232 results about "Ellipsoid" patented technology

The invention discloses a historical block scene three-dimensional reconstruction method and system based on Gaussian sputtering, and the method comprises the steps: collecting a historical block video sequence through a lightweight panorama camera, extracting a multi-frame panorama, and generating an image data set through a projection converter; monocular depth and normal estimation is carried out through a pre-training visual model, and a prior depth and normal graph data set of a historical block scene is constructed; sparse reconstruction is carried out on the multi-view image data set based on the SfM technology, initial point cloud and camera pose information are acquired, and a Gaussian ellipsoid is optimized in combination with prior depth and normal information; dynamically calculating the geometric width estimation value of the street, and guiding and adjusting the adaptive density of the Gaussian ellipsoids of the vertical surfaces on the two sides; rendering the optimized Gaussian ellipsoid through an improved rasterization renderer; and designing a multi-modal loss function and a regularization mechanism to optimize reconstruction and rendering results. According to the method, high-fidelity three-dimensional reconstruction of the historical block scene is realized, and the adaptability of the Gaussian sputtering method to the complex block scene is enhanced.

The invention provides a scene reconstruction method based on delayed rendering and three-dimensional Gaussian. The method comprises the following steps: S1, generating initial three-dimensional point cloud data based on a multi-view image; s2, constructing a trainable structural body for three-dimensional Gaussian modeling; s3, normal initialization and residual optimization are carried out on the Gaussian ellipsoid primitives, depth consistency constraint is combined, and a differentiable and learnable normal reconstruction mechanism is realized, so that the geometric expression ability of illumination modeling is enhanced; s4, introducing a reflection training mechanism based on ambient light and a reflection direction, and generating a Gaussian attribute based on a visual angle; and S5, a final image is generated through a differentiable Gaussian sputtering rendering algorithm, and optimization is carried out through pixel loss of the final image and a real image. According to the method, the reality sense and geometric consistency of the Gaussian sputtering model under the complex illumination condition are remarkably improved, and the technical problems of unreal rendering effect, inaccurate surface normal estimation, weak propagation capability and the like of the existing three-dimensional Gaussian sputtering model under the complex illumination condition are solved.

The invention discloses a mechanical arm path planning method and system based on self-adaptive ellipsoid sampling, and the method combines ellipsoid contraction sampling and dynamic step length adjustment, and uniformly samples in an ellipsoid and eliminates collision points by constructing an ellipsoid sampling domain taking a connecting line of a starting point and an end point as a main axis; meanwhile, the expansion step length is adaptively adjusted according to the local obstacle density, and the ellipsoid is dynamically shrunk and expanded in the searching process so as to continuously focus the feasible channel. After an initial path is obtained, path smoothing optimization is carried out by adopting a non-uniform B spline guided by an ellipsoid, and the curvature of the path and the safety distance between the path and an obstacle are comprehensively considered. Verification of the method in a typical complex environment shows that the planning efficiency and the success rate can be remarkably improved, the path smoothness and the safety distance are considered at the same time, and the method is suitable for mechanical arm online obstacle avoidance path planning in the real-time complex environment.

The invention provides a scene semantic occupancy prediction method based on semantic-distance adaptive Gaussian, and relates to the technical field of machine learning. The method comprises the following steps: carrying out sign extraction and point cloud acquisition on a look-around image sequence around a vehicle, inputting a feature map into a double-branch prediction network to obtain semantic information and position information of original sampling points, screening a cloud set of the original sampling points to obtain initialized Gaussian anchor points, and distributing the initialized Gaussian anchor points to levels with different spatial resolutions; according to the hierarchy and semantic information, adjusting a preset basic semantic scale to obtain a correction scale of Gaussian ellipsoids, and randomly adding a rotation vector to each Gaussian ellipsoid to obtain an initial four-dimensional attribute of the Gaussian ellipsoids; and performing multi-round dynamic adjustment on the initial four-dimensional attribute by using a Gaussian attribute iteration model, and finally projecting the initial four-dimensional attribute to a target voxel grid to generate dense 3D semantic occupancy prediction, so that the prediction result is more accurate. And intelligent dynamic allocation of computing resources and efficient and real-time three-dimensional scene understanding capability are realized.

