EarFieldSensing: A Novel In-Ear Electric Field Sensing to Enrich Wearable Gesture Input through ...
summary
EarFieldSensing places in-ear electrodes to detect both electric field changes and ear canal deformations, compares EMG, capacitive sensing, simple EFS and a differential EarFS, and records 25 facial and head gestures. A lab study collects ~14,000 gesture windows (single participant) and a mobile test logs ~600 gestures across 3 participants. Differential amplification cancels environmental noise, enabling recognition of a 5-gesture set at ~90% precision sitting and ~85.2% while walking, with schematics and PCB files provided for replication.
AI-written summary · about
chapters (10)
- 0:00Introduction and motivation
- 0:31Use cases for facial sensing
- 2:11Prior work and background
- 5:53The earfield sensing concept
- 6:49Technical design details
- 9:46Evaluation methodology
- 11:56Stationary performance study
- 13:31Mobile performance analysis
- 15:26Conclusion and summary
- 16:18Q&A session
related talks
13mSparseEMG: Computational Design of Sparse EMG Layouts for Sensing Gestures
17mEMPress: Practical Hand Gesture Classification with Wrist-Mounted EMG and Pressure Sensing
05mA Feature Adaptive Learning Method for High-Density sEMG-Based Gesture Recognition
10mEIT-kit: An Electrical Impedance Tomography Toolkit for Health and Motion Sensing
20mSkinTrack: Using the Body as an Electrical Waveguide for Continuous Finger Tracking on the Skin
07mAuraRing: Precise Electromagnetic Finger Tracking
13mEarPressure VR: Ear Canal Pressure Feedback for Enhancing Environmental Presence in Virtual Reality
06mIdentifying Contact Fingers on Touch Sensitive Surfaces by Ring-Based Vibratory Communication