Face tracking in low resolution videos under illumination variations
| Title | Face tracking in low resolution videos under illumination variations |
| Publication Type | Conference Papers |
| Year of Publication | 2011 |
| Authors | Zou WWW, Chellappa R, Yuen PC |
| Conference Name | 2011 18th IEEE International Conference on Image Processing (ICIP) |
| Date Published | 2011/09/11/14 |
| Publisher | IEEE |
| ISBN Number | 978-1-4577-1304-0 |
| Keywords | Adaptation models, Computational modeling, Face, face recognition, face tracking, GLF-based tracker, gradient methods, gradient-logarithmic field feature, illumination variations, lighting, low resolution videos, low-resolution, particle filter, particle filter framework, particle filtering (numerical methods), Robustness, tracking, video signal processing, Videos, Visual face tracking |
| Abstract | In practical face tracking applications, the face region is often small and affected by illumination variations. We address this problem by using a new feature, namely the Gradient-Logarithmic Field (GLF) feature, in the particle filter framework. The GLF feature is robust under illumination variations and the GLF-based tracker does not assume any model for the face being tracked and is effective in low-resolution video. Experimental results show that the proposed GFL-based tracker works well under significant illumination changes and outperforms some of the state-of-the-art algorithms. |
| DOI | 10.1109/ICIP.2011.6116672 |