161 results about "Spectral dimension" patented technology

The invention relates to a multispectral image and hyperspectral image fusion method and system, and belongs to the field of deep learning and signal processing, and the method comprises the steps: carrying out the coding and feature extraction of a multispectral image and a hyperspectral image through employing a coder based on a spectrum self-attention mechanism; the hyperspectral image features and the multispectral image features obtained by the encoder are input into a space-spectrum fusion module, deep fusion of the spatial dimension and the spectral dimension is carried out, and unified feature representation is obtained; inputting unified feature representation obtained by fusion into a decoder based on a spectrum self-attention mechanism, inputting layered features passing through a graph-based spectrum sensing module into a corresponding decoder symmetric layer, and then decoding and outputting to obtain a spectrum image with high spatial resolution and a spectrum image with high spectral resolution; through the above strategy, full fusion and complementation of spectral image space information and spectral information are ensured, and the method has important value for research and application of MHIF.

The invention relates to the technical field of power distribution station inspection, and discloses a power distribution station automatic inspection method based on image recognition. According to the method, multi-spectral image data of multiple areas in a power distribution station are collected in real time, and a multi-channel feature tensor of an equipment state is generated through a feature extraction network; performing feature fusion of space and frequency spectrum dimensions on the multichannel feature tensor by using a multi-scale convolutional attention network, and outputting an enhanced device feature map; inputting the data into a cascade anomaly detection module, positioning an equipment surface defect region by adopting a region segmentation algorithm, and analyzing and generating a defect evolution trend vector in combination with time sequence characteristics; on the basis of the vector, probability distribution of equipment fault risks is predicted through a space-time propagation model, and a dynamic risk field is generated; and finally, constructing a self-adaptive early warning decision tree for the dynamic risk field, and generating an inspection maintenance instruction according to risk probability threshold grading. According to the method, automation and intelligentization of power distribution station inspection are realized, and support is provided for efficient maintenance of the power distribution station.

The invention discloses an ultra-high-speed imaging device based on acousto-optic filtering modulation. The ultra-high-speed imaging device comprises a spectrum modulation system, a spectrum imaging system and a data processing system. The spectrum modulation system utilizes an acousto-optic tunable filter (AOTF) to dynamically modulate broadband continuous spectrum light, narrow-band illumination light which rapidly changes along with time is generated, and time information of a dynamic scene is effectively mapped to a spectrum dimension. And the spectral imaging system images the spectral coded dynamic scene to the hyperspectral camera to realize acquisition of spectral space-time information. The data processing system performs spectral crosstalk correction, channel separation and demosaicing reconstruction on the acquired original mosaic image, and recovers a time sequence image according to a spectrum-time mapping relation, thereby realizing single-shot superspeed imaging in a dynamic process. The device has the advantages of being simple and compact in structure, flexible in time window, high in imaging fidelity and the like, and has wide application prospects in the fields of rapid dynamics such as microfluidics, laser processing and ultrafast physics.

The invention relates to the technical field of image recognition, in particular to a red tide algae recognition method based on a hyperspectral image, and the method comprises the following steps: calculating a gradient value of each pixel in a spatial dimension and a spectral dimension according to an original hyperspectral data cube, setting a diffusion coefficient for diffusion, and obtaining a three-dimensional fidelity hyperspectral data cube. According to the method, the gradient change trends of the spatial dimension and the spectral dimension are extracted at the same time pixel by pixel, and the regional differentiation diffusion operation is matched, so that the expression ability of the alga plaque boundary and the consistency of the internal spectral characteristics are enhanced, and the fidelity of the hyperspectral data in fine-grained region identification is improved; upper convex hull calculation of a spectral reflectivity curve and construction of a continuous spectrum background baseline are introduced, and characterization of pigment absorption morphological characteristics is enhanced; and in combination with the characteristic absorption wave bands of chlorophyll and phycobiliary, the synergistic weighted response to the distribution of the algae pigment is realized, and the sensitivity and selectivity of pigment recognition are improved.