The invention discloses a plant three-dimensional reconstruction method and a related device, and relates to the technical field of computer vision, the method executes multiple iterations to update a Gaussian ellipsoid set, when a color image under each view angle is rendered in each iteration, the depth value of each key point is obtained based on a depth image, and the color image at each view angle is rendered. The depth weight of the target Gaussian ellipsoid is obtained based on the depth value, the depth weight is inversely correlated with the depth value, that is, the contribution of the Gaussian ellipsoid with the small depth value to color rendering is improved, depth information distinguishing of a fine region is enhanced by introducing the depth weight, the contribution of Gaussian ellipsoids of different depth levels to rendering dyeing is accurately controlled, and the color rendering efficiency is improved. Therefore, the geometric accuracy and layering sense of three-dimensional reconstruction of the plant are improved, and the reduction degree of the three-dimensional reconstruction model to the plant is further improved.

The invention relates to the technical field of tunnel engineering geological construction, and discloses a tunnel surrounding rock crustal stress intelligent analysis method and system based on parameters while drilling. Dynamic coordinate system construction, mechanical specific energy calculation, Stacking model classification, wave velocity ellipsoid modeling, dynamic weight fusion and differential drive re-calibration are realized, and three-dimensional stress field high-precision reconstruction and construction parameter optimization are completed; the system comprises a multi-source sensing module, a dynamic modeling module, a hybrid analysis module, an adaptive fusion module, a three-dimensional reconstruction module and a closed-loop control module. According to the method, high-precision ground stress analysis is realized through cooperation of multi-source data fusion and a mixed model and combination of dynamic weight distribution and a local re-calibration mechanism. Complementation of a wave velocity ellipsoid physical model and a Stacking integrated learning model is innovatively adopted, and octree space reconstruction and closed-loop control are combined, so that the complex geological adaptability is improved, and the construction efficiency and the system reliability are optimized.

The invention discloses a volume cloud rendering method and system based on three-dimensional Gaussian splash, and the method comprises the steps: carrying out the feature matching and structure reconstruction of a volume cloud image through an SfM algorithm, obtaining a sparse point cloud in a scene, and representing the sparse point cloud as an anisotropic Gaussian ellipsoid; decomposing the illumination transmission process of the volume cloud into two parts of forward single scattering and internal multiple scattering based on a radiation transmission equation to obtain an illumination modeling formula embedded volume cloud rendering process; determining the contribution of each three-dimensional Gaussian ellipsoid to a rendering result according to the opacity index of the three-dimensional Gaussian ellipsoid, and dynamically cutting the low-contribution three-dimensional Gaussian ellipsoid by adopting a delay deletion strategy to reduce redundancy; a comprehensive loss function is constructed, so that the three-dimensional Gaussian model is focused on the volume cloud region and the structure detail reduction capability is enhanced; and outputting the optimized volume cloud rendering result and the three-dimensional Gaussian model. According to the method, the volume cloud rendering efficiency and quality are effectively improved on the premise of ensuring real-time rendering.

According to the human body model reconstruction and body measurement method and system based on three-dimensional Gaussian splashing, the 3D GS technology is adopted, a scene is modeled through a group of Gaussian ellipsoids, and therefore efficient rendering and reconstruction are achieved. Compared with a traditional neural implicit representation method, the rendering speed and the reconstruction quality of the 3DGS are remarkably improved. The method is not limited by specific postures of the SMPL human body parameterization model, and more complex and diversified postures can be processed. Therefore, a more vivid and natural human body model can be generated in applications such as virtual reality, animation and games. According to the method, multi-view depth supervision is introduced, depth information is obtained from multiple views, and the precision of the model is further improved by using multi-modal data. By obtaining the RGB images and the depth maps of the multiple visual angles at the same time, the quality of the reconstruction result can be effectively improved, and the method is used for measuring body parameters.

The invention discloses a three-dimensional scene reconstruction method and system based on monocular depth estimation, and belongs to the technical field of computer vision and three-dimensional reconstruction, and the method comprises the steps: carrying out the multi-scale feature coding of a monocular RGB image through a mixed attention depth coding module, and obtaining the hierarchical depth feature representation; carrying out autoregression depth decoding through a self-adaptive edge perception depth decoding module to generate an initial depth map; a depth confidence map is calculated through a geometric consistency constraint optimization module and is fed back to a coding module for iterative optimization, and a refined depth map is output; and three-dimensional Gaussian ellipsoid scene representation is constructed through the Gaussian ellipsoid scene reconstruction module. According to the invention, high-precision depth estimation and high-quality three-dimensional reconstruction are realized by constructing a depth-coupled closed-loop cooperative system.

