124 results about "Octree" patented technology

The invention relates to an OpenGL (Open Graphics Library)-based large-scale three-dimensional model object quick pickup method. The method comprises the following steps: converting an interactive operation of a user into a three-dimensional space structure; a CPU constructs octree space acceleration structures based on a bounding box of an object in a large-scale three-dimensional model, and leaf nodes, intersecting with a pickup ray or a pickup view pyramid, of an axis alignment bounding box in each octree space acceleration structure are screened out to serve as candidate leaf nodes; collecting triangles contained in all candidate leaf nodes, and constructing a candidate triangle set; dynamically allocating thread groups and threads of the GPU based on the number of candidate triangles in the candidate triangle set; and performing highlight display on the candidate triangles intersected with the pickup ray or the pickup view cone, and feeding back IDs of the corresponding candidate triangles. According to the method, the data transmission quantity and the video memory access pressure are remarkably reduced, the pickup response time is greatly shortened in a large-scale three-dimensional model scene, and the requirements of real-time interaction and visual operation can be met.

In one implementation, a method of decoding point cloud data is presented, comprising: decoding features representing voxel attributes in an octree structure, wherein a decoded feature for a current voxel is representative of at least a set of voxels that are still to be reconstructed; determining an attribute probability of the current voxel based on the decoded feature for the current voxel; decoding attribute information of voxels in the octree structure, wherein the attribute information for the current voxel is decoded based on the attribute probability for the current voxel; and reconstructing the point cloud based on the attribute information of voxels in the octree structure. On the encoder side, the features are extracted and encoded into the bitstream.

The invention discloses a low-altitude path planning method and system based on a dynamic adaptive graph neural network, and belongs to the technical field of artificial intelligence and robot autonomous navigation. Aiming at the problems of large calculation amount of a fixed grid map, slow dynamic response of a static octree, failure of a traditional heuristic function on a non-uniform graph and the like, the invention provides the following scheme: constructing a resolution self-adaptive non-uniform graph by using the octree; a Morton code is adopted to realize rapid positioning of a dynamic obstacle and millisecond-level updating of a map; an attention mechanism is introduced into a graph attention network (GAT), weights are adaptively allocated to different neighbor nodes, features are aggregated, and a high-precision heuristic cost estimation value is output; and finally, integrating the estimated value into an algorithm to perform efficient path search. According to the method, the memory occupation and the calculation complexity are remarkably reduced, and the planning efficiency and the path safety in a dynamic environment are improved.

In one implementation, a method of decoding point cloud data is presented, comprising: decoding features representing voxel attributes in an octree structure, wherein a decoded feature for a current voxel is representative of at least a set of voxels that are still to be reconstructed; determining an attribute probability of the current voxel based on the decoded feature for the current voxel; decoding attribute information of voxels in the octree structure, wherein the attribute information for the current voxel is decoded based on the attribute probability for the current voxel; and reconstructing the point cloud based on the attribute information of voxels in the octree structure. On the encoder side, the features are extracted and encoded into the bitstream.

The invention discloses a millimeter wave radar point cloud compression method based on heterogeneous representation and an implicit neural network. Firstly, point cloud fine geometric features are extracted through a point-based compression network, global semantics are aggregated through a voxel-based compression network, and point-voxel heterogeneous joint representation and preliminary compression are realized. Secondly, constructing an adaptive octree to code a compressed data space structure to generate a partitioned bit stream, and performing statistical compression on the voxel-level high-dimensional features by using context-aware entropy coding to generate a feature bit stream; then, joint transmission is performed on the partition bit stream, the feature bit stream and the neural network weight for implicit representation. And finally, decoding and recovering the coarse-grained point cloud at a receiving end, inputting the coarse-grained point cloud and a neural network weight into a point-based synthesis network based on implicit neural representation, and finally reconstructing a high-fidelity point cloud through continuous surface modeling and detail compensation. According to the method, the compression efficiency and the reconstruction quality of the millimeter wave radar point cloud under the low code rate are remarkably improved.

