Abstract
This paper proposes a new approach to enhance real-world intensity-based visual servoing. The main goal is to direct successfully a robotic task without going through the entire image. An explicit two-dimensional map is used as a new global descriptor index. When sweeping the conspicuity of interest regions, a stratified random process recovers the most salient visual selections without any matching or tracking procedures which improves considerably the computing time. Several experiments with an eye-in-hand mobile robot point out the reliability of this approach.