499 results about "Multi resolution" patented technology

The invention provides a mutual inductor test data cloud edge cooperative processing method and device, and relates to the technical field of data processing, and the method comprises the steps: carrying out the time domain and frequency domain combined feature extraction of the original measurement data of a mutual inductor test through a multi-mode decoupling preprocessing model, and forming a data feature vector set, further generating a confidence label flow through state recognition and Bayesian inference, evaluating a prediction error, and realizing data classification screening and priority queue construction; the data are uploaded to a cloud end in a semantic compression and multi-resolution representation vector mode, so that the transmission efficiency is improved; carrying out deep modeling and model performance monitoring at the cloud, and if degradation is detected, returning edge original data to update the model; and finally, generating a scheduling weight factor according to the prediction error distribution graph, and dynamically optimizing an edge cloud task allocation proportion. According to the invention, the problem of low resource allocation efficiency caused by lack of a dynamic scheduling mechanism based on prediction errors and confidence driving in existing mutual inductor test data edge cloud cooperative processing can be solved.

The invention discloses a micro-grid dynamic scheduling method based on deep learning, and the method comprises the steps: fusing industrial Internet of Things collection and GIS positioning, and constructing a multivariable original spatio-temporal data set covering multiple nodes; extracting multi-scale features through multi-resolution wavelets and Fourier transform, combining the multi-scale features with a dynamic adjacency matrix, and realizing feature adaptive distribution and nonlinear dynamic modeling by using multi-scale attention gating, graph convolution and a time sequence neural network model; the micro-grid load and state prediction accuracy, the system generalization ability and the abnormal response level can be effectively improved, and powerful support is provided for intelligent scheduling and abnormal analysis.

The invention discloses a ship desulfurization system reliability evaluation method and system based on multi-source information fusion, and the method comprises the steps: collecting multi-source information data of a hybrid desulfurization system, and carrying out the self-adaptive preprocessing; generating a fusion feature vector; constructing a dynamic Bayesian network based on multi-source fusion features, performing real-time reasoning by adopting data-driven transition probability learning and particle filtering, describing transient behaviors of system state evolution and mode switching, and performing dynamic multi-state reliability modeling; a fault mode is automatically extracted, and data-driven systematic risks are identified and quantitatively analyzed; a multi-resolution digital twinborn architecture is constructed, dynamic simulation prediction is carried out, a self-adaptive updating mechanism is adopted to keep the model synchronous with a physical system, and a virtual verification environment for reliability evaluation is provided; according to the method, an intelligent decision optimization system is constructed, self-adaptive generation and dynamic adjustment of a maintenance strategy are realized, closed-loop feedback is carried out, and the accuracy of reliability evaluation of the hybrid desulfurization system is improved.

The invention discloses a bridge structure surface crack multi-scale image segmentation and damage assessment method, and belongs to the technical field of bridge structure health monitoring, and the method comprises the steps: a multi-scale pyramid feature preprocessing step: carrying out the multi-resolution feature extraction of a bridge surface image; in the adaptive attention-guided crack segmentation step, crack region response is enhanced through a channel and space attention mechanism; the crack geometric parameter accurate quantification step is used for calculating the length, width, depth and direction of the crack; in the time sequence comparison crack development trend prediction step, the crack propagation rate is calculated according to the parameter difference value between the current detection data and the historical detection data divided by the time interval, and the development trend is predicted; in the multi-dimensional damage comprehensive evaluation step, damage scores are calculated, damage grades are determined, segmentation parameters are fed back and adjusted, and scientific data support is provided for bridge safety evaluation and maintenance decision making.

