Access Restriction

Author Bue, B.D. ♦ Merenyi, E.
Sponsorship IEEE Geoscience and Remote Sensing Society
Source IEEE Xplore Digital Library
Content type Text
Publisher Institute of Electrical and Electronics Engineers, Inc. (IEEE)
File Format PDF
Copyright Year ©2004
Language English
Subject Domain (in DDC) Natural sciences & mathematics ♦ Earth sciences ♦ Geology, hydrology & meteorology
Subject Keyword Accuracy ♦ Absorption ♦ Hyperspectral imaging ♦ Training ♦ Weight measurement ♦ Materials ♦ similarity measure ♦ Adaptive ♦ continuum removal ♦ hyperspectral ♦ linear discriminant analysis (LDA) ♦ metric learning
Abstract Capturing both the shape of the spectral continuum and the positions/widths of absorption bands is essential to accurately measure similarity between hyperspectral signatures. Furthermore, the relative importance of these features is data dependent. In this letter, we present an adaptive version of our recently proposed continuum-intact (CI)/continuum-removed (CR) similarity measure which automatically determines a convex weighting between similarity measurements of CI and CR signatures according to input data. We describe an efficient technique to calculate an optimal weight for a linear combination of CI and CR similarity measurements. We evaluate the technique on the Airborne Visible/Infrared Imaging Spectrometer spectra sampled from a well-studied urban scene and show that our technique yields improved classification accuracy in comparison to CI or CR similarity measurements alone and performs comparably to calculating the weight via brute-force search, at a much reduced computational cost. A source code implementation of our algorithm is provided online.
Description Author affiliation :: Dept. of Electr. & Comput. Eng., Rice Univ., Houston, TX, USA
Author affiliation :: Dept. of Stat., Rice Univ., Houston, TX, USA
ISSN 1545598X
Education Level UG and PG
Learning Resource Type Article
Publisher Date 2013-03-01
Publisher Place U.S.A.
Rights Holder Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Volume Number 10
Issue Number 2
Size (in Bytes) 536.31 kB
Page Count 5
Starting Page 381
Ending Page 385

Source: IEEE Xplore Digital Library