A Multimodal Eye Movement Dataset and a Multimodal Eye Movement Segmentation Analysis

TL;DR

This paper introduces a comprehensive multimodal eye movement dataset collected during real-world and simulated car rides, along with an analysis of various data sources for eye movement classification to aid future research and system development.

Contribution

It provides a new multimodal eye movement dataset with detailed annotations and evaluates multiple data sources for improved eye movement segmentation.

Findings

Different data sources vary in their effectiveness for eye movement classification.

Combining multiple data sources enhances segmentation accuracy.

The dataset enables training and benchmarking of new algorithms.

Abstract

We present a new dataset with annotated eye movements. The dataset consists of over 800,000 gaze points recorded during a car ride in the real world and in the simulator. In total, the eye movements of 19 subjects were annotated. In this dataset there are several data sources such as the eyelid closure, the pupil center, the optical vector, and a vector into the pupil center starting from the center of the eye corners. These different data sources are analyzed and evaluated individually as well as in combination with respect to their goodness of fit for eye movement classification. These results will help developers of real-time systems and algorithms to find the best data sources for their application. Also, new algorithms can be trained and evaluated on this data set. The data and the Matlab code can be downloaded here https://atreus.informatik.uni-tuebingen.de/seafile/d/8e2ab8c3fdd444e1a135/?p=%2FA%20Multimodal%20Eye%20Movement%20Dataset%20and%20...&mode=list