Initialized Iterative Reweighted Least Squares For Automatic Target Recognition
Keywords
Automatic Target Recognition; Compressed Sensing; Iterative Reweighted Least Squares; Stochastic Initialization
Abstract
Automatic target recognition is typically deployed on infrared focal plane arrays with high resolution, which could be costly. Due to the compressibility of infrared images, compressive sensing allows us to reduce the resolution requirements of a focal plane array while keeping the same target recognition ability. In this paper, we develop an iterative reweighted least squares algorithm with stochastically trained initial weights. Our simulations indicate that this method has higher automatic target recognition accuracy than conventional methods such as OMP, BP, and IRLS when applied to the U.S. Army Night Vision and Electronic Sensors Directorate (NVESD) dataset.
Publication Date
12-14-2015
Publication Title
Proceedings - IEEE Military Communications Conference MILCOM
Volume
2015-December
Number of Pages
506-510
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/MILCOM.2015.7357493
Copyright Status
Unknown
Socpus ID
84959306682 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84959306682
STARS Citation
Millikan, Brian; Dutta, Aritra; Rahnavard, Nazanin; Sun, Qiyu; and Foroosh, Hassan, "Initialized Iterative Reweighted Least Squares For Automatic Target Recognition" (2015). Scopus Export 2015-2019. 2005.
https://stars.library.ucf.edu/scopus2015/2005