Arm Motion Classification Using Curve Matching of Maximum Instantaneous Doppler Frequency Signatures

TL;DR

This paper demonstrates that using curve matching techniques, specifically DTW, for maximum instantaneous Doppler frequency signatures improves arm gesture classification accuracy in RF sensing systems.

Contribution

The study introduces the application of Frechet and DTW distance measures for arm gesture recognition, showing DTW's superiority over Euclidean and Manhattan distances.

Findings

DTW improves gesture classification accuracy

Curve matching captures temporal dynamics effectively

DTW outperforms Euclidean and Manhattan distances

Abstract

Hand and arm gesture recognition using the radio frequency (RF) sensing modality proves valuable in manmachine interface and smart environment. In this paper, we use curve matching techniques for measuring the similarity of the maximum instantaneous Doppler frequencies corresponding to different arm gestures. In particular, we apply both Frechet and dynamic time warping (DTW) distances that, unlike the Euclidean (L2) and Manhattan (L1) distances, take into account both the location and the order of the points for rendering two curves similar or dissimilar. It is shown that improved arm gesture classification can be achieved by using the DTW method, in lieu of L2 and L1 distances, under the nearest neighbor (NN) classifier.