3-D-CNN fusion improves high-resolution HS images from noisy MS and HS data.
problem Improving high-resolution hyperspectral images from noisy multispectral and hyperspectral data.
method 3-D-Convolutional Neural Network (3-D-CNN) for image fusion, followed by dimensionality reduction.
result The proposed method significantly reduces computational time and noise robustness compared to conventional methods.
Efficient deep learning for hyperspectral image classification using active learning.
problem Lack of good-quality labeled samples for deep learning in hyperspectral images.
method Weighted incremental dictionary learning for active selection of training samples.
result The proposed algorithm improves deep learning efficiency and effectiveness in hyperspectral image classification.
New algorithm clusters hyperspectral images at multiple scales.
problem Clustering hyperspectral images at various scales.
method M-SRDL algorithm using spectral-spatial diffusion distances.
result More accurate clustering labels achieved with spatial regularization.
A deep clustering method for hyperspectral images improves clustering performance by constraining intra-class distances.
problem Clustering performance degradation in hyperspectral images due to high dimensionality.
method Intra-class distance constrained deep clustering algorithm using auto-encoder network.
result The proposed algorithm outperforms state-of-the-art methods in clustering hyperspectral images.
A deep learning system classifies hyperspectral images using denoising autoencoders and pixel mixtures.
problem Hyperspectral image segmentation and classification challenges.
method Multiple class-based denoising autoencoders, mixed pixel training augmentation, and morphological operations.
result High performance on the Salinas dataset, verified by deep neural network and morphological hole-filling.
Ladder Networks improve semi-supervised hyperspectral image classification.
problem Semi-supervised hyperspectral image classification with limited labeled data.
method Jointly optimizing a supervised and unsupervised cost in a Ladder Network.
result Convolutional Ladder Network achieves state-of-the-art performance with minimal labeled data.
Deep learning for Venus images uses high-res hyperspectral data to simulate ground truth.
problem Lack of accurate ground truth data for training deep neural networks in remote sensing.
method Unmixing high-resolution hyperspectral images to simulate ground truth for training a CNN.
result The model can classify mid-resolution Venus images successfully.
SaR-SVM-STV improves hyperspectral image classification with shape-adaptive reconstruction and denoising.
problem Classifying hyperspectral images with limited labeled data.
method Shape-adaptive Reconstruction (SaR) for pixel preprocessing, SVM for probability estimation, and Smoothed Total Variation (STV) for denoising.
result SaR-SVM-STV outperforms SVM-STV with fewer labeled data.
MDGCN improves hyperspectral image classification by dynamically updating graphs.
problem Traditional CNNs struggle with irregular image regions and class boundaries.
method MDGCN uses dynamic graph convolution on hyperspectral images, adapting to local regions.
result MDGCN outperforms state-of-the-art methods on benchmark datasets.
Paper presents a graph-based semi-supervised method for hyperspectral image classification.
problem Hyperspectral image classification with limited labeled data.
method Novel superpixel algorithm based on spectral covariance matrix, followed by superpixel graph construction and classification.
result The method outperforms state-of-the-art approaches, especially in scenarios with minimal labeled data.
A 3-stage method enhances hyperspectral image classification accuracy.
problem Classifying detailed classes in hyperspectral images with limited labeled data.
method Uses Nested Sliding Window and PCA for spatial consistency, SVM for spectral estimation, and TV model for spatial smoothing.
result Our method outperforms state-of-the-art algorithms, especially in scenarios with small training sets.
Attention-based CNNs improve band selection in hyperspectral images.
problem Selecting informative bands from hyperspectral images for accurate classification.
method Attention-based convolutional neural networks reusing activations at different depths.
result Deep models with attention mechanisms achieve high-quality classification and identify significant bands.
Novel graph-based framework for hyperspectral image classification using superpixels.
problem High classification accuracy with limited labelled data in hyperspectral images.
method Superpixel method for defining local regions, spectral and spatial features extraction, contracted graph representation, semi-supervised classifier.
result Our approach produces accurate classifications with minimal labelled data, outperforming state-of-the-art techniques.
A novel framework combines deep metric learning and conditional random field for hyperspectral image classification.
problem Improving classification performance in hyperspectral image processing with limited labeled data.
method Combines spectrum-based deep metric learning and conditional random field. Uses center loss for spectrum-based features and Gaussian edge potentials for pixel-wise classification.
result Demonstrates advantages in classification accuracy and computation cost compared to classical methods.
