166 results about "Hyperspectral image processing" patented technology

The invention relates to the technical field of image processing, in particular to a tongue image feature analysis method and system. The method comprises the following steps: acquiring lingual surface multi-modal image data including a hyperspectral image, a visible light image and a dynamic tongue image; performing high-frequency component amplification processing on the visible light image and the dynamic tongue image; respectively extracting tongue regions from the hyperspectral image, the processed visible light image and the dynamic tongue image, and carrying out image registration on the extracted tongue regions; performing feature extraction on the registered tongue region in the multi-modal image data of the lingual surface by using a deep neural network to obtain a tongue spectral feature, a static tongue feature and a lingual fibrillation feature, and performing fusion to obtain fused tongue image feature data; and the deep neural network is adopted to analyze the fused tongue image feature data, and the traditional Chinese medicine analysis result of the current tongue image is predicted, so that the dependence on a complex network structure is reduced, and the fusion effect of the tongue features and the accuracy of the analysis result are improved.

The invention discloses a hyperspectral unmixing method of a multi-scale collaborative attention network based on an initialized end member, and the method comprises the steps: an abundance estimation branch module extracts the spatial features and spectral features of an original hyperspectral image through a sequence module, and carries out the fusion of the spatial features and spectral features; the multi-scale collaborative attention module performs spatial enhancement and channel feature representation on the features output by the sequence module to obtain an estimated abundance matrix; the end member estimation branch module processes an original hyperspectral image through a vertex component analysis method to obtain an initialized learnable end member matrix, and optimizes the learnable end member matrix to obtain an estimated end member matrix; carrying out joint training on the estimated abundance matrix and the estimated end member matrix; in the training process, matrix multiplication is carried out on the estimated abundance matrix and the estimated end member matrix to obtain a reconstructed hyperspectral image, and a loss function is used to adjust the network parameter weight to optimize the network unmixing effect. According to the method, the problem of insufficient degree of freedom of flexibility of end member estimation can be solved, and spatial information and spectral information existing in the unmixing process are utilized.

The invention relates to the technical field of satellite-borne hyperspectral image processing and analysis, and solves the technical problem that the huge spectral and spatial resolution difference between low-resolution hyperspectral data and high-resolution multispectral data cannot be fully considered in the existing method. The forest hyperspectral satellite image-oriented deep and shallow double-branch super-resolution method comprises the steps of constructing a double-branch network architecture, performing feature fusion reconstruction on output features of the double-branch network architecture, and obtaining high-resolution hyperspectral data with low spectral variation characteristics of forest vegetation in spaceborne hyperspectral image data. According to the method, the problem of modal difference between low-resolution hyperspectral data and high-resolution multispectral data is effectively solved by learning on different feature levels and scales, and the model is enabled to pay more attention to low-spectral variation characteristics of different forest vegetation in a satellite image through a plurality of feature attention mechanisms. And the requirements of subsequent fine monitoring tasks of various forest resources can be met.

The invention discloses a method and a device for multi-scale fusion of a hyperspectral image and a multispectral image in the technical field of hyperspectral image processing, and aims to solve the problems of insufficient retention of spectrum and spatial information of a fusion result and poor spatial resolution when the hyperspectral image and the multispectral image are processed in the prior art. The image acquisition unit acquires a hyperspectral image and a multispectral image; splicing and fusing the hyperspectral image after up-sampling and the multispectral image to obtain a fused hyperspectral image; performing feature extraction on the fused hyperspectral image to obtain shallow spectral spatial features; performing wavelet transform on the shallow spectrum spatial features to obtain a multi-scale sub-band feature map; multi-scale feature extraction is achieved through wavelet transformation, the local feature extraction module is added to the Mamba module, spectral information and spatial information are fully obtained, multi-scale fusion of a hyperspectral image and a multi-spectral image is achieved, feature extraction precision is improved, and an image with higher quality is obtained.

