Manifold Learning for Object Tracking with Multiple Motion Dynamics

This paper presents a novel manifold learning approach for high dimensional data, with emphasis on the problem of motion tracking in video sequences. In this problem, the samples are time-ordered, providing additional information that most current methods do not take advantage of. Additionally, most methods assume that the manifold topology admits a single chart, which is overly restrictive. Instead, the algorithm can deal with arbitrary manifold topology by decomposing the manifold into multiple local models that are combined in a probabilistic fashion using Gaussian process regression. Thus, the algorithm is termed herein as

Gaussian Process Multiple Local Models

(GP–MLM).

Additionally, the paper describes a multiple filter architecture where standard filtering techniques,

e.g.

particle and Kalman filtering, are combined with the output of GP–MLM in a principled way. The performance of this approach is illustrated with experimental results using real video sequences. A comparison with GP–LVM [29] is also provided. Our algorithm achieves competitive state-of-the-art results on a public database concerning the left ventricle (LV) ultrasound (US) and lips images.