S
Stijn De Beugher
Researcher at Katholieke Universiteit Leuven
Publications - 15
Citations - 97
Stijn De Beugher is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Eye tracking & Gaze. The author has an hindex of 5, co-authored 15 publications receiving 88 citations. Previous affiliations of Stijn De Beugher include Lessius Mechelen & Thomas More College.
Papers
More filters
Proceedings ArticleDOI
Automatic analysis of in-the-wild mobile eye-tracking experiments using object, face and person detection
TL;DR: A novel method for the automatic analysis of mobile eye-tracking data in natural environments by applying object, face and person detection algorithms and training a new detection model for occluded person and face detections is presented.
Proceedings ArticleDOI
Automatic analysis of eye-tracking data using object detection algorithms
TL;DR: This paper investigates the integration of object detection algorithms with eye-tracking data, and uses the use ofobject detection algorithms to perform this analysis task automatically, with regard to both speed and accuracy.
Proceedings Article
The Battle of the Giants - A Case Study of GPU vs FPGA Optimisation for Real-time Image Processing
TL;DR: A thorough comparison of the two main hardware targets for real-time optimization of a computer vision algorithm: GPU and FPGA and issues and problems occurring during the code porting are detailed.
Journal ArticleDOI
A semi-automatic annotation tool for unobtrusive gesture analysis
TL;DR: This paper presents a semi-automatic alternative, in which the focus lies on minimizing the manual workload while guaranteeing highly accurate annotations, designed to provide annotations according to the McNeill gesture space and the output is compatible with annotation tools such as ELAN or ANVIL.
Proceedings ArticleDOI
Semi-automatic Hand Detection - A Case Study on Real Life Mobile Eye-tracker Data
TL;DR: This paper introduces a detection scheme in which several well known detection techniques combined with an advanced elimination mechanism to reduce false detections, and presents a novel (semi-)automatic framework achieving detection rates up to 100%, with only minimal manual input.