Multiple Collaborative Kernel Tracking

Those motion parameters that cannot be recovered from image measurements are unobservable in the visual dynamic system. This paper studies this important issue of singularity in the context of kernel-based tracking and presents a novel approach that is based on a motion field representation which employs redundant but sparsely correlated local motion parameters instead of compact but uncorrelated global ones. This approach makes it easy to design fully observable kernel-based motion estimators. This paper shows that these highdimensional motion fields can be estimated efficiently by the collaboration among a set of simpler local kernel-based motion estimators, which makes the new approach very practical.

• Type: Conference
• Year: 2005
• Where: CVPR
• Authors: Zhimin Fan, Ying Wu, Ming Yang
• Keywords: Computer Vision, CVPR 2005, Kernel-based Motion Estimators, Local Kernel-based Motion, Local Motion Parameters, Motion Field Representation, Observable Kernel-based Motion