Tracking connected objects using interacting shape models

As sensor resolution increases, estimators tracking extended objects benefit from being able to closely model the shape of the target. However, as more shape details are incorporated, this usually leads to increasingly complex estimators. A more useful approach is to describe these shapes as a combination of simpler shapes connected to each other. In this paper, we propose a modular approach to estimate these combined targets in function of their simpler components. This allows the characteristics of each component to be encapsulated, and permits the combination of multiple filtering techniques as required by each component shape. This approach can be applied to track combined objects in a large variety of environments, such as excavators, robotic arms, wagon trains, and many others.