Human motion segmentation by RPCA with Augmented Lagrange Multiplier

This paper proposes a fast and efficient algorithm, named Robust Principal Component Analysis (RPCA), for solving human motion segmentation. Given the human motion video each frame, and in many cases, it is reasonable to assume that the background vitiations are low-rank, while the foreground human motion is spatially localized, and therefore sparse. The human motion part is obtained by recovering the low-rank and sparse matrix. This process is formulated as a convex optimization problem that minimizes a constrained combination of nuclear norm and ℓ1-norm, which can be solved efficiently with Augmented Lagrange Multiplier (ALM) method. Compared to previous method for Human motion segmentation, the proposed method produces more reliable results, and is more robust to noise, yet being much faster and efficient. We do some experiments on the HumanEva human motion dataset. The results show that human motion segmentation by the proposed method is novel and promising.

[1]  Yasuyuki Matsushita,et al.  Camera calibration with lens distortion from low-rank textures , 2011, CVPR 2011.

[2]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[3]  Yi Ma,et al.  TILT: Transform Invariant Low-Rank Textures , 2010, ACCV.

[4]  Larry S. Davis,et al.  Shape-Based Human Detection and Segmentation via Hierarchical Part-Template Matching , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Dimitri P. Bertsekas,et al.  Constrained Optimization and Lagrange Multiplier Methods , 1982 .

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

[7]  Emmanuel J. Candès,et al.  The Power of Convex Relaxation: Near-Optimal Matrix Completion , 2009, IEEE Transactions on Information Theory.

[8]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[9]  Jun-Wei Hsieh,et al.  Segmentation of Human Body Parts Using Deformable Triangulation , 2006, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[10]  Chia-Feng Juang,et al.  Computer Vision-Based Human Body Segmentation and Posture Estimation , 2009, SMC 2009.

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

[12]  John Wright,et al.  Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization , 2009, NIPS.

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

[14]  Emmanuel J. Candès,et al.  Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies? , 2004, IEEE Transactions on Information Theory.

[15]  Michael J. Black,et al.  A Quantitative Evaluation of Video-based 3D Person Tracking , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[16]  Yun Fu,et al.  Human Motion Tracking by Temporal-Spatial Local Gaussian Process Experts , 2011, IEEE Transactions on Image Processing.

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

[18]  Michael J. Black,et al.  HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion , 2010, International Journal of Computer Vision.

[19]  Hossein Mobahi,et al.  Holistic 3D reconstruction of urban structures from low-rank textures , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[20]  John Wright,et al.  Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization , 2009, NIPS.

[21]  Yongtian Wang,et al.  Robust Photometric Stereo via Low-Rank Matrix Completion and Recovery , 2010, ACCV.

[22]  John Wright,et al.  RASL: Robust Alignment by Sparse and Low-Rank Decomposition for Linearly Correlated Images , 2012, IEEE Trans. Pattern Anal. Mach. Intell..