Effect of sparsity‐aware time–frequency analysis on dynamic hand gesture classification with radar micro‐Doppler signatures

Dynamic hand gesture recognition is of great importance in human–computer interaction. In this study, the authors investigate the effect of sparsity‐driven time–frequency analysis on hand gesture classification. The time–frequency spectrogram is first obtained by sparsity‐driven time–frequency analysis. Then three empirical micro‐Doppler features are extracted from the time–frequency spectrogram and a support vector machine is used to classify six kinds of dynamic hand gestures. The experimental results on measured data demonstrate that, compared to traditional time–frequency analysis techniques, sparsity‐driven time–frequency analysis provides improved accuracy and robustness in dynamic hand gesture classification.