A mineral feature extraction method based on virtual band simulation. Issue 6 (3rd June 2017)

• Record Type: Journal Article
• Authors: Zhao, Hengqian; Zhao, Xuesheng; Zhang, Lifu; Jia, Liang; Jiang, Jiaming; Wang, Liping; Yin, Zhengran; Zhu, Xiaoxin
• Is Part Of: Remote sensing letters. Volume 8:Issue 6(2017)
• Page Start: 547
• Page End: 556
• Publication Date: 2017-06-03
• Subjects: Remote sensing -- Periodicals; Remote sensing; Periodicals; 621.3678
• DOI: 10.1080/2150704X.2017.1298163
• Languages: English
• ISSNs: 2150-704X

Abstract

ABSTRACT: Remote sensing-based geological exploration is based on identifying and analyzing spectral features of minerals and rocks. Although an abundance of high quality multispectral remote sensing datasets is available, no appropriate method of full-band absorption feature extraction has been proposed for these datasets. In this work, we developed a new method, Virtual Band Continuum Removal (VBCR), for the extraction of absorption feature spectra from multispectral datasets. By setting the nodes of the continuum on virtual bands instead of the real bands, the proposed method is an improved approach for preserving the weak absorption features in multispectral datasets. VBCR was compared with a state of the art approach on both laboratory data and real image data, and the experimental results indicated the efficacy of the proposed method.