Hyperspectral target detection using manifold learning and multiple target spectra
Abstract
Imagery collected from satellites and airborne platforms provides an important tool for remotely analyzing the content of a scene. In particular, the ability to remotely detect a specific material within a scene is of critical importance in nonproliferation and other applications. The sensor systems that process hyperspectral images collect the high-dimensional spectral information necessary to perform these detection analyses. For a d-dimensional hyperspectral image, however, where d is the number of spectral bands, it is common for the data to inherently occupy an m-dimensional space with m << d. In the remote sensing community, this has led to recent interest in the use of manifold learning, which seeks to characterize the embedded lower-dimensional, nonlinear manifold that the data discretely approximate. The research presented in this paper focuses on a graph theory and manifold learning approach to target detection, using an adaptive version of locally linear embedding that is biased to separate target pixels from background pixels. Finally, this approach incorporates multiple target signatures for a particular material, accounting for the spectral variability that is often present within a solid material of interest.
- Authors:
-
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States). Intelligence and Space Research Division
- Rochester Inst. of Technology, NY (United States). Carlson Center for Imaging Science
- Publication Date:
- Research Org.:
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation
- Contributing Org.:
- Rochester Inst. of Technology, NY (United States)
- OSTI Identifier:
- 1325640
- Report Number(s):
- LA-UR-15-28507
Journal ID: ISSN 2332-5615
- Grant/Contract Number:
- AC52-06NA25396
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Proceedings (Applied Imagery Pattern Recognition Workshop. Online)
- Additional Journal Information:
- Journal Name: Proceedings (Applied Imagery Pattern Recognition Workshop. Online); Journal Volume: 2015; Conference: Applied Imagery Pattern Recognition Workshop, Washington, DC (United States), 13-15 Oct 2015; Related Information: Electronic ISBN 978-1-4673-9558-8; Journal ID: ISSN 2332-5615
- Publisher:
- IEEE
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; manifolds; object detection; hyperspectral imaging; graph theory; solids; image edge detection; spectral analysis; remote sensing
Citation Formats
Ziemann, Amanda K., Theiler, James, and Messinger, David W. Hyperspectral target detection using manifold learning and multiple target spectra. United States: N. p., 2016.
Web. doi:10.1109/AIPR.2015.7444547.
Ziemann, Amanda K., Theiler, James, & Messinger, David W. Hyperspectral target detection using manifold learning and multiple target spectra. United States. https://doi.org/10.1109/AIPR.2015.7444547
Ziemann, Amanda K., Theiler, James, and Messinger, David W. Thu .
"Hyperspectral target detection using manifold learning and multiple target spectra". United States. https://doi.org/10.1109/AIPR.2015.7444547. https://www.osti.gov/servlets/purl/1325640.
@article{osti_1325640,
title = {Hyperspectral target detection using manifold learning and multiple target spectra},
author = {Ziemann, Amanda K. and Theiler, James and Messinger, David W.},
abstractNote = {Imagery collected from satellites and airborne platforms provides an important tool for remotely analyzing the content of a scene. In particular, the ability to remotely detect a specific material within a scene is of critical importance in nonproliferation and other applications. The sensor systems that process hyperspectral images collect the high-dimensional spectral information necessary to perform these detection analyses. For a d-dimensional hyperspectral image, however, where d is the number of spectral bands, it is common for the data to inherently occupy an m-dimensional space with m << d. In the remote sensing community, this has led to recent interest in the use of manifold learning, which seeks to characterize the embedded lower-dimensional, nonlinear manifold that the data discretely approximate. The research presented in this paper focuses on a graph theory and manifold learning approach to target detection, using an adaptive version of locally linear embedding that is biased to separate target pixels from background pixels. Finally, this approach incorporates multiple target signatures for a particular material, accounting for the spectral variability that is often present within a solid material of interest.},
doi = {10.1109/AIPR.2015.7444547},
journal = {Proceedings (Applied Imagery Pattern Recognition Workshop. Online)},
number = ,
volume = 2015,
place = {United States},
year = {Thu Mar 31 00:00:00 EDT 2016},
month = {Thu Mar 31 00:00:00 EDT 2016}
}