Designing and Evaluating Hand-to-Hand Gestures with Dual Commodity Wrist-Worn Devices
summary
Dual commodity wrist devices use inertial and microphone data plus dual-device features like relative rotation and correlation and two SVMs to detect hand-to-hand taps and swipes. A design space yields 41 tap and 15 swipe candidates and selected sets: 14 gestures reach 94.6% recognition stationary, and five gestures reach 98.4% walking and 96.3% running. A real-time prototype maps gestures to phone actions and achieves about 90% task success in realistic use.
AI-written summary · about
related talks
18mM.Gesture: An Acceleration-Based Gesture Authoring System on Multiple Handheld and Wearable Devices
17mEMPress: Practical Hand Gesture Classification with Wrist-Mounted EMG and Pressure Sensing
04mDualRing: Enabling Subtle and Expressive Hand Interaction with Dual IMU Rings
06mReal-time Arm Gesture Recognition in Smart Home Scenarios via Millimeter Wave Sensing
18mCyclopsRing: Enabling Whole-Hand and Context-Aware Interactions Through a Fisheye Ring
20mTomo: Wearable, Low-Cost Electrical Impedance Tomography for Hand Gesture Recognition
11mWrist2Finger: Sensing Fingertip Force for Force-Aware Hand Interaction with a Ring-Watch Wearable
17mEchoFlex: Hand Gesture Recognition using Ultrasound Imaging