Human Action Recognition With Raw Millimeter Wave Radar Data
4th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2022, Ankara, Turkey, 9 - 11 June 2022, (Full Text)
- Publication Type: Conference Paper / Full Text
- Doi Number: 10.1109/hora55278.2022.9800009
- City: Ankara
- Country: Turkey
- Keywords: Deep Learning, FMCW, FMCW Mm Wave Radar, Human Action Recognition, Raw data processing
- Kocaeli University Affiliated: No
Abstract
© 2022 IEEE.Prediction of human movements is a current hot topic that researchers are working on. The most common technologies such as image or wearable inertial sensors are not preferable due to privacy issues or subject discomfort. In this study, we propose to use FMCW (Frequency Modulated Continuous Waves) Millimeter Wavelength (MmWave) Radar technology in raw format for this task. We recorded human movements using FMCW MmWave, and fed our CNN network by transforming a multi-channel 2D structure with our new method called Video Of Radar (VIDAR). We tested our model with both real-time human movements and offline test datasets. The results were promising with over 90% accuracy.