12 May 2005 Wavelet analysis of hyperspectral reflectance data for spectral feature extraction
Author Affiliations +
Proceedings Volume 5832, Optical Technologies for Atmospheric, Ocean, and Environmental Studies; (2005) https://doi.org/10.1117/12.619869
Event: Optical Technologies for Atmospheric, Ocean, and Environmental Studies, 2004, Beijing, China
Abstract
This study determined the potential of wavelet-based analysis for extracting spectral features of hyperspectral reflectance signals. The dyadic discrete wavelet transform is proposed for feature extraction from a high dimensional data space. The wavelet's inherent multi-resolution properties are discussed in terms related to multi-spectral and hyperspectral remote sensing. Wavelet can focus on the local structure of the signal through adjusting the scale parameter in the course of focusing. So we can find the singularities and the inflexions of the original signal. The absorption strips are thus detected consequently with the local wavelet transform modulus (absolute value) maxima. The results show a superior performance of the proposed wavelet-based features that are more meaningful for spectral feature extraction when compared to conventional methods.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Guiling Sun, Guiling Sun, Yonghua Fang, Yonghua Fang, Cuilan Zhang, Cuilan Zhang, Xianbing Wang, Xianbing Wang, Benyong Yang, Benyong Yang, } "Wavelet analysis of hyperspectral reflectance data for spectral feature extraction", Proc. SPIE 5832, Optical Technologies for Atmospheric, Ocean, and Environmental Studies, (12 May 2005); doi: 10.1117/12.619869; https://doi.org/10.1117/12.619869
PROCEEDINGS
9 PAGES


SHARE
Back to Top