Provided in the present invention is a reconstruction and driving method based on a multi-view motion video of a clothed human body. The method comprises: using a two-layer three-dimensional Gaussian representation to model a human body and corresponding clothes; defining geometric attributes of three-dimensional Gaussian ellipsoids for any face on coarse three-dimensional meshes of the human body and the clothes; at a reconstruction stage, transforming coarse triangular meshes of the clothes and the body from a canonical space to an observation space, and updating Gaussian geometric attributes; and on the basis of a camera pose and parameters of an input video, rasterizing a three-dimensional Gaussian representation of the observation space to an image space, and rendering a picture on the basis of a Gaussian splatting formula. Self-supervised training can be performed on a model by means of calculating the color difference between a rendered picture and a real picture and using same as an optimization objective; when reconstruction is completed and driving is performed, a geometric result of a current frame is used to calculate the position of the coarse triangular mesh of the clothes in the next frame; and the reconstruction-stage method and related parameters are used to render a driving picture in a new posture.

The invention discloses a degradation scene-oriented multi-residual fusion laser radar positioning method, which comprises the following steps of: firstly, performing state prediction by adopting an iterative extended Kalman filtering framework and an IMU (Inertial Measurement Unit), and constructing three complementary observation models of a global map matching residual, a local point-to-plane geometry residual and a luminosity residual; secondly, designing a degradation sensing mechanism based on a covariance ellipsoid, representing absolute and relative degradation degrees through a condition number and an information entropy respectively, realizing quantitative evaluation of system observability, and dynamically adjusting fusion weights of observation residuals; meanwhile, a self-adaptive weight strategy based on luminosity Jacobi intensity is introduced; and finally, performing anomaly detection through deviation comparison between the IMU predicted pose and the IEKF estimated pose, inhibiting pose jump, and ensuring continuity of a positioning time sequence. The method effectively overcomes the challenges of geometric constraint deficiency, positioning drift accumulation and the like of the LiDAR positioning system in the geometric degradation environment, does not need to adjust parameters for a specific scene, and improves the precision, robustness and real-time performance of global positioning in the degradation environment.

The embodiment of the invention provides an underwater scene three-dimensional reconstruction method based on three-dimensional Gaussian sputtering and related equipment, and belongs to the technical field of computer vision. The method comprises the following steps: performing feature point analysis on each real two-dimensional image to obtain a sparse point cloud set; a three-dimensional Gaussian ellipsoid of each point cloud in the sparse point cloud set is initialized to represent a three-dimensional underwater scene, and the three-dimensional Gaussian ellipsoid is used for representing Gaussian distribution of the position, the covariance matrix, the color and the opacity of the point cloud; selecting a plurality of three-dimensional Gaussian ellipsoids located in a corresponding camera view cone based on the target camera pose, and performing two-dimensional projection rendering according to the plurality of selected three-dimensional Gaussian ellipsoids to obtain a rendered two-dimensional image; and updating the three-dimensional Gaussian ellipsoids in the point cloud space according to the rendered two-dimensional image and the real two-dimensional image with the same target camera pose to obtain a plurality of three-dimensional Gaussian ellipsoids accurately representing the underwater scene. According to the invention, the accuracy and efficiency of underwater scene three-dimensional reconstruction can be improved.

The invention discloses a 3D GS cultural relic digital reconstruction method and system based on a block chain, and the method comprises the steps: collecting the RGB image data and depth perception data of a cultural relic, eliminating the influence of different shooting conditions through an illumination separation processing technology, and building a standardized image data set; recognizing a surface area suitable for reconstruction based on image analysis, determining feature point distribution by using kernel density estimation, and generating initial three-dimensional representation through Gaussian ellipsoid fitting; performing gradient calculation and feature extraction on the depth data, and combining with Gaussian representation to form a geometric constraint mechanism; self-adaptive encryption based on visual importance is executed for a sparse region, and a layered rendering effect is achieved through opacity parameter adjustment; the rendering characteristics and the conversion relation of different view angles are analyzed, key observation points are determined through stability analysis, and a smooth multi-view-angle display sequence is constructed; and integrating multi-view rendering information to generate volumetric representation, and completing right confirmation of the high-quality three-dimensional digital model through digital signature.

