3-D motion recovery via low rank matrix analysis

Skeleton tracking is a useful and popular application of Kinect. However, it cannot provide accurate reconstructions for complex motions, especially in the presence of occlusion. This paper proposes a new 3-D motion recovery method based on low-rank matrix analysis to correct invalid or corrupted motions. We address this problem by representing a motion sequence as a matrix, and introducing a convex low-rank matrix recovery model, which fixes erroneous entries and finds the correct low-rank matrix by minimizing nuclear norm and norm of constituent clean motion and error matrices. Experimental results show that our method recovers the corrupted skeleton joints, achieving accurate and smooth reconstructions even for complicated motions.

[1]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[2]  Jessica K. Hodgins,et al.  Performance animation from low-dimensional control signals , 2005, SIGGRAPH 2005.

[3]  Emmanuel J. Candès,et al.  A Singular Value Thresholding Algorithm for Matrix Completion , 2008, SIAM J. Optim..

[4]  S. Yun,et al.  An accelerated proximal gradient algorithm for nuclear norm regularized linear least squares problems , 2009 .

[5]  Taku Komura,et al.  Learning motion manifolds with convolutional autoencoders , 2015, SIGGRAPH Asia Technical Briefs.

[6]  G. Sapiro,et al.  A collaborative framework for 3D alignment and classification of heterogeneous subvolumes in cryo-electron tomography. , 2013, Journal of structural biology.

[7]  Jinxiang Chai,et al.  Accurate realtime full-body motion capture using a single depth camera , 2012, ACM Trans. Graph..

[8]  Andrew W. Fitzgibbon,et al.  3D scanning deformable objects with a single RGBD sensor , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Xiaogang Wang,et al.  Multi-source Deep Learning for Human Pose Estimation , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Jonathan W. Decker,et al.  Performance measurements for the Microsoft Kinect skeleton , 2012, 2012 IEEE Virtual Reality Workshops (VRW).

[11]  Chong Wang,et al.  Superpixel-Based Hand Gesture Recognition With Kinect Depth Camera , 2015, IEEE Transactions on Multimedia.

[12]  Kun Li,et al.  Nonrigid Structure From Motion via Sparse Representation , 2015, IEEE Transactions on Cybernetics.

[13]  Yi Ma,et al.  The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices , 2010, Journal of structural biology.

[14]  Andrew Blake,et al.  Efficient Human Pose Estimation from Single Depth Images , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Zeyu Chen,et al.  Gesture Recognition by Using Kinect Skeleton Tracking System , 2013, 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics.

[16]  Petros Daras,et al.  Fast and smooth 3D reconstruction using multiple RGB-Depth sensors , 2014, 2014 IEEE Visual Communications and Image Processing Conference.

[17]  Christian Szegedy,et al.  DeepPose: Human Pose Estimation via Deep Neural Networks , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Petros Daras,et al.  Quaternionic Signal Processing Techniques for Automatic Evaluation of Dance Performances From MoCap Data , 2014, IEEE Transactions on Multimedia.

[19]  Bruno Raffin,et al.  3D Skeleton-Based Body Pose Recovery , 2006, Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06).

[20]  Ronan Boulic,et al.  An inverse kinematics architecture enforcing an arbitrary number of strict priority levels , 2004, The Visual Computer.

[21]  Samuel B. Williams,et al.  ASSOCIATION FOR COMPUTING MACHINERY , 2000 .

[22]  Shawmin Lei,et al.  Real-time hand tracking on depth images , 2011, 2011 Visual Communications and Image Processing (VCIP).

[23]  Stepán Obdrzálek,et al.  Accuracy and robustness of Kinect pose estimation in the context of coaching of elderly population , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.