791 results about "Spatial registration" patented technology

The invention relates to the field of shale oil and gas, and discloses a method for identifying a shale oil and gas reservoir dessert, which comprises the following steps: acquiring a core CT image, three-dimensional seismic data and production dynamic data, and carrying out cross-scale preprocessing; constructing a fractional-order non-local seepage field model to represent nano-to-kilometer-level flow characteristics; predicting seepage field parameters through a Lie group symmetry constrained neural network; establishing a cross-scale coupling model of the quantum adsorption effect and the macroscopic seepage law; dynamically updating model parameters based on real-time monitoring data; and executing multi-target collaborative optimization to generate a sweet spot three-dimensional distribution and development scheme. According to the method, a fractal dimension dynamic constraint cross-scale data fusion technology is adopted, the effect of accurate mapping of nanopore and macroscopic fracture network parameters is achieved, and the problem of misalignment of CT scanning and seismic inversion data space registration is solved through pore communication fractal analysis.

The invention provides an infrared thermal imaging building facade defect intelligent diagnosis method based on multi-modal fusion, and relates to the technical field of building detection.The method comprises the steps that infrared thermal imaging, visible light images and three-dimensional point cloud data are synchronously collected to construct a multi-modal data set; segmenting a hot spot region by adopting an improved morphological watershed algorithm and extracting contour and temperature features; recognizing a surface crack and peeling area based on a double-branch attention network to generate a texture defect feature map; curvature distribution and thermal deformation gradient are calculated through space registration constrained by a heat conduction equation; multi-source features are fused to calculate a hot spot form dispersion TSMD and a structure risk quantification factor SRQF; constructing a defect risk decision matrix to output defect types, positions and risk levels; and superposing the diagnosis result to a BIM model to generate a three-dimensional visual report and predicting a thermodynamic evolution trend. The multi-modal data collaborative analysis is realized, the defect risk is accurately quantified, and the problems of poor anti-interference performance, inaccurate segmentation and large registration error of a traditional method are solved.

The invention relates to the technical field of biomedical engineering, in particular to a multi-mode brain anomaly detection method and system based on machine learning. The method comprises the following steps: acquiring brain medical image data of different modalities, and realizing spatial registration and alignment through a multi-modal registration algorithm based on mutual information; a multi-branch feature extraction model including a convolutional neural network, a converter and a state space model is utilized to perform feature embedding on the original image of each modal; performing frequency decoupling on the features of each mode through adaptive approximate wavelet transform, and decomposing the features into high-frequency detail information and low-frequency global information; a frequency band fusion strategy based on an attention mechanism is implemented on high and low frequency features of different modal images, and fused frequency sub-band features are input into a space-frequency Mama module. Through the adaptive frequency domain decomposition and cross-modal fusion mechanism, the multi-modal brain image information is effectively integrated, and the accuracy and robustness of brain anomaly detection are remarkably improved.

The invention discloses a substation autonomous inspection and foreign matter cleaning cooperative control system and method, and belongs to the technical field of intelligent inspection and foreign matter cleaning. The system comprises a multi-modal detection module used for acquiring images, point clouds and multi-source sensing data and identifying foreign matter coordinates and visual features; the space positioning module is used for executing space registration to obtain a three-dimensional coordinate of the foreign body; the risk decision module fuses the multi-dimensional information and evaluates the foreign matter risk level; the cleaning execution module generates a cleaning path and execution parameters and issues the cleaning path and the execution parameters; and the inspection execution module plans inspection paths and actions based on the state and constraint conditions, and completes subsequent equipment inspection tasks. According to the scheme, the system realizes clear division of labor and accurate control in multiple stages of foreign matter identification, space positioning, risk assessment, cleaning instruction generation, polling after cleaning and the like, and the expansibility and the overall response efficiency of the system are improved, so that efficient, safe and stable execution of autonomous polling and foreign matter cleaning tasks of the transformer substation is guaranteed.

