Actas de congresos
3d Facial Tracking From Corrupted Movie Sequences
Proceedings Of The Ieee Computer Society Conference On Computer Vision And Pattern Recognition. , v. 1, n. , p. I880 - I885, 2004.
In this paper we perform 3D face tracking on corrupted video sequences. We use a deformable model, combined with a predictive filter, to recover both the rigid transformations and the values of the parameters that describe the evolution of the facial expressions over time. To be robust, predictive filters need a good observation of the system's state. We describe a new method to measure, at each moment in time, the correct distribution of an observation of the parameters of a high-dimensional deformable model. This method is based on bounding the confidence regions of the 2D image displacements with affine forms, and propagating them into parameter space. Using Lindeberg's theorem, we measure a good Gaussian approximation of the parameters in a manner that avoids many of the traditional assumptions about the observations' distributions. We demonstrate in experiments on sequences with compression artifacts, and poor-quality video sequences of Lauren Bacall and Humphrey Bogart from the 1950s, that, without any learning involved, our method is sufficiently robust to extract information from degraded image sequences. In addition, we provide ground truth validation.1I880I885Bishop, G., Welch, G., An introduction to the kalman filter (2001) SIGGRAPH 2001 Course NotesBlake, A., Isard, M., (1998) Active Contours: the Application of Techniques from Graphics, Vision, Control Theory and Statistics to Visual Tracking of Shapes in Motion, , Springer-VerlagBlanz, V., Vetter, T., A morphable model for the synthesis of 3d faces (1999) SIGGRAPH, pp. 187-194. , AugustBrand, M., Bhotika, R., Flexible flow for 3d nonrigid tracking and shape recovery (2001) CVPR, pp. 315-322Bregler, C., Hertzmann, A., Biermann, H., Recovering Non-Rigid 3D Shape from Image Streams (2000) CVPRBrown, L., 3d head tracking using motion adaptive texture-mapping (2001) CVPR, pp. 998-1005Cascia, M., Sclaroff, S., Athitsos, V., Fast, reliable head tracking under varying illumination: An approach based on registration of texture-mapped 3d models (2000) IEEE Trans. PAMI, 22 (4), pp. 322-336Chung, K., (1974) A Course in Probability Theory, , Academic Press, Inc., 2nd editionCootes, T., Taylor, C., Active shape models - Their training and application (1995) CVIU, 61 (1), pp. 38-59De Carlo, D., Metaxas, D., Optical flow constraints on deformable models with applications to face tracking (2000) IJCV, 38 (2), pp. 99-127. , JulyDellaert, F., Burgard, W., Fox, D., Thrun, S., Using the condensation algorithm for robust, vision-based mobile robot localization (1999) CVPRGoldenstein, S., Vogler, C., Metaxas, D., Statistical cue integration in DAG deformable models (2003) IEEE Trans. PAMI, 25 (7), pp. 801-813Gordon, N., Salmon, D., Smith, A., A novel approach to nonlinear/nongaussian bayesian state estimation (1993) IEEE Proc. Radar Signal Processing, (140), pp. 107-113Isard, M., Blake, A., CONDENSATION: Conditional density propagation for visual tracking (1998) IJVC, 29 (1), pp. 5-28King, O., Forsyth, D., How does CONDENSATION behave with a finite number of samples? (2000) ECCV, pp. 695-709Maybeck, P., (1979) Stochastic Models, Estimation, and Control, , Academic PressMeer, P., Stewart, C.V., Tyler, D.E., Robust computer vision: An interdisciplinary challenge (2000) CVIU, (78), pp. 1-7Metaxas, D., (1996) Physics-based Deformable Models: Applications to Computer Vision, Graphics and Medical Imaging, , Kluwer Academic PublishersPighin, F., Szeliski, R., Salesin, D., Resynthesizing facial animation through 3d model-based tracking (1999) ICCV, pp. 143-150Pighin, F., Szeliski, R., Salesin, D., Modeling and animating realistic faces from images (2002) IJVC, 50 (2), pp. 143-169Stolfi, J., Figueiredo, L., (1997) Self-validated Numerical Methods and Applications, , 21° Colóquio Brasileiro de Matemática, IMPATao, H., Huang, T., Visual estimation and compression of facial motion parameters: Elements of a 3D model-based video coding system (2002) IJVC, 50 (2), pp. 111-125Wan, E.A., Van Der Merwe, R., (2001) Kalman Filtering and Neural Networks, p. 50. , chapter Chapter 7: The Unscented Kalman Filter, Wiley PublishingWang, L., Hu, W., Tan, T., Face tracking using motion-guided dynamic template matching (2002) ACCVWen, Z., Huang, T., Capturing subtle facial motions in 3d face tracking (2003) ICCV, pp. 1343-1350Shan, Z.Z.Y., Liu, Z., Model-based bundle adjustment with application to face modeling (2001) ICCV, pp. 644-651