English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Towards Pervasive Gaze Tracking with Low-level Image Features

Yanxia, Z., Bulling, A., & Gellersen, H. (2012). Towards Pervasive Gaze Tracking with Low-level Image Features. In S. N. Spencer (Ed.), Proceedings ETRA 2012 (pp. 261-264). New York, NY: ACM.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Yanxia, Zhang1, Author
Bulling, Andreas1, Author           
Gellersen, Hans1, Author
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: We contribute a novel gaze estimation technique, which is adaptable for person-independent applications. In a study with 17 participants, using a standard webcam, we recorded the subjects\textquoteright} left eye images for different gaze locations. From these images, we extracted five types of basic visual features. We then sub-selected a set of features with minimum Redundancy Maximum Relevance (mRMR) for the input of a 2-layer regression neural network for estimating the subjects{\textquoteright} gaze. We investigated the effect of different visual features on the accuracy of gaze estimation. Using machine learning techniques, by combing different features, we achieved average gaze estimation error of 3.44{\textdegree} horizontally and 1.37{\textdegree vertically for person-dependent.

Details

show
hide
Language(s): eng - English
 Dates: 2012-03
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1145/2168556.2168611
BibTex Citekey: zhang2012_etra
 Degree: -

Event

show
hide
Title: ETRA 2012
Place of Event: Santa Barbara, CA
Start-/End Date: 2012-03-28 - 2012-03-30

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings ETRA 2012
  Subtitle : Eye Tracking Research and Applications Symposium
Source Genre: Proceedings
 Creator(s):
Spencer, Stephen N., Editor
Affiliations:
-
Publ. Info: New York, NY : ACM
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 261 - 264 Identifier: ISBN: 978-1-4503-1221-9