Preserving the continuity of visual servoing despite changing image features

This paper deals with the problem occurring when features go in or out of the image during the visual servoing task. The appearance/disappearance of image features during the control task produces discontinuities in the control law that affect the performance of the system. In this paper, we propose a solution in order to avoid these discontinuities by the use of weighted image features. In particular, we redefine the camera invariant visual servoing approach In order to take into account the change of image features when zooming in or out during a positioning task. Simulations and experimental results demonstrate the improvements that can be obtained in the performance of the vision-based control task.