172 results about "Ellipsoid" patented technology

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 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.

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 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 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 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 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 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.

The invention relates to the technical field of computer vision, in particular to a three-dimensional scene reconstruction rendering method and system. The method comprises the following steps: generating a corresponding 3D Gaussian ellipsoid for each sparse point cloud of a scene to be reconstructed; obtaining a re-projection area of each 3D Gaussian ellipsoid on the two-dimensional image of different visual angles; taking each re-projection area as a center, and taking all re-projection areas within a set pixel distance range as adjacent re-projection areas of the re-projection area; the method is based on the sum of Gaussian kernel function values from the center of a re-projection area of each 3D Gaussian ellipsoid on a two-dimensional image of different visual angles to the center of each adjacent re-projection area of the area, the edge strength, the local variance, the normalized gradient magnitude, and the absolute value of the dot product of a gradient vector and a normal vector. Calculating a split control function value of each re-projection area; and comparing the splitting control function value of each re-projection area with a set threshold value, and controlling the 3D Gaussian ellipsoid to split. According to the invention, the reconstruction rendering precision of the three-dimensional scene is improved.

The invention discloses a digital twin model construction method based on an electric power system, and the method comprises the steps: collecting the historical operation data of each physical entity in the electric power system, screening out the normal operation data from the historical operation data, and constructing a minimum surrounding ellipsoid of each physical entity; acquiring operation data of each physical entity in the power system in real time, respectively calculating the distance between the operation data of each physical entity and the center of the corresponding minimum surrounding ellipsoid, and if the calculated distance is greater than 1, deleting the operation data corresponding to the physical entity; otherwise, keeping the operation data; carrying out missing value filling on the reserved operation data by adopting a tensor algorithm to obtain complete operation data of each physical entity in the power system; according to the method, the corresponding virtual entities are constructed in the virtual space by using the physical entities in the power system, and the corresponding virtual entities are driven to operate by using the complete operation data of the physical entities in the power system, so that the construction of the digital twinborn model is completed, and the precision of the digital twinborn model of the power system is improved.

The invention relates to a three-dimensional model reconstruction method and device based on a Gaussian sputtering model. The method comprises the following steps: acquiring a scene image of a sparse view angle of a target scene, and determining initialization parameter information of a Gaussian ellipsoid according to the scene image through a motion recovery structure technology and a Gaussian sputtering model; determining a priori depth, a color loss function and a gradient smoothing loss function through a monocular depth model according to a scene image; determining a reference depth according to the scene image through a multi-view three-dimensional depth estimation algorithm; determining a depth consistency loss function according to the prior depth and the reference depth; and updating the initialization parameter information through a Gaussian sputtering model based on a depth consistency loss function, a color loss function and a gradient smooth loss function, determining updated parameter information, and generating a three-dimensional model of the target scene according to the updated parameter information. The reliability and robustness of the three-dimensional model can be improved through depth prior constraint information and a dynamic gradient control method.

The invention provides a power distribution network probability interval power flow affine optimization method and system based on full-pure embedding, and the method carries out the affine optimization of the power distribution network probability interval power flow through a full-pure embedding method, and builds an interval variable correlation model of a mixed box-ellipsoid set to describe the uncertainty between input variables. And the function of accurately simulating the influence of distributed photovoltaic access on the uncertainty power flow distribution of the power distribution network is realized. The full-pure embedding probability interval affine optimization power flow model has good completeness and higher conservative property when solving the power flow of the power distribution network, and is suitable for uncertainty power flow analysis in a relatively large fluctuation interval. The hybrid box type-ellipsoid correlation model not only can describe the independent fluctuation range of the power of each node, but also can capture the linear or weak nonlinear correlation between the nodes; the all-pure embedded power distribution network probability interval power flow model based on the evidence theory realizes organic unification of probability power flow and interval power flow.

The invention belongs to the field of three-dimensional scene reconstruction, and particularly relates to a three-dimensional Gaussian reconstruction method based on feature matching and multi-view consistency, and the method comprises the steps: obtaining a feature matching graph and a reliable matching mask graph between image pairs; constructing a surface fitting constraint loss function, and minimizing a component along the z-axis direction in the three-dimensional Gaussian ellipsoid zoom vector to enable the three-dimensional Gaussian ellipsoid zoom vector to become a two-dimensional Gaussian plane; calculating an unbiased depth value of each pixel based on a two-dimensional Gaussian plane normal and a camera line-of-sight direction; calculating a depth re-projection error of the current view angle and the adjacent view angle according to the filtering feature matching graph, and constructing a depth consistency loss function; comparing normal directions of the current view angle and the adjacent view angle according to the filtering feature matching graph, and constructing a normal consistency loss function; and weighting the surface fitting constraint loss function, the depth consistency loss function and the normal consistency loss function to obtain overall optimization loss, and performing back propagation to finally obtain a three-dimensional reconstruction result. The geometric accuracy of a reconstruction result is remarkably improved.

