28 results about "Tight frame" patented technology

The invention discloses a space-time consistent video depth completion method under a zero sample unified diffusion framework. The method comprises the following steps: constructing a depth completion model comprising a variational auto-encoder, a semantic coding network and a space-time diffusion generation network; preparing training data, and generating a frame-level semantic feature vector and a conditional latent variable fusing an original depth and a relative depth for a video frame; training the space-time diffusion generation network in stages by taking the conditional latent variable sequence as input and the semantic features as conditions; in the inference stage, a video sequence to be complemented is processed through a sliding window fusion mechanism, a de-noising depth latent variable is obtained through a trained network, and finally a complemented depth sequence is output through decoding and scale recovery of a variational auto-encoder. The method has the advantages that a depth sequence with measurement consistency, structural integrity and time stability can be generated when depth completion is performed on a sparse, noisy or structurally damaged long sequence video.

The application provides a multiscale geological model cross-scale nesting and fusion modeling method, belonging to the geological field, including four steps of multiscale data preprocessing, data fusion, cross-scale nesting and fusion and dynamic coupling. This method can integrate multi-source heterogeneous data, realize data fusion through joint probability space, variational assimilation framework, fuzzy logic conflict factor and alternating direction multiplier method, utilize deep learning auxiliary fusion technology such as multi-scale convolutional adversarial network to improve the stability and precision of the model. At the same time, the model parameters are determined through volume average upsampling algorithm and random field conditional simulation, and the consistency of the parameters between the models is realized through dynamic adjustment of ensemble Kalman filter and localized ensemble transform Kalman filter, bidirectional feedback and iterative optimization. Finally, through the double grid strategy and the restrictive interpolation, the multiscale convergence is realized, and the convergence and dynamic balance of the model on the scale of kilometers to microns are ensured.

This invention discloses a method and system for generating static code checkers based on a large language model. The method involves: acquiring rule descriptions and a test suite containing positive and negative examples; generating detection logic corresponding to the rule descriptions and their corresponding checker specifications using the large language model; retrieving the corresponding API context based on the detection logic; generating candidate checker code based on the checker specifications, rule descriptions, test suites, and the retrieved API context; validating the candidate checker code based on the test suites and relevant rule descriptions; and obtaining the final checker code that passes the verification. The method proposed in this invention significantly reduces the technical threshold and development cost of customizing checkers for static analysis frameworks, efficiently generating checker code with high accuracy, low false positive rate, and low false negative rate, and possesses good scalability.

This disclosure generally relates to video coding / decoding, and in particular to enhancing block-adaptive weighted prediction. The method involves receiving a coded video bitstream, which includes the current block of the current frame and a first syntax element indicating the prediction mode of the current block, wherein a plurality of scaling factor lookup tables are stored and include different ranges of scaling factors. In multiple scaling factor lookup tables, the step size or precision of the scaling factor in each lookup table is the same, and A step of determining a prediction mode based on the value of a first syntax element, wherein the prediction mode is used to predict the current block based on the reference block of the reference frame. The steps include determining a scaling factor from one of several scaling factor lookup tables, The process includes the step of reconstructing the current block based on a reference block and a determined scaling factor.

The video temporal sentence localization method based on four constraints and partial supervision comprises the following steps: high-level semantic features are extracted from query text and video by using a deep neural network; a time stamp corresponding to the query event is obtained from the video features by fusing a frame-by-frame algorithm and a candidate frame algorithm, and the video features fused with the query text features are input into an event detector; a four-constraint model is constructed to facilitate learning of a semi-supervised temporal sentence localization task; a partial-full merging framework is used to predict the temporal localization result according to the features, so as to flexibly handle two types of supervision, i.e., partial supervision and full supervision; partial supervision branch optimization and full supervision branch optimization are performed, the partial supervision branch optimization comprises optimization of the four-constraint model and optimization of a localization pseudo-label localization loss constructed according to partial supervision information; and the full supervision branch optimization is performed by using a localization learning framework and relying on supervised learning optimization of the localization pseudo-label.

