Evaluation of multiple motion models for multiple pedestrian visual tracking

Multiple targets tracking is a challenging problem due to occlusions or identity switching. Although the use of prior information about the motion of the targets improves the tracking results, a single motion model may not capture the complex dynamic of the targets. This is a common situation with pedestrians, as each person moves in its own way, making tracking a difficult task. In this paper, this problem is faced by using a proposal based on the Interacting Multiple Model (IMM) and implemented in a Bayesian scheme through a particle filter. The core of this approach is to leave the filter choose the motion model that fits better the motion of the targets. The algorithm is evaluated, under several combinations of motion models, with middle-dense crowded scenes from the PETS 2009 dataset.

[1]  Bor-Sen Chen,et al.  Novel extended Viterbi-based multiple-model algorithms for state estimation of discrete-time systems with Markov jump parameters , 2006, IEEE Transactions on Signal Processing.

[2]  Jianyu Yang,et al.  A Computationally Efficient Particle Filter for Multitarget Tracking Using an Independence Approximation , 2013, IEEE Transactions on Signal Processing.

[3]  Subhash Challa,et al.  Tracking pedestrians using smoothed colour histograms in an interacting multiple model framework , 2011, 2011 18th IEEE International Conference on Image Processing.

[4]  Francisco Madrigal,et al.  Learning and Regularizing Motion Models for Enhancing Particle Filter-Based Target Tracking , 2011, PSIVT.

[5]  Pascal Fua,et al.  Tracking multiple people under global appearance constraints , 2011, 2011 International Conference on Computer Vision.

[6]  Alfred O. Hero,et al.  Multiple Model Particle Filtering For Multi-Target Tracking , 2004 .

[7]  Fuqiang Liu,et al.  Spatiotemporal energy modeling for foreground segmentation in multiple object tracking , 2011, 2011 IEEE International Conference on Robotics and Automation.

[8]  A. Ellis,et al.  PETS2010 and PETS2009 Evaluation of Results Using Individual Ground Truthed Single Views , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[9]  Y. Boers,et al.  Interacting multiple model particle filter , 2003 .

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

[11]  P. H. Foo.  Combining the interacting multiple model method with particle filters for manoeuvring target tracking with a multistatic radar system , 2011 .

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