A two-stage method for spectral-spatial classification of hyperspectral images

TL;DR

This paper introduces a two-stage spectral-spatial classification method for hyperspectral images that combines SVM-based probability estimation with variational denoising to improve accuracy, especially in challenging scenarios.

Contribution

It presents a novel two-stage approach that effectively integrates spectral and spatial information for hyperspectral image classification.

Findings

Outperforms current state-of-the-art methods on real datasets.

Effective in cases with similar inter-class spectra.

Robust when training data is limited or noisy.

Abstract

This paper proposes a novel two-stage method for the classification of hyperspectral images. Pixel-wise classifiers, such as the classical support vector machine (SVM), consider spectral information only; therefore they would generate noisy classification results as spatial information is not utilized. Many existing methods, such as morphological profiles, superpixel segmentation, and composite kernels, exploit the spatial information too. In this paper, we propose a two-stage approach to incorporate the spatial information. In the first stage, an SVM is used to estimate the class probability for each pixel. The resulting probability map for each class will be noisy. In the second stage, a variational denoising method is used to restore these noisy probability maps to get a good classification map. Our proposed method effectively utilizes both spectral and spatial information of the hyperspectral data sets. Experimental results on three widely used real hyperspectral data sets indicate that our method is very competitive when compared with current state-of-the-art methods, especially when the inter-class spectra are similar or the percentage of the training pixels is high.