Gait-based person and gender recognition using micro-doppler signatures

The ability to identify an individual quickly and accurately is a critical parameter in surveillance. Conventional contactless systems are often complex and expensive to implement since video-based processing requires high computational resources. In this paper we present a micro-Doppler (mD) system and a computationally efficient classifier for the purpose of identifying individuals and gender. Walking subjects are successfully classified based on their mD time-frequency signatures. Recognition accuracies as high as 100% are obtained for some individuals and 92% for gender classification.