Since image-based servoing is a local control solution, it requires the definition of intermediate subgoals in the sensor space when the initial robot position is far away from the desired one. This paper addresses the problem of generating and tracking realistic and optimal smooth trajectories of complex features in the image space. The model of the observed target and the internal camera parameters are assumed to be unknown. First a closed-form smooth collineation path (related to a reference plane) between given starts and end-points is obtained. This path is generated in order to correspond to an optimal camera path. The trajectories of the image features (corresponding to points belonging or not to the reference plane) are then derived and tracked using an image based control.