An efficient spatial-spectral classification method for hyperspectral imagery

Wei Li; Qian Du

doi:10.1117/12.2050710

Translator Disclaimer

22 May 2014 An efficient spatial-spectral classification method for hyperspectral imagery

Wei Li, Qian Du

Author Affiliations +

Proceedings Volume 9124, Satellite Data Compression, Communications, and Processing X; 912410 (2014) https://doi.org/10.1117/12.2050710
Event: SPIE Sensing Technology + Applications, 2014, Baltimore, Maryland, United States

Abstract

In this paper, a feature extraction method using a very simple local averaging filter for hyperspectral image classification is proposed. The method potentially smoothes out trivial variations as well as noise of hyperspectral data, and simultaneously exploits the fact that neighboring pixels tend to belong to the same class with high probability. The spectral-spatial features, which are extracted and fed into a following classifier with locality preserving character in the experimental setup, are compared with other features, such as spectral only and wavelet-features. Simulated results show that the proposed approach facilitates superior discriminant features extraction, thereby yielding significant improvement in hyperspectral image classification performance.

Citation Download Citation

Wei Li and Qian Du "An efficient spatial-spectral classification method for hyperspectral imagery", Proc. SPIE 9124, Satellite Data Compression, Communications, and Processing X, 912410 (22 May 2014); https://doi.org/10.1117/12.2050710

ACCESS THE FULL ARTICLE