Introduces NMF for hyperspectral imaging and discusses its geometry and complexity.
problem Constrained low-rank matrix approximation problems.
method NMF for hyperspectral imaging, geometry and uniqueness of NMF solutions, complexity, algorithms.
result Discussion on NMF's geometry and complexity.
In this article we give our contribution to the problem of segmentation with plug-in procedures. We give general sufficient conditions under which plug in procedure are efficient. We also give an algorithm that satisfy these conditions. We give an application of the used algorithm to hyperspectral images segmentation. …
Flexible band grouping and kernel fusion for hyperspectral image processing.
problem Large dimensionality in hyperspectral imaging.
method Non-contiguous and contiguous band grouping for dimensionality reduction; improved visual clustering; unsupervised clustering algorithms; diverse features via different proximity metrics and kernel functions; l∞-norm multiple kernel learning. result Heterogeneous features and kernels lead to performance gain.
JigsawHSI improves land-use classification using hyperspectral images.
problem Land-use land-cover classification in hyperspectral images.
method Convolutional Neural Network (CNN) tailored for geoscientific analysis, using Jigsaw architecture.
result JigsawHSI achieves state-of-the-art performance in land-use classification.
A new method clusters hyperspectral images using spatially regularized diffusion.
problem Clustering hyperspectral images effectively.
method Spatially regularized random walks and diffusion geometry.
result The method outperforms state-of-the-art algorithms on real data.
In hyperspectral images, some spectral bands suffer from low signal-to-noise ratio due to noisy acquisition and atmospheric effects, thus requiring robust techniques for the unmixing problem. This paper presents a robust supervised spectral unmixing approach for hyperspectral images. The robustness is achieved by writi…
This work presents a method to localize targets in hyperspectral images using robust PCA.
problem Localizing targets in hyperspectral images with correlated signatures.
method Modeling HS images as a low-rank plus sparse component, using generalized robust PCA.
result Recovery guarantees and experimental validation show the method's effectiveness.
Proposes a new method for hyperspectral image dimensionality reduction.
problem Highly correlated noisy hyperspectral images.
method Trace Lasso-L1 Graph Cut method using L1-norm for robustness and sparsity.
result Optimal projection matrix maximizing between-class dispersion to within-class dispersion.
Paper proposes a new method to handle spectral variability in hyperspectral unmixing.
problem Spectral variability within endmember classes affects unmixing performance.
method Adaptive bundles and double sparsity to promote sparsity on spectra and classes.
result Successfully determines variable number of classes and estimates their abundances.
When considering the problem of unmixing hyperspectral images, most of the literature in the geoscience and image processing areas relies on the widely used linear mixing model (LMM). However, the LMM may be not valid and other nonlinear models need to be considered, for instance, when there are multi-scattering effect…
New methods for hyperspectral unmixing handle intra-class variability.
problem Intra-class variability in hyperspectral images.
method Inertia-constrained Pixel-by-pixel NMF (IP-NMF) for handling variability.
result IP-NMF outperforms state-of-the-art methods in real data.
This paper addresses the problem of blind and fully constrained unmixing of hyperspectral images. Unmixing is performed without the use of any dictionary, and assumes that the number of constituent materials in the scene and their spectral signatures are unknown. The estimated abundances satisfy the desired sum-to-one …
MPRI learns multiscale features for HSI classification.
problem Hyperspectral image classification with limited training samples.
method MPRI combines PRI and regularized LDA for iterative feature learning.
result MPRI outperforms state-of-the-art methods in HSI classification.
Paper proposes ONTD for nonnegative tensor data.
problem Handling nonnegative tensor data efficiently.
method Orthogonal Nonnegative Tucker Decomposition (ONTD) with convex relaxation algorithm.
result Demonstrates effectiveness on real-world image data applications.
The nonnegative matrix factorization (NMF) is widely used in signal and image processing, including bio-informatics, blind source separation and hyperspectral image analysis in remote sensing. A great challenge arises when dealing with a nonlinear formulation of the NMF. Within the framework of kernel machines, the mod…
This paper improves land cover classification using global spatial features in CNN.
problem Limited classification accuracy and universality of traditional remote sensing image classification methods.
method Integrates global spatial features into a dual-branch CNN for hyperspectral/SAR imagery classification.
result The proposed method outperforms traditional single-channel CNN methods.
Optimal clustering framework selects bands for hyperspectral images.
problem Efficiently choosing representative bands in hyperspectral images.
method Proposes an optimal clustering framework (OCF) and rank on clusters strategy (RCS) for band selection.
result Significantly outperforms other methods on various data sets.