The present application relates to the technical field of computer vision, and particularly relates to a three-dimensional scene reconstruction rendering method and system. The present application generates a corresponding 3D Gaussian ellipsoid for each sparse point cloud of a scene to be reconstructed; obtains a re-projection area of each 3D Gaussian ellipsoid on a two-dimensional image at different viewing angles; takes each re-projection area as the center, and sets all re-projection areas within a certain pixel distance range as adjacent re-projection areas of the re-projection area; based on the sum of the Gaussian kernel function values from the center of the re-projection area of each 3D Gaussian ellipsoid on the two-dimensional image at different viewing angles to the centers of each adjacent re-projection area of the area, the edge intensity, the local variance, the normalized gradient amplitude, and the absolute value of the dot product of the gradient vector and the normal vector, calculates the split control function value of each re-projection area; compares the split control function value of each re-projection area with the size of a set threshold, and controls the 3D Gaussian ellipsoid to split. The present application improves the three-dimensional scene reconstruction rendering precision.

The invention discloses an indoor scene three-dimensional reconstruction method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a multi-view image of an indoor scene, and obtaining a plurality of three-dimensional Gaussian ellipsoids based on the multi-view image; obtaining semantic features of each three-dimensional Gaussian ellipsoid; parameters of the three-dimensional Gaussian ellipsoids are optimized based on a loss function, semantic categories are extracted based on semantic features, attribute alignment is carried out on the three-dimensional Gaussian ellipsoids of the same semantic category, and a reconstruction view after three-dimensional reconstruction is generated; and geometric completion and texture completion are performed on the reconstructed view based on the semantic features to obtain a new view, so that the problem that accurate three-dimensional reconstruction of an indoor scene cannot be realized in the prior art can be solved.

The invention relates to a water invasion volume quantitative identification method based on a semi-ellipsoid radial seepage model, and belongs to the technical field of oil reservoir engineering. The method comprises the following specific steps that dimensionless time tD and pressure increment delta pj of an oil well are calculated; calculating dynamic reserves without water invasion according to the dynamic data of the oil well and a flowing substance balance equation; calculating a water invasion coefficient; the water invasion volume is obtained. The invention relates to a novel method for calculating invasion volumes of different types of water bodies invaded into an oil reservoir by radial flow edge and bottom water by utilizing a semi-ellipsoid geometric model of a Van Everdex-Hust equation principle, which can solve the problem of quantification of the invasion volumes of the water bodies at any moment in the water invasion process of the edge and bottom water oil reservoir. The influence of unstable seepage on the water invasion process is considered, the basic law of fluid flowing in the water invasion process is met, meanwhile, the water invasion coefficient calculation method which does not need to estimate the size of an oil reservoir is provided, and the overall error is small.

The invention relates to the technical field of three-dimensional reconstruction, and discloses a three-dimensional scene reconstruction method and device, equipment, a storage medium and a program product, and the method comprises the steps: carrying out the initialization of a three-dimensional Gaussian ellipsoid based on an obtained fuzzy image sequence and an event sequence, and obtaining an initial Gaussian ellipsoid; constructing a loss function based on a clear picture sequence obtained by rendering the fuzzy picture sequence through the initial Gaussian ellipsoid and geometric constraints of an event-ungenerated area corresponding to the fuzzy picture sequence and the event sequence; taking the minimum value of the loss function as an optimization target, and adjusting the parameter information of the initial Gaussian ellipsoid to obtain a target Gaussian ellipsoid; and performing three-dimensional scene reconstruction based on the target Gaussian ellipsoid to obtain a target three-dimensional scene. Therefore, three-dimensional reconstruction is carried out in combination with a fuzzy picture sequence obtained by a traditional camera and an event sequence obtained by an event camera, the reconstruction effect of a three-dimensional scene is improved, geometric constraint is added to guide and adjust a Gaussian ellipsoid, and the reconstruction effect of the three-dimensional scene is further improved.

The application provides a scene semantic occupancy prediction method based on semantic-distance adaptive Gauss, and relates to the technical field of machine learning. The method comprises the following steps: extracting features and collecting point clouds from a surround view 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 the original sampling point cloud set to obtain initial Gauss anchor points, and distributing the initial Gauss anchor points to different spatial resolution levels; according to the levels and the semantic information, adjusting a preset basic semantic scale to obtain a modified scale of a Gauss ellipsoid, randomly adding a rotation vector to each Gauss ellipsoid to obtain initial four-dimensional attributes of the Gauss ellipsoid; using a Gauss attribute iterative model to dynamically adjust the initial four-dimensional attributes for multiple rounds, and finally projecting to a target voxel grid to generate a dense 3D semantic occupancy prediction, so that the prediction result is more accurate. The method realizes intelligent dynamic allocation of computing resources and efficient real-time three-dimensional scene understanding capability.