GAZE ESTIMATION USING LOCAL FEATURES AND NON-LINEAR REGRESSION

被引：0

作者：

Martinez, Francis ^{[1
]}

Carbone, Andrea ^{[1
]}

Pissaloux, Edwige ^{[1
]}

机构：

[1] UPMC, ISIR, F-75005 Paris, France

来源：

2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012) | 2012年

关键词：

gaze estimation; features extraction; non-linear regression;

D O I：

暂无

中图分类号：

TB8 [摄影技术];

学科分类号：

0804 ;

摘要：

In this paper, we present an appearance-based gaze estimation method for a head-mounted eye tracker. The idea is to extract discriminative image descriptors with respect to gaze before applying a regression scheme. We employ multilevel Histograms of Oriented Gradients (HOG) features as our appearance descriptor. To learn the mapping between eye appearance and gaze coordinates, two learning-based approaches are evaluated : Support Vector Regression (SVR) and Relevance Vector Regression (RVR). Experimental results demonstrate that, despite the high dimensionality, our method works well and RVR provides a more efficient and generalized solution than SVR by retaining a low number of basis functions.

引用

页码：1961 / 1964

页数：4