The invention provides a hyperspectral image reconstruction method and device based on high compression ratio snapshot compression and a readable storage medium thereof, and an end-to-end reconstruction method based on a lightweight space-spectrum aggregation block (SSAB). The SSAB includes a packet hybrid space module (GHSB), a bi-directional patch spectrum module (BPSB), and a gated feedforward network (GFFN). The GHSB performs multi-direction scanning along channel grouping, compensates information isolation through residual connection, and efficiently models spatial dependence; the BPSB divides the features into blocks and then splices the blocks along the spectral dimension, and spectral context dependence is captured through bidirectional scanning; the GFFN enhances cross-band nonlinear interaction through a gating mechanism, and optimizes space-spectrum feature fusion. According to the method, high-precision hyperspectral image reconstruction is realized in a high-compression-ratio scene, the calculation complexity and the parameter scale are reduced, the reconstruction efficiency and quality are effectively improved, and the method is suitable for unmanned aerial vehicle remote sensing, real-time monitoring and other scenes with limitation on calculation resources.

The invention relates to the technical field of hyperspectral image processing, in particular to a hyperspectral image classification model. The objective of the invention is to solve the problems of computation complexity and performance bottleneck in hyperspectral image processing. The model can be applied to hyperspectral image analysis tasks in the fields of remote sensing, environment monitoring, resource exploration and the like. Efficient dimension reduction processing is carried out by adopting random Fourier feature nonlinear principal component analysis (RFF-NLPCA), redundant information is effectively reduced, and the calculation speed is increased. A lightweight space SSM Block module and a spectrum SSM Block module are introduced into the model, and the image classification precision and robustness are improved through feature modeling of the space dimension and the spectrum dimension. The gating fusion module (GFM) optimizes the fusion capability of space and spectral features, and improves the discrimination capability of feature expression. Finally, the model can efficiently process high-dimensional hyperspectral data, provides a more accurate classification result, has relatively low calculation overhead and relatively high performance, and is particularly suitable for processing large-scale hyperspectral image data.

The invention discloses a hyperspectral image particle segmentation method and device, relates to the field of image processing, and is used for improving the accuracy of particle segmentation according to a hyperspectral image. The method comprises the steps that a local area corresponding to pixels is selected, a preset matrix of the pixels is constructed, the preset matrix is formed by covariance of any two spectral vectors in spectral vectors of the pixels in the local area corresponding to the pixels, and whether the pixels are candidate edge pixels or not is judged according to the characteristic value condition of the preset matrix; compared with the existing edge detection method which only utilizes the spatial gradient information of the image, the method has the advantages that the accuracy of edge pixel detection can be improved by judging whether the pixel is the candidate edge pixel or not through combining the characteristics of the spatial dimension and the spectral dimension; and the particle region is further segmented according to the candidate edge pixels, so that the edge pixels are detected by combining the features of the spatial dimension and the spectral dimension and the particle region is segmented according to the edge pixels, and the accuracy of performing particle segmentation according to the hyperspectral image can be improved.

The invention relates to a spatial spectrum dimension scanning method, in particular to a Mamba spatial spectrum dimension scanning method for a hyperspectral image classification task, which comprises the following steps of: 1, for an input hyperspectral image tensor, performing rotation and turnover construction on an input image through four spatial directions to obtain a hyperspectral image tensor; step 2, performing interval snakelike scanning on the view in each direction; performing interval snakelike scanning: reserving pixel points in even columns in even rows; pixel points of odd columns are reserved in odd rows, and the sequence of the selected pixels in the row is reversed so as to simulate the scanning characteristic of the snakelike path. And the feature expression capability and the calculation efficiency in a hyperspectral image classification task are improved. A scanning mechanism of jump sampling and snakelike traversal is introduced in the spatial dimension, redundant sampling in the spatial dimension can be effectively reduced, spatial structure information of the image is reserved, and the classification precision of the hyperspectral image is improved on the premise of ensuring the integrity of the image spectrum and the spatial information.

