A generic approach to simultaneous tracking and verification in video

In this paper, a generic approach to simultaneous tracking and verification in video data is presented. The approach is based on posterior density estimation using sequential Monte Carlo methods. Visual tracking, which is in essence a temporal correspondence problem, is solved through probability density propagation, with the density being defined over a proper state space characterizing the object configuration. Verification is realized through hypothesis testing using the estimated posterior density. In its most basic form, verification can be performed as follows. Given a measurement vector Z and two hypotheses H1 and H0, we first estimate posterior probabilities P(H0/Z) and P(H1/Z), and then choose the one with the larger posterior probability as the true hypothesis. Several applications of the approach are illustrated by experiments devised to evaluate its performance. The idea is first tested on synthetic data, and then experiments with real video sequences are presented, illustrating vehicle tracking and verification, human (face) tracking and verification, facial feature tracking, and image sequence stabilization.

[1]  Larry S. Davis,et al.  Tracking rigid motion using a compact-structure constraint , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[2]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[3]  Rama Chellappa,et al.  Simultaneous tracking and verification via sequential posterior estimation , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[4]  Rama Chellappa,et al.  Image stabilization and mosaicking using the overlapped basis optical flow field , 1997, Proceedings of International Conference on Image Processing.

[5]  Hilary Buxton,et al.  Towards unconstrained face recognition from image sequences , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[6]  Scott L. Zeger,et al.  Generalized linear models with random e ects: a Gibbs sampling approach , 1991 .

[7]  David C. Hogg,et al.  An efficient method for contour tracking using active shape models , 1994, Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects.

[8]  Nicholas G. Polson,et al.  A Monte Carlo Approach to Nonnormal and Nonlinear State-Space Modeling , 1992 .

[9]  Michael J. Black,et al.  EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation , 1996, International Journal of Computer Vision.

[10]  Hartmut Neven,et al.  The Bochum/USC Face Recognition System And How it Fared in the FERET Phase III Test , 1998 .

[11]  Allen M. Waxman,et al.  Aspect networks: using multiple views to learn and recognize 3-D objects , 1991, Other Conferences.

[12]  Allen M. Waxman,et al.  Combining evidence from multiple views of 3-D objects , 1992, Other Conferences.

[13]  G. Kitagawa.  Monte Carlo Filter and Smoother for Non-Gaussian Nonlinear State Space Models , 1996 .

[14]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Jun S. Liu,et al.  Sequential Monte Carlo methods for dynamic systems , 1997 .

[16]  Adrian F. M. Smith,et al.  Simple conditions for the convergence of the Gibbs sampler and Metropolis-Hastings algorithms , 1994 .

[17]  J. Hammersley,et al.  Monte Carlo Methods , 1965 .

[18]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Petros G. Voulgaris,et al.  On optimal ℓ∞ to ℓ∞ filtering , 1995, Autom..

[20]  Jun S. Liu,et al.  Sequential Imputations and Bayesian Missing Data Problems , 1994 .

[21]  Joachim M. Buhmann,et al.  Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[22]  Rama Chellappa,et al.  Fast electronic digital image stabilization , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[23]  Michael Isard,et al.  Contour Tracking by Stochastic Propagation of Conditional Density , 1996, ECCV.

[24]  Walter R. Gilks,et al.  Adaptive Direction Sampling , 1994 .

[25]  Alex Pentland,et al.  Pfinder: Real-Time Tracking of the Human Body , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Charles J. Geyer.  Conditioning in Markov Chain Monte Carlo , 1995 .

[27]  Michal Irani,et al.  Recovery of ego-motion using image stabilization , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Kristin J. Dana,et al.  Real-time scene stabilization and mosaic construction , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[29]  Daniel Freedman,et al.  A subset approach to contour tracking in clutter , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[30]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[31]  Daniel P. Huttenlocher,et al.  Tracking non-rigid objects in complex scenes , 1993, 1993 (4th) International Conference on Computer Vision.

[32]  Adrian F. M. Smith,et al.  Sampling-Based Approaches to Calculating Marginal Densities , 1990 .

[33]  C. Masreliez.  Approximate non-Gaussian filtering with linear state and observation relations , 1975 .

[34]  R Chellappa,et al.  Face verification through tracking facial features. , 2001, Journal of the Optical Society of America. A, Optics, image science, and vision.

[35]  Rama Chellappa,et al.  A feature based approach to face recognition , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.