DocumentCode :
3348066
Title :
Automatic target recognition based on simultaneous sparse representation
Author :
Patel, Vishal M. ; Nasrabadi, Nasser M. ; Chellappa, Rama
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA
fYear :
2010
fDate :
26-29 Sept. 2010
Firstpage :
1377
Lastpage :
1380
Abstract :
In this paper, an automatic target recognition algorithm is presented based on a framework for learning dictionaries for simultaneous sparse signal representation and feature extraction. The dictionary learning algorithm is based on class supervised simultaneous orthogonal matching pursuit while a matching pursuit-based similarity measure is used for classification. We show how the proposed framework can be helpful for efficient utilization of data, with the possibility of developing real-time, robust target classification. We verify the efficacy of the proposed algorithm using confusion matrices on the well known Comanche forward-looking infrared data set consisting of ten different military targets at different orientations.
Keywords :
feature extraction; image classification; iterative methods; learning (artificial intelligence); military systems; object recognition; target tracking; Comanche forward-looking infrared data set; automatic target recognition; class supervised simultaneous orthogonal matching pursuit; confusion matrix; dictionary learning algorithm; feature extraction; image classification; learning dictionary; matching pursuit based similarity measure; military target; simultaneous sparse representation; sparse signal representation; Algorithm design and analysis; Approximation methods; Artificial neural networks; Dictionaries; Matching pursuit algorithms; Target recognition; Training; Automatic Target Recognition; Forward-Looking Infrared (FLIR) Imagery; Simultaneous orthogonal matching pursuit (SOMP); Sparse representation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location :
Hong Kong
ISSN :
1522-4880
Print_ISBN :
978-1-4244-7992-4
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2010.5652306
Filename :
5652306
Link To Document :
بازگشت