1407 results about "Reconstruction algorithm" patented technology

The invention provides a news scene three-dimensional reconstruction and visualization method based on multi-source remote sensing data, and relates to the technical field of three-dimensional reconstruction, and the method comprises the steps: extracting multi-modal data feature points through employing a spatial position weighted iterative nearest point algorithm and a tensor projection algorithm; after bidirectional attention deep neural network processing and local geometric consistency constraint screening, registration multi-source remote sensing data is generated, data enhancement is carried out through a variational auto-encoder network and a generative adversarial network, the enhanced data is used for depth information generation and texture feature migration, an initial three-dimensional grid model is generated based on a Poisson reconstruction algorithm, and the initial three-dimensional grid model is constructed; and carrying out topological optimization by combining multi-view projection consistency constraint and a grid optimization algorithm to obtain an optimized three-dimensional scene model, setting a space division function, carrying out space division, constructing a grade model and a depth region, generating a scene semantic segmentation map, and updating a visual scene.

The invention discloses a stainless steel surface defect detection method based on machine vision, and relates to the field of material defect detection.The stainless steel surface defect detection method comprises the steps that stainless steel surface images are collected, the collected multispectral surface images are subjected to image fusion, and a multispectral composite image is generated; performing detail enhancement on the low-resolution image through a super-resolution reconstruction algorithm to obtain a high-resolution image set; positioning a defect area position from the high-resolution image set through a defect detection algorithm, and obtaining a defect position data set; extracting a historical image defect feature set and a real-time image defect feature set from the defect position data set, and constructing a defect classification model according to the historical image defect feature set; inputting the real-time image defect feature set into a defect classification model, and performing defect classification and evaluation to obtain a defect classification data set; and generating and distributing a defect detection report. By combining the multispectral imaging algorithm, the super-resolution reconstruction algorithm and the defect classification model, the automation, precision and efficiency of stainless steel surface defect detection are improved.

The invention provides a bridge structure crack position identification method based on deep learning and computer vision, and the method comprises the steps: obtaining a multi-view visible light image and a depth image, fusing the visible light image and the depth image according to registration parameters, and generating a fusion image containing the texture and depth information of a bridge; for the fused image, extracting a crack region by adopting an adaptive threshold segmentation algorithm, and dynamically adjusting the threshold to obtain a crack binary image; according to the crack binary image, calculating three-dimensional coordinates of crack pixel points through a three-dimensional reconstruction algorithm, and performing reconstruction to obtain three-dimensional point cloud data containing crack space position and form information; on the basis of the three-dimensional point cloud data, three-dimensional local feature descriptors are adopted to describe geometric attributes of the surface of the crack, crack fragment parameters are calculated, and a three-dimensional crack model is constructed; based on a deep learning model, a transfer learning strategy is adopted, a self-adaptive transferable bridge crack three-dimensional detection method is formed, and model parameters are updated so that the model parameters can adapt to the characteristics of a target bridge.

The invention provides a fine three-dimensional modeling method and system based on air-ground multi-source data fusion, and the method comprises the steps: collecting data from three data sources: unmanned plane oblique photography, scanning point cloud data and panoramic video data, and carrying out the preprocessing of the data; according to the method, the advantages of different data sources are comprehensively utilized, the refined and full-coverage three-dimensional reconstruction of the target environment is realized, the multi-source data fusion is realized by utilizing the improved ICP algorithm to carry out precise registration, and finally, the modeling is carried out by utilizing the improved Poisson surface reconstruction algorithm. The problems of detail missing and incomplete coverage caused by a single data source in a complex building modeling process are solved; according to the invention, the multi-source data fusion technology can comprehensively capture the geometric morphology and detail features of the building in a complex scene, is suitable for complex scenes such as villages in cities and old buildings, and achieves all-around and detailed three-dimensional modeling.

