ThermalEye: Fully Passive Eye Blink Detection on Smart Glasses via Low-Cost Thermal Sensing

Traditional blink detection systems often rely on visible-light cameras, which are sensitive to illumination and raise privacy concerns. To overcome these limitations, we present ThermalEye, a fully passive eye monitoring system integrated into smart glasses that performs robust blink detection using a low-resolution (12 × 16 pixel) infrared thermal array. Our approach features a framework co-designed with both signal processing techniques and a deep learning model to explicitly address the key challenges of this sensing modality: low signal-to-noise ratio (SNR), spatial heterogeneity, and inter- subject variability. Evaluations show that ThermalEye achieves F1-scores of 0.89 and 0.80 at the frame and event levels, highlighting its promise for fatigue monitoring and dry eye assessment.

Authors

Institutions

Publication Details

Published
2025-10-14
DOI
https://doi.org/10.1145/3737905.3769280
Primary Topic
Gaze Tracking and Assistive Technology
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

ThermalEye: Fully Passive Eye Blink Detection on Smart Glasses via Low-Cost Thermal Sensing

Yuhan Chen, Xie Zhang, Jinzhou Song, Chenshu Wu et al.
Gaze Tracking and Assistive Technology
article

ThermalEye: Fully Passive Eye Blink Detection on Smart Glasses via Low-Cost Thermal Sensing

Yuhan Chen, Xie Zhang, Jinzhou Song, Chenshu Wu, Jianqi Zhang
article en

Abstract

Traditional blink detection systems often rely on visible-light cameras, which are sensitive to illumination and raise privacy concerns. To overcome these limitations, we present ThermalEye, a fully passive eye monitoring system integrated into smart glasses that performs robust blink detection using a low-resolution (12 × 16 pixel) infrared thermal array. Our approach features a framework co-designed with both signal processing techniques and a deep learning model to explicitly address the key challenges of this sensing modality: low signal-to-noise ratio (SNR), spatial heterogeneity, and inter- subject variability. Evaluations show that ThermalEye achieves F1-scores of 0.89 and 0.80 at the frame and event levels, highlighting its promise for fatigue monitoring and dry eye assessment.

University of Hong Kong (HK)
Openalex Percentile: Top 71%
Gaze Tracking and Assistive Technology
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.