The invention provides an intelligent cashmere doping content judgment system utilizing multi-mode Raman spectrum characteristics, and relates to the technical field of intelligent spectrum analysis. The cashmere doping content intelligent judgment system utilizing the multi-mode Raman spectrum characteristics comprises a data acquisition module, a multi-wavelength laser excitation unit is used for carrying out space scanning on a sample, time sequence Raman spectrums under different polarization configurations are synchronously acquired, and the time sequence Raman spectrums are analyzed; multi-dimensional original data including space coordinates, a time sequence, spectral intensity and a polarization state is formed, and an original multi-modal data set is generated. Through multi-wavelength laser space scanning and polarization time sequence synchronous acquisition, a multi-dimensional original data set containing space coordinates, a time sequence, spectral intensity and a polarization state is constructed, the dimension limitation of a traditional spectrum is broken through, and a three-dimensional convolution kernel is adopted to perform synchronous sliding processing in space and spectrum dimensions, so that the spectrum intensity and the polarization state are obtained. And the spatial distribution rule and multi-mode spectrum correlation characteristics of the doped region are directly captured.

The invention relates to a multi-source remote sensing cooperative system based on an unmanned aerial vehicle formation and a control method, and the system can synchronously collect laser radar point cloud data, multispectral images, thermal infrared images and hyperspectral images, and breaks through the limitation of single data dimension caused by the fact that a traditional single unmanned aerial vehicle platform can only carry a single sensor. Meanwhile, the formation control module controls the heterogeneous unmanned aerial vehicle cluster to form a preset formation and perform cooperative flight to ensure spatial position cooperation of the unmanned aerial vehicles in the operation process, and the task allocation module dynamically allocates route tasks and sensor working parameters to the unmanned aerial vehicles based on target area environment information. And the data fusion module performs geometric registration, spectrum fusion and three-dimensional reconstruction processing on the multi-source remote sensing data acquired by each unmanned aerial vehicle to generate a three-dimensional spectrogram of the target area, so that accurate integration of the multi-source data in space and spectrum dimensions is realized, and the multi-source remote sensing data is acquired. Therefore, the system gives consideration to large-range area coverage capability and high monitoring precision.

The invention discloses a hyperspectral image and laser radar data fusion classification method based on an improved attention mechanism. The method comprises the following steps: obtaining hyperspectral image data and laser radar elevation data to be classified; processing the hyperspectral image data through a spectral channel attention module to extract spectral features; processing the laser radar elevation data through an elevation space attention module to extract spatial features; inputting the spectral features and the spatial features into a double-feature fusion module for coupling to generate fusion features; image classification is completed based on the fusion features; according to the method, the image features of the hyperspectral image in the spectral dimension and the elevation information of the radar image in the spatial dimension can be fully extracted, and the representation capability of the model for the spatial features and the spectral features is enhanced.

The invention discloses a computing spectrum reconstruction method based on CS-Unet and a spectral imaging system. The calculation spectrum reconstruction method comprises two parts, namely TwIST pre-reconstruction and Unet coupling reconstruction, wherein the TwIST pre-reconstruction is used for preprocessing an initial coding spectrum image to generate a pre-reconstructed spectrum image; and the Unet part couples the pre-reconstructed image and the initial coding spectral image in the spectral dimension and inputs the coupled image and the initial coding spectral image into a network for fine reconstruction, and finally a target space-spectral image is recovered. The imaging system is composed of a spectral image coding module and a CS-Unet reconstruction module, a metasurface spectral modulator applied to the spectral image coding module is composed of 36 silicon-based all-dielectric structures, and rich spectral response is achieved by adjusting the period, the size and the direction angle of three basic C4 symmetric units, namely a round unit, a cross unit and a square unit. According to the method, high-robustness and high-imaging-quality spectrum reconstruction is realized in a visible light wave band (400-700 nm), and the method has relatively high engineering applicability.

The invention provides a hyperspectral tailing pond dry beach line intelligent analysis method, and belongs to the technical field of image processing. Through multiband characteristics of a hyperspectral remote sensing image, principal component clustering analysis and characteristic wavelength selection are combined, so that the problems of insufficient spectral information of the image after dimension reduction and serious data redundancy caused by use of a full-band image are solved; single-band images corresponding to different characteristic bands emphasize different target information in the original image, and different combinations are beneficial to fully exerting the advantages of different target information of each band, so that a water area and a dry beach are distinguished more accurately; a double-branch network model is adopted, the difference between spectral dimensions and spatial dimensions is synchronously analyzed, spectral features and spatial information are fused, and the two branches have certain complementarity, so that rich spatial spectrum information of an input hyperspectral remote sensing image can be fully excavated, a dry beach line can be identified more accurately and effectively, the length of the dry beach is calculated, manual intervention is reduced, and the working efficiency is improved. The treatment efficiency is improved.

