We consider the problem of identifying chemical plumes in hyperspectral imaging data, which is challenging due to the diffusivity of plumes and the presence of excessive noise. We propose a robust nonnegative matrix factorization (RNMF) method to segment hyperspectral images considering the low-rank structure of the noisefree data and sparsity of the noise. Because the optimization objective is highly non-convex, nonnegative matrix factorization is very sensitive to initialization. We address the issue by using the fast Nystrom method and label propagation algorithm (LPA). Using the alternating direction method of multipliers (ADMM), RNMF provides high quality clustering results effectively. Experimental results on real single frame and multiframe hyperspectral data with chemical plumes show that the proposed approach is promising in terms of clustering quality and detection accuracy.

Date Published: 21 May 2015
PDF: 11 pages
Proc. SPIE 9472, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXI, 94720V (21 May 2015); doi: 10.1117/12.2177342

Published in SPIE Proceedings Vol. 9472:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXI
Miguel Velez-Reyes; Fred A. Kruse, Editor(s)