Unified analysis for robust PCA with applications to target localization in HS images.
problem Decomposing data matrices into low-rank and sparse components with known dictionaries.
method Unified convex demixing method for entry-wise and column-wise sparse structures, analyzing undercomplete and overcomplete cases.
result Successful recovery of constituent matrices under mild conditions on incoherence, sparsity, and rank.
Nowadays, hyperspectral image classification widely copes with spatial information to improve accuracy. One of the most popular way to integrate such information is to extract hierarchical features from a multiscale segmentation. In the classification context, the extracted features are commonly concatenated into a lon…
The paper classifies U.S. crop types using hyperspectral satellite imagery.
problem Classifying crop types from hyperspectral satellite imagery.
method Gaussian Bayesian models and neural networks applied to NASA data.
result Bayesian methods outperform standard LDA and QDA.
Incorporating spatial information into hyperspectral unmixing procedures has been shown to have positive effects, due to the inherent spatial-spectral duality in hyperspectral scenes. Current research works that consider spatial information are mainly focused on the linear mixing model. In this paper, we investigate a …
This paper presents an unsupervised algorithm for nonlinear unmixing of hyperspectral images. The proposed model assumes that the pixel reflectances result from a nonlinear function of the abundance vectors associated with the pure spectral components. We assume that the spectral signatures of the pure components and t…
A new method classifies hyperspectral images using dynamic graph convolutional networks.
problem Complex spatial context in HSI classification leads to inaccurate results.
method Develops a GCN-based method that captures long-range contextual relations and refines graph edges.
result Significant improvement in HSI classification performance compared to state-of-the-art methods.
New methods detect targets from imprecisely labeled hyperspectral data.
problem Challenges in acquiring labeled hyperspectral data.
method Multi-Target MI-ACE and MI-SMF methods that learn target signatures from imprecisely labeled samples.
result Effective at learning target signatures and performing target detection.
Dictionary learning algorithms have been successfully used in both reconstructive and discriminative tasks, where the input signal is represented by a linear combination of a few dictionary atoms. While these methods are usually developed under ℓ1 sparsity constrain (prior) in the input domain, recent studies hav…
Hyperspectral remote sensing images (HSIs) are characterized by having a low spatial resolution and a high spectral resolution, whereas multispectral images (MSIs) are characterized by low spectral and high spatial resolutions. These complementary characteristics have stimulated active research in the inference of imag…
Randomized ICA and LDA methods improve HSI classification efficiency.
problem Overcome curse of dimensionality in hyperspectral images.
method Proposes RFFICA and RFFLDA using Random Fourier features to handle non-linearities and scalability issues.
result Demonstrates improved overall and per-class accuracies compared to conventional kernel ICA and LDA.
A new model combines spatial and spectral features for HSI classification.
problem Inefficiency and difficulty in training RNNs for HSI classification.
method Proposes St-SS-pGRU combining shorten RNN, converlusion layer, and parallel-GRU.
result Better performance and robustness in HSI classification.
In this paper, we tackle the question of discovering an effective set of spatial filters to solve hyperspectral classification problems. Instead of fixing a priori the filters and their parameters using expert knowledge, we let the model find them within random draws in the (possibly infinite) space of possible filters…
We propose a novel approach for pixel classification in hyperspectral images, leveraging on both the spatial and spectral information in the data. The introduced method relies on a recently proposed framework for learning on distributions -- by representing them with mean elements in reproducing kernel Hilbert spaces (…
This paper improves HS classification by optimizing a geometry-aware transformation.
problem Lack of proper class discrimination in HS data points.
method Optimal geometry-aware transformation using a nonlinear objective function.
result The proposed method enhances classification accuracy on HS data.
A new method classifies high-dimensional images with minimal labels using diffusion geometry.
problem Classifying high-dimensional images efficiently and accurately.
method Spatially-regularized nonlinear diffusion geometry for clustering and active learning.
result High-accuracy labelings achieved with a very small number of training labels.
A new tensor decomposition method using a dictionary for better interpretability.
problem Ensuring interpretability in tensor decomposition models.
method Dictionary-based tensor canonical polyadic decomposition with sparse coding.
result Improves parameter identifiability and estimation accuracy in tensor decomposition.
Two active learning algorithms improve HSI classification using Fermat distances and harmonic label propagation.
problem Semi-supervised hyperspectral image classification with limited labeled data.
method Combines Fermat distances with Poisson-reweighted harmonic label propagation for active point selection.
result FALL and A-FALL algorithms enhance labeling accuracy and scalability for large HSI scenes.