The invention provides a multi-source remote sensing data classification method, which belongs to the field of hyperspectral image processing in the field of remote sensing, and comprises the following steps: acquiring remote sensing data of various target objects; extracting shallow layer features of each kind of remote sensing data; obtaining a plurality of frequency characteristics of each kind of remote sensing data; fusing the same frequency features of all remote sensing data to obtain a plurality of same frequency fusion features; splicing the plurality of same-frequency fusion features to obtain a multi-source fusion feature; enabling the multi-source fusion features to sequentially pass through a frequency modulation layer and an attention layer which are superposed to obtain fused global features and local features; and weighting the global features and the local features in the spectral dimension to obtain a prediction classification result of the target object. According to the method, directional frequency characteristic decomposition and fusion of the multi-source data are realized, the multi-source fusion characteristics are extracted based on the multi-source remote sensing data to serve as the basis of classification, more comprehensive information is provided for classification of target objects, complex ground object characteristics can be fully captured, and the classification result is more accurate.

The invention relates to the technical field of vision assistance, and discloses an anesthesia puncture positioning method and system based on vision assistance, and the method comprises the steps: accurately positioning an anesthesia puncture point through multi-view image fusion, hyperspectral image processing, image preprocessing, illumination equalization, edge enhancement, depth feature extraction and the like. The method comprises the following steps: firstly, constructing an image coordinate system, collecting a plurality of camera images, and obtaining a fused clear image through a designed multi-view fusion algorithm and distance calculation; and in combination with a hyperspectral image fusion algorithm, the image quality is further improved. Then, residual mapping filtering denoising and local histogram enhancement are used for illumination equalization, and the image contrast and edge details are enhanced; a convolutional neural network is adopted, interest point detection is carried out, a Hessian matrix is utilized to describe image second-order changes, and local depth features are extracted. And accurate positioning of an anesthesia puncture point is realized through a weighted soft voting classifier and a dynamic threshold method.

The invention relates to the technical field of hyperspectral image processing, and provides a deep-expanded spatial spectrum sparse memory hyperspectral sharpening fidelity method and system, and the method comprises the steps: carrying out the priori knowledge coding of a high-resolution hyperspectral image through a regularization technology, solving a target function of a hyperspectral panchromatic sharpening task through a semi-quadratic splitting method, and carrying out the processing of a hyperspectral image. A residual module is adopted to simulate a degradation operator, spectral fidelity and spatial fidelity sub-problems are solved through gradient descent iteration, and a sparse prior sub-problem is solved based on an iterative shrinkage threshold algorithm; the high-fidelity and high-resolution hyperspectral images are corrected through the spatial spectrum prior features, and the multi-stage reconstructed high-resolution hyperspectral images are fused through the cross-stage memory fusion network to obtain the high-resolution hyperspectral images. According to the method, the reconstruction precision of the image is improved, the calculation complexity is reduced, the extraction of the spatial spectrum combined prior features of the original image is realized, and lossless information transmission is realized.

The invention provides a hyperspectral anomaly detection method based on double-stage attention guidance and a state space model, which relates to the technical field of hyperspectral image processing and comprises the steps of scene background modeling based on an auto-encoding network, generation of a reconstructed background image and a reconstructed residual image. Carrying out target signal enhancement on the original hyperspectral data based on the reconstructed residual image to obtain attention enhancement data, carrying out target feature depth extraction by adopting a state space model based on the attention enhancement data, generating an abnormal semantic feature image, and fusing a background guide feature image and the abnormal semantic feature image to obtain a hyperspectral image; and an abnormal probability graph is generated through adaptive gating fusion, and collaborative optimization is carried out based on a multi-task loss function. According to the method, the internal contradiction of a single network architecture is fundamentally solved, the prior guiding capability of the reconstruction method and the strong feature representation capability of the state space model are fully combined, and the accuracy and reliability of hyperspectral anomaly detection are remarkably improved.

The invention discloses a blind hyperspectral unmixing method and system based on end member query design and a Transform attention mechanism, and relates to the field of hyperspectral image processing. The problems that a current simplified mixing mechanism is mainly a linear mixing model, ground feature abundance and corresponding end member accuracy are low, a deep learning blind hyperspectral unmixing method depends on good end member initialization, and unmixing performance is seriously reduced during end member initialization are solved. The method comprises the following steps: constructing an abundance mapping module, extracting features in a hyperspectral image, and performing abundance decoding on the features to form an estimated abundance image; mapping the abundance graph into abundance embedding; constructing a Transform module fitted by a hybrid mechanism, and combining end member query, reconstruction query and abundance embedding through the Transform module fitted by the hybrid mechanism to obtain reconstruction query of end member information and abundance information; the original hyperspectral image is remodeled according to the reconstructed query. The method is applied to the field of blind hyperspectral image unmixing.

