A hierarchical feature fusion framework for adaptive visual tracking

A Hierarchical Model Fusion (HMF) framework for object tracking in video sequences is presented. The Bayesian tracking equations are extended to account for multiple object models. With these equations as a basis a particle filter algorithm is developed to efficiently cope with the multi-modal distributions emerging from cluttered scenes. The update of each object model takes place hierarchically so that the lower dimensional object models, which are updated first, guide the search in the parameter space of the subsequent object models to relevant regions thus reducing the computational complexity. A method for object model adaptation is also developed. We apply the proposed framework by fusing salient points, blobs, and edges as features and verify experimentally its effectiveness in challenging conditions.

[1]  Serge J. Belongie,et al.  Tracking multiple mouse contours (without too many samples) , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[2]  Thomas B. Moeslund,et al.  A Survey of Computer Vision-Based Human Motion Capture , 2001, Comput. Vis. Image Underst..

[3]  Bernt Schiele,et al.  Towards Robust Multi-cue Integration for Visual Tracking , 2001, ICVS.

[4]  J. Odobez,et al.  Embedding Motion in Model-Based Stochastic Tracking , 2004, IEEE Transactions on Image Processing.

[5]  Jun S. Liu,et al.  Sequential Monte Carlo methods for dynamic systems , 1997 .

[6]  Anton van den Hengel,et al.  Probabilistic Multiple Cue Integration for Particle Filter Based Tracking , 2003, DICTA.

[7]  Michael Isard,et al.  BraMBLe: a Bayesian multiple-blob tracker , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[8]  Ying Wu,et al.  Robust Visual Tracking by Integrating Multiple Cues Based on Co-Inference Learning , 2004, International Journal of Computer Vision.

[9]  Jiang Li,et al.  Transductive local exploration particle filter for object tracking , 2007, Image Vis. Comput..

[10]  Michael Isard,et al.  ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework , 1998, ECCV.

[11]  Francesc Moreno-Noguer,et al.  Dependent Multiple Cue Integration for Robust Tracking , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Patrick Pérez,et al.  Data fusion for visual tracking with particles , 2004, Proceedings of the IEEE.

[13]  Roberto Cipolla,et al.  Learning to track with multiple observers , 2009, CVPR.

[14]  F. Dellaert,et al.  A Rao-Blackwellized particle filter for EigenTracking , 2004, CVPR 2004.

[15]  Michael Isard,et al.  Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking , 2000, ECCV.

[16]  T. List,et al.  Comparison of target detection algorithms using adaptive background models , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[17]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Nando de Freitas,et al.  An Introduction to MCMC for Machine Learning , 2004, Machine Learning.

[19]  Yuan Li,et al.  Robust Head Tracking Based on a Multi-State Particle Filter , 2006, 7th International Conference on Automatic Face and Gesture Recognition (FGR06).

[20]  Jean-Marc Odobez,et al.  Dynamic Partitioned Sampling For Tracking With Discriminative Features , 2009, BMVC.

[21]  Robert T. Collins,et al.  Likelihood Map Fusion for Visual Object Tracking , 2008, 2008 IEEE Workshop on Applications of Computer Vision.

[22]  David J. Fleet,et al.  Robust Online Appearance Models for Visual Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Dariu Gavrila,et al.  The Visual Analysis of Human Movement: A Survey , 1999, Comput. Vis. Image Underst..

[24]  Mark J. F. Gales,et al.  Product of Gaussians for speech recognition , 2006, Comput. Speech Lang..

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

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

[27]  Francesc Moreno-Noguer,et al.  Fusion of a Multiple Hypotheses Color Model and Deformable Contours for Figure Ground Segmentation in Dynamic Environments , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[28]  Emilio Maggio,et al.  Adaptive Multifeature Tracking in a Particle Filtering Framework , 2007, IEEE Transactions on Circuits and Systems for Video Technology.

[29]  Radford M. Neal.  Probabilistic Inference Using Markov Chain Monte Carlo Methods , 2011 .

[30]  Patrick Pérez,et al.  Towards Improved Observation Models for Visual Tracking: Selective Adaptation , 2002, ECCV.

[31]  Peihua Li,et al.  Image Cues Fusion for Object Tracking Based on Particle Filter , 2004, AMDO.

[33]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[34]  Sergios Theodoridis,et al.  Hierarchical Feature Fusion for Visual Tracking , 2007, 2007 IEEE International Conference on Image Processing.

[35]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

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