Primate eye tracking with carbon-nanotube-paper-composite based capacitive sensors and machine learning algorithms.

Area of Science:

• Biomedical Engineering
• Neuroscience
• Ophthalmology

Background:

• Accurate real-time eye tracking is essential for oculomotor system research.
• Traditional scleral search coil systems are invasive and bulky.
• Camera-based eye trackers face limitations with lighting and power consumption.

Purpose of the Study:

• To introduce a novel, non-invasive capacitive eye tracker.
• To evaluate its performance against the gold standard scleral search coil.
• To assess its potential as an alternative for oculomotor research.

Main Methods:

• Development of a novel eye tracker utilizing proximity capacitive sensors made of carbon-nanotube-paper-composite (CPC).
• Detection of femtofarad-level capacitance changes from primate corneal movement during eye rotations.
• Application of data processing and machine learning algorithms for gaze angle prediction.

Main Results:

• The capacitive eye tracker achieved up to 0.97 correlation with the scleral coil.
• Gaze angle estimation demonstrated a median absolute error as low as 0.30°.
• The system showed good consistency and accuracy compared to the scleral coil.

Conclusions:

• The developed capacitive eye tracker is lightweight and non-invasive.
• It presents a viable alternative to existing coil and camera-based eye tracking systems.
• This technology holds promise for advancing oculomotor research and vision science.