Sökning: onr:"swepub:oai:lup.lub.lu.se:a6dc0d27-e59a-453b-a88a-5a6360f103e0" >
Precise localizatio...
Precise localization of corneal reflections in eye images using deep learning trained on synthetic data
-
- Byrne, Sean Anthony (författare)
- The IMT School for Advanced Studies Lucca
-
- Nyström, Marcus (författare)
- Lund University,Lunds universitet,Humanistlaboratoriet,Fakultetsgemensamma verksamheter,Humanistiska och teologiska fakulteterna,Lund University Humanities Lab,Units,Joint Faculties of Humanities and Theology
-
- Maquiling, Virmarie (författare)
- Technical University of Munich
-
visa fler...
-
- Kasneci, Enkelejda (författare)
- Technical University of Munich
-
- Niehorster, Diederick C. (författare)
- Lund University,Lunds universitet,Humanistlaboratoriet,Fakultetsgemensamma verksamheter,Humanistiska och teologiska fakulteterna,Institutionen för psykologi,Samhällsvetenskapliga institutioner och centrumbildningar,Samhällsvetenskapliga fakulteten,Lund University Humanities Lab,Units,Joint Faculties of Humanities and Theology,Department of Psychology,Departments of Administrative, Economic and Social Sciences,Faculty of Social Sciences
-
visa färre...
-
(creator_code:org_t)
- Engelska 16 s.
-
Ingår i: Behavior Research Methods. - 1554-3528.
- Relaterad länk:
-
http://dx.doi.org/10... (free)
-
visa fler...
-
https://lup.lub.lu.s...
-
https://doi.org/10.3...
-
visa färre...
Abstract
Ämnesord
Stäng
- We present a deep learning method for accurately localizing the center of a single corneal reflection (CR) in an eye image. Unlike previous approaches, we use a convolutional neural network (CNN) that was trained solely using synthetic data. Using only synthetic data has the benefit of completely sidestepping the time-consuming process of manual annotation that is required for supervised training on real eye images. To systematically evaluate the accuracy of our method, we first tested it on images with synthetic CRs placed on different backgrounds and embedded in varying levels of noise. Second, we tested the method on two datasets consisting of high-quality videos captured from real eyes. Our method outperformed state-of-the-art algorithmic methods on real eye images with a 3-41.5% reduction in terms of spatial precision across data sets, and performed on par with state-of-the-art on synthetic images in terms of spatial accuracy. We conclude that our method provides a precise method for CR center localization and provides a solution to the data availability problem, which is one of the important common roadblocks in the development of deep learning models for gaze estimation. Due to the superior CR center localization and ease of application, our method has the potential to improve the accuracy and precision of CR-based eye trackers.
Ämnesord
- SAMHÄLLSVETENSKAP -- Psykologi (hsv//swe)
- SOCIAL SCIENCES -- Psychology (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Nyckelord
- Eye tracking
- Gaze estimation
- Neural networks
- Simulations
- Corneal reflection
- P-CR
Publikations- och innehållstyp
- art (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas