Spatial–spectral Schroedinger embedding for target detection in hyperspectral imagery

Dorado-Munoz, Leidy P.; Messinger, David W.

doi:10.1117/1.oe.56.9.093101

Spatial–spectral Schroedinger embedding for target detection in hyperspectral imagery

Journal Article · Sat Sep 09 04:00:00 EDT 2017 · Optical Engineering

DOI:https://doi.org/10.1117/1.oe.56.9.093101· OSTI ID:1581647

Dorado-Munoz, Leidy P. ^[1]; Messinger, David W. ^[2]

Rochester Inst. of Technology, Rochester, NY (United States); Rochester Institute of Technology
Rochester Inst. of Technology, Rochester, NY (United States)

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 curves and rates of detection and false alarm at object level are used as quantitative metrics to assess the detector. In addition, the Schroedinger embedding performance in target detection is compared against the performances of principal component embedding and the Laplacian embedding. Finally, results show that the SE-based detector with spatial–spectral features outperforms the other considered approaches.

Research Organization:: Rochester Inst. of Technology, Rochester, NY (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation (NA-20)

DOE Contract Number:: NA0002482

OSTI ID:: 1581647

Journal Information:: Optical Engineering, Journal Name: Optical Engineering Journal Issue: 09 Vol. 56; ISSN 0091-3286

Publisher:: SPIE

Country of Publication:: United States

Language:: English

References (14)

Initial study of Schroedinger eigenmaps for spectral target detection Dorado-Munoz, Leidy P.; Messinger, David W. Optical Engineering, Vol. 55, Issue 8 https://doi.org/10.1117/1.OE.55.8.083101	journal	August 2016
Segmentation given partial grouping constraints Yu, S. X.; Shi, Jianbo IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, Issue 2 https://doi.org/10.1109/TPAMI.2004.1262179	journal	February 2004
A Novel Method for Hyperspectral Image Classification Based on Laplacian Eigenmap Pixels Distribution-Flow Hou, Biao; Zhang, Xiangrong; Ye, Qiang IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 6, Issue 3 https://doi.org/10.1109/JSTARS.2013.2259470	journal	June 2013
Schroedinger Eigenmaps for the Analysis of Biomedical Data Czaja, Wojciech; Ehler, Martin IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, Issue 5 https://doi.org/10.1109/TPAMI.2012.270	journal	May 2013
No authors listed WIREs Computational Statistics, Vol. 2, Issue 4, 387-515 https://doi.org/10.1002/wics.v2:4	journal	July 2010
Schrodinger Eigenmaps for spectral target detection Dorado-Munoz, Leidy P.; Messinger, David W. SPIE Defense + Security, SPIE Proceedings https://doi.org/10.1117/12.2177302	conference	May 2015
Schroedinger Eigenmaps with nondiagonal potentials for spatial-spectral clustering of hyperspectral imagery Cahill, Nathan D.; Czaja, Wojciech; Messinger, David W. SPIE Defense + Security, SPIE Proceedings https://doi.org/10.1117/12.2050651	conference	June 2014
Hyperspectral image segmentation using spatial-spectral graphs Gillis, David B.; Bowles, Jeffrey H. SPIE Defense, Security, and Sensing, SPIE Proceedings https://doi.org/10.1117/12.919743	conference	May 2012
Integration of heterogeneous data for classification in hyperspectral satellite imagery Benedetto, J.; Czaja, W.; Dobrosotskaya, J. SPIE Defense, Security, and Sensing, SPIE Proceedings https://doi.org/10.1117/12.919236	conference	May 2012
SpecTIR hyperspectral airborne Rochester experiment data collection campaign Herweg, Jared A.; Kerekes, John P.; Weatherbee, Oliver SPIE Defense, Security, and Sensing, SPIE Proceedings https://doi.org/10.1117/12.919268	conference	May 2012
An adaptive locally linear embedding manifold learning approach for hyperspectral target detection Ziemann, Amanda K.; Messinger, David W. SPIE Defense + Security, SPIE Proceedings https://doi.org/10.1117/12.2177466	conference	May 2015
The SHARE 2012 data campaign Giannandrea, AnneMarie; Raqueno, Nina; Messinger, David W. SPIE Defense, Security, and Sensing, SPIE Proceedings https://doi.org/10.1117/12.2015935	conference	May 2013
Commute time distance transformation applied to spectral imagery and its utilization in material clustering Albano, James A. Optical Engineering, Vol. 51, Issue 7 https://doi.org/10.1117/1.OE.51.7.076202	journal	July 2012
Spatial-spectral dimensionality reduction of hyperspectral imagery with partial knowledge of class labels Cahill, Nathan D.; Chew, Selene E.; Wenger, Paul S. SPIE Defense + Security, SPIE Proceedings https://doi.org/10.1117/12.2177139	conference	May 2015

Similar Records

Global and adaptive K-nearest neighbor graphs in a spectral target detector based on Schroedinger Eigenmaps

Journal Article · Sun Dec 03 19:00:00 EST 2017 · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) Proceedings (Online) · OSTI ID:1581649

Initial study of Schroedinger eigenmaps for spectral target detection

Journal Article · Tue Aug 02 00:00:00 EDT 2016 · Optical Engineering · OSTI ID:1581645

Dual-Channel Densenet for Hyperspectral Image Classification

Journal Article · Sun Nov 04 23:00:00 EST 2018 · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) Proceedings (Online) · OSTI ID:1581642

Related Subjects

36 MATERIALS SCIENCE
97 MATHEMATICS AND COMPUTING
Schroedinger eigenmaps
hyperspectral image analysis
knowledge propagation scheme
spatial–spectral information
spectral graph theory
spectral target detection

Spatial–spectral Schroedinger embedding for target detection in hyperspectral imagery

Citation Formats

References (14)

Similar Records

Related Subjects