3-D Motion Recovery Via Low Rank Matrix Restoration And Wavelet Transformation On Articulation Graphs

With the development of information technology and the popularization of multimedia equipment,accurate capture of images,videos and 3D models has become an urgent need.Traditional motion capture systems have increased the research cost of these specific fields through its numerous shortcomings:inconvenient implementation,expensive prices,difficult to maintain,and need a lot of manual operations.Microsoft Kinect for Xbox 360("Kinect")has shed a light on human motion capture.With the advent of Microsoft Kinect and similar devices,significant effort and advances have been made in recent years for low-cost,accessible human motion tracking systems.This paper addresses the challenge of 3-D skeleton recovery by exploiting the spatio-temporal correlations of corrupted 3-D skeleton sequences.A skeleton sequence is represented as a matrix.We propose a novel low-rank solution that effectively integrates both a low-rank model for robust skeleton recovery based on temporal coherence,and an articulation-graph-based isometric constraint for spatial coherence,namely consistency of bone lengths.The proposed model is formulated as a constrained optimization problem,which is efficiently solved by the Augmented Lagrangian Method with a Gauss-Newton solver for the subproblem of isometric optimization.Experimental results on the CMU motion capture dataset and a Kinect dataset show that the proposed approach achieves better recovery accuracy over a state-of-the-art method.The proposed method has wide applicability for skeleton tracking devices,such as the Kinect,because these devices cannot provide accurate reconstructions of complex motions,especially in the presence of occlusion.