flight process of the unmanned aerial vehicle, the rotation matrix around the X axis, the Y axis and the Z axis is calculated in turn by using the Euler angle split shaft rotation method, and the 3*3 space rotation matrix is formed by matrix multiplication; based on the rotation matrix of the unmanned aerial vehicle and the track position vector , the camera coordinate system ray is converted to the world coordinate system, and the formula is, wherein, is the coordinate in the world coordinate system, is the attitude matrix, is the track position vector; the two-dimensional pixel mask is projected to the three-dimensional coordinate, and the real coverage area of the water accumulation area is calculated by triangulation or gridding method wherein, is the projection area grid of a single water accumulation segmentation mask, and N is the grid point number of the mask.

6. The method of claim 1, wherein, The three-dimensional overview map of the foundation pit is generated by combining the camera pose matrix, the flight path position vector and the dense point cloud surface fitting result. Using multi-view images of the foundation pit area, local feature points are extracted using SIFT or ORB methods to establish feature correspondences between the multi-view images. The structure self-motion method is employed to calculate the attitude matrix and track position vector of the image frames in the world coordinate system, and to reconstruct the sparse 3D point cloud. The formula is ,in, This represents the pinhole projection function, which maps 3D points onto the image plane. For the first Number of feature points in an image The number of image frames. Let be the pose matrix corresponding to the i-th image. Let be the trajectory position vector corresponding to the i-th image; based on the lidar altitude ranging values ​​recorded during flight, align the Z-axis coordinates of the 3D sparse point cloud with the radar ground altitude reference, and use the formula... The Z-axis of the 3D sparse point cloud is corrected, whereby... The average height of the sparse point cloud is given. Based on the camera pose parameters calculated by the structure self-motion method and the 3D sparse point cloud results, a multi-view stereo matching algorithm is used to perform disparity estimation and depth inversion on each pixel in the image to construct a high-density 3D dense point cloud. The pose parameters include spatial position and attitude parameters. The dense point cloud is then surface-fitted and topologically modeled using Poisson reconstruction or Delaunay triangulation algorithms to generate a 3D overview of the foundation pit.

7. The method of claim 1, wherein, The three-dimensional coordinate point set of the water accumulation region is determined according to the three-dimensional coordinate point set of the water accumulation region in each image frame, and the area estimation result of the water accumulation region is determined according to the area coincidence degree of the cross-temporal multi-view segmentation point set. According to all pixel points in the real coverage area of the waterlogging area of each acquisition frame, the corresponding three-dimensional coordinate points are converted through the pose parameters at the corresponding moment; the segmented coordinate point sets of multiple views and multiple moments in time sequence are expressed as , the area coincidence degrees of different detection results on the reference plane are calculated through formula , based on a preset coincidence degree threshold, low-confidence detection results less than the preset coincidence degree threshold are removed , wherein represents the overlap ratio of the detection results and on the projection plane, , are three-dimensional coordinate point sets of the two detection results; according to the remaining high-confidence detection results, the three-dimensional coordinate point set and the area estimation result of the waterlogging area are determined using formula , wherein is a weight, which is obtained by comprehensively calculating the segmentation confidence, the area coincidence degree or the multi-view coverage degree, is the area of the ith detection area.

8. The method of claim 1, wherein, The hidden danger monitoring report is generated by projecting the three-dimensional coordinate point set of the water accumulation region to the three-dimensional overview map of the foundation pit, and combining the center position of the water accumulation region bounding box and the image frame index. According to the three-dimensional coordinate point set of the water accumulation region, the grid structure of the three-dimensional overview map of the foundation pit, the face normal vector and the position relationship, the nearest surface region corresponding to each water accumulation point is determined, the projection position of the water accumulation region in the three-dimensional overview map of the foundation pit is determined by using the vertical projection, the normal projection or the shortest distance matching strategy, and the three-dimensional coordinate point set of the water accumulation region is projected into the three-dimensional overview map of the foundation pit; the number of water accumulation targets in the current task period is determined according to the projection position of the water accumulation region in the three-dimensional overview map of the foundation pit, and each target is assigned a unique number identifier; the three-dimensional position coordinates of the water accumulation region in the world coordinate system are determined based on the bounding box center position of the three-dimensional coordinate point set of the water accumulation region, the original image frame index corresponding to the water accumulation region is obtained, the image cropping region containing the segmentation mask of the water accumulation region is extracted as image evidence; the hidden danger monitoring report of the foundation pit region is generated according to the number, the number, the three-dimensional position coordinates, the area and the corresponding image evidence of the water accumulation region, and is stored in the foundation pit region monitoring database.

9. A UAV inspection system for monitoring water accumulation in a foundation pit, which is implemented based on the UAV inspection method for monitoring water accumulation in a foundation pit according to any one of claims 1-8, characterized in that, The system comprises the following modules: An optimal flight monitoring route generation module is configured to construct an initial route set according to the spatial boundary coordinates of the foundation pit region, the flight operation height, the camera field of view angle and the image resolution parameters, determine an optimal route node sequence, and generate a set of unmanned aerial vehicle control instructions; A multi-source sensor calibration and time alignment module is configured to obtain multi-source sensor internal and external parameters according to camera calibration board images, radar ranging residual errors and IMU motion simulation data, and perform time alignment compensation on image frames and sensor data; A water accumulation region identification module is configured to extract the segmentation mask of the water accumulation region, the corresponding bounding box information and the confidence score in the foundation pit region image based on historical foundation pit region image frames and corresponding time stamp information, to obtain the water accumulation region image coordinate set and attribute data; A three-dimensional projection area estimation module is configured to perform world coordinate system conversion by combining the rotation matrix constructed according to the Euler angle and the flight path position vector of the unmanned aerial vehicle, and calculate the real coverage area of the water accumulation region. A three-dimensional projection area estimation module is configured to perform world coordinate system conversion by combining the rotation matrix constructed according to the Euler angle and the flight path position vector of the unmanned aerial vehicle, and calculate the real coverage area of the water accumulation region. The foundation pit three-dimensional overview map construction module is configured to extract SIFT or ORB local feature points by using multi-view images of the foundation pit area, construct a cross-view correspondence relationship, and generate a foundation pit three-dimensional overview map in combination with a camera pose matrix, a track position vector, and a dense point cloud surface fitting result; The multi-view water point set fusion module is configured to determine a three-dimensional coordinate point set and an area estimation result of the water area in combination with an area coincidence degree of the cross-temporal multi-view segmented point set according to the three-dimensional coordinate point set of the water area in each image frame; The hidden danger monitoring report generation module is configured to project the three-dimensional coordinate point set of the water area to the foundation pit three-dimensional overview map, and generate a hidden danger monitoring report in combination with a water area bounding box center position and an image frame index.

Images