The invention provides an esophageal squamous carcinoma detection method and system based on combination of multi-modal information fusion and artificial intelligence, and relates to the technical field of detection. And inputting the fusion feature map corresponding to the multi-modal image information into a pre-trained esophageal squamous carcinoma detection model to perform focus area detection and segmentation on the fusion feature map, and based on a detection result, performing benign and malignant classification and staging prediction on a detected focus by using an integrated learning method in combination with a classification algorithm to obtain the esophageal squamous carcinoma. Outputting a classification result and a visual heat map; converting the extracted focus area information into three-dimensional point cloud data by using an improved point cloud reconstruction algorithm; performing space division and noise reduction processing on the three-dimensional point cloud data by adopting a self-adaptive octree structure; and generating a smooth lesion three-dimensional model by using an improved Poisson surface reconstruction algorithm in combination with a curved surface subdivision technology.

The invention discloses an integrated power distribution cabinet energy efficiency dynamic optimization method based on multi-modal data fusion, and relates to the technical field of intelligent power grids. The problems of failure of an energy efficiency optimization model and poor long-term operation stability caused by data time sequence misalignment and error accumulation of a multi-source sensor in the prior art are solved. According to the scheme, the time offset is dynamically corrected through the adaptive time sequence deviation prediction model; compensating missing data by adopting a non-uniform time step reconstruction algorithm and Kalman filtering; detecting an error drift trend through an exponentially weighted moving average model, updating a feature weight, and inhibiting long-term error accumulation; constructing a self-adaptive time sequence attention fusion network model, and fusing physical constraints and a data driving mechanism to generate an optimization decision; bayesian optimization is utilized to quantify parameter uncertainty, closed-loop feedback execution data is carried out, and model parameters are dynamically updated; according to the invention, the precision, long-term stability and equipment safety of energy efficiency optimization of the power distribution cabinet are remarkably improved, and efficient and reliable operation under multi-physics field coupling constraint is ensured.

The invention provides a high-temperature chemical pipeline defect detection system and method based on magnetostrictive ultrasonic guided waves, and relates to the technical field of high-temperature chemical pipeline defect detection.The method comprises the steps that magnetostrictive excitation signals are applied, the propagation process of the guided waves in a pipeline is calculated through numerical simulation, and the amplitude and phase information of guided wave signals is obtained; performing time-frequency domain analysis on the guided wave signal, extracting group velocities and phase velocities of guided waves in different modes, determining frequency dispersion characteristics of the guided waves, and evaluating the influence of a high-temperature environment on guided wave propagation; processing the received guided wave signal by adopting a modal decomposition and reconstruction algorithm to obtain a corrected guided wave signal; and carrying out feature extraction and parameter estimation on the corrected guided wave signal to obtain the position, size and type information of the pipeline defect. According to the invention, the problem of multilayer heterogeneous pipeline guided wave detection in a high-temperature environment is solved, the accuracy and reliability of defect detection are improved, and an effective method is provided for pipeline health monitoring and safety assessment.

The invention relates to the technical field of hydraulic engineering safety monitoring, and particularly discloses a hydraulic engineering potential safety hazard assessment and prediction system and method based on image recognition. A multi-scale convolutional neural network is combined with a three-dimensional point cloud registration technology to extract surface visual feature parameters, and adaptive time-frequency analysis and a wavelet packet reconstruction algorithm are used to extract physical feature parameters of internal concealment defects; constructing a dual machine learning framework, eliminating environmental interference through a deep residual network, analyzing a causal relationship between features based on a gating cycle unit, and screening a key feature parameter set; a Gaussian process regression model of an adaptive kernel function is used for dynamic risk prediction, risk abrupt change points are identified in combination with multi-scale wavelet transform, and finally a safety state score and a grading early warning signal are generated through a fuzzy comprehensive evaluation algorithm.