The invention relates to a hyperspectral image super-resolution method and system based on spectral space decoupling attention, and aims to solve the contradictory problem of insufficient space-spectrum cross-dimension feature collaborative modeling and serious deep network calculation redundancy in the existing single-image super-resolution technology. According to the method, a double-stage decoupling attention mechanism and a feature multiplexing architecture are innovatively designed by constructing a superficial layer space spectrum unwrapping attention network (SSDAN): firstly, a space-spectrum decoupling attention (SSDA) module composed of cascaded banded space attention and grouped spectrum attention is adopted; through spatial dimension direction perception feature extraction and spectral dimension long-range correlation modeling, decoupling type cooperative expression of global spatial features and cross-band spectral features is realized; and secondly, constructing a cross-layer feature dynamic aggregation mechanism, and realizing high-precision reconstruction under an extremely shallow architecture only comprising two SSDA layers by strategically reusing intermediate features of a shallow network.

The application discloses a hyperspectral image Transformer network training and classification method, which first divides a hyperspectral image sample based on a spectral dimension to obtain a plurality of spectral subbands, wherein the hyperspectral image sample is an unlabeled training sample; each spectral subband is input into an embedding module to obtain local space-spectrum embedding features output by each embedding module, wherein the embedding module extracts space-spectrum features of the spectral subband at multiple scales; all local space-spectrum embedding features are fused according to the positions of the spectral subbands to obtain global space-spectrum embedding features; the global space-spectrum embedding features are input into a Transformer encoder, and a center region token is masked and reconstructed in a Transformer decoder to train the Transformer encoder in a self-supervised manner. Compared with the prior art, the unlabeled sample can be effectively utilized to improve the training effect of the Transformer network, and the hyperspectral image can be classified with high precision.

The invention belongs to the technical field of cleanliness detection, and particularly relates to a semiconductor adhesive tape surface cleanliness detection method and system based on Raman spectroscopy, and the method comprises the following steps: S1, obtaining a multi-spectrum image of the surface of a semiconductor adhesive tape; for each pixel point in the multi-spectrum image, calculating the weighted sum of the mahalanobis distance of the spectral dimension of the pixel point and the Gabor texture response of the spatial dimension to obtain a spatial spectrum-texture anomaly index; determining excitation points of the Raman spectrum based on the spatial spectrum-texture anomaly index, and collecting Raman spectrum data of each excitation point; s2, extracting a multi-spectrum feature vector and a Raman spectrum feature vector of the excitation point; according to the method, the full-view-field cleanliness distribution diagram is generated through interpolation based on the high-quality sparse measurement result with the confidence coefficient weight, comprehensive evaluation of the surface pollution condition of the adhesive tape is achieved, and the contradiction among detection efficiency, recognition precision and representation comprehensiveness of a traditional method is solved.

This invention relates to the field of optoelectronic detection technology and discloses an online detection system for screen color uniformity based on dynamic rotating polarization spectrum. The system includes an online transmission module for carrying and driving the illuminated screen under test to move continuously along a set direction at a set speed; and a combined optical encoding module, positioned above the screen under test, comprising a static spatial-spectral phase delay mask and a continuously rotating polarization modulator arranged sequentially along the beam propagation direction. By driving the screen to continuously translate using the online transmission module, and cooperating with the continuously rotating polarization modulator and hyperspectral acquisition module to acquire dynamic spatiotemporal aliasing data, the accuracy of the spectral dimension can be guaranteed. Furthermore, by extracting high-precision chromaticity parameter matrices and multidimensional polarization distortion feature matrices from the decoupled and reconstructed optimal polarization spectral tensor solution, the system's ability to detect complex internal quality problems can be significantly enhanced.