The invention relates to the technical field of digital twinning, particularly provides a digital twinning scene adaptive optimization method based on point cloud data, and solves the problems that smoothness and detail presentation cannot be balanced during network fluctuation, and a scene prediction optimization mechanism based on space-time semantic analysis is not established. The method comprises the following steps: data preprocessing and hierarchical construction: carrying out preprocessing of abnormal point elimination, missing value complementation and density adjustment on original point cloud data, dividing key and common regions according to scene requirements, and constructing a multi-scale and multi-resolution hierarchical point cloud data system; the method can deeply analyze the spatio-temporal dynamic characteristics of the point cloud data through the technologies of spatio-temporal dynamic semantic segmentation, dynamic change monitoring, prediction optimization and the like, processes the continuous time sequence point cloud data after adaptive transmission, models a time dependency relationship and extracts local and global characteristics in time and space dimensions respectively, and improves the accuracy of point cloud data processing. Accurate identification of object types, positions and dynamic change information is realized.

The invention relates to the technical field of mine safety and geological environment evaluation, in particular to a mine goaf geological environment dynamic evaluation method based on digital twinning. The method comprises the following steps: constructing a digital twinborn model of a mine goaf, designing a data structure and a virtual-real mapping rule, collecting multi-source heterogeneous data, and performing spatio-temporal data indexing processing to form a spatio-temporal associated data stream; microseismic travel time data are extracted from the space-time associated data stream; performing parallel ray tracing and rapid inversion on the microseismic travel time data to obtain a wave velocity distribution initial value; carrying out wave velocity field self-adaptive grid refinement on the micro-seismic travel time data by utilizing the wave velocity distribution initial value to obtain a multi-resolution wave velocity field; and carrying out wave velocity change rate analysis on the multi-resolution wave velocity field to obtain a wave velocity variability tensor. According to the method, the abstract energy transfer process is concrete into a data field capable of being quantitatively analyzed, so that the geological environment of the goaf is accurately and dynamically evaluated.

A monocular self-supervision depth estimation method fusing multi-resolution features and global context belongs to the technical field of computer vision, and comprises the following steps: firstly, providing an encoder based on a cross-stage feature high-resolution network, and enhancing the extraction capability of multi-scale features by improving a cross-stage connection mechanism of an HRNet network; secondly, a visual Transform module is introduced to improve complex down-sampling operation, and a multi-head self-attention mechanism is utilized to establish global pixel association; then, an improved decoder network is provided, a channel attention module is used for re-weighting coding features, multi-level features of an encoder are utilized more efficiently, and the balance between segmentation precision and calculation cost is achieved; and finally, proposing an improved attitude estimation network based on lightweight ResNet18, predicting 6-DoF relative poses of adjacent frames in combination with a four-layer convolutional decoder, and accurately estimating the depth of each object. According to the invention, the accuracy of depth estimation is improved, and the visual effect of the depth view is improved.

The invention provides a geotechnical engineering slope deformation monitoring method and system, belongs to the field of geotechnical engineering monitoring, and is used for solving the problems of low monitoring precision and poor early warning reliability caused by spatial-temporal dislocation of multi-source data, static geological parameters, poor swivel scene adaptation and no closed-loop optimization in related technologies. According to the method, multi-source deformation data, geological parameters and rotation characteristics are collected, the type and progress of a rotation are identified, multi-resolution hierarchical fusion (dynamic weight adaptive data credibility and environmental interference) and dynamic inversion geological parameters are performed after space-time alignment to construct a prediction model, model parameters and an early warning threshold are dynamically scheduled in combination with the rotation characteristics, and the prediction result is obtained. The precision is improved through closed-loop feedback optimization iteration, the system provides hardware support for the method, and precise monitoring and efficient early warning of slope deformation are achieved.

