Advances in Hyperspectral Image Classification: Earth monitoring with statistical learning methods
This is an incremental tutorial for researchers in remote sensing and Earth monitoring, summarizing existing statistical learning methods without introducing new techniques.
The paper reviews advances in hyperspectral image classification, addressing challenges like high dimensionality and limited labeled data, and highlights methods such as spatial homogeneity, active learning, and semisupervised learning to improve classification.
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.