The invention discloses a hyperspectral image classification method for cross-domain small sample learning based on diffusion enhancement prototype knowledge distillation, and belongs to the technical field of hyperspectral image processing. The method comprises the following steps: extracting a neighborhood data cube, aligning spectrums, dividing a support set and a query set, and applying a mask and enhancing noise; executing domain adversarial denoising and reconstruction tasks, aligning feature distribution, and outputting a pre-training encoder; decoupling features, capturing spectrum-space global and local dependency relationships, and calculating similarity between a query set and a category prototype; constructing a distillation framework to realize knowledge migration; optimizing model parameters, and introducing a signal-to-noise ratio to enhance loss suppression noise; and performing feature extraction by using the optimized student model to generate a hyperspectral image classification result. According to the method, the problems of domain offset, intra-class feature dispersion, inter-class boundary fuzziness, noise interference and the like are solved, and the classification accuracy in a small sample scene is improved.

The invention relates to a hyperspectral classification method and system based on wavelet spatial spectrum Mamba, and belongs to the technical field of hyperspectral image processing and deep learning. According to the method, a hyperspectral image cube is used as input, an image is divided into overlapped 3D small blocks, spatial and spectral characteristic decomposition is carried out on each small block at the same time, multi-resolution analysis is carried out on reconstructed characteristics by using classical Haar wavelets, long-range dependence is captured through a Mama network of a state space model, and finally the image is input into a classifier for classification. The method effectively balances the relationship between the network model performance and the calculation complexity, has the multi-scale feature extraction capability and the global modeling capability at the same time, can reduce the calculation resource consumption while remarkably improving the classification precision, and has excellent robustness and generalization capability.

The invention discloses a hyperspectral image classification method in the field of hyperspectral image processing, and aims to solve the technical problem of low recognition accuracy caused by difficult utilization of complex information in a hyperspectral image. The method comprises the following steps: firstly, removing useless information through preliminary feature extraction processing; space and spectral features are captured by using the characteristic of mutual learning activation between elements during KAN convolution operation processing, and the space and spectral features are amplified by using an adaptive attention mechanism, so that the occupation of useless information on computing resources is reduced; according to the adaptive attention mechanism, similarity between query and keys is calculated on the basis of Hamming distance, and the adverse effect of useless information can be reduced; response intensity of each local area in the feature map is adjusted in a self-adaptive mode through refocusing convolution, feature expression is controlled through the response intensity, mining of image depth detail information is achieved, complex spatial relation and texture information existing in the hyperspectral image are fully utilized, and classification efficiency and accuracy are improved.

The invention provides a hyperspectral image classification method fusing a hybrid multi-hop graph convolutional network, and belongs to the technical field of hyperspectral image processing, and the method comprises the steps: carrying out the dimension reduction processing of original HSI image data, and obtaining the HSI image data after the dimension reduction; segmenting the HSI image data after dimension reduction to obtain a superpixel segmentation result; inputting the original HSI image data into a convolutional feature pyramid network to obtain a first feature representation, and inputting the superpixel segmentation result into a hybrid multi-hop graph convolutional neural network to obtain a second feature representation; splicing the first feature representation and the second feature representation, and inputting the spliced feature representation into a mixed feature fusion module to obtain a fused feature; and inputting the features into a softmax classifier to obtain a final classification result. Local spatial-spectral features in the superpixel can be learned, long-distance associated information of the captured image can be captured, and rich multi-scale features and semantic information in the image can be effectively extracted; and higher classification precision is realized with less parameter quantity.

The invention discloses a hyperspectral image classification method based on a spectrum-space double fusion network, and belongs to the technical field of hyperspectral image processing methods, and the method comprises the following steps: step 1, hyperspectral image data set preparation, step 2, data preprocessing, step 3, hyperspectral image classification task, step 4, optimizer and loss function setting, and step 5, hyperspectral image classification task setting. According to the hyperspectral image classification method based on the S2DFT, the S2DFT has higher accuracy and generalization ability, and the hyperspectral image classification method is mainly applied to the aspect of hyperspectral image classification.

