Topic: “Micro-Doppler Based Automatic Target Recognition”
Presenter: Mr. Peter Khomchuk, ECE Ph.D. Student, University of Massachusetts Dartmouth
Advisor: Dr. Igal Bilik
Radars play an important role in the modern ground surveillance systems. They can provide high resolution images in the poor visibility conditions - during the night time, fog, rain or snow, were other sensors like video and infrared cameras fail. In addition, radars can detect moving objects and estimate their velocities. Using range resolution profiles and Doppler information obtained by the radar the type of the observed target can be automatically identified. Different automatic target recognition (ATR) algorithms and approaches have been developed for different system requirements, types of radars and targets. In the last decade, the algorithms based on the micro-Doppler signatures of the target gained significant popularity in the radar ATR community, and were shown to be highly effective and robust against models mismatches and low signal to noise ratio (SNR) scenarios. In this project we propose to improve existing micro-Doppler based ATR algorithms by invoking the micro-Doppler models based on the target’s motion dynamics. In addition, we propose to employ a novel concept of the multiple-input multiple-output (MIMO) radar, which provides spatial and waveform diversity, to obtain better estimates of the micro-Doppler signatures and improve the performance of the ATR system.
Peter Khomchuk received his B.Sc. and M.Sc. degrees in electrical engineering from the Vinnitsa National Technical University, Vinnitsa, Ukraine in 2006 and 2008, respectively. Currently he is pursuing a Ph.D. degree in electrical engineering in the University of Massachusetts, Darmouth. His research interests are in statistical signal processing, array processing and pattern recognition with application to remote sensing and automatic target classification.
The seminar is open to the public free of charge.