Bidirectional Markov Chain Monte Carlo Particle Filter for Articulated Human Motion Tracking

A novel framework of particle filter, named bidirectional Markov chain Monte Carlo particle filter (BMCMCPF), has been proposed to estimate articulated human movement state and action category jointly. Owing to the reason that we regard action category as the estimated state in our framework, firstly the motion models for every possible action are built via autoregressive modeling for the captured motion data with minimum distance. Meanwhile, the dynamic model and observation model also get coupled so that tracking and recognition can achieve synchronously. Then, the state estimation is completed by using the bidirectional Marko chain Monte Carlo sampling. BMCMCPF can not only improve the tracking performance as its global optimization property, but also smooth the joint’s movement trajectories to ensure the motion coordination. The experimental results on HumanEva datasets show that the effectiveness of BMCMCPF with unknown motion modality in solving the tracking problem.

[1]  F. Charpillet,et al.  Factored Interval Particle Filtering for Gait Analysis , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  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.

[3]  David J. Fleet,et al.  Dynamical binary latent variable models for 3D human pose tracking , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Xianghua Xie,et al.  Tracking 3D human pose with large root node uncertainty , 2011, CVPR 2011.

[5]  Rui Li,et al.  3D Human Motion Tracking with a Coordinated Mixture of Factor Analyzers , 2009, International Journal of Computer Vision.

[6]  Jakub M. Tomczak,et al.  Articulated tracking with manifold regularized particle filter , 2016, Machine Vision and Applications.

[7]  Ankur Agarwal,et al.  Tracking Articulated Motion Using a Mixture of Autoregressive Models , 2004, ECCV.

[8]  A. M. Khalili,et al.  Quantum particle filter: a multiple mode method for low delay abrupt pedestrian motion tracking , 2015 .

[9]  Francisco Madrigal,et al.  Evaluation of multiple motion models for multiple pedestrian visual tracking , 2013, 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[10]  Y. Bar-Shalom,et al.  The interacting multiple model algorithm for systems with Markovian switching coefficients , 1988 .

[11]  I-Cheng Chang,et al.  Dynamic Kernel-Based Progressive Particle Filter for 3D Human Motion Tracking , 2009, ACCV.

[12]  Svetha Venkatesh,et al.  A Study on Smoothing for Particle-Filtered 3D Human Body Tracking , 2010, International Journal of Computer Vision.

[13]  I-Cheng Chang,et al.  3D human motion tracking based on a progressive particle filter , 2010, Pattern Recognit..

[14]  David J. Fleet.  Motion Models for People Tracking , 2011, Visual Analysis of Humans.

[15]  Qiang Guo,et al.  Continuous action recognition based on hybrid CNN-LDCRF model , 2016, 2016 International Conference on Image, Vision and Computing (ICIVC).

[16]  X. R. Li,et al.  Survey of maneuvering target tracking. Part I. Dynamic models , 2003 .

[17]  Chung-Lin Huang,et al.  Human Motion Parameter Capturing Using Particle Filter and Nonparametric Belief Propagation , 2008, 2008 IEEE Southwest Symposium on Image Analysis and Interpretation.

[18]  I-Cheng Chang,et al.  3D Human Motion Tracking Using Progressive Particle Filter , 2008, ISVC.

[19]  Michael J. Black,et al.  HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion , 2006 .