The invention relates to the technical field of hyperspectral image processing, in particular to a hyperspectral image classification model training method, system and device and a medium. The method comprises the following steps: acquiring a hyperspectral image data set; constructing a hyperspectral image classification model, and generating target images corresponding to the hyperspectral images through the hyperspectral image classification model; taking the hyperspectral image and the target image as binding training samples; and training the hyperspectral image classification model according to the binding training samples corresponding to the hyperspectral images to obtain a target hyperspectral image classification model. Through methods of multi-scale feature extraction, attention mechanism introduction, feature enhancement and the like, the features of the hyperspectral image can be extracted more comprehensively and accurately, and the classification accuracy is greatly improved; meanwhile, due to the lightweight model design, the parameter quantity and the calculation complexity are reduced, the operation efficiency is improved, the calculation resource requirement of the model can be reduced, and the model can be operated on resource-limited equipment.

The invention discloses a hyperspectral anomaly detection method based on background attention and anomaly suppression, and relates to the technical field of hyperspectral image processing, and the method comprises the following steps: S1, employing a pyramid similarity downsampling module to reduce the anomaly content in an image; s2, multi-scale background attention is calculated for the image after abnormity reduction; s3, performing pixel reconstruction on the obtained feature map through depth separable blind block convolution; and S4, using an l1 norm as a loss function, and using a reconstructed image difference to guide model training. And S5, reconstructing an image by using the trained model, and taking a reconstruction error as a detection result. According to the invention, a pyramid similarity down-sampling module is used for reducing the abnormal degree of an image; the multi-scale attention module is used for improving the attention of the network to the background; the depth separable blind block convolution shields the perception of the network on a central blind block, and reduces the possibility of abnormal reconstruction; the reconstructed image difference is used to determine an optimal training round.

The invention relates to a hyperspectral bacteria classification method based on lightweight deep learning and membership width learning, and belongs to the technical field of hyperspectral image processing and microbiological detection. The method comprises the following steps: collecting hyperspectral image data of food-borne pathogenic bacteria, and carrying out correction and region-of-interest extraction to obtain bacterial spectral data; the method comprises the following steps: preprocessing bacterial spectral data by using a fractional differential method, enhancing spectral features and suppressing noise to obtain enhanced spectral data, and inputting the enhanced spectral data into a lightweight deep network to extract multilevel space-spectral features to obtain depth features; inputting the depth features into a membership width learning module, and outputting a bacterial category classification result; wherein the membership width learning module comprises operations of defining a membership function, constructing a fuzzy score membership matrix and optimizing a width learning weight matrix. The objective of the invention is to solve the technical problems of insufficient feature extraction, outlier interference and high model complexity in hyperspectral bacterial classification in the prior art.

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 relates to a medical hyperspectral image classification method based on a lightweight model of an improved CNN network, and belongs to the technical field of hyperspectral image processing. The method comprises the following steps: firstly, carrying out black and white correction, wave band elimination, smooth dimensionality reduction and standardized preprocessing on a medical hyperspectral image data set, and then cutting a preprocessed medical hyperspectral image into overlapped 3D image blocks with a target category as a center; secondly, dividing a medical hyperspectral image data set into a training set, a verification set and a test set, constructing a lightweight architecture of an improved convolutional neural network, and learning spectral and spatial features; then, the learned features are input into a weight adaptive lightweight convolution module; and finally, a final classification result is obtained through Kolmogorov-Arnold Networks, and evaluation of classification precision is carried out in combination with an evaluation index and other models. According to the method, the parameter quantity and the calculation quantity of the model are reduced, meanwhile, accurate classification of the medical hyperspectral images can be achieved, and real-time detection can be carried out clinically.

The invention relates to a hyperspectral image classification method based on a residual spectrum and a multi-scale spatial feature extraction network, and belongs to the technical field of hyperspectral image processing, and the method comprises the following steps: S1, inputting a hyperspectral image, preprocessing the hyperspectral image, and dividing the hyperspectral image into training, verification and test sets; s2, performing initial convolution dimension reduction on the data; s3, mining spectral features of the hyperspectral image data from the dimension reduction features through a Ghost3D residual block and a spectral residual attention mechanism, and performing dimension conversion; s4, extracting spatial texture features from the spectral features by using a multi-scale spatial convolution block; s5, packaging the step S1 to the step S4 into a convolutional neural network model for training, iteratively training parameters in the model through a back propagation method, and stopping after the maximum number of iterations is reached to obtain a hyperspectral image classification model; and S6, finally, inputting the test set and the verification set into the hyperspectral image classification model for testing and verification, obtaining a classification label, and completing classification.

