Multiple Spectral–Spatial Classification Approach for Hyperspectral Data

TLDR

Different segmentation methods based on dissimilar principles lead to different classification results. The study proposes a multiple‑classifier spectral–spatial approach for hyperspectral image classification that combines pixelwise classification with segmentation maps in a marker‑selection step. Multiple independent classifiers are applied; pixels classified identically by all are retained as markers that seed a minimum spanning forest, which grows spatial regions, and the approach integrates pixelwise classification with segmentation maps before marker selection. The proposed method significantly improves classification accuracies compared with previously proposed techniques.

Abstract

A new multiple-classifier approach for spectral–spatial classification of hyperspectral images is proposed. Several classifiers are used independently to classify an image. For every pixel, if all the classifiers have assigned this pixel to the same class, the pixel is kept as a marker, i.e., a seed of the spatial region with a corresponding class label. We propose to use spectral–spatial classifiers at the preliminary step of the marker-selection procedure, each of them combining the results of a pixelwise classification and a segmentation map. Different segmentation methods based on dissimilar principles lead to different classification results. Furthermore, a minimum spanning forest is built, where each tree is rooted on a classification-driven marker and forms a region in the spectral–spatial classification map. Experimental results are presented for two hyperspectral airborne images. The proposed method significantly improves classification accuracies when compared with previously proposed classification techniques.