The invention discloses a Gaussian splash dynamic three-dimensional reconstruction method and system based on spiking neurons, and the method comprises the steps: carrying out the multi-view video recording of a reconstruction target, and obtaining a two-dimensional RGB image sequence and time dimension data; based on the two-dimensional RGB image sequence, sparse point cloud data and a camera pose are calculated by using a COLMAP algorithm, and a three-dimensional Gaussian ellipsoid is initialized based on the sparse point cloud data; constructing a Gaussian deformation field network, and inputting time dimension data and position information of a three-dimensional Gaussian ellipsoid for training a time-varying deformation field of the Gaussian ellipsoid; and based on the camera pose and the two-dimensional RGB image sequence, optimizing parameters of a three-dimensional Gaussian ellipsoid and a deformation field by using a spiking neuron-based Gaussian splash algorithm, outputting the optimized three-dimensional Gaussian ellipsoid and the deformation field, rendering an RGB image in a specific pose state and time, and realizing dynamic three-dimensional reconstruction. According to the method, Gaussian storage redundancy is remarkably reduced, generation of reconstruction artifacts is inhibited, and rendering and training efficiency is improved.

The invention discloses an unmanned aerial vehicle autonomous flight control method and a related device. The method comprises the steps of obtaining environment map information and unmanned aerial vehicle information; based on the environmental map information and the unmanned aerial vehicle information, obtaining a global optimal path by using a fusion dynamic exploration path planning algorithm; taking each path section in the global optimal path as a center to generate a plurality of ellipsoid areas covering the path sections, converting the boundary of each ellipsoid area into a convex polyhedron formed by a plurality of hyperplanes, and connecting the convex polyhedrons in series according to the sequence of the path sections to obtain a safe flight corridor; in the trajectory optimization process, the safe flight corridor is used as a constraint basis of space feasibility, it is ensured that the trajectory is always located in the safe flight corridor, and space constraints are determined; and carrying out trajectory tracking by adopting a DLQR controller based on the spatial constraint. According to the invention, efficient cooperation of path planning and trajectory tracking is realized.

The invention relates to the technical field of computer vision and robot positioning, and discloses a dynamic 3DGS-SLAM method and system based on Gaussian pyramid and adaptive densification. The method comprises the following steps: generating a semantic mask through real-time dynamic target detection so as to distinguish a static background from a dynamic object; constructing a 3D Gaussian map model of the scene; rendering images in parallel on a full-resolution view and a down-sampling resolution view by adopting a motion perception Gaussian pyramid rendering method, and fusing rendering results by utilizing a dynamic mask so as to eliminate motion edge artifacts; a self-adaptive densification strategy based on a monotonic attenuation function is adopted, the initialization radius of the Gaussian ellipsoid is dynamically adjusted based on the training progress, and high-density initialization and progressive redundancy pruning are executed to optimize the geometric fidelity; and finally, performing coarse-to-fine camera pose optimization, and outputting a precise pose and a high-fidelity static map. According to the method, the problems of tracking drift and rendering artifacts under dynamic interference are effectively solved, and the positioning precision and the rendering quality are improved.

The invention discloses a 3D Gaussian weak texture compensation and density control reconstruction method, and the method comprises the steps: recovering a camera pose P through employing a Colmap frame, merging the obtained first sparse point cloud data with laser point cloud data, solving a vacancy problem possibly existing in the sparse point cloud, and especially in an area with insufficient environment illumination or texture loss, carrying out the reconstruction of the 3D Gaussian weak texture compensation and density control, and carrying out the reconstruction of the 3D Gaussian weak texture compensation and density control. More accurate position information is provided for the Gaussian ellipsoid by using depth information of the laser point cloud, and floating objects are reduced; a depth image is generated based on the laser point cloud data and the camera pose P, an obtained depth value Z is fused with the laser point cloud data and the image data, and reasonable distribution of Gaussian ellipsoids in the space is ensured; excessive Gaussian distribution in a dense region is reduced through a dynamic threshold value and a voxel point number limiting strategy, so that the training cost and the rendering pressure are reduced; and particularly, by applying point number limitation in voxels and a dynamic threshold rejection strategy, the Gaussian density is reduced, so that ellipsoids at dense positions are reduced, and the training cost and the rendering pressure are reduced.