The embodiment of the invention provides a hyperspectral image processing method and device, a storage medium and computer equipment, and the method comprises the steps: solving least square regression to generate a channel filter coefficient matrix through employing an original hyperspectral image and a lossy compressed image, and transmitting the compressed image and the channel filter coefficient matrix to a decoding end, therefore, the decoding end improves the quality of the compressed image through the channel filter coefficient matrix, thereby obtaining a target image with the image quality similar to that of an original hyperspectral image, and improving the image quality under the condition of increasing a small amount of transmission data.

In remote sensing, hyperspectral (HS) images are acquired to study earth's surface. Processing of HS images through neural networks demands significant computational resources for both training and inference phases. The present disclosure addresses the unresolved problem of the conventional methods for reducing dimensions in hyper-spectral data and accelerating the training and inference of a model by applying approximate computing techniques. The approximate computing techniques leverage physical properties of a reflectance spectra. This makes the HS images interpretable across various applications. In the present disclosure, three reflexivity-based approximate computing techniques namely R-Hop(K), R-Top(N), and R-Proximity(N) are implemented. These reflexivity-based approximate computing techniques use spectral clustering methods that rely on reflectance values to capture inherent characteristics from hyperspectral images across diverse domains. Further, existing spatial dimension reduction techniques and a combination of spatial and spectral dimension reduction techniques are evaluated.

The invention discloses a multi-view hyperspectral image processing method capable of being used for ocean target analysis, and belongs to the technical field of hyperspectral image processing. According to the method, the spectral features and the spatial features of the hyperspectral image are extracted at the same time, and multi-dimensional information of data is effectively utilized. According to the method, AAP and SD algorithms are introduced, and dimensionality reduction is carried out on high-dimensional spectral data in a self-adaptive manner according to the characteristics of spectral bands. According to the method, an end-to-end deep learning framework is adopted, and spectral feature extraction, spatial feature fusion, unmixing and data reconstruction are integrated in the same network. The method can perform efficient unmixing and accurate classification on complex spectrum and spatial information in the multi-view hyperspectral image, is especially suitable for the fields of marine environment monitoring, resource exploration, environmental protection and the like, and has important application value in the aspects of spectrum separation and classification of complex oceans.

The invention relates to the technical field of hyperspectral image processing, and provides a hyperspectral image fusion method and system based on hyper-band aggregation and Dirichlet, and the method comprises the steps: obtaining an LRHS image through a remote sensing optical imaging system; fusing the LRHS image and the panchromatic image through a spatial spectrum data distribution fusion module to obtain a PANHS image; carrying out band aggregation on the LRHS through an aggregation algorithm, calculating a compression association graph according to a hyper-band, and extracting a current state feature according to a cyclic memory network; memory state characteristics are obtained through the Dirichlet auto-encoder module; fusion features are obtained through a cyclic memory network; integrating the fusion features into the PANHS image to obtain integrated features; and obtaining a hyperspectral image with high spatial resolution through the residual block. According to the method, the spatial resolution of the hyperspectral image is remarkably improved, meanwhile, the spectral consistency is kept, and technical support is provided for refined analysis and practical application of the hyperspectral image.

The invention discloses a hyperspectral image classification method in the field of hyperspectral image processing, and aims to solve the technical problems that complex spatial relation and texture information exist in hyperspectral images, and a conventional classification algorithm is difficult to fully utilize the information. The method comprises the following steps: a pulse neural network can adaptively extract more effective features and improve the sensitivity to hyperspectral data, and a dynamic threshold adjustment layer avoids manual setting of a fixed threshold and better adapts to the complexity of the hyperspectral data; the pulse neural network can effectively process spatio-temporal data by simulating dynamic processing characteristics of a biological nervous system, and the feature extraction layer highlights key features in binarized pulse signals, so that the classification performance of the key features is enhanced; according to specific information of each pixel, automatic binarization coding is carried out to form a pulse sequence, and better information fidelity is achieved; therefore, key features are fully extracted from the hyperspectral image, and classification of the hyperspectral image is realized.

