Gesture-Radar: A Dual Doppler Radar Based System for Robust Recognition and Quantitative Profiling of Human Gestures

Gesture recognition is key to enabling natural human-computer interactions. Existing approaches based on wireless sensing focus accurate identification of arm gesture types. It remains a challenge recognize and profile the details gestures for precise interaction control. In addition, current have strict positioning requirements between radars users, making them difficult real-world deployment. this article, we adopt multisensor approach present gesture-radar-a dual Doppler radar-based profiling system, which can capture subtle with less or environmental dependence. Gesture-radar uses two vertically placed collect complementary data gestures, cross-analysis be performed profiling. Specifically, first propose two-stage classification model enhance signal proximity matching method by applying constraint functions DTW algorithm, aiming improve accuracy type recognition. Afterward, establish analyze unique features from time-frequency spectrogram, used characterize in-depth details, e.g., angle range an movement. Experimental results show that gesture-radar achieves up 93.5% average recognition, over 80% precision details. This proves proposed viable work in environments.