The invention discloses a multi-modal data fusion power equipment health state diagnosis method and system, and belongs to the field of power equipment state monitoring, and the method comprises the steps: S100, collecting infrared thermal imaging data, vibration signals, current harmonic data and partial discharge signals of power equipment, and carrying out the time synchronization and space registration; and S200, acquiring infrared thermal imaging data, vibration signals, current harmonic data and partial discharge signals, and inputting the infrared thermal imaging data, the vibration signals, the current harmonic data and the partial discharge signals into the dynamic weight fusion model to obtain an equipment health state score and a fault type. And S300, according to the equipment health state score and the fault type, triggering grading alarm. According to the invention, timely early warning can be carried out on potential fault hidden dangers of power equipment.

The invention relates to the technical field of printed circuit board assembly quality detection, and discloses a PCBA anomaly detection method and system based on three-dimensional modeling and AI fusion, and a medium. The method comprises the following steps: acquiring three-dimensional point cloud data of a PCBA board to be detected; generating a reference three-dimensional digital twin model according to a standard PCBA design drawing; carrying out spatial registration on the three-dimensional point cloud data and the reference three-dimensional digital twin model, obtaining the three-dimensional point cloud data, carrying out hierarchical processing on the obtained three-dimensional point cloud data, extracting geometric features of a welding spot region, contour features of an element region and surface features of a substrate region, and carrying out fusion to generate a feature vector group; constructing a generative adversarial model based on a preset semi-supervised learning framework and the normal PCBA sample vector group; and inputting the feature vector group into a generative adversarial model, and examining the abnormal vectors, the corresponding three-dimensional coordinates and the abnormal types in the feature vector group by the generative adversarial model to complete the abnormal detection of the PCBA board. The method is suitable for quality control of a high-density and miniaturized PCBA.

The invention relates to the technical field of optical engineering, in particular to an AI silicon carbide lens-oriented aspheric laser polishing precision online detection and feedback system. Comprising a detection module; the data processing module is electrically connected with the detection module and used for constructing a lens surface three-dimensional model and calculating polishing precision parameters; the feedback control module is electrically connected with the data processing module, is used for generating a feedback control strategy and comprises a strategy generation unit and a parameter optimization unit; an execution module; and an intelligent learning module. According to the design, a laser measuring head, an energy sensor array and an environment sensor are integrated through the detection module, synchronous acquisition of multi-dimensional data such as surface profile, laser energy distribution and environment parameters is realized, and three-dimensional point cloud data with consistent time and space are generated through multi-modal fusion processing (time domain synchronization, space registration and feature enhancement) of the data preprocessing unit; the physical essence of the polishing process is completely represented, and the detection comprehensiveness and the data relevance are improved.

The invention relates to the technical field of visual inspection, in particular to a multi-mode industrial product dynamic defect detection system based on edge calculation. According to the method, by introducing a multi-modal image construction and enhancement mode, three-dimensional acquisition and enhanced expression of detail information of the surface of the wind power blade are realized, and by means of inter-modal image synchronization and a space registration mechanism, the consistency extraction capability of defect information under different sensor view angles is improved; through combination of density change trend analysis and direction mutation identification means, surface micro cracks, edge damages and other structural changes can be accurately identified in continuous frames, and further through multi-source discrimination and mutual elimination comparison of abnormal indexes, environmental interference and misjudgment risks are effectively eliminated, and the accuracy of the detection result is improved. Therefore, a stable defect track area with direction consistency and distribution continuity is screened out, accurate detection and partition identification of the surface defects of the wind power blade under the dynamic condition are achieved, and the reliability and precision of defect positioning are remarkably improved.

The invention provides a tunnel crack identification method and system based on multi-source image processing, and relates to the technical field of tunnel engineering, and the method comprises the steps: obtaining multi-source data of a horizontal rock stratum tunnel; performing spatial registration on the multi-source data to generate a multi-modal image under the same reference system; extracting multi-modal features according to the multi-modal image, and constructing a multi-source feature map under the same space grid; performing crack initial detection on the multi-source feature map in combination with multi-scale filtering and structure tensor analysis to obtain a crack candidate region mask; accurate crack identification is carried out through the crack candidate area mask, a crack identification result is obtained by combining bedding direction constraint and a microconditional random field, and the crack identification result comprises a crack segmentation map and a crack category. The method solves the problem that existing crack identification does not consider the bedding characteristics of the horizontal rock stratum tunnel.