The invention relates to an artificial precipitation enhancement operation area identification method and system based on multi-source data, and relates to the technical field of meteorological intervention operation, and the method comprises the steps: building a multi-resolution dynamic data grid system, and enabling a coarse-grained grid layer to cover the whole operation area, and to be used for bearing the macro data of a satellite cloud picture and a conventional radar; the fineness grid layer is used for receiving and mapping real-time data provided by the high-resolution radar; receiving real-time data of all cloud blocks, mapping the real-time data to corresponding grid layers, and projecting the data collected at different time points to a unified time reference frame to obtain a cloud system state view; predictive interpolation is carried out by using the latest data of the conventional radar and the macroscopic trend of the satellite cloud picture in combination with the motion vector and confidence weighting so as to obtain cloud system information; and forming a visual cloud system three-dimensional view, identifying and tracking a target cloud block with an artificial precipitation enhancement potential, and generating an operation instruction. The method has the effect that the target cloud block with the operation value can be identified and tracked to generate the accurate operation instruction.

Systems and methods are disclosed for anomaly detection using a “detect and collect” cybersecurity monitoring approach. Initially, a cybersecurity monitoring system obtains and analyzes a baseline subset of telemetry data from computing resources to detect potential anomalies indicative of cybersecurity threats. Responsive to identifying such anomalies, the system selectively determines additional, contextually relevant telemetry data for targeted collection. This selective data collection significantly reduces telemetry volumes, enhancing efficiency and scalability. An intelligent data fabric and dynamic security knowledge graph are employed to enrich telemetry data in real-time, enabling comprehensive anomaly characterization, risk scoring, and automated security responses. The disclosed techniques support multimodal and multiresolution anomaly detection, adaptive learning, and rapid threat response within diverse distributed computing environments.

The invention discloses an ultra-low illumination-oriented SPAD active imaging data compression method, which comprises the following steps of: performing wavelet decomposition on histogram data of a single pixel in a time-frequency domain based on wavelet transform to obtain low-frequency data of each pixel after wavelet decomposition; by taking each pixel as a center, performing non-maximum suppression and data enhancement on the low-frequency data after the wavelet decomposition of the current pixel by using adjacent pixels to obtain processed compressed data; customizing different Gaussian kernel parameters for each pixel according to the possibility that each pixel is located at the boundary, and performing Gaussian filtering on the processed compressed data of each pixel to obtain filtered data; and performing depth estimation on the filtered data to obtain a final depth image. According to the method, the depth reconstruction performance of the laser pulse can be improved by utilizing the multi-resolution characteristic of wavelet transform, the space-time correlation of signal photons and the smoothness of Gaussian filtering.

The present disclosure relates to the technical field of multimodal learning, and particularly relates to a multimodal interleaved image-text generative model based on a dynamic feature synchronizer. An image encoder extracts multi-resolution multi-scale feature maps from input images of interleaved image-text data; and a dynamic feature synchronizer in a multimodal large language model acquires fine-grained information, so as to determine output feature data corresponding to the interleaved image-text data and then generate a target image and / or target text associated with the interleaved image-text data.

The invention relates to the technical field of image processing, and discloses a pathological image classification method and system based on graph neural feature fusion, a terminal and a storage medium, and the method comprises the steps: obtaining multi-scale digital image data, carrying out the extraction of the multi-scale digital image data, obtaining a plurality of image features, fusing the plurality of image features through a pyramid-shaped multi-scale feature fusion model to obtain a multi-resolution feature; obtaining a slide level label, constructing an initial graph neural network model based on a dynamic graph construction mechanism, a self-attention mechanism, a channel reduction mechanism and multi-resolution features, and training the graph neural network model according to the slide level label to obtain a target graph neural network model; and obtaining to-be-detected pathological image features, inputting the to-be-detected pathological image features into the target image neural network model for classification, and outputting a classification result. According to the method, features of the to-be-detected pathological image are classified according to the target image neural network model, and efficient and accurate classification is realized.

