Abstract A novel particle filter based on mean shift is presented. The standard particle filter is supposed to track a target in a whole state space. The proposed algorithm decomposes the target state space into two independent subspaces: a displacement subspace and a deformation subspace. Mean shift algorithm embedded in the particle filter is utilized to track the state transfer in displacement subspace while the particle filter is used to track the transfer in deformation space. In this way, the particle filter tracks the target in a lower order subspace and thus its realtime performance is improved. On the other hand, the mean shift algorithm is granted a new capability to track the target deformation. The validity and efficiency of the new algorithm are demonstrated by a series of real time tracking experiments.
[1] Comaniciu D, Ramesh V, Meer P. Real-Time Tracking of Non-Rigid Objects Using Mean Shift // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head, USA, 2000, Ⅰ: 142-149 [2] Zivkovic Z, Krse B. An EM-Like Algoithm for Color-Histogram-Based Object Tracking // Proc of the International Conference on Computer Vision and Pattern Recognition. Washington, USA, 2004, Ⅰ: 798-803 [3]Isard M, Blake A. Contour Tracking by Stochastic Propagation of Conditional Density // Proc of the 3th European Conference on Computer Vision. Cambridge, UK, 1996, Ⅰ: 343-356 [4] Isard M, Blake A. Icondensation: Unifying Low-Level and High-Level Tracking in a Stochastic Framework // Proc of the 5th European Conference on Computer Vision. Freiburg, Germany, 1998, Ⅰ: 893-908 [5] Wu Y, Huang T S. A Co-Inference Approach to Robust Visual Tracking // Proc of the 8th IEEE International Conference on Computer Vision. Vancouver, Canada, 2001, Ⅱ: 26-33 [6] Wu Y, Yu T, Hua G. Tracking Appearance with Occlusions // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Madison, USA, 2003, Ⅰ: 789-795 [7] Li P H, Zhang T W, Pece A C E. Visual Contour Tracking Based on Particle Filters. Image and Vision Computing, 2003, 21(1): 111-123 [8] Wu Y, Hua G, Yu T. Switching Observation Models for Contour Tracking in Clutter // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Madison, USA, 2003, I: 295-302 [9] Nummiaro K, Koller-Meier E, van Gool L. An Adaptive Color-Based Particle Filter. Image and Vision Computing, 2003, 21(1): 99-110 [10] Nait-Charif H, McKenna S J. Tracking Poorly Modelled Motion Using Particle Filters with Iterated Likelihood Weighting // Proc of the Asian Conference on Computer Vision. Jeju Island, Korea, 2004: 156-161 [11] Birchfield S. Elliptical Head Tracking Using Intensity Gradients and Color Histograms // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Santa Borbara, USA, 1998: 232-237
2006, Vol. 19 
