Robust and efficient tracking in image sequences using a Kalman filter and an affine motion model
Hanna K. Karlsson, Jonas Nygårds · 2003
This paper summarizes an already existing tracking algorithm and presents an approach to improve it by incorporating a Kalman filter. The aim is to develop a lightweight, robust real-time tracking system, to be used on an experimental geo-referenced camera platform. The result is a more robust, occlusion-resistant tracking algorithm exemplified by some tracking scenarios.