823 results about "Lidar data" patented technology

The invention provides a water area safety patrol method and system based on multi-modal feature analysis, and relates to the technical field of image recognition. The method comprises the steps of collecting a visible light image, an infrared image and laser radar data corresponding to a target water area, and performing time synchronization and space alignment to obtain visible light alignment data, infrared alignment data and laser radar alignment data; in response to the condition that the definition of the visible light image is higher than a quality reference value, carrying out edge detection and region segmentation processing on the visible light alignment data, and generating a candidate region set containing a target contour; for the infrared alignment data corresponding to the candidate region set, screening out a thermal anomaly region from the candidate region set; and carrying out three-dimensional space feature extraction and motion state feature extraction on the laser radar alignment data corresponding to the thermal anomaly region, and carrying out anomaly identification on the thermal anomaly region. According to the scheme, high-precision safety patrol of the target water area in various environments can be realized.

The invention discloses a navigation matching correction method based on an inspection robot, and the method comprises the steps: building a feature database through the deployment of a physical calibration object and the recognition of a natural feature object, providing a reliable positioning reference for a robot, achieving the coarse positioning through the fusion of visual and laser radar data in a positioning process, and introducing a dynamic credibility evaluation mechanism. The positioning reliability is quantified in real time through an exponential decay model, when the credibility is lower than a threshold value, the system automatically triggers a compensation behavior to re-search features, in the aspect of multi-robot cooperation, secondary positioning correction is achieved through track matching and data fusion, high-confidence-coefficient reference data are screened through a clustering algorithm, the group positioning precision is improved, and the positioning accuracy is improved. Aiming at a key inspection area, multi-angle image matching is adopted to realize fine positioning, a positioning error is dynamically corrected through a sliding window, the continuity and accuracy of robot navigation in a complex environment are remarkably improved through closed-loop correction and self-adaptive optimization, and the method is suitable for intelligent inspection requirements of railway trains.

The invention discloses an intelligent lighting management system and method based on multi-source data, and relates to the technical field of intelligent lighting management, and the system comprises a multi-source data collection module, an environment feature anchoring module, a dynamic error modeling and calibration module, an edge-cloud collaborative decision module and a lighting strategy execution module. The multi-source data acquisition module fuses environment sensor, visual perception and laser radar data to construct a'sensor original data + environment characteristic data 'dual-input system; the environment feature anchoring module extracts stable features from the visual / laser radar data to serve as a calibration reference; the dynamic error modeling and calibration module quantifies the error in real time based on the reference and generates calibration parameters; the edge-cloud collaborative decision-making module and cloud long-term optimization form a hierarchical collaborative architecture through edge node real-time control; and the lighting strategy execution module dynamically adjusts lighting parameters according to the calibration data and feeds back an effect to form a closed loop.

The invention relates to a multi-sensor fusion positioning method and device based on environmental characteristics. The method comprises the following steps: respectively acquiring RTK data, laser radar data and IMU data; converting the RTK data into RTK positioning data, converting the laser radar data into laser radar positioning data, and obtaining IMU positioning data according to IMU output; monitoring the quality state of the output signal of each sensor in the current environment, and calculating to obtain a corresponding quality score; constructing and forming an input matrix according to the quality score of each sensor, mapping the input matrix to a high-dimensional feature space through an embedded layer and adding a position code, inputting the input matrix into a Transform model for time sequence modeling and extracting environment dynamic features, and finally outputting a real-time fusion weight of each sensor; and performing weighted fusion by using the real-time fusion weight to obtain final pose output. The method has the advantages of being simple in implementation method, high in positioning precision and stability, high in environmental adaptability and robustness and the like.

The invention discloses a hyperspectral image and LiDAR data collaborative classification method based on double-domain mask and multi-scale local reconstruction, and belongs to the field of remote sensing image classification. According to the method, the problems of scarcity of annotation data and insufficient multi-source feature fusion precision in cross-modal classification of a traditional method are solved. According to the invention, feature learning is carried out through mask random image blocks and channels; a hierarchical multi-scale reconstruction architecture is designed, a lower-layer encoder learns fine-grained features, an upper-layer encoder recovers macroscopic semantic information, and multi-level feature space alignment is realized in combination with deconvolution up-sampling and adaptive pooling. According to the method, a multi-modal feature interaction mechanism and a cross-modal attention module are constructed by fusing the local feature extraction advantages of a convolutional neural network (CNN) and the global modeling capability of Transform, and the complementarity of heterogeneous data is enhanced. According to the method, through multi-level feature dynamic fusion and adaptive weight distribution, the collaborative classification precision of the hyperspectral image and the LiDAR data is improved. The method can be applied to remote sensing image classification.