The invention discloses a radar camera external parameter calibration method and system based on 3D Gaussian sputtering, and the method comprises the steps: enabling a laser radar and a camera system to stand, and accumulating laser radar point clouds of a collection scene; secondly, carrying out voxel segmentation on the point cloud density according to the point cloud density, constructing a covariance and a mean value of an initial Gaussian ellipsoid, expressing a three-dimensional scene by using a 3D Gaussian ellipsoid, and obtaining a rendering result; then, constructing a covariance change loss function and a total loss function, and performing coarse optimization and fine optimization on external parameters of the camera and the radar through back propagation of the loss functions; and finally, programming the calibration method, and finishing external parameter adjustment of the laser radar and the camera by using a computer processor. According to the invention, efficient and accurate external parameter calibration is carried out on the laser radar and the camera, the calibration precision of the camera and the radar in a non-structural environment can be effectively improved, and the problem of external parameter calibration in multi-sensor data fusion can be solved.

The invention discloses a configuration acquisition method and system for realizing a maximum violation five-setting CHSH measurement device, and relates to the technical field of quantum information processing, and the method comprises the steps: S1, obtaining the probability amplitude of the pure state of a pair of two-dimensional non-maximum entangled particle A and particle B, and calculating the concurrency; s2, constructing an incidence matrix based on the concurrency, and mapping the measurement vector of the particle B from the Bloch spherical surface to the ellipsoid surface by using the incidence matrix; s3, taking five points on the same plane on the ellipsoid as vertexes of a five-pointed star, wherein a perimeter formula of the five-pointed star is equivalent to a correlation function maximum value formula; s4, traversing vertex positions of the five-pointed star to obtain a maximum perimeter value; s5, obtaining the measurement vector of the particle B and the measurement vector of the particle A to obtain the optimal measurement configuration; and S6, configuring a quantum measurement device to measure the particles A and B. According to the method, the problem of setting the maximum value of the CHSH correlation function is converted into the problem of solving the maximum value of the perimeter of the ellipsoid inscribed five-pointed star, and the optimal measurement scheme is obtained through simple numerical fitting.

The invention discloses a 3D human avatar method and a 3D human avatar system which are generated based on 3d gaussian patterning and can be driven in real time. The 3D human avatar system comprises a data acquisition module, a Gaussian initialization module and a training rendering module, the data acquisition module acquires a small amount of human body data based on a single camera, predicts human body posture information based on an smplx model and expression information based on a Flame model from two-dimensional human body image data, and makes labels; a Gaussian initialization module carries out adaptive Gaussian initialization on a human body smplx model grid in any frame label to obtain a 3D Gaussian ellipsoid; and the training rendering module is used for training the 3D Gaussian ellipsoid initialized in the step 2 based on an improved 3d Gaussian sputtering model, and rendering a 3D human avatar capable of being driven in real time. According to the method, the topological consistency of the Gaussian point and the human body smplx model can be highly maintained, artifacts are reduced, and high fidelity is improved.

The invention discloses a multi-view image Gaussian reconstruction method and system guided by LiDAR point cloud. The method comprises the following steps: step S1, realizing accurate registration of LiDAR point cloud and a multi-view image in the same earth-centered earth-fixed coordinate system through GNSS constrained aerial triangulation, and uniformly carrying out center-of-gravity normalization to ensure space consistency and numerical stability; s2, estimating surface normal and scale parameters based on the local geometric features of the LiDAR point cloud, constructing a Gaussian ellipsoid consistent with the local geometry, and realizing Gaussian ellipsoid initialization of geometric perception; and S3, generating a sub Gaussian ellipsoid according to the Gaussian gradient and the tangent plane direction, and improving the modeling density and geometric continuity of the detail region through local encryption and parameter inheritance. According to the method, the fusion of LiDAR point cloud high-precision geometry and multi-view image texture information is realized, the geometric precision, the structural integrity and the detail expression capability of three-dimensional reconstruction are effectively improved, and the method is particularly suitable for high-precision live-action three-dimensional modeling of unmanned aerial vehicle multi-view images.

