Modelling 3D scenes from sequences of depth images in a personal micro-navigation aid for the visually impaired: Supplementary material (video sequences)

An overarching goal of research presented in this work is a development of a method for the three-dimensional scene modelling from depth images in a personal micro-navigation aid for the visually impaired. Such a simplified model of the scene that will make an automatic, quick but still robust and reliable micro-navigation of the blind pedestrian in an unknown environment possible. This concept put an emphasis on determining a ground plane, that is a flat area devoid of any objects in the bottom part of the imaged scene. Detection of the ground plane significantly simplify identifying obstacles in the way of the blind pedestrian.