Closed Loop Visual Tracking Using Observer-Based Dynamic Active Contours

Abstract

This paper describes and demonstrates an algorithm to visually track ying vehicles in a leader-follower scenario. The algorithm consists of two nested control loops. One that assures a proper position estimation for the object(s) to be followed (the visual observer) and one that exploits this position estimation to control the maneuvers of the follower such that it pursues the leader. The visual observer is based on some novel geometric principles tailored to controlled active vision. In particular, we describe the use of dynamic active contours as motion priors for such geometrically motivated observers.

Publication
Proceedings of the Conference on Guidance Navigation and Control
Marc Niethammer
Marc Niethammer
Professor of Computer Science

My research interests include image registration, image segmentation, shape analysis, machine learning, and biomedical applications.