An indoor human motion recognition system based on FMCW radar

• Published in: Transactions of Japanese Society for Medical and Biological Engineering Vol. Annual62; no. Abstract; p. 197_1
• Main Authors: 黒沢, 正樹, 桐本, 哲郎, 孫, 光鎬
• Format: Journal Article
• Language: Japanese
• Published: 公益社団法人 日本生体医工学会 2024; Japanese Society for Medical and Biological Engineering
• ISSN: 1347-443X; 1881-4379
• DOI: 10.11239/jsmbe.Annual62.197_1

Radar technology, particularly Frequency-Modulated Continuous Wave (FMCW) radar, has garnered attention in the field of smart home monitoring due to its high sensitivity, long-range surveillance capabilities, and privacy-preserving characteristics. This study proposed a human motion state recognition system to determine motion state based on the spectrums form radar signals in home environment. A target’s velocity is assessed via micro-Doppler signature, compare against a velocity threshold, while its height signature discerns between high and low postures against a height threshold. The target’s horizontal position is determined via the Range-Angle map. The proposed threshold algorithm defines the motion state on velocity, height postures and indoor position. Subsequently, the performance of the system was evaluated by conducting experiments on three subjects. The results show the effectiveness, achieving accuracy of approximately 90%.