The invention discloses a real-time three-dimensional modeling method and system based on 5G flight control and a medium, and belongs to the field of three-dimensional modeling, and the method comprises the steps: obtaining a modeling demand and task environment parameters of a user, and planning a route; controlling the unmanned aerial vehicle to fly according to the planned route; judging whether the position data and the attitude data of the unmanned aerial vehicle at each waypoint are within a preset threshold range, and if so, controlling the unmanned aerial vehicle to collect image data of the target area; the collected image data is preprocessed; extracting feature point data of the target area by utilizing machine learning according to the preprocessed image data; converting the feature point data of the target area into sparse point clouds by using a triangulation algorithm; converting the sparse point clouds into dense point clouds through an MVS algorithm; and according to the pre-processed dense point cloud, a Poisson surface reconstruction algorithm is adopted to establish a three-dimensional grid model of the target area. Aiming at the low precision of unmanned aerial vehicle three-dimensional modeling in the prior art, the method improves the precision of unmanned aerial vehicle three-dimensional modeling.

Provided in the present invention are an interaction and generation method for obtaining a three-dimensional model by means of photographing, a method for obtaining a picture by means of a three-dimensional model, and a part machining and manufacturing method. The interaction and generation method comprises: a user using a terminal to capture scene information, wherein the scene information can be an outdoor or indoor scene, the terminal can be a smart phone, an AR / VR device or other smart terminals having a photographic function, and the captured scene information is RGB and / or RGBD (including depth) information; and sending an RGB image and / or RGBD image I to a monocular three-dimensional reconstruction algorithm, so as to obtain a corresponding three-dimensional model, which can be displayed on an interaction interface and superimposed with a real scene, or can be displayed on a single page.

The invention relates to the technical field of rock mechanics, and discloses a rock three-dimensional reconstruction method and system based on multi-source information fusion, and the method comprises the steps: obtaining and preprocessing data, carrying out the spatial feature learning of a fusion feature vector through a 3D-CNN network, and constructing a three-dimensional voxel model of rock microscopic damage; converting the fused image data into a point cloud model of the underground cavern surrounding rock structure by adopting a three-dimensional reconstruction algorithm based on point cloud, and constructing a digital twin framework of the underground cavern surrounding rock structure based on an implicit surface reconstruction algorithm; feature parameters output by the three-dimensional voxel model and the digital twinning framework are used as input, and the optimal supporting opportunity and supporting parameters are output through an LSTM-CNN fusion model; in the underground engineering construction process, surrounding rock deformation data are collected in real time, and a supporting scheme is adjusted in real time through a depth deterministic strategy gradient algorithm; according to the method, the scientificity and timeliness of support design under complex geological conditions can be improved.

The invention discloses an unmanned aerial vehicle-mechanical arm system cooperative control method for precise spraying. According to the method, through a depth camera and a point cloud reconstruction algorithm, three-dimensional modeling of a target surface and semantic recognition of a spraying area are achieved, and a spraying path and spraying posture data are generated. Based on spraying task requirements, a spraying film thickness experience estimation model is established, and path point-level spraying parameters are obtained. Load mass change, mechanical arm mass center change and spraying reaction force of each path point are calculated, and a coupling dynamic model is constructed in combination with the system state. And dynamic compensation control input is generated by using an adaptive sliding mode control algorithm. After spraying is completed, the actual spraying effect is collected through image and point cloud detection, color, film thickness and texture features are extracted and compared with task requirements, error feedback is generated, and control parameters are adjusted online. According to the method, the problems of dynamic change and error compensation in the spraying process are effectively solved, and the method is suitable for a high-precision spraying task in a complex environment.

The invention discloses an LED large screen automatic repair and fault-tolerant display system and method, and relates to the technical field of LED display. The method comprises the steps that a sensor network and a high-definition camera collect data in real time; when an abnormal area is found, an intelligent diagnosis algorithm carries out comprehensive judgment according to sensor data and an image processing result, and the position and the type of a fault lamp bead are determined; starting an automatic repair process; redundant pixels are started to carry out hardware restoration; the dynamic reconstruction algorithm automatically adjusts the arrangement and brightness of redundant pixels, so that the redundant pixels replace fault lamp beads to participate in display; the system automatically adjusts the resolution and the display mode of the large screen according to the number and the distribution of the fault lamp beads. The problem that the display effect of an existing LED large screen is reduced when part of LED lamp beads are damaged is solved, it is ensured that the large screen can still maintain the good display effect under the fault condition through an innovative automatic repair and fault-tolerant mechanism, and the reliability of the system and the user experience are improved.