The invention relates to the field of 3D data compression, in particular to a 3D video sequence data compression, decompression and transmission method and electronic equipment, and the compression method comprises the steps: obtaining RGB-D sequence frame data, and setting a label for each frame of RGB-D sequence frame data; the RGB-D sequence frame data comprises RGB texture sequence frame data and 32-bit depth sequence frame data; selecting RGB-D sequence frame data of a corresponding frame based on the label, and compressing the RGB-D sequence frame data to obtain RGB-D sequence frame compressed data with the label; the compression comprises the following steps: compressing the RGB texture sequence frame data by adopting a standard video compression protocol to obtain RGB texture sequence frame compression data; and compressing the 32-bit depth sequence frame data by adopting a 32-bit half-truncation compression frame to obtain 32-bit depth sequence frame compressed data. Through a 32-bit half-truncation compression technology, a high compression ratio is realized on the premise of ensuring depth data precision, the storage and transmission pressure of massive 3D video data is effectively relieved, and real-time application is supported.

This invention discloses a method and system for order reduction and decoupling of high-dimensional stochastic systems based on stochastic approximation conjugacy, belonging to the field of complex system modeling and analysis technology. This method acquires multi-condition state data of the high-dimensional system, constructs a reduced-order analysis framework including embedding mapping, a low-dimensional decoupled dynamic model, and lifting mapping. Using stochastic approximation conjugacy as a constraint, it minimizes the total loss function to complete joint model training. After solving the system's stochastic response characteristics within a low-dimensional feature manifold, it maps back to the high-dimensional space to complete dynamic behavior analysis. The corresponding system includes modules for data acquisition, model construction, model training, low-dimensional solution, and mapping analysis. This invention solves the curse of dimensionality problem of traditional methods, ensures the reliability and interpretability of the reduced-order model, has strong versatility, and can be widely applied to intelligent operation and maintenance and control optimization of major engineering systems.

Post training compression of 3DGS data is agnostic to training in a traditional signal compression perspective. Gaussian parameters are treated as signals. Pre-processing and transform coding techniques are used to compress the signals effectively. Firstly, lossless / lossy compression is performed on 3DGS geometry (positions, scales, rotations) using a point cloud coding-based (e.g., G-PCC, GeS) framework. Positions are compressed using occupancy tree coding. Scales and rotations are encoded as attributes using transform coding. The widely used block-based graph Fourier transform (GFT) is used to compress the attributes (base colors, spherical harmonic coefficients and opacities). In addition, a graph construction strategy is used for 3DGS data that computes the edge weights based on similarity (or dissimilarity) between the 3D Gaussian distributions using KL-divergence. Alternatively, positions can be encoded using occupancy tree (e.g., G-PCC, GeS) or AI-based PCC methods, and any subset of Gaussian parameters or the transformed coefficients of Gaussian parameters can be mapped into 2D frames and encoded by video coders.

A frame processor may generate a mask based on one or more static regions of a first set of frames of a plurality of previous frame and adjust the mask to at least one of determine alpha data or conceal distorted content associated with the one or more static regions of the first set of frames. The distorted content may be caused by extrapolation of a frame from a second set of frames of the plurality of previous frames. The frame processor may generate a composite frame based on application of at least one of the mask or the alpha data to a previous frame of the plurality of frames, and application of the previous frame based on the at least one of the mask or the alpha data to the frame extrapolated from the second set of frames of the plurality of previous frames.