The invention discloses a mineral resource intelligent prediction method and system based on multi-source heterogeneous data fusion and deep learning, and the method comprises the steps: collecting and preprocessing multi-source heterogeneous data, and carrying out the standardization processing to form a structured data set; multi-source heterogeneous data fusion: realizing data layer space registration and feature layer weight dynamic allocation through an attention mechanism multi-modal fusion module, and outputting a high-dimensional metallogenic feature vector; constructing a CNN-LSTM mixed deep learning model and completing initialization training, and outputting an initial mineralization probability graph; and establishing a dynamic updating engine, performing model increment training based on transfer learning, correcting the mineralization probability through positive and negative sample reinforcement learning in combination with a newly added data type, and outputting a time sequence dynamic mineralization probability graph. According to the method, mineralization probability dynamic evaluation and risk quantitative updating are realized, the prediction precision and the model updating efficiency are improved, the method is adaptive to a multi-stage exploration scene, and accurate real-time support is provided for exploration decision making.

The invention relates to the technical field of remote sensing data processing and glacier area calculation, in particular to an unmanned aerial vehicle and satellite remote sensing data fused glacier area calculation method, which comprises the following steps of: cooperatively acquiring a satellite multispectral image and unmanned aerial vehicle high-resolution optical and LiDAR data, performing time synchronization, high-precision space registration and data enhancement processing, and calculating the glacier area through the unmanned aerial vehicle and satellite remote sensing data fusion. A satellite image glacier macroscopic feature and an initial mask are extracted by using a convolutional neural network and an NDSI / NDWI algorithm, and unmanned aerial vehicle image microscopic texture, edge and topographic features are acquired through a local binary pattern, edge detection and LiDAR point cloud; based on pyramid layering and a conditional random field, adopting a variance weighting algorithm to realize multi-scale feature level fusion; and after segmentation through an Otsu algorithm, calculating the area through a pixel counting method and introducing gradient correction, and evaluating the reliability through three types of precision. The method breaks through the limitation of a single data source, fuses macroscopic and microscopic features, improves the boundary positioning precision and calculation efficiency, and is suitable for glacier dynamic monitoring in a complex environment.

The invention discloses a dynamic time-space synchronous mapping method and system based on multi-sensor data fusion, and belongs to the technical field of environmental perception. According to an existing mapping scheme based on multi-sensor data, space-time deviation between sensor data is not considered, so that when the sensor data are fused, the problem of insufficient space-time synchronism exists, and the map building precision is influenced. According to the dynamic space-time synchronous mapping method based on multi-sensor data fusion, the point cloud distortion correction module, the sensor time alignment module, the dynamic target sensing module and the multi-map fusion module are constructed, so that the problem of insufficient space-time synchronism during multi-sensor data fusion can be effectively solved; the space registration precision of the point cloud and the image is remarkably improved, the map construction effect of a dynamic scene is effectively improved, a robot can accurately recognize and track a dynamic target, and the autonomous operation capability of the robot in a complex environment is improved.

The invention discloses a double-station robot sorting optimization method and system based on digital twinning and a terminal, double improvement of sorting efficiency and safety is achieved by constructing a digital twinning driven collaborative operation system, and the method comprises the steps that firstly, a laser radar and a polarization camera are used for forming a composite sensing unit; geometric morphology, material reflection characteristics and spatial pose data of a target object are synchronously obtained, and are input into a digital twin engine after time synchronization processing; an engine constructs a virtual sorting scene containing a material attribute database based on a physical rendering technology, sub-millimeter-level space registration is achieved through feature fusion of a binocular stereoscopic vision depth map and geometric parameters, high-precision digital twin stations are generated, a system plans a space-time constraint trajectory of a double-station robot in a virtual environment, and a target object is obtained. And an integrated discrete event simulation engine performs operation time sequence conflict prediction, and when a space overlapping risk is detected, an alternative path containing a dynamic obstacle avoidance strategy is generated through a trajectory re-planning algorithm.

