PupilNet: Convolutional Neural Networks for Robust Pupil Detection

TL;DR

This paper introduces PupilNet, a dual convolutional neural network system that significantly improves real-time pupil detection accuracy in challenging conditions for eye-tracking applications.

Contribution

It presents a novel dual CNN pipeline that enhances pupil detection robustness and speed in real-world scenarios, outperforming existing algorithms.

Findings

Increased detection rate by up to 25% over state-of-the-art methods.

Effective handling of illumination changes and occlusions.

Real-time performance with reduced computational costs.

Abstract

Real-time, accurate, and robust pupil detection is an essential prerequisite for pervasive video-based eye-tracking. However, automated pupil detection in real-world scenarios has proven to be an intricate challenge due to fast illumination changes, pupil occlusion, non centered and off-axis eye recording, and physiological eye characteristics. In this paper, we propose and evaluate a method based on a novel dual convolutional neural network pipeline. In its first stage the pipeline performs coarse pupil position identification using a convolutional neural network and subregions from a downscaled input image to decrease computational costs. Using subregions derived from a small window around the initial pupil position estimate, the second pipeline stage employs another convolutional neural network to refine this position, resulting in an increased pupil detection rate up to 25% in comparison with the best performing state-of-the-art algorithm. Annotated data sets can be made available upon request.