The invention provides a parameterized swept curved surface design method, and relates to the field of aircraft design. The method comprises the following steps of: processing a two-dimensional graph by adopting a sequence-preserving and feature-preserving discrete sampling method, so that a sampling sequence has consistent point sequence index rules and adjacency relations while keeping geometric details; under a normalized coordinate system, a measurement base is constructed by using the reference graph and the coordinate sequence of the interpolation center, parameterization of other graphs is completed, and an analysis framework with consistent meaning is formed; graphic shape change is achieved through coordinate transformation based on the frame, and smooth deformation between complex graphs is guaranteed with an S-shaped curve with the acceleration at the two ends being 0 as a control rule; and finally, describing shape change, size change and scanning path design through a parameterized curve or a discrete point list, and realizing parameterized generation of a scanning curved surface by combining parameter coordinates of each section graph and different section assembly strategies. By adopting the method, different types of sweeping requirements can be flexibly met.

The application discloses a kind of multi-agent preset time formation control methods based on backstepping method under distance rigidity matrix, comprising: 1) based on the double integrator dynamics model of multi-agent system is established based on rigidity graph theory, define the minimum and infinitesimal rigidity frame corresponding to the expected formation;2) introduce backstepping design framework, define virtual speed error variable;3) introduce time-varying scaling function to construct time scale transformation;4) design distributed preset time controller;5) through numerical simulation and physical platform are verified, verify the effectiveness of distance error in user preset time under different initial conditions converges to the vicinity of zero.The application is fused by backstepping and preset time scaling function, for the first time in only local relative measurement distance rigidity formation Convergence time user self-defined preset is realized, and convergence time upper bound is independent of initial condition and controller parameter, provides reliable, engineering implementation solution for time-critical multi-agent cooperative task.

The invention relates to a coding representation, retrieval and matching method of a lead frame design model, and belongs to the field of computer aided design (CAD). According to the method, on the basis of text readability of a DXF format, a deep learning model DualDXF is used for carrying out overall coding representation on an LF design model, so that the retrieval problem of 2D LF design is solved; in addition, the invention further provides an effective LF design matching method which is used for comparing two similar LF design models and visually marking the differences in the LF design of the DXF format. According to the method, the problem of input dimension disasters when a deep learning model retrieves high-complexity LF design is solved, and retrieval of similar LF design can be completed without manual annotation.

The application discloses a kind of spatiotemporal consistent video depth completion method under zero sample unified diffusion framework, comprising: constructing the depth completion model including variational autoencoder, semantic coding network and spatiotemporal diffusion generation network;Prepare training data, generate frame-level semantic feature vector for video frame and condition latent variable fused original depth and relative depth;With the input of condition latent variable sequence, as a condition, spatiotemporal diffusion generation network is trained in stages;In inference stage, the video sequence to be completed is processed by sliding window fusion mechanism, and the trained network obtains denoised depth latent variable, and finally the completed depth sequence is output by the decoding of variational autoencoder and scale recovery;The advantage is that when the long sequence video of sparse, noise or structural damage exists is completed, depth sequence with metric consistency, structural integrity and time stability can be generated.

The invention discloses a webpage element positioning method and device, electronic equipment and a storage medium, and relates to the technical field of data processing.According to the webpage element positioning method and device, a hierarchical tree structure containing a node unique identifier, an element position and cross-framework association can be established, so that a basis is provided for positioning; positioning accuracy is improved through structured query and server API matching verification, local AI model semantic analysis sorting is triggered when matching fails, and dynamic page adaptability and semantic consistency are enhanced; in addition, recursive processing of inline frames, marking of paths and switching of frame environments can be achieved, and the cross-frame positioning problem is solved in a targeted mode, so that the technical problems that dynamic page adaptability is poor, semantic consistency is insufficient, and cross-frame processing has defects can be solved, and the accuracy of cross-frame positioning is improved. The technical effects that the dynamic adaptability and semantic consistency of element positioning are improved, the cross-frame positioning problem is solved, the positioning accuracy and stability are improved, and the requirement for automatically testing multiple scenes is met are achieved.

