Proper

Abstract

In this paper, we describe a hand tracking system using a RGB-D camera. The user's 3D geometry is obtained from the depth capture device, and the user's hand information is computed based on the depth image. In addition, we restrict the hand tracking area within a predefined space in order to minimize the hand tracking error. The shape of the tracking area is determined according to the statistics of the user’s motion. The proposed system aims to be employed in diverse kiosk systems. The experimental results verify accuracy and efficiency of the proposed system.