Real-time Tracking of Multiple Fingertips and Its Applications for Augmented Desk Interface Systems

摘要: In this paper, we propose a fast and robust method for tracking multiple fingertips; then demonstrate gesture recognition an application based on measured fingertip trajectories augmented desk interface systems. Our can track fingertips reliably even in complex background under dynamically changing lighting condition with- out any markers. After are detected each input infrared image frame, correspondences of those between successive frames determined prediction technique. system is particularly advantageous Human-Computer Interaction (HCI) that users achieve interactions both symbolic gestures direct manipulation with their own hands.