Syed A. Rizvi is Associate Professor of Engineering at The Graduate Center and a member of the Department of Engineering Science and Physics at the College of Staten Island. His current research interests include image and video coding, applications of artificial neural networks to image processing, and automatic target recognition. His current research project, which is funded by the US Army Research Office, deals with automatic target recognition (ATR) that uses forward-looking infrared (FLIR) imagery. This project focuses on two issues of FLIR-ATR: clutter rejection and fusion of ATR algorithm.
FLIR ATR, however, is a challenging problem, because of the unpredictable nature of thermal signatures. This high variability of target thermal signatures is due to several factors, including meteorological conditions, time of day, location, and range. The high variability of target signatures, target obscuration, and background clutter results in a large number of false alarms at the target-detection stage. These false alarms must be discarded at the clutter-rejection stage; otherwise, the recognition performed by the subsequent classification stage would be unreliable, regardless of the dependability of the classification technique. Therefore, his current research deals with the development of a clutter-rejection technique that can substantially reduce the number of false alarms produced by the detection stage.
This research also investigates fusion techniques for designing a composite classifier to improve the performance (probability of correct classification) of FLIR ATR. The motivation behind the fusion of ATR algorithms is that if each contributing technique in a fusion algorithm (composite classifier) emphasizes on learning at least some features of the targets that are not learned by other contributing techniques for making a classification decision, a fusion of ATR algorithms may improve overall probability of correct classification of the composite classifier.