Integration of a Sound Source Detection into a Probabilistic-based Multimodal Approach for Person Detection and Tracking

Abstract. Dealing with methods of Human-Robot-Interaction and using a real mobile robot, stable methods for people detection and tracking are fundamental features of such a system and require information from different sources. Based on an existing probability-based and multimodal approach for person detection and tracking, in this paper, we discuss the integration of a further sensory cue. This sensory cue is a sound source detection emerged from auditory information. Firstly, we discuss a newly developed approach for a sound source detection applied for a real world problem, dealing with the difficulty of reverberant environments. Secondly, we show a possible solution to integrate the sound source detection into the already existing person detection and tracking system applied for the mobile interaction robot Horos working in a real office environment.

• Type: Conference
• Year: 2005
• Where: AMS
• Authors: Robert Brückmann, Andrea Scheidig, Christian Martin, Horst-Michael Gross
• Keywords: AMS 2005, Person Detection, Sensory Cue, Sound Source Detection