Image-Based Visual Servoing for Vanishing Features and Ground Lines Tracking: Application to a UAV Automatic Landing

A unified modeling framework is defined and an image-based visual servoing scheme is introduced to evaluate the feasibility of a vision-based guidance for a UAV model during survey missions and for automatic landing. Relevant image features are selected to allow for the proposed objective, namely decoupling rotation and translation in the image, and allowing to respect the natural separation between the lateral and longitudinal motions of the aircraft. The controller design is adapted to include the aircraft dynamics and the vision output in an linear optimal control approach. Simulation results are presented in order to validate the proposed solution and allow for a critical evaluation.