Share Email Print
cover

Proceedings Paper

Spectral unmixing and image classification supported by spatial knowledge
Author(s): Bing Zhang; Xia Zhang; Liangyun Liu; Lanfen Zheng; Qingxi Tong
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Usually the spectral unmixing and endmember extraction were based on the spectral statistics algorithm. In this paper, spatial knowledge, such as field patch information, was involved in the pure pixel selecting. In this way, endmember extraction was not only carried out in spectral space but also considering the spatial location of pixels. In addition, these known background information can also improve the accuracy of image classification, and also can be used to intellectually separate pixels and evaluate each sub-pixels different attributes.

Paper Details

Date Published: 16 June 2003
PDF: 5 pages
Proc. SPIE 4897, Multispectral and Hyperspectral Remote Sensing Instruments and Applications, (16 June 2003); doi: 10.1117/12.467408
Show Author Affiliations
Bing Zhang, Institute of Remote Sensing Applications (China)
Xia Zhang, Institute of Remote Sensing Applications (China)
Liangyun Liu, Institute of Remote Sensing Applications (China)
Lanfen Zheng, Institute of Remote Sensing Applications (China)
Qingxi Tong, Institute of Remote Sensing Applications (China)


Published in SPIE Proceedings Vol. 4897:
Multispectral and Hyperspectral Remote Sensing Instruments and Applications
Allen M. Larar; Qingxi Tong; Makoto Suzuki, Editor(s)

© SPIE. Terms of Use
Back to Top