Unsupervised change detection in hyperspectral images using principal components space data clustering.

Li, Yinhe; Ren, Jinchang; Yan, Yijun; Liu, Qiaoyuan; Petrovski, Andrei; McCall, John

Abstract

Change detection of hyperspectral images is a very important subject in the field of remote sensing application. Due to the large number of bands and the high correlation between adjacent bands in the hyperspectral image cube, information redundancy is a big problem, which increases the computational complexity and brings negative factor to detection performance. To address this problem, the principal component analysis (PCA) has been widely used for dimension reduction. It has the capability of projecting the original multi-dimensional hyperspectral data into new eigenvector space which allows it to extract light but representative information. The difference image of the PCA components is obtained by subtracting the two dimensionality-reduced images, on which the change detection is considered as a binary classification problem. The first several principal components of each pixel are taken as a feature vector for data classification using k-means clustering with k=2, where the two classes are changed pixels and unchanged pixels, respectively. The centroids of two clusters are determined by iteratively finding the minimum Euclidean distance between pixel's eigenvectors. Experiments on two publicly available datasets have been carried out and evaluated by overall accuracy. The results have validated the efficacy and efficiency of the proposed approach.

Citation

LI, Y., REN, J., YAN, Y., LIU, Q., PETROVSKI, A. and MCCALL, J. 2022. Unsupervised change detection in hyperspectral images using principal components space data clustering. Journal of physics: conference series [online], 2278: proceedings of the 6th International conference on machine vision and information technology (CMVIT 2022), 25 February 2022, [virtual event], article number 012021. Available from: https://doi.org/10.1088/1742-6596/2278/1/012021

• Presentation Conference Type: Conference Paper (published)
• Acceptance Date: May 13, 2022
• Online Publication Date: Jun 1, 2022
• Publication Date: Jun 1, 2022
• Deposit Date: May 28, 2024
• Publicly Available Date: May 28, 2024
• Journal: Journal of physics: conference series
• Print ISSN: 1742-6588
• Electronic ISSN: 1742-6596
• Publisher: IOP Publishing
• Peer Reviewed: Peer Reviewed
• Volume: 2278
• Issue: 1
• Article Number: 012021
• DOI: https://doi.org/10.1088/1742-6596/2278/1/012021
• Keywords: Change detection; Hyperspectral images; Remote sensing applications; Algorithms
• Public URL: https://rgu-repository.worktribe.com/output/2054857