VergeIO: Depth-Aware Eye Interaction on Glasses

2025-07-02

AI Summary

This study addresses the challenge of enabling natural, low-power depth-aware eye interaction for smart glasses. We propose the first calibration-free depth gaze estimation method leveraging electrooculography (EOG)-based vergence motion. Our approach optimizes dry-electrode placement, constructs personalized EOG-to-depth mapping models, and integrates a pre-activation mechanism with a motion-artifact detection pipeline to achieve real-time, on-device depth gesture recognition (<3 mW power consumption). Key contributions include: (i) the first use of EOG signals to infer vergence-driven depth of gaze; (ii) cross-subject generalization without user-specific calibration; and (iii) robustness against head movement and blink artifacts. Evaluated on 11 subjects with 1,320 samples, our method achieves 83–98% average accuracy; even for unseen users without calibration, accuracy remains at 80–98%. These results significantly enhance the practicality and robustness of wearable gaze-controlled systems.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Humans and AI: Interaction Techniques and Devices
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

There is growing industry interest in creating unobtrusive designs for electrooculography (EOG) sensing of eye gestures on glasses (e.g. JINS MEME and Apple eyewear). We present VergeIO, the first EOG-based glasses that enables depth-aware eye interaction using vergence with an optimized electrode layout and novel smart glass prototype. It can distinguish between four and six depth-based eye gestures with 83-98% accuracy using personalized models in a user study across 11 users and 1,320 gesture instances. It generalizes to unseen users with an accuracy of 80-98% without any calibration. To reduce false detections, we incorporate a motion artifact detection pipeline and a preamble-based activation scheme. The system uses dry sensors without any adhesives or gel, and operates in real time with 3 mW power consumption by the sensing front-end, making it suitable for always-on sensing.

Problem

• Enables depth-aware eye interaction using vergence
• Distinguishes depth-based eye gestures with high accuracy
• Reduces false detections with artifact detection and activation

Innovation

• Depth-aware eye interaction using vergence
• Optimized electrode layout and glass prototype
• Motion artifact detection and preamble activation