Gaze estimation using a hybrid appearance and motion descriptor

Chunshui Xiong, Lei Huang, Changping LiuProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2015 · DOI

Abstract

It is a challenging problem to realize a robust and low cost gaze estimation system. Existing appearance-based and feature-based methods both have achieved impressive progress in the past several years, while their improvements are still limited by feature representation. Therefore, in this paper, we propose a novel descriptor combining eye appearance and pupil center-cornea reflections (PCCR). The hybrid gaze descriptor represents eye structure from both feature level and topology level. At the feature level, a glints-centered appearance descriptor is presented to capture intensity and contour information of eye, and a polynomial representation of normalized PCCR vector is employed to capture motion information of eyeball. At the topology level, the partial least squares is applied for feature fusion and selection. At last, sparse representation based regression is employed to map the descriptor to the point-of-gaze (PoG). Experimental results show that the proposed method achieves high accuracy and has a good tolerance to head movements.
BibTeX
@inproceedings{xiong2015gaze,
  author = {Chunshui Xiong and Lei Huang and Changping Liu},
  title = {{Gaze estimation using a hybrid appearance and motion descriptor}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2015},
  doi = {10.1117/12.2178824},
}

Loading related content...

Figure