GIUC: A Gesture Interface for Ubiquitous Computing

This paper presents a vision-based gesture interface called GIUC for ubiquitous computing environments. A camera mounted on top of screen facing the user is used to capture and interpret the movements of hand gestures for intelligent human computer interactions. We propose a tracking and recognition algorithm combining particle filter algorithms and elastic graph matching to recover gesture parameters robustly against complex backgrounds. A two-hierarchical parameter estimation scheme is introduced to improve the tracking speed and accurateness. Experimental results show that the GIUC system works robustly for indoor desktop interaction environments.