The invention provides an under-mine video stream dynamic denoising method based on multi-modal fusion, which comprises the following steps: constructing a time sequence synchronous fusion mechanism of visible light, infrared and laser radar data, and realizing time-space alignment of multi-source heterogeneous data; a dynamic noise model is established by introducing a fractional calculus optical flow field concept and combining a Gaussian mixture model, so that a dynamic noise region is accurately identified; an improved self-adaptive wavelet threshold function is constructed, a function threshold parameter can be linked with a dust concentration sensor in real time, and the de-noising intensity is dynamically adjusted according to the actual dust concentration; designing a dual-path feature enhancement neural network to effectively separate and enhance structural features and texture features in the video image; a cascaded detection decision system is created, a lightweight network is used as a primary detector, a high-confidence detection result is directly output, and a low-confidence detection result is input into a Transform correction module for secondary reasoning. According to the invention, dynamic denoising, feature enhancement and target intelligent monitoring of the video stream under the mine can be realized.

The invention relates to the technical field of artificial intelligence and remote sensing image processing, and particularly provides a hyperspectral image and laser radar data classification method based on a dynamic fusion network. The method comprises the following steps: preprocessing acquired multi-modal data, and constructing multi-scale input; a dual-scale local attention module is designed, and context information of different scales is fused in a self-adaptive weighted mode through gating soft pooling; a dynamic down-sampling feature enhancement module is designed, the down-sampling rate is dynamically adjusted according to the complexity of the feature map, and deep multi-scale interaction is carried out based on a Mama backbone; constructing a directional interactive attention module, extracting features in horizontal, vertical and diagonal directions through directional gating convolution, and capturing an anisotropic structure of a linear ground feature; through the design of a double-path classifier, fusing shallow space details and deep semantic information; and the model is trained, optimized and reasoned to obtain data classification, and the method improves the classification precision and the calculation efficiency.

The invention discloses a distributed photovoltaic power station surveying method and system based on an unmanned aerial vehicle, and the method comprises the steps: dynamically planning an obstacle avoidance and supplementary shooting route, and collecting multi-modal data; visible light, thermal infrared and laser radar data are fused and analyzed, missing images are complemented in a generative mode, and defects are diagnosed in a combined mode; generating a dynamic shadow thermodynamic diagram by fusing the historical weather and the real-time cloud picture; and a report is automatically generated and AR interaction visualization is realized. The system correspondingly comprises a route planning module, a defect diagnosis module, a shadow prediction module and an analysis display module. Through the generative AI and spatio-temporal data fusion technology, the exploration efficiency and the defect recognition precision in a complex environment are remarkably improved, and intelligent operation and maintenance decision support of the whole life cycle of the photovoltaic power station is achieved.

The invention discloses an automatic identification method for a popular shallow soil landslide disaster risk area. The method comprises a landslide risk area identification method and an intra-area landslide threat house identification method. The method comprises the following steps: firstly, acquiring terrain, soil layer structure, vegetation and rock-soil distribution information of a region through a remote sensing technology, and performing data acquisition and processing by adopting remote sensing images, infrared images, laser radar data and synthetic aperture radar data to generate a high-precision digital elevation model and a geologic structure map; through data fusion and analysis, in combination with information such as soil layers, terrains and vegetation, a potential landslide risk area is identified, and houses in the landslide risk area are identified and evaluated. According to the method, the identification precision of the landslide risk area and the threatened house is improved, and efficient and accurate technical support is provided for early warning and prevention of landslide disasters. The system has the advantages of automation, high efficiency and accuracy, and can be widely applied to real-time monitoring, risk assessment and emergency management of landslide disasters.

Embodiments of the present disclosure relate to multi-view LIDAR perception with motion cues for autonomous and semi-autonomous machines and applications. A DNN may be used to detect objects, a navigable space, weather or surface conditions, artifacts, and / or other parts or features of an environment based on multiple views of LIDAR data from multiple time slices. The DNN may include multiple input channels for processing multiple views of sensor data from multiple time slices to provide motion cues, and the extracted features from the different time slices may be geometrically projected from a first 2D view to a second 2D view, combined with features that were extracted from the second 2D view, and applied to a subsequent stage of the DNN. The data generated by the DNN may be provided to the drive stack of an autonomous vehicle or other ego-machine to enable safe planning and control of the vehicle.

