Abstract

Quadratic correlation filters (QCFs) have been used successfully to detect and recognize targets embedded in background clutter. Recently, a QCF called the Rayleigh quotient quadratic correlation filter (RQQCF) was formulated for automatic target recognition (ATR) in IR imagery. Using training images from target and clutter classes, the RQQCF explicitly maximized a class separation metric. What we believe to be a novel approach is presented for ATR that synthesizes the RQQCF using compressed images. The proposed approach considerably reduces the computational complexity and storage requirements while retaining the high recognition accuracy of the original RQQCF technique. The advantages of the proposed scheme are illustrated using sample results obtained from experiments on IR imagery.

© 2007 Optical Society of America

Quadratic correlation filter design methodology for target detection and surveillance applications

Abhijit Mahalanobis, Robert R. Muise, and S. Robert Stanfill
Appl. Opt. 43(27) 5198-5205 (2004)

Constrained quadratic correlation filters for target detection

Robert Muise, Abhijit Mahalanobis, Ram Mohapatra, Xin Li, Deguang Han, and Wasfy Mikhael
Appl. Opt. 43(2) 304-314 (2004)

Integrated approach for automatic target recognition using a network of collaborative sensors

Abhijit Mahalanobis and Alan Van Nevel
Appl. Opt. 45(28) 7365-7374 (2006)

Clutter metric based on the Cramer-Rao lower bound on automatic target recognition

Guojing He, Jianqi Zhang, Delian Liu, and Honghua Chang
Appl. Opt. 47(29) 5534-5540 (2008)

Sparsity-motivated automatic target recognition

Vishal M. Patel, Nasser M. Nasrabadi, and Rama Chellappa
Appl. Opt. 50(10) 1425-1433 (2011)