The invention discloses a small sample hyperspectral image classification method and device based on sample expansion and a space-spectrum attention mechanism and a medium, and relates to the technical field of computer vision and hyperspectral image processing. The objective of the invention is to solve the problem of insufficient samples in hyperspectral image classification. The method comprises the following steps: extracting spectral features from a hyperspectral image by using a spectral attention module, and obtaining a feature block for enhancing the spectral features; calculating a spatial-spectral joint feature according to the feature block of the enhanced spectral feature by using a spatial attention module; and inputting the spatial-spectral joint features into a classifier to realize classification of the hyperspectral image. The method can effectively improve the classification precision under the condition of limited training samples, and is suitable for various hyperspectral image processing scenes such as agricultural remote sensing, ecological monitoring, target recognition and the like.

The invention discloses a spectral image detection model, a detection method and an on-chip calculation camera processor. The spectral image detection model comprises N KAM blocks connected in series and a classifier block connected behind the N KAM blocks. The KAM block comprises a depth separable convolution layer, a batch normalization layer, an improved triple attention layer and a ReLU activation function layer which are connected in sequence; the depth separable convolution layer is used for extracting image features, and the improved triple attention layer is used for enhancing information interaction in the feature maps and information interaction between the feature maps; the classifier block comprises a depth separable convolution layer, a batch normalization layer, a common convolution layer and a Sigmoid activation function layer which are connected in sequence. The spectral image detection model provided by the invention has the characteristics of light weight, small calculation amount and the like, and can be deployed in a camera processor in a camera so as to meet the hyperspectral image processing requirements of a mobile end and an edge end.

The invention discloses a perception method based on multi-semantic space attention and Daubechies wavelet double-branch Mama, and belongs to the field of hyperspectral image processing. The problem that in the existing Mama-based model feature extraction process, the capacity of capturing multi-scale local structures and direction sensing information is insufficient is solved. The method comprises the following steps: inputting a hyperspectral image; projecting the spectral vector to an embedding space through an embedding layer to obtain an embedding feature; inputting the embedded features into an encoder, wherein the encoder comprises an SMSAMama branch, a DWTMama branch and a self-adaptive feature fusion module; the SMSAMama branch is used for extracting spatial features; the DWTAMba branch is used for extracting spectral features; the adaptive feature fusion module performs weighted integration on the spatial features and the spectral features by using randomly initialized fusion weights; and inputting the integrated features into a segmentation head to generate a final perception result. The method is used in agricultural monitoring and urban planning fields.

The invention discloses a hyperspectral image classification method based on spectral feature reconstruction, and belongs to the technical field of hyperspectral image processing, and the method comprises the steps: S1, collecting an original hyperspectral image block # imgabs0 #; s2, constructing a spectrum space feature reconstruction reversible fusion network, wherein the spectrum space feature reconstruction reversible fusion network comprises FIR, SSIF, SP and TE; s3, inputting the # imgabs1 # into FIR (Finite Impulse Response) to generate reconstruction features; s4, inputting the reconstructed features into the SSIF to generate enhanced features; s5, inputting the enhanced features into the SP to generate a semantic mark sequence; s6, inputting the semantic marking sequence into TE, and generating # imgabs2; according to the hyperspectral image classification method based on spectral feature reconstruction, lossless transmission of difficult sample features is realized, distinguishing feature expression of mixed pixels is enhanced, and classification balance of few sample categories is improved.

The invention discloses a hyperspectral image segmentation method and device based on fusion point prompt and Markov diffusion, and relates to the technical field of hyperspectral image processing. The method comprises the following steps: performing spectrum-space dimension reduction processing according to hyperspectral initial data; on the basis of preset uniform distribution points, according to the spatial partitioning features, a spectrum-spatial feature adaptation module is used to carry out point prompt guided coarse segmentation; based on a cross double-attention mechanism, using a multi-modal fusion module to perform text-image feature fusion; performing multi-scale feature extraction by using a U-net encoder according to the hyperspectral initial data; diffusion reconstruction is carried out based on a symmetric codec convolutional network of a Markov diffusion model, and de-noised hyperspectral features and high-order fusion masks are extracted; and based on a cross entropy loss function, performing model optimization according to the segmentation prediction data. The hyperspectral image segmentation method is based on the text semantic features, fully considers the characteristics of the hyperspectral image, and is high in efficiency and robustness.