The invention discloses a mudflat soil salinity remote sensing inversion method, which comprises the following steps of 1, acquiring mudflat area remote sensing data and ground actually-measured soil salinity data; step 2, constructing a composite spectral index as a salt sensitive characteristic; step 3, performing multi-dimensional feature fusion on the salinity sensitive features to construct a salinity sensitive feature set, and constructing a multi-dimensional fusion feature vector data set including a spectral dimension, a spatial dimension and a statistical dimension; 4, constructing a small sample adaptive deep learning salinity inversion model with a three-layer progressive feature extraction architecture, and training the model through a multi-dimensional fusion feature vector data set; and step 5, performing inversion through the trained small sample adaptive deep learning salinity inversion model to generate a regional soil salinity spatial distribution map. According to the invention, through novel composite spectral index construction, a multi-dimensional feature fusion system, a sample equalization strategy and a small sample adaptive model, high-precision inversion of mud flat soil salinity is realized.

The application belongs to the technical field of ubiquitous computing. The application provides an end-side hyperspectral imaging and fine identification method for an open environment. The disclosure embodiment designs a spatial spectrum two-type modal encoder for extracting spatial spectrum features of RGB and NIR images and outputting a fused feature stream; a light hyperspectral imaging model is used to process the fused feature stream and reconstruct a hyperspectral image. A light decoupling loss function design is used to replace the original loss function of the light hyperspectral imaging model, and robust hyperspectral image imaging in an open environment is realized. An analysis module based on grouping attention is designed, different weights are assigned to different absorption peaks of different substances by grouping along the spectral dimension, and the huge calculation amount and calculation delay caused by full-band analysis are avoided. A mixed quantization method is used to reduce the calculation amount and storage amount of the model deployed on the end side without obvious decrease in imaging and analysis accuracy of the model.

The invention relates to the field of medical image analysis, in particular to a drug distribution and metabolism dynamic analysis system of a multispectral microscopic image, which comprises a light source module, a drug distribution module, a drug distribution module, a drug metabolism dynamic analysis module and a drug metabolism dynamic analysis module, and is characterized in that the light source module emits a multiband light source comprising broadband white light and time sequence switching narrow-band monochromatic exciting light; the data acquisition module is used for acquiring a multi-channel spectral image signal and generating a multi-spectral image containing a spatial dimension and a spectral dimension; the pharmacokinetic analysis module constructs a geometric characterization framework of drug metabolism based on a differential geometry theory, and comprises a Riemannian manifold characterization unit for mapping multispectral data to a Riemannian manifold space, a curvature tensor analysis unit for calculating manifold curvature characteristics and a parallel transmission optimization unit for evaluating drug transmission efficiency; the application analysis module carries out drug target co-localization analysis, space-time metabolic map analysis and delivery system optimization based on the analysis result, the spectrum channel limitation of traditional fluorescence imaging is broken through, and the precision and dimension of drug metabolism analysis are remarkably improved.

The present invention discloses a multi-scale hyperspectral image reconstruction algorithm and system from RGB images, which belongs to the field of computer vision hyperspectral images. The algorithm includes: processing the original RGB image through a multi-scale processing module, and outputting a feature map Y' i ; The feature map Y' i The feature image with multi-scale preprocessing information is added and stacked with the original RGB image itself in the spectral channel dimension to obtain a feature image with multi-scale preprocessing information; the feature image with multi-scale preprocessing information is passed through three spatial-spectral Transformer joint processing modules in sequence to jointly process the spatial-spectral dimensions to obtain a feature image with spatial-spectral feature information; the feature image with spatial-spectral feature information is processed through the spectral dimension Transformer to obtain a feature image with the spectral dimension feature information fully extracted by the Transformer; the feature image with the spectral dimension feature information fully extracted by the Transformer is passed through a 3×3 convolutional layer to adjust the channel dimension to the target 31-channel output, and finally a hyperspectral image is obtained.

