One of the alternative techniques to GPS for the development of pedestrian navigation assistive systems inurban environments is embedded vision. The walker localization is, then, based on the camera poseestimation from images acquired during the path. Inspired by previous work on autonomous navigation ofmobile robots, this thesis explores two approaches in the specific context of pedestrian localization. The firstlocalization method is based on image primitive matching with a pre-estimated 3D map of the environment. Itallows an accurate estimate of the complete pose of the camera (6 dof), but experiments show criticallimitations of robustness and computation time related to the matching step. An alternative solution isproposed using vanishing points. Robust and fast camera orientation (3 dof) is estimated by tracking threeorthogonal vanishing points in a video sequence. The developed algorithm allows indoor pedestrianlocalization in two steps: an off-line learning step defines a reference path by selecting key frames along theway, then, in localization step, an approximate but realistic position of the walker is estimated in real time bycomparing the orientation of the camera in the current image and that of reference.