The invention relates to the technical field of photovoltaic module detection, in particular to a hot spot detection system and method for a photovoltaic module. Comprises: a multispectral imaging module configured to synchronously collect image data of a photovoltaic module in a visible light band, a near-infrared band and a long-wave infrared band; the electroluminescence analysis module is in signal connection with the multispectral imaging module and is used for acquiring carrier recombination radiation data of the photovoltaic module in a reverse bias state; the dynamic threshold value processing module is configured to establish a dynamic correlation model of the environment parameters and the hot spot characteristic parameters; the three-dimensional reconstruction module is configured to perform spatial registration on the multispectral imaging data and the electroluminescence data and construct three-dimensional temperature field distribution of the photovoltaic module; the defect positioning module is configured to determine the accurate position of a hot spot according to temperature field distribution and carrier recombination characteristics; according to the scheme, a novel detection system architecture with multi-mode collaboration, high dynamic adaptability and three-dimensional analysis capability is constructed.

The invention discloses a dam crack identification method and system based on unmanned aerial vehicle inspection. The method comprises the steps that a multispectral image and point cloud data of the surface of a to-be-detected dam are collected through an unmanned aerial vehicle; carrying out preprocessing and spatial registration on the multispectral image and the point cloud data; fusing the multispectral enhanced image and the point cloud calibration data to obtain a six-channel fusion tensor, and constructing a fused image by the six-channel fusion tensor; extracting fusion features through the six-channel fusion tensor, performing multi-scale context aggregation on the fusion features to obtain crack aggregation features, and performing crack segmentation on the fusion image according to the crack aggregation features to obtain a dam crack recognition model; obtaining a dam crack identification result and a crack size based on the dam crack identification model; according to the invention, data are collected through the unmanned aerial vehicle, multispectral and point cloud information are fused, the model is constructed to accurately identify the dam crack and the measurement size, the detection efficiency and accuracy are improved, and the dam safety is guaranteed.

The invention discloses an intelligent park management system based on cloud computing and Internet of Things, and relates to the technical field of park management systems, and the system comprises a dynamic digital twinborn body module which comprises a heterogeneous data fusion layer which integrates a BIM model, LiDAR point cloud, an unmanned aerial vehicle inspection image and distributed loT sensor data, and eliminating timestamp deviation of multi-source data by adopting a space-time alignment algorithm, and generating a millimeter-level precision three-dimensional park twin model. Through the construction of the high-precision digital twinborn model, the panorama and equipment operation state of the park can be accurately presented in real time, the timestamp deviation and spatial registration error of multi-source data are eliminated, the real-time performance and accuracy of the data are improved, a solid data basis is provided for subsequent intelligent simulation and early warning decision, and the response and monitoring capabilities of the system are improved.

The invention provides a tunnel deformation parameter inversion method and device based on distributed optical fibers, and relates to the technical field of tunnel deformation parameter inversion, and the method specifically comprises the steps: selecting a monitoring point in a tunnel, arranging an optical fiber sensor, and obtaining a Brillouin scattering signal generated by the optical fiber sensor under the stress effect of the corresponding monitoring point; extracting a Brillouin frequency shift corresponding to the monitoring point, and determining an environmental effect frequency shift correction value by using the temperature change data, the humidity change data and the service time of the optical fiber sensor; determining the structural strain of the monitoring point according to the Brillouin frequency shift and the environmental effect frequency shift correction value, generating a three-dimensional strain field cloud picture, performing spatial registration on the three-dimensional strain field cloud picture and the geometric topology of the model, and performing three-dimensional grid division; the structure strain of the monitoring point is mapped to the grid node at the corresponding position, the structure strain of other grid nodes is determined based on the space distance attenuation law, inversion of the whole tunnel deformation parameters is completed, and the tunnel deformation monitoring precision and efficiency are improved.

