Visual servoing based on dynamic vision

Abstract

This paper deals with the way to achieve positioning tasks by visual servoing in the case of planar and motionless objects whose shape is unknown. In fact, we consider here complex objects like those one can encounter in the agrifood industry. A 3D reconstruction phase is first considered yielding to the parameters of the plane. This computation is based on the measurement of the 2D velocity in a region of interest and on the measurement of the camera velocity. Once the parameters of the plane are sufficiently stable, a visual servoing scheme is used to control the orientation of the camera with respect to the object and to ensure that it remains in the camera field of view for any desired orientation. This 3D reconstruction phase is maintained active during the servoing to improve the accuracy of the parameters and, consequently, to obtain a small positioning error. Finally, experimental results validate the proposed approach as well as for its effectiveness than for the obtained accuracy.