PSSA: PCA-domain superpixelwise singular spectral analysis for unsupervised hyperspectral image classification.

Liu, Qiaoyuan; Xue, Donglin; Tang, Yanhui; Zhao, Yongxian; Ren, Jinchang; Sun, Haijiang

Abstract

Although supervised classification of hyperspectral images (HSI) has achieved success in remote sensing, its applications in real scenarios are often constrained, mainly due to the insufficiently available or lack of labelled data. As a result, unsupervised HSI classification based on data clustering is highly desired, yet it generally suffers from high computational cost and low classification accuracy, especially in large datasets. To tackle these challenges, a novel unsupervised spatial-spectral HSI classification method is proposed. By combining the entropy rate superpixel segmentation (ERS), superpixel-based principal component analysis (PCA), and PCA-domain 2D singular spectral analysis (SSA), both the efficacy and efficiency of feature extraction are improved, followed by the anchor-based graph clustering (AGC) for effective classification. Experiments on three publicly available and five self-collected aerial HSI datasets have fully demonstrated the efficacy of the proposed PCA-domain superpixelwise SSA (PSSA) method, with a gain of 15–20% in terms of the overall accuracy, in comparison to a few state-of-the-art methods. In addition, as an extra outcome, the HSI dataset we acquired is provided freely online.

Citation

LIU, Q., XUE, D., TANG, Y., ZHAO, Y., REN, J. and SUN, H. 2023. PSSA: PCA-domain superpixelwise singular spectral analysis for unsupervised hyperspectral image classification. Remote sensing [online], 15(4), article 890. Available from: https://doi.org/10.3390/rs15040890

• Journal Article Type: Article
• Acceptance Date: Feb 1, 2023
• Online Publication Date: Feb 6, 2023
• Publication Date: Feb 28, 2023
• Deposit Date: Mar 17, 2023
• Publicly Available Date: Mar 17, 2023
• Journal: Remote sensing
• Electronic ISSN: 2072-4292
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 15
• Issue: 4
• Article Number: 890
• DOI: https://doi.org/10.3390/rs15040890
• Keywords: Anchor-based graph clustering (AGC); Hyperspectral image (HSI); Singular spectral analysis (SSA); Superpixels; Unsupervised classification
• Public URL: https://rgu-repository.worktribe.com/output/1908495