Hyperspectral target detection using manifold learning and multiple target spectra

Ziemann, Amanda K.; Theiler, James; Messinger, David W.

doi:10.1109/AIPR.2015.7444547

Title: Hyperspectral target detection using manifold learning and multiple target spectra

Full Record
Other Related Research

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:

Ziemann, Amanda K. ^[1]; Theiler, James ^[1]; Messinger, David W. ^[2]

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:: Thu Mar 31 00:00:00 EDT 2016

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.

Copy to clipboard


                    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

Copy to clipboard


                    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.

Copy to clipboard


                    
@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}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1109/AIPR.2015.7444547

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

Spatial–spectral Schroedinger embedding for target detection in hyperspectral imagery

Journal Article Dorado-Munoz, Leidy P. ; Messinger, David W. - Optical Engineering

In this work, the Schroedinger eigenmaps (SE) algorithm using spatial and spectral information has been applied to supervised classification of hyperspectral imagery (HSI). We have previously introduced the use of SE in spectral target detection problems. The original SE-based target detector was built on the spectral information encoded in the Laplacian and Schroedinger operators. The original SE-based detector is extended such that spatial connectivity of target-like pixels is explored and encoded into the Schroedinger operator using a “knowledge propagation” scheme. The modified SE-based detector is applied to two HSI data sets that share similar target materials. Receiver operating characteristic curvesmore »« less
https://doi.org/10.1117/1.oe.56.9.093101
Identification of unknown waste sites using MIVIS hyperspectral images

Conference Gomarasca, M A ; Strobelt, S

This paper presents the results on the individuation of known and unknown (illegal) waste sites using Landsat TM satellite imagery and airborne MIVIS (Multispectral Infrared and Visible Imaging Spectrometer) data for detailed analysis in Italy. Previous results with Landsat TM imagery were partially positive for large waste site identification and negative for small sites. Information acquired by the MIVIS hyperspectral system presents three main characteristics: local scale study, possibility to plan the proper period based on the objectives of the study, high number of spectral bands with high spectral and geometrical resolution. MIVIS airborne shootings were carried out on 7more »« less
Programmable matched filter and Hadamard transform hyperspectral imagers based on micro-mirror arrays

Conference Love, Steven P

Hyperspectral imaging (HSI), in which each pixel contains a high-resolution spectrum, is a powerful technique that can remotely detect, identify, and quantify a multitude of materials and chemicals. The advent of addressable micro-mirror arrays (MMAs) makes possible a new class of programmable hyperspectral imagers that can perform key spectral processing functions directly in the optical hardware, thus alleviating some of HSI's high computational overhead, as well as offering improved signal-to-noise in certain important regimes (e.g. when using uncooled infrared detectors). We have built and demonstrated a prototype UV-Visible micro-mirror hyperspectral imager that is capable not only of matched-filter imaging, butmore »« less
Full Text Available
Initial study of Schroedinger eigenmaps for spectral target detection

Journal Article Dorado-Munoz, Leidy P. ; Messinger, David W. - Optical Engineering

Spectral target detection refers to the process of searching for a specific material with a known spectrum over a large area containing materials with different spectral signatures. Traditional target detection methods in hyperspectral imagery (HSI) require assuming the data fit some statistical or geometric models and based on the model, to estimate parameters for defining a hypothesis test, where one class (i.e., target class) is chosen over the other classes (i.e., background class). Nonlinear manifold learning methods such as Laplacian eigenmaps (LE) have extensively shown their potential use in HSI processing, specifically in classification or segmentation. Recently, Schroedinger eigenmaps (SE),more »« less
https://doi.org/10.1117/1.oe.55.8.083101
Enhanced sensitivity for hyperspectral infrared chemical detection

Conference Jacobson, P L ; Petrin, R R ; Koskelo, A C ; ...

The sensitivity of imaging, hyperspectral, passive remote sensors in the long-wavelength infrared (LWIR) spectral region is currently limited by the ability to achieve an accurate, time-invariant, pixel-to-pixel calibration of the elements composing the Focal Plane Array (FPA). Pursuing conventional techniques to improve the accuracy of the calibration will always be limited by the trade-off between the time required to collect calibration data of improved precision and the drift in the pixel response that occurs on a timescale comparable to the calibration time. This paper will present the results from a study of a method to circumvent these problems. Improvements inmore »« less
Full Text Available

Similar Records