Automatic and Self-adaptive Facial Expression Tracking
We present a novel automatic and self-adaptive technique for facial expression tracking. The face point clouds are acquired at video rate with 3D scanner or reconstructed from 2D images. A single time-varying deformable mesh model is computed with our new metric to track these point clouds. A normal constraint is presented and introduced in the new metric to measure the direction consistency of vertex normal and vertex motion in the tracking process. Combined with other constraints in the new metric, it can automatically ensure the vertices move to optimal position. The normal constraint also works effectively where the model is very different from the point clouds in geometry. Experiment results show that the new technique can well track facial expression without manual aid.
KeywordsFacial Expression Point Cloud Optical Flow Iterative Close Point Normal Constraint
Unable to display preview. Download preview PDF.
- 1.J. Lien, T. Kanade, A. Zlochower, J. Cohn, and C. Li. 1998. Subtly different facial expression recognition and expression intensity estimation. In CVPR’98, 853–859.Google Scholar
- 2.Y. Yacoob and L. Davis. 1994. Computing spatio-temporal representations of human faces. In CVPR’94, 70–75.Google Scholar
- 3.Pighin, F., Salesin, D. H., and Szeliski, R. 1999. Resynthesizing facial animation through 3D model-based tracking. In Proc. Int. Conf. on Computer Vision, 143–150.Google Scholar
- 4.Blanz, V., Basso, C., Poggio, T., and Vetter, T. 2003. Reanimating faces in images and video. In Proceedings of EUROGRAPHICS, vol. 22, 641–650.Google Scholar
- 6.Li, H., Sumner, R. W., and Pauly, M. 2008. Global correspondence optimization for nonrigid registration of depth scans. In Symposium on Geometry Processing, 27(5).Google Scholar
- 9.Xiaolei Huang, Song Zhang, Yang Wang, D. Metaxas, D., Samaras. 2004. A Hierarchical Framework For High Resolution Facial Expression Tracking. In proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshop, 22–29.Google Scholar
- 10.B. Amberg, S. Romdhani, T.Vetter. 2007. Optimal Step Nonrigid ICP Algorithms for Surface Registration. IEEE Conference on Computer Vision and Pattern Recognition, 1–8.Google Scholar