The invention discloses a steel truss extraction method based on point cloud segmentation and feature analysis, and belongs to the technical field of three-dimensional point cloud processing. The method mainly comprises the following steps: firstly, carrying out multi-scale filtering denoising on an original point cloud and constructing an octree index; local geometric features such as normal vectors, curvatures and first-order plane fitting errors of all the points are calculated; based on the adaptively selected seed points, carrying out region growth by combining a normal vector included angle, a curvature difference and an adaptive edge criterion to realize preliminary segmentation; and finally, a coarse-to-fine multi-layer cascade classifier is adopted to screen the segmented areas, and the steel truss point cloud is accurately extracted through geometric dimension filtering, shape feature screening and multi-dimensional feature matching in sequence. The method does not need pre-training, has the advantages of strong anti-interference capability, high extraction precision and high calculation efficiency, and is suitable for engineering scenes of bridge detection, building surveying and mapping and the like.

In one implementation, a method of encoding or decoding point cloud data is provided, comprising: obtaining a feature map representing attributes of voxels in an octree structure; determining one or more probability distribution parameters for a probability density function associated with an attribute of a current voxel, based on the feature map; determining a probability mass function of the attribute of the current voxel based on the one or more probability distribution parameters for the probability density function for the current voxel; and encoding or decoding attribute information of the current voxel in the octree structure, based on the probability mass function of the attribute for the current voxel.

The invention discloses a dynamic octree mapping method and system based on probability semantic fusion and a storage medium, and mainly solves the problem that a traditional octree map lacks semantic information and cannot support an advanced cognitive task. According to the implementation scheme, the method comprises the following steps: acquiring an RGB image, depth information and pose data through a sensor; extracting pixel-level semantic probability distribution by using a pre-trained semantic segmentation network; geometric information in the perception data is projected to a three-dimensional space based on the pose, and a three-dimensional observation point with semantic information is formed; performing ray projection on octree nodes, respectively updating geometric occupancy states of penetrated non-end-point nodes, and synchronously updating geometric occupancy states and semantic belief distribution of end-point surface nodes by using three-dimensional observation point data; semantic information is continuously optimized through Bayesian probability fusion, and dynamic pruning and map optimization are realized based on semantic entropy. According to the method, the map storage efficiency and the calculation speed can be remarkably improved while refined and real-time updated geometric and semantic information is given. The method can be used for map construction and storage of visual SLAM positioning, and fine three-dimensional object modeling and environment information description.

The invention discloses a 3D Gaussian splash rendering optimization method based on a Unity engine in VR, and relates to the technical field of computer graphics. PLY point cloud files are converted into SOG high-compression formats containing multi-level LOD information, after low-transparency Gaussian points are removed, Morton coding sorting is carried out on the center coordinates of the Gaussian points, and then the 3D Gaussian splash rendering optimization method based on the Unity engine in VR is realized. The method comprises the following steps: constructing an octree spatial index containing a spatial bounding box and multiple LOD data, removing Gaussian points in a grading manner according to a camera distance, selecting an LOD hierarchy, carrying out deep barrel sorting on visible Gaussian points, executing drawing by taking a barrel as a unit, and combining near-to-far sorting, an improved mixed equation and screen space edge removal and amplification operation to obtain a target image. According to the method, through multi-dimensional optimization such as loading, space elimination and rendering, the loading efficiency of the VR equipment is improved, the rendering burden is reduced, Tile-Based hardware is adapted, and smooth operation of 3D Gaussian splashing on the VR all-in-one machine is realized.

The invention discloses a block file space topology aggregation and cross-modal indexing method based on HDF5, and relates to the technical field of electric digital data processing. The method comprises the following steps of point cloud space division, space data separation and storage, multi-modal data fusion and multi-level index construction. The method comprises the following steps: performing space division on a point cloud space through an octree algorithm to obtain octree nodes, analyzing the relevance between the space division and a memory in real time to determine whether to perform octree division dynamic adjustment, then encoding each octree node, performing space block data separation storage, and simultaneously performing point cloud data access optimization. According to the method, the multi-level index system of the point cloud space is established, then spatial attribute aggregation is performed to establish the spatial diagram, multi-modal data integration fusion is performed, and finally the multi-level index system of the point cloud space is established, so that the efficiency of accessing and retrieving the image block file space is improved, and the problem of low cross-modal retrieval efficiency of the point cloud space divided based on an octree algorithm in the prior art is solved.

