Automatic Arm Motion Recognition Using Radar for Smart Home Technologies

In considering man-machine interface for smart home technology, we introduce a simple but effective technique in automatic arm motion recognition using radar. The proposed technique classifies arm motions based on the envelopes of their micro-Doppler (MD) signatures. These envelopes capture the distinctions among different arm movements and their corresponding positive and negative Doppler frequencies that are generated during each arm motion. We detect the positive and negative frequency envelopes of MD separately, and form a feature vector of their augmentation. We use the k-nearest neighbor (kNN) classifier and Manhattan distance (L1) measure, in lieu of Euclidean distance (L2), so as not to diminish small but critical envelope values. It is shown that this method can achieve higher than 99% classification rates when choosing specific arm motion articulations from a sitting down position.