Image-based visual servoing on planar objects of unknown shape

This paper proposes a way to achieve positioning tasks by visual servoing, for any orientation of the camera, when the desired image of the observed object cannot be precisely described. The object is assumed to be planar and motionless but no knowledge about its shape or pose is required. To simplify the problem, first, we treat the case of a thread-like object and then we show how our approach can be generalized to an object with three particular points. The control law is based on the use of 2D visual servoing and on an estimation of a 3D parameter. Experimental results relative to objects of unknown shape are given to validate the approach. In addition, an algorithm to estimate the depth between the object and the camera is provided which leads to the dimensions of the object.