A machine learning method of estimating State of Charge (SOC) and State of Health (SOH) of a battery pack, the method including collecting time-series data of a battery pack; processing the collected data utilizing a reconstruction algorithm to reconstruct a first phase state space reconstruction; training a first neural network model using the first phase state space reconstruction for predicting the SOH; feeding the time-series data to the first neural network to predict an estimated SOH value; processing the time-series data utilizing the reconstruction algorithm to reconstruct a second phase state space reconstruction; training a second neural network model using the second phase state space reconstruction, taking into account the estimated SOH value, for predicting the SOC, and feeding the time-series data and the estimated SOH value to the second neural network to obtain an estimated SOC value. A system configured to perform the above method is also disclosed.

The embodiment of the invention provides a scene surface reconstruction method and device, equipment and a medium, and relates to the technical field of computer graphics. The method comprises the following steps of: firstly, introducing an initialized three-dimensional Gaussian model, and determining attribute information and position information of two-dimensional Gaussian corresponding to three-dimensional anchor Gaussian by combining a multi-view image sequence of a target scene; secondly, utilizing the attribute information and the position information to generate a rendered image through a Gaussian splashing method; and then, according to the rendered image and an image with the same view angle as the rendered image in the multi-view image sequence, updating the initialized three-dimensional Gaussian model by minimizing a rendering loss function. And finally, depth information is determined according to the updated three-dimensional Gaussian model and the multi-view image sequence, and a surface model of the target scene is constructed through a three-dimensional reconstruction algorithm according to the depth information and the rendered image, so that the structure and details of the target scene can be reflected more accurately, the floating object phenomenon is avoided, and the accuracy of the target scene is improved. And the quality and the accuracy of scene reconstruction are obviously improved.

The invention discloses a load balancing control method based on data traffic, and relates to the technical field of data transmission. Comprising the following steps: constructing a flow monitoring module based on data flow, constructing a self-adaptive flow classification model, dynamically allocating weights to load nodes with balanced loads, dynamically adjusting a transmission path of the flow, carrying out real-time load balancing scheduling, and processing abnormal flow. According to the load balancing control method based on the data traffic, the self-adaptive traffic classification model and the multi-path traffic reconstruction algorithm are introduced, so that the defects in the prior art are fundamentally overcome. The real-time performance, the stability and the resource utilization rate of the system are remarkably improved through deep classification of the traffic characteristics and a multi-path dynamic segmentation strategy. According to the method, resource allocation can be optimized in a complex traffic scene, the load balancing efficiency is improved, meanwhile, the service quality of delay-sensitive and bandwidth-intensive services is guaranteed, and the availability and reliability of the whole system are enhanced.

The invention provides a distribution network power transmission line insulator damage detection method based on a YOLO algorithm, and the method comprises the steps: collecting a plurality of insulator defect images, and carrying out the data enhancement of the images; performing image detail enhancement on an insulator defect area in the image by using a super-resolution reconstruction algorithm; constructing a composite loss function to guide an image detail enhancement process; constructing an insulator defect detection model based on a YOLOv8 framework; constructing a multi-task joint loss function as an insulator defect detection model training target; and a real-time feedback mechanism is introduced, a weighted combination loss function is constructed, gradient updating optimization is executed, and the detection capability of the insulator defect detection model is improved. The method has high detection precision and robustness, can effectively improve the efficiency and accuracy of fault detection, significantly reduces the burden and cost of manual inspection, improves the safety and reliability of a power system, and provides powerful support for the operation and maintenance of power equipment.