The invention discloses a blind signal source separation method based on a multi-resolution attention separation network, and belongs to the technical field of signal processing. The method comprises the following steps of signal preprocessing, multi-scale feature extraction, attention module training, multi-resolution feature fusion, signal source recognition model training, model performance real-time monitoring and multi-scene adaptation optimization, and microcosmic and macroscopic features of signals are effectively captured through a multi-scale channel feature coding network. The adaptability of the model to non-stationary signals and complex structure signals is enhanced, the separation precision is improved, the attention mechanism can dynamically adjust feature weights, highlight target signal features, suppress background noise and remarkably improve the signal separation quality, meanwhile, calculation resource allocation is optimized, the model reasoning time is shortened, and the method is suitable for large-scale popularization and application. The MRAS-Net adopts a classification-oriented consistency synthesis strategy to ensure that the synthesized virtual signal features and the real signal features are highly consistent in classification tasks, and the generalization ability and the result interpretation of the model are enhanced.

The invention relates to the technical field of image recognition, and particularly provides a multi-view point cloud registration method, which comprises the following steps of: performing coarse registration on a source point cloud and a target point cloud based on multi-dimensional features by using an RANSAC (Random Sample Consensus) algorithm in a coarse registration stage to obtain a coarse registration transformation matrix; in the fine registration stage, the coarse registration transformation matrix is used as an initial value, point cloud registration is carried out in at least two resolution spaces, segmented iterative optimization is carried out by using an error loss function set in each resolution space, rapid convergence is carried out in a low-resolution space through an iterative nearest point algorithm, and the point cloud registration is realized. And local geometric alignment optimization is carried out in other resolution spaces through a generalized iterative nearest point algorithm, and fine registration of the source point cloud and the target point cloud is completed after multi-resolution space progressive optimization registration. According to the method, the robustness of feature matching of the low-overlap region is remarkably improved, the registration speed and precision are balanced, and the limitation of a traditional point cloud registration method under the low-overlap and non-ideal point cloud condition is solved.

The invention relates to the field of numerical reservoir simulation, and provides a proxy modeling method for embedding a coarse grid simulator, so as to solve the problems of poor space-time extrapolation performance and unstable long-term prediction. According to the method, a coarse mesh numerical simulator is used as a physical prior module to be embedded into a multi-resolution fusion neural network structure (MNN), and a complex nonlinear relation in the physical prior module is captured by means of a Fourier neural operator (FNO), so that efficient, long-time-sequence and stable prediction of multiple physical fields such as pressure, oil saturation and gas saturation is realized. According to the method, a coarse mesh numerical solution is used as an intermediate drive, multi-scale physical information is fused through a modular MNN network, and the physical consistency and the space-time generalization ability of the proxy model are remarkably improved. In the model, the FNO is utilized to extract global frequency domain characteristics of a coarse grid simulation result field, and through verification of multiple cases, the model shows good space-time extrapolation performance under various coarsening scales and well control conditions. The method has the robustness of numerical simulation and the high efficiency of deep learning.

The invention discloses a dynamic icon transition method and system based on intelligent interpolation, and belongs to the technical field of digital media, and the method comprises the following steps: decomposing a source icon and a target icon into basic graphic primitives, and retaining a graphic layer relationship and a nested structure; analyzing the parameterized data, matching corresponding primitives according to specific priorities, and calculating parameter differences; automatically generating an interpolation path and a complement frame based on the difference, and realizing the automatic generation of the transition animation; and through a built-in slow motion function library and a dynamic parameter interface, an animation curve and a rhythm are adjusted during operation, and multi-resolution adaptation and SDK packaging calling are supported. Through parametric modeling and intelligent interpolation, automation, style unification and cross-platform adaptation of icon transition are achieved, and development efficiency and interaction experience are remarkably improved.

The invention relates to the field of image processing, and discloses a figure image optimization method based on green screen image matting, which is used for carrying out optimization processing on a figure image. The figure image optimization method based on green screen image matting comprises the steps of performing fractional order differential transformation and other processing on an input green screen figure image, constructing a continuous chromaticity representation space, generating a chromaticity gradient field and multi-resolution chromaticity representation, establishing a geometric topology constraint model according to chromaticity information, generating an initial transparency field, and performing collaborative optimization. Optimizing a boundary curve, generating an accurate boundary contour, establishing a color mixing model, realizing natural transition between a foreground and a background, generating an optimized image, performing subsequent processing such as material optical attribute analysis and the like, and finally outputting an image completely fused with a background environment. According to the method, the foreground can be accurately separated, the edge can be optimized, natural transition and material simulation can be realized, and finally a high-quality figure image which is seamlessly fused with the background and has a physical reality sense is generated.

