Depth Compensation Model for Gaze Estimation in Sport Analysis
Abstract
A depth compensation model is presented as a novel approach to reduce the effects of parallax error for head-mounted eye trackers. The method can reduce the parallax error when the distance between the user and the target is prior known. The model is geometrically presented and its performance is tested in a totally controlled environment with aim to check the influences of eye tracker parameters and ocular biometric parameters on its behavior. We also present a gaze estimation method based on epipolar geometry for binocular eye tracking setups. The depth compensation model has shown very promising to the field of eye tracking. It can reduce 10 times less the influence of parallax error in multiple depth planes.
Type
Publication
In 2015 IEEE International Conference on Computer Vision Workshop
Eye-Tracking
Sport Analysis
Binocular Eye Tracking Setup
Depth Compensation Model
Epipolar Geometry
Eye Tracker Parameters
Gaze Estimation
Head-Mounted Eye Trackers
Parallax Error
Gaze Tracking
Authors
Fabricio Batista Narcizo
(he/him)
Senior AI Research Scientist
Fabricio Batista Narcizo is a Senior AI Research Scientist in the Video Technology department at GN Hearing A/S (Jabra) and a Part-Time Lecturer and Course Manager at the IT University of Copenhagen (ITU). He received his Ph.D. degree in Computer Science from the ITU in 2017, his M.Sc. degree in Electronic & Computer Engineering from the Aeronautics Institute of Technology (ITA) in 2008, and his B.Sc. degree in Computer Science from the University of Western Santa Catarina (UNOESC) in 2005. His research interests lie in computer vision, image analysis, artificial intelligence, data science, data mining, machine learning, edge AI, and human-computer interaction, with a particular interest in eye-tracking.