The invention relates to the technical field of vehicle driving, in particular to a construction method of an intelligent driving vehicle digital twin system. Comprising the following steps: collecting multi-dimensional data of a vehicle in real time, taking the multi-dimensional data as original data, and preprocessing the original data to obtain preprocessed data; performing enhancement processing by using a multi-scale dynamic feature enhancement and reconstruction algorithm to obtain data after enhancement processing; constructing and training a digital twinborn model in combination with the multi-dimensional historical data of the vehicle to obtain a trained digital twinborn model; in combination with real-time environment perception data and behavior habit data of a driver, a driving state, a driving decision and path planning of a vehicle are intelligently optimized by using a multi-level adaptive variational optimization algorithm to obtain an optimal path planning. The technical problems that in the construction process of the intelligent driving vehicle digital twin system, processing of real-time vehicle data is not accurate enough, and the driving state cannot be accurately and efficiently obtained under different environment conditions are solved.

The invention provides a high-precision intelligent welding system adapting to complex working conditions, and relates to the technical field of laser welding. The high-precision intelligent welding system adapting to the complex working conditions comprises the steps of S1, based on a high-resolution visual sensor and a laser scanner, S2, based on preprocessed point cloud data, S3, based on a workpiece three-dimensional model, S4, based on an optimized welding path and a material attribute database, S5, based on a dynamic welding parameter set, S6, based on a real-time welding track, and S7, based on multi-sensor monitoring data. S8, based on a defect detection report; and S9, based on a repaired welding result and historical welding data. According to the invention, the geometric data of the workpiece are collected through the high-resolution visual sensor and the laser scanner, the filtering algorithm is applied to remove noise to generate high-quality point cloud data, and a subsequent processing foundation is laid; workpiece features are identified by using a point cloud processing algorithm and a machine learning method based on the point cloud data, and an accurate digital model is generated through a three-dimensional reconstruction algorithm.

The invention discloses a method for determining a preset position of a video monitoring camera. Camera presetting positions usually need to be manually set one by one, and time and labor are wasted. The method is used for a video monitoring system, and automatic setting of the preset position of the camera is realized by utilizing a group of scene images and the to-be-monitored target image, so that the efficiency is greatly improved. The method comprises the following steps: acquiring feature points based on a scene image set by adopting a computer vision technology, generating a three-dimensional model of a scene by adopting a motion recovery structure technology and a surface reconstruction algorithm, and obtaining the position of a to-be-monitored target in a three-dimensional space by matching the feature points of a to-be-monitored target image with the feature points of the scene image set. Therefore, a proper camera is selected, a corresponding preset position is calculated, and finally the preset position is corrected according to an actual monitoring effect.

The invention discloses a scene building method and system based on three-dimensional reconstruction. The method comprises the following steps: collecting a multi-view two-dimensional image of an environment; preprocessing the obtained two-dimensional image, and automatically identifying and labeling different objects and areas in the image by applying a semantic segmentation technology to understand semantic information in the image; according to the marked two-dimensional image data, reconstructing a three-dimensional model from the two-dimensional image by using a multi-view geometric three-dimensional reconstruction algorithm based on bundle adjustment, and storing the reconstructed three-dimensional model as a sub-scene model; according to the method, the three-dimensional model is accurately reconstructed by collecting the multi-view two-dimensional image and applying the semantic segmentation and bundle adjustment technology, the technical bottleneck of real-time rendering of a complex scene is solved, and the scene building efficiency and precision are improved; and in combination with the generative adversarial network and the variational auto-encoder optimization model, authenticity, detail expressive force and diversity are enhanced, and rich and real scene experience is provided for the field of virtual reality.

The invention provides a real-time map route construction method and system. The method comprises the following steps: installing various sensors on an unmanned aerial vehicle to obtain multi-modal data of an environment; converting the multi-modal features into a high-dimensional embedding space, and constructing a real-time three-dimensional environment model based on a multi-modal point cloud reconstruction algorithm; deploying edge computing nodes, and distributing computing tasks to the edge computing nodes; planning a cooperative path among the multiple unmanned aerial vehicles; constructing a multi-unmanned aerial vehicle cooperative global adaptive adjustment mechanism to dynamically adjust the flight path of the unmanned aerial vehicle; and performing priority ranking on the tasks of the flight path of the unmanned aerial vehicle, constructing a path adjustment optimization mechanism according to the real-time flight condition to minimize the task failure risk, and updating the task priority and the scheduling strategy according to the feedback after each task is executed. According to the invention, a plurality of key problems in the prior art are effectively solved, and a technical guarantee is provided for successful application of the unmanned aerial vehicle in more complex application scenes.