The present invention discloses a scene-based push-broom hyperspectral image adaptive non-uniformity correction method, which automatically sorts each scan line of a band of a hyperspectral image from small to large according to the DN values ​​of different spatial dimension pixels, and adaptively selects at least one dark uniform area and bright uniform area of ​​the spatial dimension to obtain the correction coefficient of each spatial dimension pixel, thereby completing the non-uniformity correction of each spatial dimension; based on the spectral dimension characteristics, the spectral dimension non-uniformity correction is completed based on the non-uniformity correction result of the spatial dimension, and the spatial dimension non-uniformity correction is repeated based on the non-uniformity correction result of the spectral dimension, thereby completing the non-uniformity correction of the hyperspectral image. This method is fully automated and can break through the limitations of the scene. It uses spatial and spectral joint information to perform non-uniform correction, retaining the spatial structure information and spectral information of the hyperspectral image to the greatest extent, effectively improving the quality of the hyperspectral image, and is suitable for adaptive non-uniform correction of massive hyperspectral images in various complex scenes, with good versatility.

The invention provides a hyperspectral and multispectral image fusion method and system. The method comprises the following steps: acquiring hyperspectral and multispectral data of the same spatial region; performing up-sampling on the low-resolution hyperspectral image by adopting bilinear interpolation; one-dimensional wavelet transform is utilized to extract reflection peak and spectrum change characteristics in a spectrum dimension, two-dimensional wavelet transform is utilized to extract texture and edge information in a space dimension, and pixel-by-pixel wavelet basis adaptive selection is realized through Softmax gating; multi-granularity feature modeling is realized for the spectral branches by adopting grouped multi-scale convolution, and a self-adaptive weighting mechanism is formed for the spatial branches through global average pooling, a convolution layer and Sigmoid activation so as to enhance spatial details and compensate spatial feature loss by utilizing MSI; a cross-scale two-way attention mechanism is introduced, and long-range dependence modeling and information interaction of spectrum and spatial characteristics are achieved; and a high-resolution hyperspectral image is generated through a feature aggregation and reconstruction module.

The application relates to an abnormality detection method based on a hyperspectral image. The main body is based on a space-spectrum combined feature extraction method of filtering and low-rank decomposition to perform abnormality detection on the hyperspectral image. The specific method comprises the following steps: firstly, in the spatial dimension, a reduced dimension image is obtained through a data dimension reduction and eigenvalue weighted fusion method, and then an improved spatial filtering method is used to extract the spatial features of the image to obtain an initial spatial feature image. In the spectral dimension, a background reconstruction image of the approximate background is obtained by using a Tucker decomposition method on the original hyperspectral image, and a background dictionary of the image is obtained by using an improved k-means clustering method, then the background dictionary is input into a low-rank decomposition model to obtain a sparse matrix, and an initial spectral feature image is obtained, finally, the initial spectral feature image is fused with the spatial feature image to realize abnormality detection.

The present invention discloses a graph convolution fusion network for hyperspectral image classification, comprising: image data preprocessing, mainly comprising utilizing methods such as block partitioning, linear discriminant analysis and simple linear iterative clustering to divide segmentation and block data of different scales, and constructing a pixel-level graph structure based on the segmentation and block data; constructing a classification network, comprising a spectral conversion module, a block data graph convolution branch, a block data convolution branch, a segmentation data graph convolution branch, a block data graph convolution feature processing module, a segmentation data feature processing module and a feature fusion module; the block data graph convolution feature processing module improves pixel-level feature expression and enhances classification accuracy by combining a large convolution kernel convolution layer with neighborhood aggregation; the segmentation data feature processing module improves pixel-level feature expression and enhances classification accuracy by utilizing feature similarity weight aggregation; the feature fusion module learns the intrinsic connection between features through void convolution, improves feature fusion effect and enhances classification accuracy. The present invention designs a new convolution and graph convolution fusion neural network to perform hyperspectral image classification. First, block partitioning, linear discriminant analysis and simple linear iterative clustering are used to divide the segmentation and block data of different scales, and a pixel-level graph structure is constructed based on the segmentation and block data. Then, the spectral features of the segmentation and block data are extracted and their spectral dimensions are reduced through the spectral conversion module. Then, convolution and graph convolution are used to extract the spatial features of the segmentation and block data. Then, the block data graph convolution feature processing module is used to process the block data graph convolution features, and the segmentation data feature processing module is used to process the segmentation data features. Finally, the feature fusion module is used to adaptively fuse the features, and the fused features are finally classified.