The invention discloses an automatic verification method and system for a topological relation of ocean charting data, and relates to the technical field of charting verification, and the method comprises the steps: obtaining a chart vector element, splitting a broken line into a line segment unit according to a node, splitting a surface domain into a ring domain unit according to an outer ring and an inner hole, and extracting a control point; constructing fractal spectrums for the line segment units based on a multi-resolution box dimension method, comparing the fractal spectrums with normal spectrums, and marking complexity abnormal sections; constructing a polymorphic behavior matrix according to predefined geometric expectation and semantic rules, analyzing conflicts, and identifying topology anomalies; a tide level field is obtained, a coupling constraint field is constructed in combination with equal-depth closed loop hierarchical nesting, and tide depth coupling abnormity of a channel boundary and a closed loop is verified; a lighthouse, a navigation mark and a tide level station control point are screened, and connectivity abnormity is verified according to a semantic rule; and summarizing to generate a verification report. Fractal analysis, a semantic matrix, isodepth coupling and a communication rule are combined, break point errors are accurately distinguished, topological anomaly is detected in a fusion mode, and the time-space consistency of a sea chart and the connectivity of control points are guaranteed.

The invention relates to the technical field of carving, in particular to a traditional wood carving innovation method and system based on 3D scanning, and the method comprises the steps: carrying out the high-precision scanning of a core region through a 3D scanner, carrying out the lightweight scanning of a secondary region, obtaining multi-view point cloud data, and carrying out the preprocessing; inputting the preprocessed multi-view point cloud data into the point cloud network model, outputting the filled point cloud, and manually carrying out refinement on the filled point cloud to obtain a repaired point cloud; geometric features are extracted, pattern semantics are marked, and a dynamic element library is constructed and stored; the parameterized design and modeling processing platform is in butt joint with the dynamic element library, generates and screens a design scheme, manually corrects the design scheme, verifies the corrected design scheme, and performs finite element analysis on the verified design scheme to obtain a final scheme; and matching the corrected final scheme process parameters through an SWRL rule. According to the scheme, the digital precision and efficiency of the woodcarving are improved through multi-resolution scanning.

The invention relates to the technical field of GIS partial discharge high-precision three-dimensional positioning, and discloses a multi-stage iteration GIS partial discharge high-precision three-dimensional positioning method, and the technical scheme is characterized in that S1, an electromagnetic simulation model is constructed based on a GIS equipment structure, and the installation position of an ultrahigh frequency sensor is optimized through electromagnetic simulation; s2, performing wide-band adaptive sub-band reconstruction and multi-resolution feature enhancement processing on the acquired signals; s3, calculating three-dimensional focusing energy distribution by adopting a multi-band time inversion method, and extracting candidate discharge positions; s4, screening candidate positions; s5, performing multi-stage hybrid optimization on the screening result to obtain refined three-dimensional positioning coordinates; and S6, outputting a three-dimensional positioning result, and performing performance evaluation based on a confidence index. According to the method, a time delay consistency screening mechanism is introduced, false candidate points which do not conform to an actual signal propagation rule are effectively eliminated, and the accuracy and reliability of a positioning result are remarkably improved.

