Volume 20 Issue 11 - Publications Date: 1 November 2001
Application of Motion-Based Visual Servoing to Target Tracking
A. Crétual IRISA/INRIA Rennes, France and F. Chaumette
In this paper, the classical task of mobile target tracking using a pan and tilt camera is considered. We use recent results in motion-based visual servoing to deal with complex targets whose shape and texture are unknown. The first method we present consists in designing a control law directly from the estimated image motion. This leads to compute the pan and tilt acceleration necessary to reduce the tracking error. A second method, more efficient for target tracking, consists in retrieving the target position in the image from its estimated motion. This leads to classical image-based visual servoing. For both methods, experimental results obtained at video rate are presented and discussed.
Return to Contents