The invention discloses a robot multi-modal sensing and motion cooperative control method and device, and the method comprises the steps: obtaining the information of a plurality of types of sensors according to a preset period through the plurality of types of sensors disposed in a robot operation region, and taking the information as multi-modal sensing data, the multi-mode sensing data comprises laser radar data, infrared sensor data and visual sensor data, and a conveying device is arranged in the robot operation area; analyzing conveying parameters of a conveying belt of the conveying equipment and cargo parameters of cargoes on the conveying belt based on the multi-mode sensing data; according to the conveying parameters and the cargo parameters, historical motion parameters of a mechanical arm of the robot are dynamically adjusted, and optimal motion cooperation parameters suitable for the conveying equipment are obtained; and constructing and executing a motion control instruction corresponding to the optimal motion cooperation parameter so as to carry out operation on the goods on the conveyor belt. Therefore, by adopting the embodiment of the invention, the sorting efficiency can be improved, the maintenance cost can be reduced, and the stability of the whole production process can be ensured.

The invention discloses a vehicle positioning method and system, and relates to unmanned driving. According to IMU data and laser radar data, a fast-lio algorithm is used to construct a global prior map; constructing a local point cloud map according to laser radar data collected in real time; recognizing and rejecting dynamic point clouds, and carrying out NDT registration on residual static point clouds and the global prior map to obtain a laser odometer pose; extracting feature points of the camera data by adopting a shii-tomasi algorithm; a Lucas-Kanade optical flow method is used to acquire motion vectors of the feature points; calculating the speed of the feature points according to the motion vector, removing the dynamic feature points with the speed exceeding a preset threshold value, and obtaining the pose of the visual odometer; reckoning the position and course of the vehicle through a CTRV model to obtain a track reckoning result; and carrying out multi-source heterogeneous data fusion by adopting a non-destructive Kalman filtering algorithm. Aiming at the defects of dynamic environment interference and non-linear motion trail modeling existing in traditional open air and mines, the positioning stability of the unmanned vehicle is improved.

The invention discloses a hyperspectral image and laser radar data collaborative classification method and system based on a multi-modal mutual guidance attention network. The method comprises the following steps: obtaining a hyperspectral image and laser radar data; preprocessing the hyperspectral image and the laser radar data to obtain to-be-processed data, wherein the to-be-processed data comprises to-be-processed hyperspectral data and to-be-processed radar data; performing mask processing on the to-be-processed hyperspectral data based on the elevation information of the to-be-processed radar data to obtain hyperspectral modal features; performing mask processing on the to-be-processed radar data based on the spectral information of the to-be-processed hyperspectral data to obtain laser radar modal features; performing cross-modal interaction fusion on the hyperspectral modal features and the laser radar modal features to obtain a fusion result; and using a pre-trained classifier to classify the fusion result to obtain a classification result. The method can effectively improve the classification precision of the ground object pixel sample in the remote sensing image, and provides an efficient and robust solution for the high-precision collaborative classification of hyperspectral and laser radar remote sensing images.

The invention belongs to the technical field of crop growth prediction, and particularly relates to a crop growth prediction method and system based on multispectral unmanned aerial vehicle monitoring. The method comprises the following steps: acquiring multi-dimensional data of real crops in different growth stages under different soil water contents and disease and insect pest states, determining the contribution degree of each vegetation index to crop growth through a factor analysis algorithm, carrying out dimension reduction on hyperspectral data by using a principal component analysis algorithm, fusing with the multi-spectral data, constructing a multi-spectral resolution characteristic space, and carrying out multi-spectral analysis on the hyperspectral data. The method comprises the following steps: firstly, obtaining a real plant height growth fitting function of crops through analogue simulation by combining LiDAR data and vegetation indexes, thirdly, calculating a real growth vegetation index space and obtaining a real growth state space of a standard staged growth period, and finally, inputting the calculated space and function into a model constructed by a reinforcement learning algorithm for training, and accurate prediction of the crop growth state is realized.

The invention provides a robot fire-fighting inspection early-warning supervision system, and relates to the technical field of fire-fighting inspection, the robot fire-fighting inspection early-warning supervision system comprises a robot body and a master control system, the robot body is internally provided with a multi-mode sensing array and an autonomous navigation unit, and the master control system comprises a dynamic prediction engine, a data fusion platform and a remote communication terminal. The remote communication terminal is used for connecting the robot body and the master control system for data communication and supervision; the multi-modal sensing array integrates a plurality of sensing units and is used for collecting sensing data in a plurality of types; according to the invention, a multi-modal sensing array is integrated, multiple kinds of sensing data are collected, synchronous monitoring of multiple parameters is realized, a laser radar and visual SLAM fusion technology is adopted, a three-dimensional risk map is constructed, the precision of autonomous navigation is improved, a double-Kalman filtering algorithm is adopted, dynamic noise reduction is carried out on laser radar data, and the accuracy of autonomous navigation is improved. And the navigation precision can still be kept in an external complex environment.

