Micro-Doppler-Based Human Activity Classification Using the Mote-Scale BumbleBee Radar

Abstract

Human activity recognition is an emerging technology formany security, surveillance, and health service applications utilizing wireless sensor networks (WSNs). However, the exploitation of radar in WSNs has been only recently made possible through the development of small, low-power, and low-cost wireless radar motes, such as the BumbleBee radar developed by the Samraksh Company. This letter explores the capacity of using the BumbleBee radar for indoor human activity classification based on micro-Doppler signatures. The electromagnetic measurements of the signal transmitted by the BumbleBee radar are made to fully characterize the sensor and its limitations. A database of the multiperspective micro-Doppler signatures measured from the BumbleBee radar is compiled to analyze the classification performance and limitations due to the dwell time and the aspect angle. Within the operational constraints delineated, it is shown that the BumbleBee radar can be used to discriminate between walking, running, and crawling, even under variable conditions.