Title :
Efficient ATR using compression
Author :
B. Ulug;S.C. Ahalt;R.A. Mitchell
Author_Institution :
Dept. of Electr. Eng., Ohio State Univ., Columbus, OH, USA
Abstract :
We examine various model-based automatic target recognition (MBATR) classifiers to investigate the utility of model-catalog compression realized via signal-vector quantization (VQ) and feature extraction. We specifically investigate the impact of various compression rates and common automatic target recognition (ATR) scenario variations such as noise and occlusion through simulations on high-range resolution (HRR) radar and synthetic aperture radar (SAR) data. For this data, we show that significant computational savings are possible for modest decreases in classification performance.
Keywords :
"Target recognition","Synthetic aperture radar","Sensor systems","Transaction databases","Quantization","Feature extraction","Computational modeling","Signal resolution","Remote sensing","Degradation"
Journal_Title :
IEEE Transactions on Aerospace and Electronic Systems
