Visual servo control - Part II: Advanced approaches

For position-based visual servo (PBVS) schemes, three-dimensional parameters appear both in the error e and in the interaction matrix, while for basic image-based visual servo (IBVS), the depth of each point considered appears in the coefficients of the interaction matrix related to the tranlational motions. In all cases, an estimation of the current depth must be made at each iteration of the control scheme. This paper describes how epipolar geometry can be used to estimate the 3-D parameters, which can then be used to construct the interaction matrix. It also illustrates how it is possible to estimate directly the numerical value of the pseudo-inverse of Le. With these methods, more advanced techniques in visual servo control are presented. The techniques aim to compensate for the relative shortcomings of the PBVS and IBVS methods. Following consideration of the target tracking tracks, a generalization of the modeling issues that allows one to consider both eye-in-hand systems and eye-to-hand systems is introduced.