Data fusion and eigenface based tracking dedicated to a Tour-Guide Robot

Abstract

This article presents a key-scenario of H/R interaction for our tour-guide robot. Given this scenario, three visual modalities, the robot deals with, have been outlined, namely the "search of visitors" attending the exhibition, the "proximal interaction" through the robot interface and the "guidance mission". The paper focuses on the two last ones which involves face recognition and visual data fusion in a particle filtering framework. Evaluations on key-sequences in a human centred environment show the tracker robustness to background clutter, sporadic occlusions and group of persons. The tracker is able to cope with target loss by detecting and re-initializing automatically thanks to the face recognition outcome. Moreover, the multi-cues association proved to be more robust to clutter than any of the cues individually.