The application discloses a hyperspectral remote sensing image recognition method and device based on spectral space feature coupling, and utilizes different linear spectral filters to perform feature extraction on the whole hyperspectral remote sensing image, so that multi-class spectral features are obtained. Compared with the traditional technology, the application does not need to perform spectral dimension reduction, thereby avoiding the problem that the traditional technology weakens the subtle spectral information and high-order spectral correlation contained in the hyperspectral data. Meanwhile, the application takes the minimization of image background energy as an objective function to optimize the optimal real spectral feature vector of each linear spectral filter to the target class. Based on this, when the constructed linear spectral filter is used for feature extraction, the background energy can be minimized while the target spectral response is maintained and enhanced, so that the spectral clutter and noise in the complex environment are suppressed, and thus the detection precision of the model in the complex environment background can be improved.

This invention discloses a method for classifying defects in patternless wafers based on multi-feature joint decision-making, belonging to the field of wafer defect detection technology. The method includes the following steps: irradiating the surface of a patternless wafer with a probe beam having a preset polarization state; acquiring spatial scattered light intensity information of the scattered light from the wafer surface under different combinations of polarization states based on a probe array distributed at multiple spatial angles; extracting local optical features of the candidate defect regions and constructing a feature tensor based on these local optical features; analyzing the candidate defect regions according to the polarization degradation evolution law of the feature tensor in the spectral dimension and outputting the defect classification result. This approach avoids the low classification accuracy caused by highly similar scattering features of small defects, significantly improving the accuracy of the detection results.

This invention discloses a hyperspectral target detection method based on adversarial autoencoders and attention mechanisms, comprising: performing coarse detection on an input hyperspectral image; obtaining background samples as clean as possible as training data by adjusting the binarization threshold of the coarse detection result image; training a model based on adversarial autoencoders and attention mechanisms using the prepared training data to obtain a model that can accurately reconstruct the background of the hyperspectral image; inputting a test hyperspectral image into the network for reconstruction; calculating the spectral distance between the reconstructed result and the original hyperspectral image pixel by pixel to obtain a distance map; and applying background suppression to the distance map to obtain the final detection result image. This invention introduces a spectral attention mechanism to assign weights to the spectral dimensions, accelerating the training and convergence speed of the network; and overcomes the problem of imbalanced positive and negative samples in hyperspectral images by selecting only background samples as training data to train the image reconstruction model based on adversarial autoencoders.

The invention discloses a hyperspectral remote sensing image recognition method and device based on spectral spatial feature coupling, different linear spectral filters are utilized to perform feature extraction of the whole hyperspectral remote sensing image so as to obtain multi-category spectral features, and compared with a traditional technology, the hyperspectral remote sensing image recognition method does not need spectral dimension reduction, and is high in recognition efficiency. Therefore, the problem that the correlation between fine spectral information and high-order spectrum contained in the hyperspectral data is weakened in the traditional technology is avoided; meanwhile, minimization of image background energy is used as a target function to optimize the optimal real spectral feature vector of each linear spectral filter for the target category, so that when the constructed linear spectral filters are used for feature extraction, the background energy can be minimized while the target spectral response is maintained and enhanced, and the target spectral response is improved. Therefore, spectral clutter and noise in a complex environment are suppressed, and the detection precision of the model in a complex environment background can be improved.

The application belongs to the technical field of remote sensing data processing, and discloses a hyperspectral and laser radar data joint ground feature classification method, equipment and medium, the method comprises the following steps: acquiring hyperspectral image data and laser radar elevation data; feature extraction is carried out by adopting a three-branch parallel structure, wherein the hyperspectral image branch extracts global spectral spatial features by three-dimensional convolution and bidirectional scanning along the spectral dimension, the laser radar branch extracts elevation structure features by multi-level convolution, and the multi-modal branch extracts multi-modal fusion features by early fusion and a multi-scale feature enhancement module; a multi-head bidirectional cross attention module is used to perform deep bidirectional interaction and fusion on the features extracted by the three branches, thereby generating a final fusion feature vector; finally, the final fusion feature vector is input into a classifier to obtain a classification result. The method realizes deep interaction between modes and adaptive perception of multi-scale ground features, and significantly improves the accuracy of joint classification.