English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Labeled Pupils in the Wild: A Dataset for Studying Pupil Detection in Unconstrained Environments

Tonsen, M., Zhang, X., Sugano, Y., & Bulling, A. (2015). Labeled Pupils in the Wild: A Dataset for Studying Pupil Detection in Unconstrained Environments. Retrieved from http://arxiv.org/abs/1511.05768.

Item is

Basic

show hide
Genre: Paper
Latex : Labeled Pupils in the Wild: {A} Dataset for Studying Pupil Detection in Unconstrained Environments

Files

show Files
hide Files
:
arXiv:1511.05768.pdf (Preprint), 5MB
Name:
arXiv:1511.05768.pdf
Description:
File downloaded from arXiv at 2016-01-22 15:34
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Tonsen, Marc1, Author           
Zhang, Xucong1, Author           
Sugano, Yusuke1, Author           
Bulling, Andreas1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 Abstract: We present labelled pupils in the wild (LPW), a novel dataset of 66 high-quality, high-speed eye region videos for the development and evaluation of pupil detection algorithms. The videos in our dataset were recorded from 22 participants in everyday locations at about 95 FPS using a state-of-the-art dark-pupil head-mounted eye tracker. They cover people with different ethnicities, a diverse set of everyday indoor and outdoor illumination environments, as well as natural gaze direction distributions. The dataset also includes participants wearing glasses, contact lenses, as well as make-up. We benchmark five state-of-the-art pupil detection algorithms on our dataset with respect to robustness and accuracy. We further study the influence of image resolution, vision aids, as well as recording location (indoor, outdoor) on pupil detection performance. Our evaluations provide valuable insights into the general pupil detection problem and allow us to identify key challenges for robust pupil detection on head-mounted eye trackers.

Details

show
hide
Language(s): eng - English
 Dates: 2015-11-182015
 Publication Status: Published online
 Pages: 4 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1511.05768
URI: http://arxiv.org/abs/1511.05768
BibTex Citekey: Tonsen14_arxiv
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show