A novel band selection and spatial noise reduction method for hyperspectral image classification.

Fu, Hang; Zhang, Aizhu; Sun, Genyun; Ren, Jinchang; Jia, Xiuping; Pan, Zhaojie; Ma, Hongzhang

Abstract

As an essential reprocessing method, dimensionality reduction (DR) can reduce the data redundancy and improve the performance of hyperspectral image (HSI) classification. A novel unsupervised DR framework with feature interpretability, which integrates both band selection (BS) and spatial noise reduction method, is proposed to extract low-dimensional spectral-spatial features of HSI. We proposed a new Neighboring band Grouping and Normalized Matching Filter (NGNMF) for BS, which can reduce the data dimension whilst preserve the corresponding spectral information. An enhanced 2-D singular spectrum analysis (E2DSSA) method is also proposed to extract the spatial context and structural information from each selected band, aiming to decrease the intra-class variability and reduce the effect of noise in the spatial domain. The support vector machine (SVM) classifier is used to evaluate the effectiveness of the extracted spectral-spatial low-dimensional features. Experimental results on three publicly available HSI datasets have fully demonstrated the efficacy of the proposed NGNMF-E2DSSA method, which has surpassed a number of state-of-the-art DR methods.

Citation

FU, H., ZHANG, A., SUN, G., REN, J., JIA, X., PAN, Z. and MA, H. 2022. A novel band selection and spatial noise reduction method for hyperspectral image classification. IEEE transactions on geoscience and remote sensing [online], 60, article 5535713. Available from: https://doi.org/10.1109/TGRS.2022.3189015

• Journal Article Type: Article
• Acceptance Date: Jun 25, 2022
• Online Publication Date: Jul 7, 2022
• Publication Date: Dec 31, 2022
• Deposit Date: Oct 26, 2022
• Publicly Available Date: Oct 26, 2022
• Journal: IEEE transactions on geoscience and remote sensing
• Print ISSN: 0196-2892
• Electronic ISSN: 1558-0644
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Volume: 60
• Article Number: 5535713
• DOI: https://doi.org/10.1109/TGRS.2022.3189015
• Keywords: Band selection (BS); Dimensionality reduction (DR); Enhanced 2-D singular spectrum analysis (E2DSSA); Hyperspectral image (HSI); Image classification
• Public URL: https://rgu-repository.worktribe.com/output/1753312