The Detection and Following of Human Legs Through Inductive Approaches for a Mobile Robot With a Single Laser Range Finder

Abstract

The human-friendly navigation of mobile robots is a significant social and technological issue. There are many potential applications of human-following technology. Good examples are human-following shopping carts, porter robots at airports, and museum guide robots. In this paper, we propose detection and tracking schemes for human legs by the use of a single laser range finder. The leg detection algorithm takes an inductive approach by the application of a support vector data description scheme and simple attributes. We establish an efficient leg-tracking scheme by exploiting a human walking model to achieve robust tracking under occlusions. The proposed schemes are successfully verified through experiments.