The invention discloses a multi-modal medical image 3D reconstruction and visualization system for surgical planning, and relates to the technical field of medical image processing, and the system comprises a multi-modal image collection and preprocessing module which is used for collecting and preprocessing medical images including CT, MRI and PET modalities; the multi-modal image segmentation module is used for accurately segmenting the multi-modal image; the 3D reconstruction and fusion module is used for reconstructing and fusing a 3D model through a multi-scale reconstruction algorithm; the intra-operation augmented reality visualization module projects the reconstructed 3D model to an operation area through a self-adaptive projection algorithm; the error analysis and correction module is used for ensuring that the real-time error correction precision in surgical navigation reaches the submicron level; the feature matching and fusion module ensures a multi-modal fusion effect through feature matching and performs nonlinear fusion by using feature splicing; according to the multi-modal medical image 3D reconstruction and visualization system for surgical planning, the limitation of a traditional surgical planning system is solved.

The invention provides a moving target capturing method and system based on AI multi-view vision, and relates to the technical field of data processing.The method comprises the steps that camera parameters in all vision systems are calibrated, and the camera parameters comprise a camera internal parameter matrix and a camera external parameter matrix; extracting 2D feature points of the moving target through each calibrated visual system; reconstructing each 2D feature point by combining a multi-view geometric reconstruction algorithm and a least square method according to the calibrated camera parameters to obtain 3D feature points; constraints are added to the 3D feature points, and the constraints comprise spatial constraints, direction vector constraints and time sequence constraints; reconstructing the 3D feature points added with the constraints through a multi-view geometric analysis algorithm to obtain three-dimensional motion information of the moving target; and outputting the three-dimensional motion information of the moving target to complete the capture of the moving target. And non-contact high-precision capture of the moving target can be realized.

The invention discloses a storage intelligent monitoring and checking integrated system and method based on multi-technology fusion, and particularly relates to the technical field of storage monitoring, the system obtains environmental parameters and cargo data in real time through a multi-source data acquisition module, carries out cargo identification and segmentation by using YOLOv7 and Mask R-CNN, and carries out storage monitoring and checking on the cargo. A three-dimensional model is constructed in combination with a Poisson surface reconstruction algorithm to calculate volume weight, an environment anomaly analysis module generates an early warning signal through dynamic threshold and influence level evaluation, and an intelligent decision module fuses data to realize quantity anomaly alarm and multi-level response and outputs a three-dimensional visual inventory report. According to the method, the problems of multiple blind areas, low checking efficiency, slow abnormal response and the like of traditional storage monitoring are solved, full coverage of environment monitoring, high accuracy of goods identification, low error of volume calculation and intelligence of abnormal handling are realized, and the automation and digitization levels of storage management are remarkably improved.

The invention discloses a personalized design intelligent interaction method based on topological optimization, and the method comprises the steps: S1, constructing a user behavior monitoring system based on multi-modal data collection, and generating a high-dimensional data set containing time sequence features; s2, based on an adaptive deep neural network model, performing dynamic prediction and hierarchical modeling on the personalized demand of the user; s3, generating an optimal solution of the design parameters in real time through a dynamic topology reconstruction algorithm; s4, iteratively updating a design scheme generation rule through a reinforcement learning mechanism; s5, constructing a multi-objective design space exploration and optimization framework supported by the neural network, and rapidly screening and optimizing design parameters; s6, dynamic updating and local optimization of the design scheme are achieved through multi-dimensional data mapping and parameterization regulation and control means; and S7, establishing a data-driven continuous learning and evolution mechanism, continuously optimizing the user demand prediction model and designing an optimization algorithm. The method has the advantages of being high in dynamic adaptability, high in intelligent level and high in personalized meeting precision.

