Can Diversity Amongst Learners Improve Online Object Tracking?

Georg Nebehay, Walter Chibamu, Peter R. Lewis, Arjun Chandra, Roman Pflugfelder and Xin Yao
In Multiple Classifier Systems, Lecture Notes in Computer Science, vol. 7872, pp 212-223. Springer, 2013.

We present a novel analysis of the state of the art in object tracking with respect to diversity found in its main component, an ensemble classifier that is updated in an online manner. By interpreting object tracking as a classical online learning problem, we are able to employ established measures for diversity and performance from the rich literature on ensemble classification and online learning. We present a detailed evaluation of diversity and performance on benchmark sequences in order to gain an insight into how the tracking performance can be improved.

booktitle={Multiple Classifier Systems},
series={Lecture Notes in Computer Science},
editor={Zhou, Zhi-Hua and Roli, Fabio and Kittler, Josef},
title={Can Diversity amongst Learners Improve Online Object Tracking?},
publisher={Springer Berlin Heidelberg},
author={Nebehay, Georg and Chibamu, Walter and Lewis, Peter R. and Chandra, Arjun and Pflugfelder, Roman and Yao, Xin},