In one implementation, we propose a bitwise octree coding approach based on deep neural networks and operations on 3D sparse tensors. To encode / decode a certain level of detail (LoD) in an octree, geometric features are first inherited from the previous LoD by upsampling. Then based on the already encoded / decoded voxels, the point cloud geometry is firstly refined by pruning, followed by combining with the known context information. In the end, feature aggregation and probability estimation can be applied to obtain the occupancy probabilities for actual arithmetic encoding / decoding. A corresponding probabilistic training strategy is also proposed for our bitwise octree coding approach.

The application discloses a semi-airborne full-time electromagnetic forward method based on an Octree grid, which performs spatial discretization on time-domain Maxwell equations, thereby effectively reducing unknowns of equations to be solved. For full-time electromagnetic field numerical simulation, the application combines the high calculation precision of the second-order backward Euler method with the high OFF-Time calculation efficiency of the model reduction algorithm, adopts the second-order BDF and the model reduction algorithm to respectively solve ON-Time and OFF-Time time-domain control equations, forms a joint algorithm to realize simulation of semi-airborne time-domain electromagnetic full-time response, and finally completes the forward calculation process. Through numerical simulation verification, in the full-time transient electromagnetic forward process, the application can keep small occupied memory and also has higher calculation efficiency, and the calculation precision is not lower than that of other methods.

The invention relates to the field of building three-dimensional reconstruction, in particular to a building three-dimensional reconstruction method based on multi-source data alignment, which comprises the following steps executed in sequence: S1, acquiring building three-dimensional feature data shot by a plurality of unmanned aerial vehicles, and performing multi-source collaborative alignment processing on the plurality of building three-dimensional feature data, the method comprises the following steps: S1, aligning building three-dimensional feature data to obtain aligned building three-dimensional feature data, S2, carrying out recursive space segmentation on the aligned building three-dimensional feature data by using an octree algorithm to obtain a plurality of segmented regions, and S3, defining each segmented region as a local center point by using tile type space decomposition and generating tile units; s4, feature points with the SDF value being 0 are extracted from the global symbol distance field through a moving cube algorithm, then a continuous geometric surface of the building is constructed through linear interpolation, the model is scaled to a real proportion through a distance reference provided by an RTK-GNSS system of the unmanned aerial vehicle, and a reconstructed model is output; the limitation that a traditional three-dimensional reconstruction model only has a visual rendering effect is broken through.

This invention discloses a dual-stream point cloud compression method and system based on semantic scene graphs, relating to the field of point cloud compression. It constructs a point cloud compression network comprising an encoder network and a decoder network: In the encoder network, semantic labels are mapped onto the input point cloud, and scene graphs and octree representations are constructed respectively. Semantic modulation parameters are generated based on the scene graph and encoded to obtain a semantic bitstream. The octree representation, under the influence of semantic modulation parameters, undergoes feature enhancement and attention probability prediction to obtain node occupancy probabilities, and a geometric bitstream is generated through arithmetic encoding. These two bitstreams serve as compressed data. In the decoder network, the bitstreams are decoded, and the octree structure and scene graph information are reconstructed. Node feature representations are recovered by combining the semantic modulation parameters. The reconstructed octree structure is mapped back to the point cloud space through spatial querying and indexing to reconstruct the point cloud. This invention solves the problem of local geometric distortion in low-bitrate octree point cloud compression, ensuring reconstruction quality while reducing the transmission bitrate.

The invention discloses an end-to-end field optimization surface reconstruction method based on Gaussian sputtering guidance, and belongs to the field of computer vision and computer graphics. Comprising the following steps: 1) Gaussian guidance field optimization: defining an implicit symbol distance field by using a parameterized MLP network, and initializing and optimizing a surface through a microcosmic contour surface extraction method; gaussian units are bound with the extracted surface triangular patches, the positions of the patches are parameterized through the vertexes of the patches, rotation and scaling are carried out, regularization constraints based on the minimum wrapped ellipse and the distribution entropy are introduced, it is ensured that the Gaussian units are accurately attached to the surface and evenly distributed on the surface, and a result obtained through rendering guides field optimization. And 2) local multi-resolution: identifying surface voxels based on the optimized symbol distance field to carry out adaptive octree subdivision so as to realize multi-resolution improvement. And 3) adopting an inner and outer double-layer cyclic training architecture, optimizing the symbolic distance field and the grid geometric parameters on the outer layer, and optimizing a bound Gaussian unit on the inner layer to realize end-to-end joint optimization of surface geometry and Gaussian rendering.