A self-calibration method for frame non-orthogonality error and accelerometer error in a dual-axis frame inertial system is proposed. Under static base conditions, the platform is locked at 10 frame angular positions, accelerometer measurements are collected, and the specific force measurement of the inertial system in the platform coordinate system at each locked position is calculated. The attitude matrix of the inertial system from the platform coordinate system to the local horizontal coordinate system at each locked position is also calculated, yielding the acceleration of the inertial system in the local horizontal coordinate system at each locked position, which is used as the error observation. The residuals of the error coefficients are calculated using a total least squares algorithm, and the estimated values ​​of the measured parameters are corrected. Iterative calculations are performed until the iterative convergence criterion is met, obtaining the self-calibration results for each error coefficient. Through the self-calibration and compensation of the error coefficients, the accuracy of attitude measurement of the dual-axis frame inertial system carrier or base affected by the non-orthogonality error of the axis system can be improved.

1. A method (100) for compressing and decompressing a data file, the method (100) comprising: (i) receiving a data file for compression including a plurality of different attributes (120); (ii) identifying a first attribute of the plurality of different attributes (130); (iii) selecting a plurality of compression types and / or configurations (140); (iv) compressing at least a portion of data from the received data file for the identified first attribute using each of the selected plurality of compression types and / or configurations (150); (v) determining which of the selected plurality of compression types and / or configurations is most suitable for compression (160); (vi) generating a compression parameter data structure (170) including an identification of the selected plurality of compression types and / or configurations; (vii) compressing data from the received data file for the first attribute to generate a compressed data file (180); and (viii) storing the compression parameter data structure and the compressed data file (190).

This invention discloses a non-gradient and gradient-coordinated topology optimization method for a single-phase elastic superstructure, comprising: generating a random initial configuration and encoding the random initial configuration and design variables into real numbers, denoted as X; constructing a multi-objective optimization model based on X that considers maximizing bandgap performance and maximizing structural connectivity, to convert the wave vector... k The constraints are limited to characteristic paths on the boundaries of irreducible Brillouin zones. A non-dominated sorting genetic algorithm is used to solve these constraints to obtain the Pareto front. High-performance candidate solutions are selected from the Pareto front as initial inputs. Based on the high-performance candidate solutions, a topology optimization model considering bandgap performance maximization and structural connectivity as constraints is constructed to solve for the current design variables. A three-field floating projection topology optimization framework is introduced to update the design field design variables. Implicit floating projection constraints are then introduced to further iterate and update the design field design variables until convergence.

The disclosure relates to methods for predictive physics compression (PPC) for efficient simulations and calculation leveraging techniques described as fractal compression. Unlike traditional calculus-based methods relying on differential equations and related numerical methods, embodiments of the disclosure are directed towards representation and calculation of physical systems as hierarchical frames within a universal grid, where each frame encapsulates properties such as position and velocity. The simulations and calculations progress in discrete time steps recursively traversing the frame hierarchy. Each tick involves actions such as incorporating the previous frame relation's displacement, detecting collisions, applying stochastic movement and attractive force transforms, and limiting displacement based on defined constraints. Embodiments of the disclosure may be implemented on a single device or distributed across a network, with a coordination server distributing frames to client devices for parallel processing.

In one implementation, a method for reconstructing attributes of a current point cloud frame from a sequence of point cloud frames is provided wherein a predicted feature map from attributes of a reference point cloud frame is obtained, a residual feature map is decoded from a bitstream, a feature map is reconstructed that represents voxel attributes at a current level in an octree structure of the current point cloud frame, from the decoded residual feature map and the predicted feature map, and voxel attributes are reconstructed at the current level in the octree structure based on the reconstructed feature map, wherein a reconstructed feature in the reconstructed feature map for a current voxel is representative of at least a set of voxels that are still to be reconstructed.

In one implementation, a method for reconstructing attributes of a current point cloud frame from a sequence of point cloud frames is provided wherein a predicted feature map from attributes of a reference point cloud frame is obtained, a residual feature map is decoded from a bitstream, a feature map is reconstructed that represents voxel attributes at a current level in an octree structure of the current point cloud frame, from the decoded residual feature map and the predicted feature map, and voxel attributes are reconstructed at the current level in the octree structure based on the reconstructed feature map, wherein a reconstructed feature in the reconstructed feature map for a current voxel is representative of at least a set of voxels that are still to be reconstructed.