The invention relates to the technical field of automatic driving, in particular to an automatic homeward voyage method for multi-sensor data fusion of an unmanned vehicle, which comprises the following steps: acquiring laser radar obstacle points, image edges and attitude data, completing synchronous registration, identifying space mapping, extracting track and boundary trends, screening forward sections, and judging track offset and trafficability. Screening an error band boundary, adjusting a steering instruction, analyzing path overlapping change, and outputting a path keeping label. According to the method, through time synchronization and space registration of various sensor data, high-precision fusion of the data under a unified space-time framework is realized, the reliability of environment perception is improved, accurate mapping of the data in a unified reference coordinate system is ensured, the reliability of path planning and decision making is enhanced, and the optimal advancing direction is determined by combining a homing point; the accuracy of return route planning is improved, the traffic feasibility is dynamically evaluated, the effective error band boundary is screened to improve the safety, and the reliability of the return route is ensured through track stability analysis.

The invention relates to the field of urban road modeling, in particular to an aerial photography data processing method and system for urban road modeling. The invention discloses an aerial photography data processing system for urban road modeling. The aerial photography data processing system comprises an aerial photography video acquisition module, a road modeling module, a photogrammetry module, a spatial registration module and a rendering synthesis module. According to the invention, on the basis of a spatial calibration mechanism of the original aerial image and the BIM model, redundant processes such as point cloud acquisition, data fusion and manual correction are eliminated, and linear processing from data acquisition to dynamic result output is realized; according to the architecture, the hardware resource dependency and the operation complexity are greatly reduced, and designers are endowed with the capability of completing large-scale scene visualization processing in a conventional engineering environment; according to the method, a transmission chain from original data to decision support is remarkably shortened, and important engineering scheme deduction and dynamic review have unprecedented timeliness.

The invention discloses a robot operation object positioning method and system, and relates to the image processing related technical field, and the method comprises the steps: building a three-dimensional point cloud data set based on laser scanning and design data, and enabling the three-dimensional point cloud data set to be marked with key features; activating a positioning camera of the robot, executing operation scene image acquisition, and establishing a scene image; carrying out contour matching identification on the RGB image according to the workpiece features, establishing a matching identification result, and calling a mapping depth image; executing search matching of the key features, and establishing a search matching result; local point cloud region fusion matching is executed, and a spatial registration result is established; and resolving attitude parameters of the target workpiece in the three-dimensional point cloud data set, and completing positioning based on a resolving result. The technical problems of poor adaptability and insufficient positioning precision of robot operation object positioning in a complex environment in the prior art are solved, and the technical effects of realizing high-precision positioning of the operation object and improving the positioning real-time performance and reliability are achieved.

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 relates to the technical field of geological disaster detection, in particular to an unmanned aerial vehicle multi-sensor image fusion slope geological disaster detection system which comprises a data acquisition module, a manifold registration module, a feature fusion module, a weight optimization module, a fusion execution module, a disaster detection module and the like. RGB images, thermal infrared images and laser point cloud data of a slope are collected through an unmanned aerial vehicle, the surface of the slope is modeled as a Riemannian manifold, and high-precision space registration of heterogeneous data is achieved; constructing a feature manifold based on a manifold learning method, and extracting and fusing multi-scale features; evaluating the information amount of different areas by adopting a differential entropy theory, and generating a self-adaptive weight distribution diagram; performing weighted fusion on the registered multi-source data to generate a fused image; geological disaster features such as cracks, abnormal vegetation and water seepage points on the surface of the slope are recognized based on the fused image, and high-precision recognition and early warning of the geological disaster of the slope are achieved.