The application discloses a kind of based on adaptive boundary perception's spare part point cloud hierarchical super voxel segmentation method, it is related to three-dimensional point cloud super voxel segmentation technical field, this method calculates the multidimensional geometry feature of each point of point cloud first, constructs point cloud boundary weight model by weighted fusion and nonlinear transformation;Again, complete point cloud voxelization based on octree space division mechanism, according to boundary weight value, voxel is divided into boundary voxel and seed voxel, and the initial super voxel is generated by merging the point set in voxel through union-find set data structure;Then, relying on global energy optimization framework, combined with distance measurement function containing boundary weight difference item, hierarchical iterative fusion is carried out on the representative point of initial super voxel;Finally, the super voxel after fusion is corrected and the spatial connectivity is corrected, and the multi-resolution super voxel segmentation result is output.The application can solve the problem that traditional method is easy to over-segmentation, under-segmentation, and enhance the adaptive level of complex equipment spare part structure.

The application discloses a millimeter wave radar point cloud compression method based on heterogeneous representation and implicit neural network. First, the point cloud fine geometric features are extracted through a point-based compression network, and then the global semantics are aggregated through a voxel-based compression network to realize point-voxel heterogeneous joint representation and preliminary compression. Secondly, an adaptive octree is constructed to encode the compressed data space structure to generate a partition bit stream, and a context-aware entropy coding is used to statistically compress the voxel-level high-dimensional features to generate a feature bit stream. Then, the partition bit stream, the feature bit stream and the neural network weight for implicit representation are jointly transmitted. Finally, the coarse-grained point cloud is decoded and recovered at the receiving end, and is input into a point-based synthesis network based on implicit neural representation together with the neural network weight, and through continuous surface modeling and detail compensation, a high-fidelity point cloud is finally reconstructed. The method significantly improves the compression efficiency and reconstruction quality of the millimeter wave radar point cloud at a low code rate.

Systems, methods, and other embodiments described herein relate to using octrees and trilinear interpretation to generate field-specific representations. In one embodiment, a method includes acquiring a latent vector describing an object. The method includes generating an octree from the latent vector according to a recursive network, the octree representing the object at a desired level-of-detail (LoD). The method includes extracting features from the octree at separate resolutions. The method includes providing a field as a representation of the object according to the features.

The present application relates to the engineering geophysical exploration technical field, specifically to a kind of complex terrain direct current resistivity three-dimensional forward and inversion method and system based on octree;Method includes: establishing target information sequence;Three-dimensional geoelectric model based on octree grid is constructed using target information sequence, and local encryption is carried out in the surface near the detection area and electrode neighborhood, and the modeling result is output;Based on the modeling result, the underground active unit located below the terrain surface and the air unit located above the terrain surface are distinguished, the finite volume method is used to discretize and solve the direct current resistivity method potential field control equation of underground active unit, the theoretical potential response corresponding to electrode device is obtained, and the theoretical apparent resistivity response is obtained;Construct inversion objective function, and iteratively update resistivity parameters of three-dimensional geoelectric model using inversion strategy;The three-dimensional resistivity imaging result of underground medium in detection area is output through updated three-dimensional geoelectric model, and adverse geological body is identified.

The invention discloses a joint compression method for building point cloud data based on geometric features, and the method comprises the steps: firstly carrying out the sampling and statistical filtering preprocessing of the building point cloud data under an octree, so as to remove noise and reduce the data density; secondly, accurately identifying and retaining key contour and structural features of the building through an edge point extraction algorithm based on curvature calculation, and then performing redundancy removal on non-edge points by adopting an adaptive multi-scale normal differential segmentation technology (DoN) which can adaptively adjust scale radius parameters according to geometric complexity of the surface of the building; and structure key points are effectively distinguished and reserved. And finally, merging the edge points and the points subjected to normal differential segmentation to form compressed point cloud data. Through verification of a precision evaluation index, the method can remarkably improve the quality of reconstructed point cloud while keeping a low compression ratio, and provides powerful support for efficient storage and transmission of building point cloud data.