The invention relates to an external parameter online calibration method for a laser radar and a camera in a cross-country environment, and the method comprises the steps: constructing an external parameter calibration network MLLANet based on a Mama-like linear attention model, taking a camera RGB image and a laser radar initial depth map as input, extracting multi-scale features through multistage convolution and a Mama-like attention module in sequence, and carrying out the multi-scale feature extraction; and feature matching is realized through multi-resolution feature fusion and cost volume construction, and translation and rotation parameters are respectively predicted by a global regression layer. According to the network, regression loss and depth map loss based on Huber are introduced into a loss function part, and a mixed loss system is constructed, so that training robustness is enhanced, and the influence of point cloud outliers is inhibited. And gradually reducing the external parameter search range through multi-stage iterative optimization, and finally realizing high-precision estimation of the six-degree-of-freedom external parameters. The method does not need a manual calibration board, can still keep high precision and real-time performance in a cross-country unstructured environment, and can be widely applied to environment perception and autonomous navigation tasks of an unmanned system.

The invention relates to the technical field of intelligent operation and maintenance supervision, and discloses an industry intelligent operation and maintenance supervision method and system based on a large model. The method comprises the steps of collecting multi-source time sequence data of an industry operation and maintenance system; performing time-frequency conversion on the data to obtain time-frequency feature representation, and configuring a decomposition basis function and hierarchical parameters of an adaptive decomposition model according to the time-frequency feature representation; the model is used for carrying out multi-scale analysis on data to obtain a multi-resolution characteristic component, and permutation entropy of the multi-resolution characteristic component is calculated to serve as complexity measurement. And based on the feature component and complexity, selecting a core feature set through importance evaluation, and generating a customized monitoring strategy in combination with a system operation baseline portrait, a real-time working mode and large model reasoning. Constructing an operation and maintenance event feature sequence according to the core features and strategies, and performing variational mode decomposition on the operation and maintenance event feature sequence to extract steady-state and transient components; and a machine learning classifier is adopted to carry out mode recognition on the components, event categories are output, and intelligent operation and maintenance decision and accurate supervision are realized.

The invention provides a mine land occupation instance segmentation method, and relates to the technical field of image processing, and the method comprises the steps: inputting obtained mine land occupation remote sensing image raster data into a trained mine land occupation instance segmentation model, and outputting a corresponding instance mask, the mine land occupation instance segmentation model comprises a boundary enhancement module and a boundary optimization module; the boundary enhancement module is used for processing the feature map of the raster data of the mine land occupation remote sensing image to obtain an initial mask of the remote sensing image; and the boundary optimization module is used for extracting boundary blocks along the boundary of the initial mask according to a preset sliding window, optimizing the boundary blocks by fusing different scale features through multi-resolution branches to obtain optimized boundary blocks, and splicing the optimized boundary blocks to generate an instance mask. According to the invention, the segmentation precision of the mine land occupation instance can be effectively improved.

The invention discloses a tunnel face geological information acquisition and image processing method based on machine vision, which belongs to the technical field of image processing, and comprises the following steps: resolving the pose of a terminal in real time through a visual inertial odometer, generating augmented reality guide information, and guiding the terminal to move to a standard acquisition point; at each acquisition point, performing multi-stage verification of scene semantic compliance, motion blur and defocus and illumination uniformity on the image flow to ensure the acquisition quality; for tunnel high-dynamic illumination, adopting an adaptive brightness segmentation and multi-resolution fusion technology based on an improved Otsu algorithm to perform high-dynamic range reconstruction on a single-frame image so as to recover details; and finally, performing clustering optimization based on the feature matching similarity, and screening out an optimal image subset for three-dimensional reconstruction. According to the method, the problems of subjective and random acquisition process, many image quality defects, detail loss under extreme illumination and large image data redundancy are solved.

The invention discloses a marine geological environment multi-dimensional data reconstruction and dynamic visualization mapping method and system, and belongs to the technical field of marine information technology and data visualization. In order to solve the problems that in the prior art, standard data asset structure is isolated, heterogeneous data deep fusion is difficult, and mass data visualization performance is bottleneck, the method mainly adopts the following technical scheme that standardized multi-source data is received, a data volume mapping rule is established, discrete observation data is reconstructed and fused into a unified and continuous three-dimensional data volume, and the three-dimensional data volume is obtained; and executing a three-dimensional space pattern recognition algorithm on the three-dimensional data volume to recognize a feature entity, and providing on-demand query and multi-resolution access services through a visual mapping interface. According to the method, efficient automatic modeling and high-performance interactive analysis of mass and multi-dimensional marine geological environment data can be realized.

