Regressing local to global shape properties for online segmentation and tracking

Abstract

We propose a novel regression based framework that uses online learned shape information to reconstruct occluded object contours. Our key insight is to regress the global, coarse, properties of shape from its local properties, i.e. its details. We do this by representing shapes using their 2D discrete cosine transforms and by regressing low frequency from high frequency harmonics. We learn this regression model using Locally Weighted Projection Regression which expedites online, incremental learning. After sufficient observation of a set of unoccluded shapes, the learned model can detect occlusion and recover the full shapes from the occluded ones. We demonstrate the ideas using a level-set based tracking system that provides shape and pose, however, the framework could be embedded in any segmentation-based tracking system. Our experiments demonstrate the efficacy of the method on a variety of objects using both real data and artificial data.