The invention relates to the technical field of three-dimensional geographic modeling, in particular to a land utilization planning auxiliary method and system based on a 3D terrain model, and the method comprises the following steps: obtaining point cloud and elevation information, converting the information into a terrain curved surface, discretizing the information into a voxel grid, analyzing a planning index, converting the planning index into a geometric constraint boundary, and traversing to construct a planning voxel field. Calculating earthwork digging and filling requirements and sunshine hours to generate an evaluation matrix, correcting the building voxel distribution and finely adjusting the terrain elevation. According to the method, terrain refined expression is realized by using an octree segmentation algorithm, indexes such as a plot ratio are converted into three-dimensional space geometric constraints, site suitability is evaluated through connectivity analysis, and building layout and earthwork balance are automatically optimized by adopting morphological operation, so that the problems of lack of space intuition and error accumulation in traditional two-dimensional planning are solved; the planning calculation precision and decision scientificity under the complex terrain are remarkably improved, and dynamic adjustment and visual expression of the scheme are achieved.

This invention provides a 3D dense mapping method based on ORB-SLAM2 and a monocular depth camera, comprising: estimating the camera's state using ORB-SLAM2 to obtain the position and related pose information of the monocular depth camera; simultaneously reading the monocular depth image from the monocular depth camera and publishing topics on both; using the position and pose of the depth camera, the monocular depth image, and the monocular color image as input, and employing a posterior probability-based method to utilize the point cloud information generated from the depth image to construct a 3D dense map; recursively expanding the grid of the 3D dense map as the root node to construct an octree map; for idle obstacle grids, using the Euclidean distance algorithm to calculate the distance between the idle grid and the nearest obstacle grid, further constructing a signed Euclidean distance map; and finally displaying it using an NVIDIA edge intelligence development board and a monitor.

The invention discloses a hydroelectric generating set overhauling and disassembling method based on an improved seat head whale migration algorithm, and aims to solve the problems of long period, high cost, poor safety and the like caused by complex structure, narrow space and dependence on artificial experience in large-scale hydroelectric generating set overhauling. The method comprises the following steps: constructing a three-dimensional visual model containing equipment and tools by using SolidWorks according to a ratio of 1: 1; constructing a geometric constraint matrix and a working area conflict matrix based on an octree to form a comprehensive priority constraint model; defining a disassembly time sequence and an operator allocation decision variable, and establishing a mathematical programming model for minimizing the total disassembly time; designing a hybrid coding mode, and proposing an improved seat head whale migration algorithm containing a self-adaptive strategy and a local search mechanism; and automatically solving an optimal disassembling sequence and a personnel allocation scheme. Verification shows that the solving quality and stability of the method are remarkably superior to those of a genetic algorithm and a particle swarm algorithm, the maintenance efficiency and safety are greatly improved, the operation and maintenance cost is reduced, and technical support is provided for stable operation of the hydroelectric generating set.

The invention belongs to the technical field of underground water numerical simulation, and provides an underground water pollution migration simulation method and device, electronic equipment and a storage medium, and the method comprises the steps: constructing a three-dimensional octree grid, a control equation and a definite solution condition of a hydrogeological structure of a target region; carrying out discrete solution on the control equation in the three-dimensional octree grid by adopting a finite volume method taking a node as a center; constructing a post-processing approximation function and a local posterior error indicator on octree leaf subunits of the three-dimensional octree grid; determining a unit set contributed by a global error by adopting a Drfler marking strategy, then performing splitting or merging operation on leaf units, and performing grid updating by adopting a high-order interpolation or volume weighted average method; and according to a preset simulation termination condition, repeatedly executing underground water pollution migration simulation and finally performing visual display. According to the method, the simulation accuracy of water pollution migration is improved in a posterior error estimation mode.