The invention discloses a surface temperature medium and long term forecasting method based on a multi-scale TransFuse pyramid network. The surface temperature medium and long term forecasting method comprises the steps of S1, acquiring original LST time sequence data and performing preprocessing; s2, constructing a three-dimensional time delay embedded feature tensor for the data preprocessed in the S1 by adopting a stepped cross-node tensor feature reconstruction method; s3, on the basis of the three-dimensional time delay embedded feature tensor constructed in the S2, meteorological features of different time scales are extracted in parallel through a dynamic multi-resolution convolution kernel group; s4, performing five-stage cascade operation on the meteorological features of different time scales extracted in the S3 to realize deep fusion of cross-scale features, and performing high-level semantic information integration through a global feature pyramid; and S5, finally outputting a multi-step prediction result through a regression prediction framework based on the fusion features obtained in the S4. According to the invention, an extensible technical normal form is effectively provided for high-precision meteorological prediction in a limited computing power scene, and important application potential is shown in actual business deployment.

The invention relates to the technical field of wind power generation control, and discloses a yaw calibration method and system based on a fan sensor, and the method comprises the steps: carrying out the frequency domain and multi-resolution decomposition of a real-time wind direction signal, and obtaining a short-term disturbance level; if yes, recursive state estimation is executed to obtain a smooth wind direction trend; calculating a long-term drift value and carrying out probability state simulation and power loss model mapping to obtain nonlinear influence estimation; if high turbulence is judged, a dynamic compensation threshold value is calculated to generate an adaptive yaw instruction; the actuator is driven, and the alignment precision grade is determined according to the corrected feedback position; and iteratively updating the reference turbulence intensity index to match and optimize the compensation control parameter. According to the method, accurate identification of short-term disturbance and long-term change under complex turbulent flow can be realized, yaw maloperation is effectively reduced, and the alignment precision and the power generation efficiency are improved.

The invention relates to the technical field of three-dimensional modeling, and provides a lightweight hierarchical digital twin modeling and rendering method for a large-scale scene. The method comprises the following steps: analyzing the surface geometry of an original high-precision three-dimensional model, calculating and extracting curvature characteristics of the high-precision three-dimensional model corresponding to each local area, and constructing curvature response distribution through the curvature characteristics; screening and judging each model region corresponding to the original high-precision three-dimensional model based on the obtained curvature response distribution and the dynamic curvature threshold, and obtaining a second key detail region; generating an independent multi-resolution detail enhancement data block for the second key detail area, generating a plurality of data versions with gradually decreased detail degrees for the same second key detail area, and forming a multi-resolution detail library capable of being directly indexed; in the real-time rendering stage, seamless fusion rendering is completed according to the detail data blocks and the basic main body model, and unification of overall scene light weight and local detail high fidelity is achieved.

This invention relates to the field of image recognition technology, specifically providing a multi-view point cloud registration method. In the coarse registration stage, the RANSAC algorithm is used to perform coarse registration of the source and target point clouds based on multi-dimensional features, obtaining a coarse registration transformation matrix. In the fine registration stage, the coarse registration transformation matrix is ​​used as the initial value, and point cloud registration is performed in at least two resolution spaces. Segmented iterative optimization is performed using an error loss function set for each resolution space. In the low-resolution space, an iterative nearest-point algorithm is used for rapid convergence, while in the remaining resolution spaces, a generalized iterative nearest-point algorithm is used for local geometric alignment optimization. After progressive optimization registration in multiple resolution spaces, the fine registration of the source and target point clouds is completed. This invention significantly improves the robustness of feature matching in low-overlap regions, balances registration speed and accuracy, and overcomes the limitations of traditional point cloud registration methods under low-overlap and non-ideal point cloud conditions.