The invention relates to the technical field of oral medical treatment, in particular to an oral disease analysis method and system based on AI intelligent recognition. Comprising the following steps that oral cavity three-dimensional surface data are obtained through an oral scanning module integrated with a dental chair, and the oral scanning module adopts a structured light coding and multi-view fusion algorithm; an oral soft tissue high-definition image is collected through an endoscope module, and an AI analysis unit is arranged in an endoscope to recognize mucous membrane lesion features in real time; calling CBCT image data of the patient, and aligning a three-dimensional image with oral scanning data through a spatial registration algorithm; the mouth scanning data, the endoscope image and the CBCT data are subjected to multi-modal fusion by adopting a dynamic weight fusion mechanism. According to the scheme, the problem of accurate registration of cross-modal data, the lack of a dynamic quality evaluation mechanism of heterogeneous data and the real-time collaboration bottleneck of dispersed equipment can be solved.

The invention discloses a real-time image registration and path planning system in bronchoscope surgical navigation, relates to the technical field of image registration, and is used for solving the problems that in a thoracic and abdominal minimally invasive interventional operation, organ movement and deformation caused by breathing of a patient can cause obvious influence on the registration precision of a navigation system, and the navigation precision is poor. Space registration of preoperative images and an anatomical structure of a patient in an operation often has errors due to mismatching of breathing phase changes; multi-attitude data are fused, the respiration interference degree is comprehensively evaluated through double indexes, the problem that a traditional static deformation field cannot be matched with dynamic respiration is solved through respiratory cycle driving deformation prediction, displacement errors are corrected through tidal volume observation values, and B spline control point weights are reversely optimized through registration residual errors. A deformation field can adapt to breathing amplitude and frequency differences of different patients, online distillation learning is carried out by taking a registration error output by a filter as a teacher signal, and local residual deformation and chronic changes which are difficult to describe by a traditional global model are accurately captured.

According to the displacement modulation and optical assistance-based SERF atom magnetometer magnetic imaging method, an SERF atom magnetometer integrated with a magnetic flux guider is used as a magnetic sensor, and low-frequency magnetic field modulation is introduced to the magnetic sensor by controlling a to-be-tested sample to perform periodic infinitesimal displacement in the sensitive direction of the magnetic sensor; the modulation signal is demodulated by combining a phase-locked amplification technology, and a magnetic response signal subjected to phase-locked demodulation at each spatial position is extracted; constructing a magnetic response matrix through two-dimensional track scanning of micron-order step pitch; an image acquisition module and a reflection optical assembly are introduced for spatial registration so as to monitor the relative position in real time, and the visibility and controllability of the magnetic imaging process are guaranteed; the point-by-point detection of fT-level weak magnetic signals can be realized on the premise that an array structure is not needed; the low-frequency noise interference can be effectively inhibited, the stability and definition of direct-current and low-frequency magnetic field imaging are improved, and the method is suitable for high-resolution space imaging application of weak magnetic sources such as magnetic domain structures, nervous tissue slices and ancient rock samples.

The invention provides a remote sensing-based land utilization carbon emission evaluation method, device and equipment and a medium, and the method comprises the steps: carrying out the radiometric calibration and spatial registration of obtained multi-source remote sensing data, and obtaining a standardized raster data set; generating a land utilization classification grid map based on the standardized grid data set; generating a land change vector layer through a continuous multi-stage land utilization classification grid map; generating a dynamic evaluation unit vector boundary according to the land utilization classification grid map and the land change vector layer; correcting a vegetation carbon absorption coefficient and an industrial emission coefficient in real time based on remote sensing inversion data, and constructing a spatial carbon transfer model; and inputting the land utilization classification grid map, the dynamic evaluation unit vector boundary and the spatial carbon transfer model into a layered mixed carbon emission evaluation model to obtain a carbon emission intensity distribution map. By adopting the scheme, the carbon emission under different land utilization modes can be accurately evaluated, and the scientificity and policy applicability of regional carbon balance evaluation are improved.

