PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection
Abstract
Real-time, accurate, and robust pupil detection is an essential prerequisite for pervasive video-based eye-tracking. However, automated pupil detection in realworld scenarios has proven to be an intricate challenge due to fast illumination changes, pupil occlusion, non-centered and off-axis eye recording, as well as physiological eye characteristics. In this paper, we approach this challenge through: I) a convolutional neural network (CNN) running in real time on a single core, II) a novel computational intensive two stage CNN for accuracy improvement, and III) a fast propability distribution based refinement method as a practical alternative to II. We evaluate the proposed approaches against the state-of-the-art pupil detection algorithms, improving the detection rate up to ~9% percent points on average over all data sets (~7% on one CPU core 7ms). This evaluation was performed on over 135,000 images: 94,000 images from the literature, and 41,000 new hand-labeled and challenging images contributed by this work (v1.0).
Cite
@article{arxiv.1711.00112,
title = {PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection},
author = {Wolfgang Fuhl and Thiago Santini and Gjergji Kasneci and Wolfgang Rosenstiel and Enkelejda Kasneci},
journal= {arXiv preprint arXiv:1711.00112},
year = {2017}
}
Comments
Pupil detection, pupil center estimation, image processing, CNN. arXiv admin note: substantial text overlap with arXiv:1601.04902