IR tag detection and tracking with omnidirectional camera using track-before-detect particle filter

Abstract

Robust user detection and tracking is one of the key issues for a personal robot to follow the target person. In this paper, a novel tracking system using an omnidirectional camera and IR LED tags is proposed. The users wear the tags on their ankles, and the tags emit a light pattern as its ID. The camera on the robot is used to detect and track their positions individually. A novel approach based on a track-before-detect particle filter is proposed. It detects and tracks the tags simultaneously, even if the tags are not synchronized with the camera sampling or are not fully observable. The effectiveness of the proposed system is evaluated by experiments using a prototype personal robot. ARTICLE HISTORY