The invention relates to the technical field of three-dimensional modeling, in particular to an electromechanical pipeline model construction system and method based on unmanned aerial vehicle oblique photography. The method comprises the following steps: collecting electromechanical pipeline images; extracting feature points from the image by using an SfM technology, matching a multi-view image, reconstructing a sparse point cloud, and obtaining an initial three-dimensional structure and a camera track of a scene; initializing the point cloud into a 3D Gaussian ellipsoid, and decomposing a covariance matrix through a rotation matrix and a scaling matrix to optimize calculation; projecting the 3D ellipsoid to an image plane based on the view transformation matrix and the Jacobian matrix to realize rasterization rendering; calculating an error between a rendered image and a real image by adopting a mixed loss function, optimizing Gaussian primitive parameters through back propagation, and performing adaptive density control at the same time; a high-precision three-dimensional model is generated, BIM or CAD format export is supported, and visual display can be performed in a VR / AR environment; according to the invention, intelligent management and monitoring of electromechanical pipelines are realized.

The invention relates to the technical field of building geometric reconstruction and crack detection, in particular to a three-dimensional reconstruction and damage detection method for a building in an intelligent driving environment, and the method comprises the steps: collecting a building video in a road environment during intelligent driving, and reconstructing a sparse point cloud of the building through an SfM algorithm; inputting each frame of time sequence image into a pre-trained semantic segmentation model to generate a crack highlight image; according to the sparse point cloud, initializing a corresponding parameterized 3D Gaussian ellipsoid, and optimizing parameters of the 3D Gaussian ellipsoid; mapping the 3D Gaussian ellipsoid to a two-dimensional image plane through a camera model, and generating a rendered image through a differentiable rendering algorithm; and comparing the rendered image with the crack highlight image, iteratively calculating the overall loss, and transmitting the overall loss through a back propagation gradient until a preset convergence condition is reached, thereby obtaining a final 3D model which simultaneously expresses the overall structure of the building and crack details. According to the invention, accurate environment data can be provided for the automatic driving system.

The invention belongs to the technical field of computer vision and three-dimensional reconstruction, and discloses an endoscope image dynamic reconstruction method based on point cloud compensation and double-domain deformation, and the method comprises the steps: firstly, carrying out the point cloud compensation of a shielding region, generating a reference frame point cloud for a reference frame from which a surgical tool is removed, and carrying out the point cloud compensation; generating compensation point clouds by utilizing parts, visible to the shielding area of the reference frame, in other frames, and combining the compensation point clouds to obtain initialized point clouds with sufficient distribution priori; then, a Gaussian ellipsoid set is constructed based on the initialized point cloud, and two-stage double-domain deformation training is executed, in the first stage, Gaussian preheating training is carried out, and the position and rotation of a Gaussian ellipsoid are kept not to change along with time; in the second stage, the Gaussian distribution function of the time domain and the Fourier series of the frequency domain are adopted to cooperatively fit the position of the Gaussian ellipsoid and the deformation quantity of rotation along with time. According to the method, the initialization quality is optimized through point cloud compensation, and rapid and high-quality endoscope image dynamic reconstruction is realized through a two-stage double-domain deformation method.

The invention discloses a post-restoration efficient three-dimensional modeling method for building colored drawing, which comprises the following steps of: 1, introducing a pre-restoration module, and restoring an acquired picture by adopting a pre-trained SD (Secure Digital) model; filtering a part of hue gauss with relatively high overlap ratio; step 3, respectively obtaining Gaussian point clouds of the repaired part and the original scene by using the step 2; and after the optimized final point cloud representation is obtained, combining the repaired part with the Gaussian point cloud of the original scene, and modeling the scene into a Gaussian ellipsoid by imitating a 3DGS method, so as to repair the traditional building on the three-dimensional level. The method is based on a stable diffusion model (Stable Diffusion) and a 3DGS technology, aims to overcome the defects in building repair modeling in the prior art, and particularly can realize optimization on time and space overhead.

