Advances in Hyperspectral Image Classification: Earth monitoring with statistical learning methods

Abstract

Hyperspectral images show similar statistical properties to natural grayscale or color photographic images. However, the classification of hyperspectral images is more challenging because of the very high dimensionality of the pixels and the small number of labeled examples typically available for learning. These peculiarities lead to particular signal processing problems, mainly characterized by indetermination and complex manifolds. The framework of statistical learning has gained popularity in the last decade. New methods have been presented to account for the spatial homogeneity of images, to include user's interaction via active learning, to take advantage of the manifold structure with semisupervised learning, to extract and encode invariances, or to adapt classifiers and image representations to unseen yet similar scenes. This tutuorial reviews the main advances for hyperspectral remote sensing image classification through illustrative examples.

IEEE Signal Processing Magazine, 2013

References in corpus (1)

• A survey of active learning algorithms for supervised remote sensing image classification

Cited by in corpus (50)

• Deep learning in remote sensing: a review
• HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification
• Three dimensional Deep Learning approach for remote sensing image classification
• Unsupervised Deep Feature Extraction for Remote Sensing Image Classification
• A Comprehensive Survey of Deep Learning in Remote Sensing: Theories, Tools and Challenges for the Community
• Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects
• Spatial-Spectral Feature Extraction via Deep ConvLSTM Neural Networks for Hyperspectral Image Classification
• FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification
• A3CLNN: Spatial, Spectral and Multiscale Attention ConvLSTM Neural Network for Multisource Remote Sensing Data Classification
• BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification
• Spectral-Spatial Mamba for Hyperspectral Image Classification
• Tensor-Based Classifiers for Hyperspectral Data Analysis
• Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification
• GeoShapley: A Game Theory Approach to Measuring Spatial Effects in Machine Learning Models
• Learned Spectral Super-Resolution
• Multiclass feature learning for hyperspectral image classification: sparse and hierarchical solutions
• Efficient Deep Learning of Non-local Features for Hyperspectral Image Classification
• Multi-temporal and multi-source remote sensing image classification by nonlinear relative normalization
• Task-Driven Dictionary Learning for Hyperspectral Image Classification with Structured Sparsity Constraints
• Dimensionality Reduction via Regression in Hyperspectral Imagery
• Multitask Deep Learning with Spectral Knowledge for Hyperspectral Image Classification
• Cross-Domain Collaborative Learning via Cluster Canonical Correlation Analysis and Random Walker for Hyperspectral Image Classification
• Spectral-spatial classification of hyperspectral images: three tricks and a new supervised learning setting
• A novel information gain-based approach for classification and dimensionality reduction of hyperspectral images
• Shapelet-based Sparse Representation for Landcover Classification of Hyperspectral Images
• Tensor Alignment Based Domain Adaptation for Hyperspectral Image Classification
• Non-convex regularization in remote sensing
• Active Ensemble Deep Learning for Polarimetric Synthetic Aperture Radar Image Classification
• 1D-Convolutional Capsule Network for Hyperspectral Image Classification
• Graph Embedding via High Dimensional Model Representation for Hyperspectral Images
• Randomized Principal Component Analysis for Hyperspectral Image Classification
• Hierarchical Bayesian image analysis: from low-level modeling to robust supervised learning
• Advances in Deep Learning for Hyperspectral Image Analysis--Addressing Challenges Arising in Practical Imaging Scenarios
• Unsupervised Anomaly and Change Detection with Multivariate Gaussianization
• High-Order Coupled Fully-Connected Tensor Network Decomposition for Hyperspectral Image Super-Resolution
• Dropout Concrete Autoencoder for Band Selection on HSI Scenes
• Wavelet-Based Semantic Features for Hyperspectral Signature Discrimination
• 3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
• Simultaneous Spectral-Spatial Feature Selection and Extraction for Hyperspectral Images
• Subspace-Based Feature Fusion From Hyperspectral And Multispectral Image For Land Cover Classification
• Recurrent U-net: Deep learning to predict daily summertime ozone in the United States
• Pattern Recognition Scheme for Large-Scale Cloud Detection over Landmarks
• Multi-Spectral Imaging via Computed Tomography (MUSIC) - Comparing Unsupervised Spectral Segmentations for Material Differentiation
• Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolution
• EM-based approach to 3D reconstruction from single-waveform multispectral Lidar data
• Active Multi-Kernel Domain Adaptation for Hyperspectral Image Classification
• Domain Adaptor Networks for Hyperspectral Image Recognition
• PUNCH: Positive UNlabelled Classification based information retrieval in Hyperspectral images
• Online Sensor Hallucination via Knowledge Distillation for Multimodal Image Classification
• High Performance Hyperspectral Image Classification using Graphics Processing Units