Abstract
In this paper, we determine the analytical form of the interaction matrix related to any moments that can be computed from binary or segmented images. We then apply this theoretical result to image-based visual servoing by selecting six combinations of moments able to control the six DOF of the system. The experimental results we present show that a correct behavior of the system is obtained if we consider either a simple symmetrical object or a planar object with complex and unknown shape.

This publication has 9 references indexed in Scilit: