Performance metrics for the evaluation of hyperspectral chemical identification systems
Remote sensing of chemical vapor plumes is a difficult but important task for many military and civilian applications. Hyperspectral sensors operating in the long-wave infrared regime have well-demonstrated detection capabilities. However, the identification of a plume’s chemical constituents, based...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
SPIE--Society of Photo-Optical Instrumentation Engineers
2017
|
| Online Access: | http://hdl.handle.net/1721.1/108594 |
| _version_ | 1811091415212490752 |
|---|---|
| author | Ingle, Vinay Truslow, Eric O. Golowich, Steven E. Manolakis, Dimitris G. |
| author2 | Lincoln Laboratory |
| author_facet | Lincoln Laboratory Ingle, Vinay Truslow, Eric O. Golowich, Steven E. Manolakis, Dimitris G. |
| author_sort | Ingle, Vinay |
| collection | MIT |
| description | Remote sensing of chemical vapor plumes is a difficult but important task for many military and civilian applications. Hyperspectral sensors operating in the long-wave infrared regime have well-demonstrated detection capabilities. However, the identification of a plume’s chemical constituents, based on a chemical library, is a multiple hypothesis testing problem which standard detection metrics do not fully describe. We propose using an additional performance metric for identification based on the so-called Dice index. Our approach partitions and weights a confusion matrix to develop both the standard detection metrics and identification metric. Using the proposed metrics, we demonstrate that the intuitive system design of a detector bank followed by an identifier is indeed justified when incorporating performance information beyond the standard detection metrics. |
| first_indexed | 2024-09-23T15:02:03Z |
| format | Article |
| id | mit-1721.1/108594 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:02:03Z |
| publishDate | 2017 |
| publisher | SPIE--Society of Photo-Optical Instrumentation Engineers |
| record_format | dspace |
| spelling | mit-1721.1/1085942022-09-29T12:11:03Z Performance metrics for the evaluation of hyperspectral chemical identification systems Ingle, Vinay Truslow, Eric O. Golowich, Steven E. Manolakis, Dimitris G. Lincoln Laboratory Truslow, Eric O. Golowich, Steven E. Manolakis, Dimitris G. Remote sensing of chemical vapor plumes is a difficult but important task for many military and civilian applications. Hyperspectral sensors operating in the long-wave infrared regime have well-demonstrated detection capabilities. However, the identification of a plume’s chemical constituents, based on a chemical library, is a multiple hypothesis testing problem which standard detection metrics do not fully describe. We propose using an additional performance metric for identification based on the so-called Dice index. Our approach partitions and weights a confusion matrix to develop both the standard detection metrics and identification metric. Using the proposed metrics, we demonstrate that the intuitive system design of a detector bank followed by an identifier is indeed justified when incorporating performance information beyond the standard detection metrics. United States. Defense Threat Reduction Agency (Air Force contract FA8721-05-C-0002) 2017-05-02T17:29:03Z 2017-05-02T17:29:03Z 2016-02 2015-06 Article http://purl.org/eprint/type/JournalArticle 0091-3286 http://hdl.handle.net/1721.1/108594 Truslow, Eric, Steven Golowich, Dimitris Manolakis, and Vinay Ingle. “Performance Metrics for the Evaluation of Hyperspectral Chemical Identification Systems.” Opt. Eng 55, no. 2 (February 10, 2016): 023106. ©2016 SPIE. en_US http://dx.doi.org/10.1117/1.oe.55.2.023106 Optical Engineering Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf SPIE--Society of Photo-Optical Instrumentation Engineers SPIE |
| spellingShingle | Ingle, Vinay Truslow, Eric O. Golowich, Steven E. Manolakis, Dimitris G. Performance metrics for the evaluation of hyperspectral chemical identification systems |
| title | Performance metrics for the evaluation of hyperspectral chemical identification systems |
| title_full | Performance metrics for the evaluation of hyperspectral chemical identification systems |
| title_fullStr | Performance metrics for the evaluation of hyperspectral chemical identification systems |
| title_full_unstemmed | Performance metrics for the evaluation of hyperspectral chemical identification systems |
| title_short | Performance metrics for the evaluation of hyperspectral chemical identification systems |
| title_sort | performance metrics for the evaluation of hyperspectral chemical identification systems |
| url | http://hdl.handle.net/1721.1/108594 |
| work_keys_str_mv | AT inglevinay performancemetricsfortheevaluationofhyperspectralchemicalidentificationsystems AT truslowerico performancemetricsfortheevaluationofhyperspectralchemicalidentificationsystems AT golowichstevene performancemetricsfortheevaluationofhyperspectralchemicalidentificationsystems AT manolakisdimitrisg performancemetricsfortheevaluationofhyperspectralchemicalidentificationsystems |