Towards Domain-Independent and Real-Time Gesture Recognition Using mmWave Signal
This addresses the need for robust, adaptable gesture recognition in applications like smart homes and in-car interfaces, though it appears incremental by enhancing existing methods with domain adaptation and real-time capabilities.
The paper tackles the problem of practical mmWave gesture recognition by proposing DI-Gesture, a system that achieves domain independence and real-time performance, with average accuracies of 97.92% for new users, 99.18% for new environments, and 98.76% for new locations.
Human gesture recognition using millimeter-wave (mmWave) signals provides attractive applications including smart home and in-car interfaces. While existing works achieve promising performance under controlled settings, practical applications are still limited due to the need of intensive data collection, extra training efforts when adapting to new domains, and poor performance for real-time recognition. In this paper, we propose DI-Gesture, a domain-independent and real-time mmWave gesture recognition system. Specifically, we first derive signal variations corresponding to human gestures with spatial-temporal processing. To enhance the robustness of the system and reduce data collecting efforts, we design a data augmentation framework for mmWave signals based on correlations between signal patterns and gesture variations. Furthermore, a spatial-temporal gesture segmentation algorithm is employed for real-time recognition. Extensive experimental results show DI-Gesture achieves an average accuracy of 97.92\%, 99.18\%, and 98.76\% for new users, environments, and locations, respectively. We also evaluate DI-Gesture in challenging scenarios like real-time recognition and sensing at extreme angles, all of which demonstrate the superior robustness and effectiveness of our system.