Real-time Arm Gesture Recognition in Smart Home Scenarios via Millimeter Wave Sensing
summary
A real-time system uses a commodity mmWave radar to recognize 10 fine-grained arm gestures across realistic smart-home scenes by extracting a concentrate position Doppler profile, classifying with a 3-layer CNN, and stabilizing outputs with a hidden Markov model voting scheme. A user-discovery clustering step removes surrounding interference. Evaluation with 25 volunteers (30 repetitions each, 97 days, ~22,000 samples) and 21 family deployments reports robust real-time recognition at >95.3% accuracy.
AI-written summary · about
related talks
20mInteracting with Soli: Exploring Fine-Grained Dynamic Gesture Recognition in the Radio-Frequency ...
06mDesigning and Evaluating Hand-to-Hand Gestures with Dual Commodity Wrist-Worn Devices
20mAdvancing Hand Gesture Recognition with High Resolution Electrical Impedance Tomography
17mEchoFlex: Hand Gesture Recognition using Ultrasound Imaging
06mVibroSense: Recognizing home activities by deep learning subtle vibrations on an interior ...
01h 13mHealth Monitoring with Wireless Sensors and Machine Learning
19mBackHand: Sensing Hand Gestures via Back of the Hand
10mIMUs FTW!! Building IMU-based gesture recognition!