Efficient Human Body Tracking by Quick Shift Belief Propagation

We propose a novel and efficient approach for tracking 2D articulated human body parts. In our approach, the human body is modeled by a graphical model where each part is represented by a node and the relationship between a pair of adjacent parts is indicated by an edge in the graph. Various approaches have been proposed to solve such problems, but efficiency is still a vital problem. We present a new Quick Shift Belief Propagation (QSBP) based approach which benefits from Quick Shift, a simple and efficient mode seeking method, in a part based belief propagation model. The unique aspect of this model is its ability to efficiently discover modes of the underlying marginal probability distribution while preserving the accuracy. This gives QSBP a significant advantage over approaches like Belief Propagation (BP) and Mean Shift Belief Propagation (MSBP). Moreover, we demonstrate the use of QSBP with an action based model; this provides additional advantages of handling self-occlusion and further reducing the search space. We present qualitative and quantitative analysis of the proposed approach with encouraging results.

[1]  David J. Fleet,et al.  Monocular 3-D Tracking of the Golf Swing , 2005, CVPR.

[2]  Michael Isard,et al.  Attractive People: Assembling Loose-Limbed Models using Non-parametric Belief Propagation , 2003, NIPS.

[3]  Stefano Soatto,et al.  Quick Shift and Kernel Methods for Mode Seeking , 2008, ECCV.

[4]  Michael Isard,et al.  Tracking loose-limbed people , 2004, CVPR 2004.

[5]  Yang Wang,et al.  Multiple Tree Models for Occlusion and Spatial Constraints in Human Pose Estimation , 2008, ECCV.

[6]  Michael Isard,et al.  PAMPAS: real-valued graphical models for computer vision , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[7]  Tony X. Han,et al.  Efficient Nonparametric Belief Propagation with Application to Articulated Body Tracking , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[8]  Mubarak Shah,et al.  Geometric constraints on 2D action models for tracking human body , 2008, 2008 19th International Conference on Pattern Recognition.

[9]  Gang Hua,et al.  Learning to estimate human pose with data driven belief propagation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Yanxi Liu,et al.  Efficient mean shift belief propagation for vision tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Anton van den Hengel,et al.  2D articulated tracking with dynamic Bayesian networks , 2004, The Fourth International Conference onComputer and Information Technology, 2004. CIT '04..

[12]  Michael J. Black,et al.  Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[13]  Michael I. Mandel,et al.  Visual Hand Tracking Using Nonparametric Belief Propagation , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[14]  Gang Hua,et al.  Tracking articulated body by dynamic Markov network , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[15]  Andrew Zisserman,et al.  Tracking People by Learning Their Appearance , 2007 .

[16]  Ramakant Nevatia,et al.  Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[17]  Takeo Kanade,et al.  Mode-seeking by Medoidshifts , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[18]  Michael I. Mandel,et al.  Distributed Occlusion Reasoning for Tracking with Nonparametric Belief Propagation , 2004, NIPS.

[19]  Rashid Ansari,et al.  Kernel particle filter: iterative sampling for efficient visual tracking , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[20]  Jianbo Shi,et al.  Multiple frame motion inference using belief propagation , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[21]  James W. Davis,et al.  The Recognition of Human Movement Using Temporal Templates , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Adam Prügel-Bennett,et al.  A Bayesian Framework for Extracting Human Gait Using Strong Prior Knowledge , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  H. Sidenbladh,et al.  Detecting human motion with support vector machines , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[24]  David J. Fleet,et al.  People tracking using hybrid Monte Carlo filtering , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[25]  Gary R. Bradski,et al.  Motion segmentation and pose recognition with motion history gradients , 2002, Machine Vision and Applications.

[26]  William T. Freeman,et al.  Nonparametric belief propagation , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[27]  David A. Forsyth,et al.  Strike a pose: tracking people by finding stylized poses , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[28]  Yizong Cheng,et al.  Mean Shift, Mode Seeking, and Clustering , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Daniel P. Huttenlocher,et al.  Pictorial Structures for Object Recognition , 2004, International Journal of Computer Vision.

[30]  Andrew Blake,et al.  Articulated body motion capture by annealed particle filtering , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).