The invention relates to the technical field of occupancy network training, and discloses a self-supervised occupancy network training method and system based on 3D Gaussian splash rendering, and the method comprises the steps: fusing the 3D voxel features of a vehicle-mounted image with embedded features containing initial Gaussian attributes, obtaining the fused voxel features, and carrying out the decoding based on a Gaussian attribute decoder, obtaining a 3D Gaussian ellipsoid of each voxel grid; projecting the 3D Gaussian ellipsoid to a 2D image space by using a Gaussian splash rendering technology to obtain a 2D depth map; and generating a target view through linear sampling based on the 2D depth map and the vehicle-mounted image at the adjacent moment, and calculating luminosity reprojection loss based on the vehicle-mounted image and the target view to train the occupancy network. According to the method, the volume rendering calculation complexity and the reasoning time proportion are reduced, and the operation efficiency of the self-supervised occupation network is improved; and meanwhile, rendering can be carried out on the premise of not reducing the resolution of the depth map and supervising the quality, and the training effect and performance of the self-supervised occupancy network are improved.

An EUV collector (24) is used in an EUV projection exposure system. The EUV collector (24) is designed to guide EUV useful light (3) from a source area (19) to a collecting area (26). The EUV collector (24) has at least one reflective surface area (28) which has the shape of a segment of an ellipsoid with two ellipsoidal focal points (F1, F2). The source area (19) is located in the region of one of the ellipsoidal focal points (F1), and the collecting area (26) is located in the region of the other ellipsoidal focal point (F2). The reflective surface area (28) has a maximum collecting angle S2 greater than 120° for useful light beams emanating from the source area (19). Alternatively or additionally, the reflection surface area (28) has at least two detachably connected reflection surface sub-areas, each representing sub-areas of a shape of a section of an ellipsoid with two ellipsoid focal points (F1, F2).

The invention discloses a power line corridor intrusion detection method based on 3D Gaussian sputtering. The method comprises the following steps: acquiring an unmanned aerial vehicle video sequence of a power line corridor and preprocessing the unmanned aerial vehicle video sequence; based on the preprocessed data, performing three-dimensional reconstruction by using a motion recovery structure and a 3D Gaussian sputtering technology to obtain a high-precision 3D GS model of the power line corridor; based on a two-dimensional image detection and segmentation result, performing semantic annotation on a three-dimensional Gaussian ellipsoid in the 3D GS model through multi-view back projection and fusion, and identifying a target object at least including the engineering machinery and the power transmission conductor; calculating the minimum space distance between the identified engineering machinery and the transmission conductor in the three-dimensional space; and judging whether intrusion occurs or not according to whether the minimum spatial distance is smaller than a safety threshold, and outputting alarm information. According to the method, the problems of low reconstruction precision, indirect measurement, poor real-time performance and the like in the prior art are solved, and real-time three-dimensional detection and early warning of the power line corridor intrusion target are realized.

The invention provides a landslide volume estimation method and device, and relates to the technical field of surveying and mapping, and the method comprises the steps: carrying out the boundary recognition of a landslide remote sensing image, obtaining a landslide vector boundary, and obtaining a landslide orthographic projection plane; determining a landslide target area, a landslide target length and a landslide target width according to the landslide orthographic projection plane, and determining a target length-width ratio based on the landslide target length and the landslide target width; based on the landslide target area and the target length-width ratio, generating a normalized center distance based on an ellipsoid geometric model; and estimating the landslide volume based on the normalized center distance, the landslide target area and the landslide target width. Based on the technical scheme, the landslide volume can be quickly estimated.

The invention discloses a power distribution scene reconstruction method and device based on three-dimensional Gaussian sputtering, and belongs to the technical field of scene three-dimensional reconstruction, and the method comprises the steps: obtaining a plurality of visible light images of a power distribution scene; performing three-dimensional reconstruction on the plurality of visible light images by using a motion structure recovery algorithm to obtain camera parameters corresponding to the visible light images and sparse point clouds of the power distribution scene; performing densification processing on the sparse point clouds based on the camera parameters corresponding to the visible light images by using a monocular depth estimation model to obtain dense point clouds of the power distribution scene; constructing a plurality of initial three-dimensional Gaussian ellipsoids based on the dense point cloud; performing parameter optimization on the plurality of initial three-dimensional Gaussian ellipsoids based on the plurality of visible light images to obtain a plurality of optimized three-dimensional Gaussian ellipsoids; and generating a three-dimensional reconstruction result of the power distribution scene based on the plurality of optimized three-dimensional Gaussian ellipsoids. Therefore, by implementing the method and the device, the problem of low accuracy of three-dimensional reconstruction in the prior art can be solved.