The invention discloses a quadruped robot inspection method based on multi-modal sensing fusion. The method comprises the following steps of: 1, initializing a global task, loading a basic navigation map, and generating the basic navigation map comprising topographic features, forbidden areas and parking positions; 2, autonomous navigation and dynamic correction of positioning deviation are realized according to laser radar SLAM data, and the positioning deviation is dynamically corrected according to real-time observation data; 3, dynamically switching or adjusting the gait strategy according to the terrain category, training the gait strategy of the quadruped robot to be matched with the terrain category, and generating a self-adaptive motion control instruction to adapt to the terrain in real time; and step 4, synchronously realizing parking area structured data acquisition and dynamic abnormal information perception through multi-sensor fusion, and realizing target state monitoring and abnormal event response in the inspection task. According to the invention, through collaborative innovation of the bionic motion platform and multi-mode intelligent detection, all-terrain coverage, total-factor perception and full-process autonomous intelligent inspection in a complex parking lot environment is realized.

The invention discloses a mine semi-autogenous grinding process analog simulation method and system based on discrete elements, and relates to the field of analog simulation, and the method comprises the steps: according to a crushing characteristic label and a parameter mapping matrix, fusing Internet of Things sensor data, constructing a particle size distribution prediction model and an energy consumption optimization scheduling strategy, and obtaining an energy-saving operation plan; comparing the simulation data set with field production data, adjusting multi-phase coupling particle model parameters, generating a calibration parameter set, researching the influence law of semi-autogenous mill operation parameters by adopting a control variable method based on the calibration parameter set, obtaining a performance index database and an analysis report, and fusing multi-sensor data and laser radar data to obtain a semi-autogenous mill operation parameter analysis result. An ore grinding process sensing mechanism and optimization control logic are constructed, and a visual interface is generated; through multiphase modeling and data driving optimization, the simulation precision and the process suitability are comprehensively improved, and an efficient and economical solution is provided for the mine semi-autogenous grinding process.

The invention relates to the technical field of computer vision and multi-sensor data fusion, in particular to a multi-sensor image fusion obstacle real-time detection and tracking system, which comprises the following steps of: firstly, fusing data of a camera, a millimeter wave radar and a laser radar, and extracting and fusing multi-modal features; performing multi-target tracking based on a recurrent neural network: generating a target state through space-time modeling, associating a target with a historical track by using an attention mechanism, and maintaining track consistency; and the system performs semantic classification and interaction analysis on the obstacle, predicts the movement track of the obstacle, realizes deep semantic understanding, and finally outputs the identity label and the complete historical track of the obstacle.

The invention relates to the technical field of biomass monitoring, and provides a forest above-ground biomass estimation method and device based on stereo density, and the method comprises the steps: obtaining various canopy height information and quadrat AGB stereo density from ground survey data, and obtaining forest features from airborne laser radar data; carrying out regression analysis on at least one of the various canopy height information and the quadrat AGB stereo density and the forest features to obtain the AGB stereo density of the flight area; stepwise linear regression analysis based on the regional scale is carried out on the AGB stereo density and the target parameters of the flight area to obtain an AGB stereo density estimation result, and a regional scale AGB estimation result is determined according to the AGB stereo density estimation result, the various canopy height information and the corresponding pixel areas. According to the method, planar AGB density calculation is converted into three-dimensional AGB density estimation, and the accuracy of the forest above-ground biomass estimation result in a complex scene is improved.

The invention belongs to the technical field of electrical equipment detection, and discloses a defect image enhancement method fusing reasoning and generation, which integrates visible light, infrared and laser radar data through a multi-modal feature fusion network, breaks through the limitation that a contrast file CN114281093A only depends on a visible light image, and improves the detection accuracy. The dynamic attention mechanism can flexibly deploy visual, spatial and semantic feature weights according to defect types, key features can still be captured in complex environments such as strong light and shielding, and meanwhile, the spatial form of the defects is analyzed by means of three-dimensional point cloud; by means of the design, missing detection caused by insufficient characteristics of tiny parts such as hardware fittings and pins is effectively avoided. Aiming at the problem of distortion of a sample generated by a traditional data enhancement method in a comparison file, the sample quality is guaranteed through double mechanisms of reasoning constraint and physical verification, defect features output by a reasoning model directly constrain feature distribution of the generated sample, and meanwhile, a material mechanics rule is introduced to verify the physical rationality of the generated sample.

