Visual object tracking using particle filter

In this paper, we propose a new observation model with optimizing particle filter framework for visual object tracking in the present of occlusion. Most of the existing algorithms are able to track the object only in predefined and well controlled environment. In computer vision research area, it is challenging task to track when objects get close and circle each others. Some algorithm doesn't even consider the optimization problem. In this work, we develop a robust phase correlation based observation model for particle filter framework and also introduce an optimization technique to improve the performance and accuracy of tracking. Phase correlation provides straight-forward estimation of rigid translational motion between two images. Phase correlation has the advantage that it is not affected by any intensity or contrast differences between two images. Therefore, we apply the phase correlation in particle filter framework for robust tracking. To solve the optimization problem every certain time, we calculate the variance of each weight values to estimate whether there is appeared or not the similar objects around the target object. Based on the estimation results we increase or decrease the number of particles for optimization rather than generate the constant number of particles. We obtained a surprising result with the propose algorithm. Experiments of propose tracker show that our system is robust against cluttered background and optimization problem.

[1]  Alan Fern,et al.  Discriminatively trained particle filters for complex multi-object tracking , 2009, CVPR.

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

[3]  Joo Kooi Tan,et al.  A moving object tracking based on color information employing a particle filter algorithm , 2009, Artificial Life and Robotics.

[4]  Hongshi Yan,et al.  ROBUST PHASE CORRELATION BASED FEATURE MATCHINIG FOR IMAGE CO-REGISTRATION AND DEM GENERATION , 2008 .

[5]  Aamir S. Malik,et al.  Stochastic filters for object tracking , 2011, 2011 IEEE 15th International Symposium on Consumer Electronics (ISCE).

[6]  Gustavo Carneiro,et al.  Multi-scale phase-based local features , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[7]  Katja Nummiaro.  A Color-based Particle Filter , 2002 .

[8]  Patrick Pérez,et al.  An adaptive mixture color model for robust visual tracking , 2006, 2006 International Conference on Image Processing.

[9]  Sergio N. Torres,et al.  Subpixel accuracy analysis of phase correlation registration methods applied to aliased imagery , 2008, 2008 16th European Signal Processing Conference.

[10]  Bin Feng,et al.  Tracking Object by Combining Particle Filters and SIFT Features , 2009, 2009 Fifth International Conference on Image and Graphics.

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

[12]  Cedric Nishan Canagarajah,et al.  Sequential Monte Carlo tracking by fusing multiple cues in video sequences , 2007, Image Vis. Comput..

[13]  Zhidong Deng,et al.  A Post-Resampling Based Particle Filter for Online Bayesian Estimation and Tracking , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[14]  Alan Fern,et al.  Discriminatively trained particle filters for complex multi-object tracking , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.