Systems and techniques are provided for image processing. For instance, a process can include identifying a keyframe from a received sequence of frames based on differences between features of frames of the received sequence of frames; receiving an annotation for the keyframe; identifying a first set of frames from the received sequence of frames based on differences between features of frames in the received sequence of frames and features of the keyframe; and generating annotated frames by extrapolating the annotation for the keyframe to the first set of frames.

Post training compression of 3DGS data is agnostic to training in a traditional signal compression perspective. Gaussian parameters are treated as signals. Pre-processing and transform coding techniques are used to compress the signals effectively. Firstly, lossless / lossy compression is performed on 3DGS geometry (positions, scales, rotations) using a point cloud coding-based (e.g., G-PCC, GeS) framework. Positions are compressed using occupancy tree coding. Scales and rotations are encoded as attributes using transform coding. The widely used block-based graph Fourier transform (GFT) is used to compress the attributes (base colors, spherical harmonic coefficients and opacities). In addition, a graph construction strategy is used for 3DGS data that computes the edge weights based on similarity (or dissimilarity) between the 3D Gaussian distributions using KL-divergence. Alternatively, positions can be encoded using occupancy tree (e.g., G-PCC, GeS) or AI-based PCC methods, and any subset of Gaussian parameters or the transformed coefficients of Gaussian parameters can be mapped into 2D frames and encoded by video coders.

The invention provides an underwater micro-grid group topology design method and device, and relates to the technical field of power system toughness evaluation and multi-objective optimization, and the method comprises the steps: configuring power generation element parameters and energy storage element parameters of each micro-grid in a micro-grid group system, setting a fault probability and maintenance time, and obtaining load information; determining a basic operation constraint condition and an energy scheduling rule constraint condition; generating a running state table of each element according to the fault probability; constructing a target optimization function based on the basic operation constraint condition, the energy scheduling rule constraint condition and the operation state table; and solving the target optimization function to obtain a target topology design. The total length and toughness evaluation index of a connecting line are considered as optimization targets, and different from a traditional topology design scheme following a fixed topology framework, only investment cost is considered, and the influence of different topologies on the toughness of the system is not considered. According to the method provided by the invention, element faults are considered, and the method is more in line with a real operation scene.

In one implementation, for the purpose of grid compression, we present a first base graph-based framework that enables correct decoupling of grid geometry and grid connectivity. In particular, we propose an end-to-end learning-based mesh compression network framework WrappingNet that can operate on meshes of different sizes and connectivity while producing a potential representation of useful fixed length. Furthermore, when optimal reconstruction performance (at a lower compression rate) is desired instead of fixed length codeword compression summarizing the global topology of the grid, we propose encoder and decoder modules that can be adapted to (respectively) generate and parse potential feature maps that depend on a low resolution base grid.

According to the dynamic test design and efficient optimization method in the design space considering the engineering actual constraint condition, the program, the equipment and the storage medium provided by the invention, accurate learning and explicit expression are carried out on the engineering actual constraint condition of which mathematical expression cannot be given in advance through a neural network model; based on an improved sequence constraint Monte Carlo method, it is ensured that sampling points are efficiently converged to the interior of an irregular design space meeting all constraints, and a maximum minimum distance criterion is introduced to screen initial dense samples; the method combines an adaptive response surface model, constructs a feasible region potential tradeoff function, intelligently recognizes and preferentially supplements sample points in a function minimum value and a high-uncertainty region, finally automatically controls a sampling process according to a convergence threshold value through a progressive dynamic optimization frame, and improves the sampling efficiency on the premise of ensuring the spatial distribution quality of the sample points. The global optimal solution is quickly approached with the minimum calculation cost, and the solving efficiency and reliability of the complex engineering optimization problem are remarkably improved.