Since image-based visual servoing is a local feedback control solution, it requires the definition of intermediate subgoals in the sensor space at the task planning level. In this paper, we describe a general technique for specifying and tracking trajectories of an unknown object in the camera image space. First, physically valid C2 image trajectories which correspond to quasi-optimal 3D camera trajectory (approaching as much as possible a straight line) are performed. Both mechanical (joint limits) and visibility constraints are taken into account at the task planning level. The good behavior of Image-based control when desired and current camera positions are closed is then exploited to design an efficient control scheme. Real time experimental results using a camera mounted on the end effector of a six d-o-f robot confirm the validity of our approach.