Actas de congresos
When Occlusions Are Outliers
Registro en:
0769526462; 9780769526461
Proceedings Of The Ieee Computer Society Conference On Computer Vision And Pattern Recognition. , v. 2006, n. , p. - , 2006.
10636919
10.1109/CVPRW.2006.215
2-s2.0-33845532985
Autor
Goldenstein S.
Vogler C.
Institución
Resumen
In many tracking applications, the deformable object of interest suffers from frequent occlusions. Traditional augmenting methods use templates and measures of similarity to recover from occlusions. In this paper, we break with these methods. Instead, we model bad image correspondences, which are induced by occlusions, as statistical outliers in the context of tracking high-dimensional deformable models. This interpretation allows us to use robust statistical estimators in the deformable model's parameter space to detect and eliminate such outliers. Because fast-moving occlusions can generate an excessively large outlier to inlier ratio in the occluded areas, we combine the robust statistical estimation with an initial rejection of correspondences based on the magnitude of the optical flow, a simple 2D criterion. To improve robustness even further, we have the final outlier rejection test take into account both the statistical distribution of the deformable model's parameters, and that different parameters are affected by different sub-sets of correspondences. We validate and demonstrate our technique on real sequences of American Sign Language, which exhibit frequent and extensive occlusions caused by fast movement of the subjects' hands. © 2006 IEEE. 2006
Blanz, V., Vetter, T., A morphable model for the synthesis of 3D faces (1999) SIGGRAPH, pp. 187-194 Chen, H., Meer, P., Robust computer vision through kernel density estimation (2002) Proc. of European Conference of Computer Vision, pp. 236-250 Chen, H., Meer, P., Robust regression with projection based m-estimators (2003) Proc. of International Conference of Computer Vision, pp. 878-885 Cootes, T., Taylor, C., Active shape models - Their training and application (1995) Computer Vision and Image Understanding, 61 (1), pp. 38-59 Dimitrijevic, M., Ilic, S., Fua, P., Accurate face models from uncalibrated and ill-lit video sequences (2004) Proc. of IEEE Computer Vision and Pattern Recognition, pp. 1034-1041 Fischler, M., Bolles, R., Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography (1981) Communications of the ACM, 24 (6), pp. 381-395 Goldenstein, S., Vogler, C., Metaxas, D., Statistical cue integration in DAG deformable models (2003) IEEE Transactions on Pattern Analysis and Machine Intelligence, 25 (7), pp. 801-813 Gordon, N., Salmon, D., Smith, A., A novel approach to nonlinear/nongaussian bayesian state estimation (1993) IEEE Proc. Radar Signal Processing, (140), pp. 107-113 Isard, M., Blake, A., Condensation: Conditional density propagation for visual tracking (1998) International Journal of Computer Vision, 29 (1), pp. 5-28 Jin, H., Favaro, P., Soatto, S., Real-time feature tracking and outlier rejection with changes in illumination (2001) Proc. of International Conference of Computer Vision Kass, M., Witkin, A., Terzopoulos, D., Snakes: Active contour models (1988) International Journal of Computer Vision, 1, pp. 321-331 Marona, R., Robust m-estimators of multivariate location and scatter (1976) Ann. Stat., 4, pp. 51-67 Maybeck, P., (1979) Stochastic Models, Estimation, and Control, , Academic Press Neidle, C., Sclaroff, S., (2002) Data Collected at the National Center for Sign Language and Gesture Resources, , http://www.bu.edu/asllrp/ncslgr.html Pighin, F., Hecker, J., Lischinski, D., Szeliski, R., Salesin, D., Synthesizing realistic facial expressions from photographs (1998) Proceedings of the SIGGRAPH, pp. 75-84 Rousseeuw, P., Leroy, A., (1987) Robust Regression and Outlier Detection, , Wiley Rousseeuw, P.J., Driessen, K.V., A fast algorithm for the minimum covariance determinant estimator (1999) Technometrics, 41, pp. 212-223 Samaras, D., Metaxas, D., Fua, P., Leclerc, Y., Variable albedo surface reconstruction from stereo and shape from shading (2000) Proc. of IEEE Computer Vision and Pattern Recognition, pp. 480-487 Shi, J., Tomasi, C., Good features to track (1994) Proc. of IEEE Computer Vision and Pattern Recognition, pp. 593-600 Simoncelli, E., (1999) Handbook of Computer Vision and Applications, 2, pp. 397-422. , chapter Bayesian Multi-scale Differential Optical Flow, Acad. Press Stolfi, J., Figueiredo, L., (1997) Self-validated Numerical Methods and Applications, , 21° Colóquio Brasileiro de Matemática, IMPA Tao, H., Huang, T., Visual estimation and compression of facial motion parameters: Elements of a 3D model-based video coding system (2002) International Journal of Computer Vision, 50 (2), pp. 111-125 Torr, P., Davidson, C., IMPSAC: A synthesis of importance sampling and random sample consensus (2003) IEEE Transactions on Pattern Analysis and Machine Intelligence, 25 (3), pp. 354-365 Torr, P., Murray, D., The development and comparison of robust methods for estimating the fundamental matrix (1997) International Journal of Computer Vision, 24 (3), pp. 271-300 Torr, P., Zisserman, A., MLESAC: A new robust estimator with application to estimating image geometry (2000) Computer Vision and Image Understanding, 78 (1), pp. 138-156 Vogler, C., Goldenstein, S., Stolfi, J., Pavlovic, V., Metaxas, D., Outlier rejection in high-dimensional deformable models (2006) Image and Vision Computing, , In Press Wan, E.A., Van Der Merwe, R., (2001) Kalman Filtering and Neural Networks, , chapter Chapter 7: The Unscented Kalman Filter, (50 pages). Wiley Publishing Wen, Z., Huang, T., Capturing subtle facial motions in 3D face tracking (2003) Proc. of International Conference of Computer Vision, pp. 1343-1350