Detection and following of human legs using the SVDD (Support Vector Data Description) scheme for a mobile robot with a single Laser Range Finder
This work presents our method for people detection on the surroundings of a mobile robot by using two layers of multiple LRFs, allowing to simultaneously detect two set of different features for every person: chest and legs areas. A person model is created according to the association of these features and a volume representation allows to estimate the current person position. We present experimental results of multiple people detection in an indoor environment. The main problem of our research the development of a mobile robot acting as member of a group of people, simple but accurate people detection and tracking is an important requirement.