Fast Detection of Compressively Sensed IR Targets Using Stochastically Trained Least Squares and Compressed Quadratic Correlation Filters

Handle URI:
http://hdl.handle.net/10754/626601
Title:
Fast Detection of Compressively Sensed IR Targets Using Stochastically Trained Least Squares and Compressed Quadratic Correlation Filters
Authors:
Millikan, Brian ( 0000-0003-2404-9119 ) ; Dutta, Aritra; Sun, Qiyu; Foroosh, Hassan
Abstract:
Target detection of potential threats at night can be deployed on a costly infrared focal plane array with high resolution. Due to the compressibility of infrared image patches, the high resolution requirement could be reduced with target detection capability preserved. For this reason, a compressive midwave infrared imager (MWIR) with a low-resolution focal plane array has been developed. As the most probable coefficient indices of the support set of the infrared image patches could be learned from the training data, we develop stochastically trained least squares (STLS) for MWIR image reconstruction. Quadratic correlation filters (QCF) have been shown to be effective for target detection and there are several methods for designing a filter. Using the same measurement matrix as in STLS, we construct a compressed quadratic correlation filter (CQCF) employing filter designs for compressed infrared target detection. We apply CQCF to the U.S. Army Night Vision and Electronic Sensors Directorate dataset. Numerical simulations show that the recognition performance of our algorithm matches that of the standard full reconstruction methods, but at a fraction of the execution time.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
Millikan B, Dutta A, Sun Q, Foroosh H (2017) Fast Detection of Compressively Sensed IR Targets Using Stochastically Trained Least Squares and Compressed Quadratic Correlation Filters. IEEE Transactions on Aerospace and Electronic Systems 53: 2449–2461. Available: http://dx.doi.org/10.1109/taes.2017.2700598.
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
IEEE Transactions on Aerospace and Electronic Systems
Issue Date:
2-May-2017
DOI:
10.1109/taes.2017.2700598
Type:
Article
ISSN:
0018-9251
Sponsors:
This work was supported in part by the National Science Foundation under Grant IIS-1212948 and Grant DMS-1412413.
Additional Links:
http://ieeexplore.ieee.org/document/7917343/
Appears in Collections:
Articles; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorMillikan, Brianen
dc.contributor.authorDutta, Aritraen
dc.contributor.authorSun, Qiyuen
dc.contributor.authorForoosh, Hassanen
dc.date.accessioned2018-01-01T12:19:02Z-
dc.date.available2018-01-01T12:19:02Z-
dc.date.issued2017-05-02en
dc.identifier.citationMillikan B, Dutta A, Sun Q, Foroosh H (2017) Fast Detection of Compressively Sensed IR Targets Using Stochastically Trained Least Squares and Compressed Quadratic Correlation Filters. IEEE Transactions on Aerospace and Electronic Systems 53: 2449–2461. Available: http://dx.doi.org/10.1109/taes.2017.2700598.en
dc.identifier.issn0018-9251en
dc.identifier.doi10.1109/taes.2017.2700598en
dc.identifier.urihttp://hdl.handle.net/10754/626601-
dc.description.abstractTarget detection of potential threats at night can be deployed on a costly infrared focal plane array with high resolution. Due to the compressibility of infrared image patches, the high resolution requirement could be reduced with target detection capability preserved. For this reason, a compressive midwave infrared imager (MWIR) with a low-resolution focal plane array has been developed. As the most probable coefficient indices of the support set of the infrared image patches could be learned from the training data, we develop stochastically trained least squares (STLS) for MWIR image reconstruction. Quadratic correlation filters (QCF) have been shown to be effective for target detection and there are several methods for designing a filter. Using the same measurement matrix as in STLS, we construct a compressed quadratic correlation filter (CQCF) employing filter designs for compressed infrared target detection. We apply CQCF to the U.S. Army Night Vision and Electronic Sensors Directorate dataset. Numerical simulations show that the recognition performance of our algorithm matches that of the standard full reconstruction methods, but at a fraction of the execution time.en
dc.description.sponsorshipThis work was supported in part by the National Science Foundation under Grant IIS-1212948 and Grant DMS-1412413.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.urlhttp://ieeexplore.ieee.org/document/7917343/en
dc.subjectTarget Detectionen
dc.subjectTarget Recognitionen
dc.subjectCompressive Sensingen
dc.subjectStochastically Trained Least Squaresen
dc.subjectQuadratic Correlation Filteren
dc.subjectLinear Decoderen
dc.titleFast Detection of Compressively Sensed IR Targets Using Stochastically Trained Least Squares and Compressed Quadratic Correlation Filtersen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalIEEE Transactions on Aerospace and Electronic Systemsen
dc.contributor.institutionUniversity of Central Florida, Orlando, USAen
dc.contributor.institutionUniversity of Central Florida, Orlando, FL, USAen
kaust.authorDutta, Aritraen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.