The disclosure provides an improved canopy height correction method. The method includes: obtaining GEDI LiDAR data, airborne canopy height data, GDEM with high resolution and land cover product within the selected target area and timeframe; performing quality filtering and spatial-scale filtering on GEDI footprints; extracting laser pointing parameters and waveform parameters; extracting reference canopy height from airborne data for each footprint; extracting laser pointing parameters and waveform parameters; preprocessing the GDEM and calculating topographic parameters, including topographic variability index (TVI); constructing the Laser Pointing and Topographic Index (LPTI) according to the 3D forest-ground geometry model; inputting the waveform parameters, even topographic parameters, TVI and LPTI as independent variables, and the reference canopy height as the dependent variable to modeling an improved forest canopy height extraction, and utilizing the improved canopy height extraction model to correct the twofold influence of topographic on GEDI canopy height extraction.

Techniques for estimating a ground plane based on lidar data and / or attributes of the ground plane are discussed herein. A vehicle captures radar data, e.g., 4D radar data including height information, as it traverses an environment. The radar data can include direct returns from an object and reflected or multipath returns, e.g., that reflect off a ground surface and the object. A position of the ground plane can be estimated based at least in part on a distance between direct returns and the reflected returns. Attributes of the ground plane may be determined from differences between the direct returns and the reflected returns.

Techniques for selectively illuminating regions of an environment are disclosed herein. For example, an autonomous vehicle can include one or more emitter systems (e.g., a headlight(s)) comprising an array of light emitters configured to controllably emit light into an environment. In some examples, a machine learned model(s) may generate configuration signals to control the individual light emitters of an emitter system based at least in part on one or more of sensor data (e.g., lidar data, image data, etc.). In some examples, the machine learned model may generate configuration signals based at least in part on map data. Additional sensor data may be captured after the emitter system is reconfigured and used to control the autonomous vehicle.

The invention relates to the technical field of ecological environment protection, in particular to a mangrove forest carbon sink monitoring and metering method based on an unmanned aerial vehicle, a radar and an AI technology, and the method comprises the steps: 1, obtaining the laser radar data of a mangrove forest through a laser radar carried by the unmanned aerial vehicle; step 2, acquiring elevation data in a mangrove forest vegetation layer area, and obtaining point cloud data after topographic error correction; 3, obtaining a multispectral image of the mangrove forest, and obtaining a multispectral data matrix; 4, identifying forest growth data features, constructing a mangrove forest carbon sink prediction model, and predicting the mangrove forest carbon sink amount; step 5, marking the image region with the NDVI value higher than a preset NDVI threshold value as a blade over-dense region; and according to the area of the overdense leaf region and the multispectral data matrix, calculating a light depression factor by using a photosynthetic depression factor formula, determining the carbon sink deviation of the overdense leaf region by using a regional carbon sink deviation formula, and obtaining a real carbon sink value of the mangrove forest according to a carbon sink calculated value obtained by prediction.

The invention discloses a forest patrol method and device based on an unmanned aerial vehicle, electronic equipment and a medium, and relates to the technical field of forest resource management. The unmanned aerial vehicle carrying a laser radar and image acquisition equipment is controlled to acquire initial laser radar data and initial image data according to a preset flight route; the three-dimensional perception of the complex three-dimensional environment of the forest is realized, and the concealment abnormity is effectively captured. Performing data preprocessing on the initial laser radar data and the initial image data to generate target laser radar data and target image data; and carrying out feature fusion on the target laser radar data and the target image data. Through data preprocessing and multi-source data fusion analysis, the precision of capturing subtle anomalies is improved, and the limitation of a single sensing means is overcome. And finally, forest anomaly recognition is performed based on the fusion features, the geographic information system data and the multi-source sensor data, so that the comprehensive sensing capability of forest anomaly is comprehensively improved, and the forest patrol effect is optimized.

