Home // ACCSE 2017, The Second International Conference on Advances in Computation, Communications and Services // View article

Evaluation of Gaze-Depth Prediction Using Support Vector Machines

Authors:
Choonsung Shin
Youngho Lee
Youngmin Kim
Jisoo Hong
Sung-Hee Hong
Hoonjong Kang

Keywords: gaze depth, eye tracking, augmented reality, smart eyeglasses

Abstract:
This paper presents the evaluation results of a gaze depth prediction method for natural gaze interaction of wearable augmented reality. To calculate the gaze depth, we extracted the position of the center of the eyeball and the gaze vector of participants’ eyes from a binocular eye tracker while the distance between participants’ eyes and an object changed. We then applied support vector machines (SVM) to predict gaze depth. Based on our evaluation, prediction of gaze depth to actual focal distance was accurate to within +/- 20 cm.

Pages: 21 to 22

Copyright: Copyright (c) IARIA, 2017

Publication date: June 25, 2017

Published in: conference

ISSN: 2519-8459

ISBN: 978-1-61208-570-8

Location: Venice, Italy

Dates: from June 25, 2017 to June 29, 2017