The invention provides a structure surface multi-disease three-dimensional measurement method and device, equipment and a medium. The method comprises the steps that an image sequence carrying GPS coordinate information is collected; performing depth calculation on the image sequence by using a three-dimensional reconstruction technology, and performing three-dimensional reconstruction on a scene to generate an initial three-dimensional model; carrying out disease determination and point cloud processing to obtain a three-dimensional point cloud model of a specified color and each disease point cloud instance; using a skeleton extraction method and a boundary point extraction algorithm to extract a boundary point set and a skeleton point set of the skeleton point set corresponding to the crack point cloud, and according to each obtained skeleton point set and the corresponding boundary point set, performing quantitative calculation on the length and the width of each crack; generating a spalling surface grid model by using a Poisson surface reconstruction algorithm and a hole filling algorithm, and calculating and determining the volume of the three-dimensional spalling instance according to the spalling surface grid model; and determining the normal direction of each point of the corrosion cloud instance, generating a grid model by using a Poisson surface reconstruction algorithm, and calculating the corrosion area.

The invention relates to the technical field of three-dimensional imaging, in particular to a four-eye structured light stereoscopic vision imaging method, which comprises the following steps of: arranging four cameras and synchronously acquiring multi-view image data with structured light stripes; carrying out image preprocessing and stripe code identification on the obtained four-view-angle structured light image data, and extracting structured light stripe center line positions and corresponding space projection information under each view angle; generating three-dimensional point cloud data of the high-precision target sample by using parallax calculation and a three-dimensional reconstruction algorithm, and completing spatial registration and filtering optimization of point cloud; fusing the point cloud and the light intensity data by combining the reflection intensity information of the multi-view structured light stripes to generate a composite data set containing space and spectral information; and constructing a dense parallax field and executing three-dimensional consistency verification, and generating a high-fidelity three-dimensional reconstruction model with a complete topological relation and sparse shielding compensation capability. According to the invention, the problems of insufficient view angle coverage, shielding area information loss, difficult edge structure matching and the like of traditional stereoscopic vision imaging can be solved.

The invention discloses a cross-platform virtual-real fusion scene construction method and system based on AI space calculation, and relates to the technical field of artificial intelligence and space calculation, and the method comprises the steps: carrying out the multi-scale feature fusion based on a received cross-modal conversion instruction set, and generating an initial image sequence; carrying out implicit field coding on a target object by combining a three-dimensional reconstruction algorithm to obtain an initial parameterized model; performing space-time alignment on the multi-view video stream, loading a digital scene asset package in combination with physical sensing data and a preset spatial index structure, and establishing a bidirectional data channel between a virtual scene and a physical sensor; performing rendering and illumination parameter adjustment on the initial parameterized model to obtain an optimized parameter model; performing differential coding processing on the optimization parameter model to obtain a target virtual-real scene fusion model; and distributing the target virtual-real scene fusion model to a preset terminal. The invention provides a virtual-real fusion construction method for end-to-end collaborative optimization, which is suitable for cross-platform live broadcast or dynamic interaction scenes.

The invention relates to the field of three-dimensional reconstruction, and discloses a three-dimensional scene online reconstruction method, device and equipment and a storage medium, and the method is used for realizing the online reconstruction of a three-dimensional scene. The method comprises the following steps: acquiring and processing multiple frames of ordered scene RGB images to obtain sparse point clouds of each frame of scene RGB image under a camera coordinate system, and converting the sparse point clouds into sparse point clouds under a world coordinate system; initializing a sparse point cloud under a world coordinate system to obtain a local Gaussian surface element of each frame of scene RGB image; based on a fusion mechanism of a gating loop unit, reading global features of sparse point clouds of each frame of scene RGB image in a world coordinate system frame by frame from the first frame, and fusing the global features of the scene RGB image of the previous frame with the local Gaussian surface element of the scene RGB image of the current frame to generate a global Gaussian surface element of the scene RGB image of the current frame; and rendering the global Gaussian surface element of each frame of scene RGB image from a plurality of visual angles, and generating a scene reconstruction surface by using a Poisson reconstruction algorithm.