Enabling gesture interaction with 3D point cloud

Abstract

This paper presents a novel 3D point cloud gesture recognition system, based on an existing low-cost, accurate and easy to implement 2D point cloud gesture recognition system called $P. Our work improves recognition rates and lowers algorithmic complexity. We develop new 3D gestures, such as the GUN gesture and the SHAKE gesture, while also developing 3D poses like the L pose, OK pose, ROCK pose and PEACE pose for the LeapMotion Device. We demonstrate proposed gesture and pose methods on various 3D environments including a Monsoon mini-game, a cave painting interaction and a target practice scene. The average recognition rates for 3D gestures and poses were compared against the 2D, 3D and 3D+ recognition systems. The results indicate that most gestures in the proposed system were improved in comparison to the existing ones.