Abstract-Since the advent of multitouch screens users have been able to interact using fingertip gestures in a two dimensional plane. With the development of depth cameras, such as the Kinect, attempts have been made to reproduce the detection of gestures for three dimensional interaction. Many of these use contour analysis to find the fingertips, however the success of such approaches is limited due to sensor noise and rapid movements. This paper discusses an approach to identify fingertips during rapid movement at varying depths allowing multitouch without contact with a screen. To achieve this, we use a weighted graph that is built using the depth information of the hand to determine the geodesic maxima of the surface. Fingertips are then selected from these maxima using a simplified model of the hand and correspondence found over successive frames. Our experiments show real-time performance for multiple users providing tracking at 30fps for up to 4 hands and we compare our results with stateof-the-art methods, providing accuracy an order of magnitude better than existing approaches.

No abstract

Abstract-In this paper we present an approach to hand pose estimation that combines both discriminative and modelbased methods to overcome the limitations of each technique in isolation. A Randomised Decision Forests (RDF) is used to provide an initial estimate of the regions of the hand. This initial segmentation provides constraints to which a 3D model is fitted using Rigid Body Dynamics. Model fitting is guided using point to surface constraints which bind a kinematic model of the hand to the depth cloud using the segmentation of the discriminative approach. This combines the advantages of both techniques, reducing the training requirements for discriminative classification and simplifying the optimization process involved in model fitting by incorporating physical constraints from the segmentation. Our experiments on two challenging sequences show that this combined method outperforms the current stateof-the-art approach.

No abstract