Share Email Print
cover

Proceedings Paper

Supervised non-negative tensor factorization for automatic hyperspectral feature extraction and target discrimination
Author(s): Dylan Anderson; Aleksander Bapst; Joshua Coon; Aaron Pung; Michael Kudenov
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Hyperspectral imaging provides a highly discriminative and powerful signature for target detection and discrimination. Recent literature has shown that considering additional target characteristics, such as spatial or temporal profiles, simultaneously with spectral content can greatly increase classifier performance. Considering these additional characteristics in a traditional discriminative algorithm requires a feature extraction step be performed first. An example of such a pipeline is computing a filter bank response to extract spatial features followed by a support vector machine (SVM) to discriminate between targets. This decoupling between feature extraction and target discrimination yields features that are suboptimal for discrimination, reducing performance. This performance reduction is especially pronounced when the number of features or available data is limited. In this paper, we propose the use of Supervised Nonnegative Tensor Factorization (SNTF) to jointly perform feature extraction and target discrimination over hyperspectral data products. SNTF learns a tensor factorization and a classification boundary from labeled training data simultaneously. This ensures that the features learned via tensor factorization are optimal for both summarizing the input data and separating the targets of interest. Practical considerations for applying SNTF to hyperspectral data are presented, and results from this framework are compared to decoupled feature extraction/target discrimination pipelines.

Paper Details

Date Published: 5 May 2017
PDF: 13 pages
Proc. SPIE 10198, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXIII, 101980Q (5 May 2017); doi: 10.1117/12.2267730
Show Author Affiliations
Dylan Anderson, Sandia National Labs. (United States)
Aleksander Bapst, Sandia National Labs. (United States)
Joshua Coon, Sandia National Labs. (United States)
Aaron Pung, Sandia National Labs. (United States)
Michael Kudenov, North Carolina State Univ. (United States)


Published in SPIE Proceedings Vol. 10198:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXIII
Miguel Velez-Reyes; David W. Messinger, Editor(s)

© SPIE. Terms of Use
Back to Top