Keeping Flexible Active Contours on Track using Metropolis Updates

Condensation, a form of likelihood-weighted particle filtering, has been successfully used to infer the shapes of highly constrained "active" contours in video sequences. However, when the contours are highly flexible (e.g. for tracking fingers of a hand), a computationally burdensome number of particles is needed to successfully approximate the contour distribution. We show how the Metropolis algorithm can be used to update a particle set representing a distribution over contours at each frame in a video sequence. We compare this method to condensation using a video sequence that requires highly flexible contours, and show that the new algorithm performs dramatically better that the condensation algorithm. We discuss the incorporation of this method into the "active contour" framework where a shape-subspace is used constrain shape variation.

[1]  Yair Weiss,et al.  Smoothness in layers: Motion segmentation using nonparametric mixture estimation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  William T. Freeman,et al.  Learning low-level vision , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  Michael Isard,et al.  Active Contours , 2000, Springer London.

[4]  Edward H. Adelson,et al.  Representing moving images with layers , 1994, IEEE Trans. Image Process..

[5]  Michael Isard,et al.  ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework , 1998, ECCV.

[6]  Richard Szeliski,et al.  Tracking with Kalman snakes , 1993 .

[7]  Paul A. Viola,et al.  Bayesian Model of Surface Perception , 1997, NIPS.

[8]  Yee Whye Teh,et al.  Learning to Parse Images , 1999, NIPS.

[9]  William T. Freeman,et al.  Bayesian Reconstruction of 3D Human Motion from Single-Camera Video , 1999, NIPS.

[10]  Michael J. Black,et al.  Mixture models for optical flow computation , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Michael Isard,et al.  Object localization by Bayesian correlation , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[12]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[13]  Takeo Kanade,et al.  Vision and control techniques for robotic visual tracking , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.