The invention discloses a target scattering characteristic efficient solving method of a multilayer fast multi-pole collaborative principal component analysis compression algorithm. The method comprises the following steps: dividing a target model by using a hybrid tree, changing an impedance matrix into a laminated matrix by binary tree grouping, and dividing a target into a near field and a far field by octree grouping; a multi-layer fast multi-pole algorithm acceleration principal component analysis compression algorithm is adopted to compress the low-rank impedance matrix; performing nearest layer-by-layer inversion on the impedance matrix according to an SMW formula; and finally, current is obtained through matrix vector multiplication of a series of inverse matrixes and a right vector, and target scattering characteristics are solved. The method achieves the solving of the electromagnetic scattering characteristics of the complex target, and can improve the calculation efficiency of the analysis of the electromagnetic scattering characteristics of the complex target.

The invention belongs to the technical field of point cloud rendering, aims to solve the problem that rendering effect and rendering efficiency cannot be considered during dynamic rendering of point cloud, and discloses a point cloud rendering method based on an octree structure, and the method comprises the steps: obtaining point cloud data, carrying out the data preprocessing, building a user-defined storage structural body based on an octree storage structure, and carrying out the rendering of the point cloud. The method comprises the following steps: acquiring point cloud data, converting the point cloud data into voxelized point cloud data based on an octree structure, storing the voxelized point cloud data to a self-defined storage structure body, constructing a traversal recursive tree, cutting the voxelized point cloud data, performing detail level construction on the cut voxelized point cloud data, and performing point cloud rendering based on a detail level structure. According to the method, the node division layers can be flexibly adjusted according to the point cloud density, multi-layer division can be carried out on the part needing detail rendering, few-layer division can be carried out on other parts, and on the premise of ensuring the rendering effect, the volume of the point cloud data is reduced, the rendering difficulty is reduced, and the rendering efficiency is improved.

This invention discloses an electromagnetic simulation method based on incomplete octree strongly compatible skeleton decomposition, belonging to the field of electromagnetic simulation technology. The method of this invention discretizes the target surface into a triangular mesh, discretizes the surface integral equations, and generates a system of linear equations characterizing the relationship between the impedance matrix and the current coefficients to be solved. It constructs an incomplete octree structure based on strongly compatible skeleton decomposition, forming a multi-layer skeletonized matrix based on the incomplete octree as the impedance matrix. Solving the linear equations yields the current coefficients to be solved, and then the target surface current and the target electromagnetic properties are solved. The method of this invention has higher computational efficiency when handling electrically small models and complex multi-scale models, significantly improving the computational efficiency of the impedance matrix and the computational speed of matrix-vector multiplication operations during iteration, thus achieving rapid calculation of the target's electromagnetic properties.

The invention relates to an object-level three-dimensional reconstruction method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a sparse point cloud of a target object based on an image set of the target object; dividing a three-dimensional space of the target object through an octree data structure according to the sparse point cloud of the target object, and obtaining signed distance field SDF geometric information in each voxel of an octree according to the sparse point cloud; a plurality of three-dimensional Gaussian distributions are constructed according to the SDF geometric information, iterative optimization is carried out on the plurality of three-dimensional Gaussian distributions, an optimized Gaussian point cloud is obtained, optimization of a loss function is carried out based on characteristic values of a curvature matrix in the optimization process, and the curvature matrix is constructed based on the Gaussian point cloud; and according to the optimized Gaussian point cloud, through the rendered depth map, performing reconstruction to obtain a surface geometric model of the target object. According to the method and the device, high-quality object-level three-dimensional reconstruction can be realized through a reconstruction mode combining an octree and three-dimensional Gaussian splashing.

This invention discloses a method, system, device, medium, and program product for optimizing tile data caching. The method includes: retrieving cache records of the model to be loaded from a browser database based on the unique identifier of the model; generating an octree-structured tile node queue based on the cache records and a preset maximum cache level, where each level of the tile node queue corresponds to the tile data at each level of the model to be loaded; and finally, asynchronously requesting the tile data corresponding to each node from the backend level by level based on the tile node queue. This invention achieves efficient caching and loading of digital twin platform models, significantly improving the user's browsing experience.