Information Theoretic Focal Length Selection for Real-Time Active 3-D Object Tracking

Abstract

Active object tracking, for example, in surveillance tasks, becomes more and more important these days. Besides the tracking algorithms themselves methodologies have to be developed for reasonable active control of the degrees of freedom of all involved cameras. In this paper we present an information theoretic ap-proach that allows the optimal selection of the focal lengths of two cameras during active 3–D object tracking. The se-lection is based on the uncertainty in the 3–D estimation. This allows us to resolve the trade–off between small and large focal length: in the former case, the chance is in-creased to keep the object in the field of view of the cameras. In the latter one, 3–D estimation becomes more reliable. Also, more details are provided, for example for recogniz-ing the objects. Beyond a rigorous mathematical framework we present real–time experiments demonstrating that we gain an im-provement in 3–D trajectory estimation by up to 42 % in comparison with tracking using a fixed focal length. 1.