Abrupt Motion Tracking via Nearest Neighbor Field Driven Stochastic Sampling

Stochastic sampling based trackers have shown good performance for abrupt motion tracking so that they have gained popularity in recent years. However, conventional methods tend to use a two-stage sampling paradigm in which the search space needs to be uniformly explored with an inefficient preliminary sampling phase. In this paper, we propose a novel sampling-based method in the Bayesian filtering framework to address the problem. Within the framework, nearest neighbor field estimation is utilized to compute the importance proposal probabilities, which guide the Markov chain search towards promising regions and thus enhance the sampling efficiency; given the motion priors, a smoothing stochastic sampling Monte Carlo algorithm is proposed to approximate the posterior distribution through a smoothing weight-updating scheme. Moreover, to track the abrupt and the smooth motions simultaneously, we develop an abrupt-motion detection scheme which can discover the presence of abrupt motions during online tracking. Extensive experiments on challenging image sequences demonstrate the effectiveness and the robustness of our algorithm in handling the abrupt motions.

[1]  Faming Liang,et al.  Improving SAMC using smoothing methods: Theory and applications to Bayesian model selection problems , 2009, 0908.3553.

[2]  Z. M. Hefed Object tracking , 1999 .

[3]  W. Gilks Markov Chain Monte Carlo , 2005 .

[4]  Ying Wu,et al.  Large Displacement Optical Flow from Nearest Neighbor Fields , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Mingyu Lu,et al.  Hamiltonian Monte Carlo estimator for abrupt motion tracking , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[6]  Hailin Jin,et al.  Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow , 2014, CVPR.

[7]  Huchuan Lu,et al.  Visual tracking via adaptive structural local sparse appearance model , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Eli Shechtman,et al.  PatchMatch: a randomized correspondence algorithm for structural image editing , 2009, ACM Trans. Graph..

[9]  Yuan Li,et al.  Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans , 2007, CVPR.

[10]  Junseok Kwon,et al.  Wang-Landau Monte Carlo-Based Tracking Methods for Abrupt Motions , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Yi Wu,et al.  Online Object Tracking: A Benchmark , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Jian Sun,et al.  Computing nearest-neighbor fields via Propagation-Assisted KD-Trees , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Junseok Kwon,et al.  Visual tracking decomposition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Frank Dellaert,et al.  An MCMC-Based Particle Filter for Tracking Multiple Interacting Targets , 2004, ECCV.

[15]  Yao Lu,et al.  Nearest neighbor field driven stochastic sampling for abrupt motion tracking , 2014, 2014 IEEE International Conference on Multimedia and Expo (ICME).

[16]  Kurt Keutzer,et al.  Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow , 2010, ECCV.

[17]  Ales Leonardis,et al.  An adaptive coupled-layer visual model for robust visual tracking , 2011, 2011 International Conference on Computer Vision.

[18]  N. Paragios A level set approach for shape-driven segmentation and tracking of the left ventricle , 2003, IEEE Transactions on Medical Imaging.

[19]  Shai Avidan,et al.  Coherency Sensitive Hashing , 2011, ICCV.

[20]  Jiwen Lu,et al.  Abrupt Motion Tracking Via Intensively Adaptive Markov-Chain Monte Carlo Sampling , 2012, IEEE Transactions on Image Processing.

[21]  Seunghoon Hong,et al.  Online Graph-Based Tracking , 2014, ECCV.

[22]  Larry S. Davis,et al.  Quasi-Random Sampling for Condensation , 2000, ECCV.

[23]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[24]  Ling Shao,et al.  Recent advances and trends in visual tracking: A review , 2011, Neurocomputing.

[25]  Sze Kim Pang,et al.  On MCMC-Based particle methods for Bayesian filtering: Application to multitarget tracking , 2009, 2009 3rd IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).

[26]  Frank Dellaert,et al.  MCMC-based particle filtering for tracking a variable number of interacting targets , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Luc Van Gool,et al.  An adaptive color-based particle filter , 2003, Image Vis. Comput..

[28]  Seunghoon Hong,et al.  Visual Tracking by Sampling Tree-Structured Graphical Models , 2014, ECCV.

[29]  Yuan Li,et al.  Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Danijel Skocaj,et al.  Multivariate online kernel density estimation with Gaussian kernels , 2011, Pattern Recognit..

[31]  ShaoLing,et al.  Recent advances and trends in visual tracking , 2011 .

[32]  Ming-Hsuan Yang,et al.  Robust Object Tracking with Online Multiple Instance Learning , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  R. Carroll,et al.  Stochastic Approximation in Monte Carlo Computation , 2007 .

[34]  Patrick Pérez,et al.  Color-Based Probabilistic Tracking , 2002, ECCV.

[35]  Huchuan Lu,et al.  Robust Object Tracking via Sparse Collaborative Appearance Model , 2014, IEEE Transactions on Image Processing.

[36]  Seunghoon Hong,et al.  Orderless Tracking through Model-Averaged Posterior Estimation , 2013, 2013 IEEE International Conference on Computer Vision.

[37]  Huchuan Lu,et al.  Least Soft-Threshold Squares Tracking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[38]  G. Hua,et al.  Multi-scale visual tracking by sequential belief propagation , 2004, CVPR 2004.

[39]  Michael Isard,et al.  Object localization by Bayesian correlation , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[40]  Ian D. Reid,et al.  Stable multi-target tracking in real-time surveillance video , 2011, CVPR 2011.

[41]  Dongbing Gu,et al.  Abrupt motion tracking using a visual saliency embedded particle filter , 2014, Pattern Recognit..

[42]  Vladimir Pavlovic,et al.  Face tracking and recognition with visual constraints in real-world videos , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[43]  Jianfang Dou,et al.  Robust visual tracking based on interactive multiple model particle filter by integrating multiple cues , 2014, Neurocomputing.

[44]  W. Eric L. Grimson,et al.  Learning Patterns of Activity Using Real-Time Tracking , 2000, IEEE Trans. Pattern Anal. Mach. Intell..