The invention discloses a large-scale forest land carbon reserve estimation method and system based on an active and passive remote sensing technology. The method comprises the following steps: acquiring satellite-borne laser radar data of different sensors in a research area, SAR data of an L wave band and a C wave band, multispectral remote sensing image data, airborne laser radar data, topographic data and land coverage category data containing forest land; discontinuous combined spaceborne laser radar canopy height products are obtained by using spaceborne laser radar data of different sensors; improving a geographic weighted regression model to estimate the canopy height of a continuous scale; extracting polarization parameters by using C-band SAR data, extracting vegetation indexes and texture indexes by using multispectral remote sensing image data, constructing characteristic variables together with topographic data, and screening the characteristic variables based on a variance reduction criterion; and constructing an overground carbon reserve inversion model, and carrying out large-scale forest land carbon reserve estimation. According to the method, the forest land carbon reserve estimation precision of the large-scale regional broken plot is improved.

The invention relates to a self-adaptive control method for a rain and snow mode of rail transit, electronic equipment and a medium, and the method comprises the steps: comprehensively studying and judging a rain condition based on multi-sensor data and numerical weather forecast data, and calculating a weather grade in the rain and snow mode, the multi-sensor data including video detection data, laser radar data and rainfall data; whether a rain and snow mode is set or not is judged according to the weather level, if yes, the current track slip degree is evaluated according to the multi-sensor data, and the GEBR value is adaptively updated based on the slip degree; the CC calculates the running safety braking envelope of the train by using the updated GEBR value, and feeds back a slip detection result and a dynamic parameter adjustment result in real time; and the ATS dynamically adjusts the operation plan of the train according to the slip detection result reported by the CC, and optimizes the operation scheduling of the whole train. Compared with the prior art, the method has the advantages that self-adaptive management of the rain and snow mode is achieved based on the dynamically-adjusted GEBR, and the running safety and reliability of the train in the rain and snow weather are effectively improved.

The invention discloses a visibility inversion method based on millimeter wave cloud radar and laser radar data fusion, and relates to the technical field of meteorology, and the method comprises the steps: guiding a millimeter wave cloud radar and a laser radar to carry out data correction and equivalent relation construction through employing a fog drop particle size distribution function measured by a fog drop spectrometer in a sample scene in advance; and then applying the correction coefficient and the equivalent function relationship to a target scene to perform multi-source data correction and fusion on the millimeter wave cloud radar and the laser radar and invert visibility. The method can fuse complementary advantages of the laser radar and the millimeter wave cloud radar; the introduction of the fogdrop particle size distribution function effectively avoids the distribution hypothesis of fogdrop shapes in the traditional model, can weaken the seasonal drift of the traditional empirical coefficient, significantly improves the accuracy and reliability of visibility inversion, and achieves the high-precision visibility monitoring under various weather conditions from clear sky to dense fog.

The invention relates to the technical field of three-dimensional real-time wind speed measurement, and discloses a large-span roof three-dimensional ultrasonic anemometer and a measurement method thereof, and the method comprises the steps: building a three-dimensional coordinate system through laser ranging, and analyzing and compensating installation errors; an initial calibration coefficient is generated through a self-inspection and optimization algorithm, and the initial calibration coefficient is compared and analyzed with a standard instrument for initial calibration; ultrasonic pulse emission is controlled, full-path scanning and redundancy measurement of all axes are completed, signal quality is improved through multi-modal signal processing detection, and abnormal values are eliminated through weighted median values; the sound velocity is corrected based on real-time temperature data, the influence of humidity and air pressure on the sound velocity is adjusted through a nonlinear regression model, and a Reynolds stress correction term is introduced to compensate for sound wave path bending in an eddy current field; a three-dimensional turbulence intensity distribution diagram is constructed by fusing ultrasonic and LiDAR data, meteorological parameters are calculated, an extreme weather event is early warned by using a machine learning model, a visual three-dimensional wind speed field is provided through a cloud platform, and a potential risk area is identified.

The invention discloses a remote sensing image classification method based on multi-modal data fusion and a storage medium, and the method comprises the steps: collecting multi-source data which comprises a multispectral image, a hyperspectral image, laser radar data and open source map data; performing preliminary feature extraction on the multispectral image, the hyperspectral image and the laser radar data by using a CNN (Convolutional Neural Network); extracting primary features of open source map data by using GNN; the extracted multi-modal features are processed and fused through a multi-head attention mechanism, and the mutual relation between the different modal features is captured; a Transform encoder backbone network capable of realizing position embedding is designed, features of different modes are integrated and mapped to a unified feature space, and the space recognition capability of the features is kept. By improving the fusion efficiency and feature extraction capability of the multi-modal data, a new thought and framework are provided for accurate classification of remote sensing images, and the method has a wide application prospect.