The invention discloses an evaluation and improvement method and device for a tunnel blasting effect and a medium, and relates to the technical field of tunnel engineering.The evaluation and improvement method comprises the steps that a tunnel coupling data set is collected, space registration and three-dimensional shape reconstruction are conducted, fracture space distribution is formed, risk probability mapping is conducted on the fracture space distribution, and a fracture risk thermodynamic diagram is output; the fracture risk thermodynamic diagram and tunnel rock mass data are input into a digital twin blasting model, a load mapping layer carries out load gradient distribution, a rock mass response deduction layer carries out stress wave propagation simulation and damage accumulation quantification, an optimized blasting number instruction set is generated, and a drill jumbo is driven to execute blasting operation and vibration monitoring according to the optimized blasting instruction set. And actual blasting effect parameters are obtained. According to the method, accurate simulation of geological conditions and optimal adjustment of blasting parameters are realized through the digital twin blasting model, and meanwhile, refined and interpretable evaluation of the blasting effect is realized through vibration monitoring and error propagation modeling of the actual blasting effect.

The invention provides a fruit tree canopy three-dimensional model reconstruction method and a fruit tree canopy three-dimensional model reconstruction system based on multi-modal data, and relates to the technical field of fruit tree canopy three-dimensional model reconstruction based on multi-modal data. Sub-pixel-level space registration is achieved by means of ground control points, voxelization division is carried out based on the range of a point cloud bounding box, and the number of point clouds is screened to construct an initial seed set; and adopting a structure-spectrum collaborative growth strategy, taking the adjacent voxels which are not accessed as candidate voxels, calculating a spectrum similarity mean value of the candidate voxels and directly adjacent voxels in the seed set, stopping growth when no new voxels are added in continuous three times of iteration, and outputting a final seed set. Meanwhile, the set is converted into a three-dimensional canopy model fusing space coordinates and full-wave-band spectral reflectivity, voxel-level pathological labeling is achieved based on the chlorophyll sensitivity index and the blue-red slope, and the whole process of reconstruction and analysis is completed.

The invention discloses a laser energy threshold millisecond-level dynamic matching method for multi-metal fuse manufacturing, and the method comprises the steps: pre-storing a multi-metal thermophysical parameter model, calibrating a thermal signal in real time through Kalman filtering, and carrying out the online correction of a melting threshold key parameter during the switching of a material; millisecond-level thermal feedback closed-loop control is achieved through the high-frame-rate thermal imaging technology, and the laser power accurately follows the corrected melting threshold value; meanwhile, a three-dimensional imaging and deep learning segmentation algorithm is adopted, geometric information of a welding wire and a molten pool is obtained, the position and the diameter of a light spot are adjusted in real time through an adjustable optical system after the offset is calculated, and millimeter-level space registration closed-loop control is achieved; the two closed-loop systems cooperatively operate according to respective control periods, and precise dynamic matching of laser heat input in a time domain and a space domain is achieved. The problem that the adaptability of a traditional process is insufficient during multi-metal switching and complex geometric change is solved, and the forming quality, the process stability and the efficiency of manufacturing are remarkably improved.

The invention provides a self-adaptive spraying mechanical arm based on multi-mode perception and a control method of the self-adaptive spraying mechanical arm. The method comprises the steps that multi-source perception data of a to-be-repaired area is obtained through a dual-mode vision system and a laser scanning device, a two-dimensional repairing area segmentation map is generated, and space registration and local geometric modeling are achieved in combination with three-dimensional point cloud; on the basis of local geometric features extracted by the model, retrieving matched process parameters from the knowledge graph, generating a digital spraying instruction set containing tracks, postures and dynamic process parameters, and performing simulation verification in a digital twin environment; the mechanical arm state and the virtual model are synchronized in real time in the execution process, the paint film thickness is dynamically monitored, and compensation adjustment is triggered; and after spraying is completed, the coating quality is detected, and a result is fed back to the knowledge graph to update the parameter mapping relation. According to the method, closed-loop control from sensing, decision making, execution, evaluation to learning is achieved, and the spraying uniformity, the self-adaptability and the intelligent level under the complex working condition are improved.