Robust tracking method by MeanShift using Spatiograms

For tracking a non-rigid moving object in a video sequence, it is effective to evaluate the similarity of color histograms. The MeanShift algorithm is one of the popular algorithms. However, MeanShift algorithm may be unable to correspond to extreme changes of the target rotation movement and rapid movement. Recently, Spatiograms which extended the histogram is also studied and the validity is proved. This paper presents a method combined with Spatiograms and MeanShift in order to respond to changes which cannot be tracking by the conventional MeanShift algorithm, and we aimed at robust tracking.

[1]  Stanley T. Birchfield,et al.  Spatiograms versus histograms for region-based tracking , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[2]  Dorin Comaniciu,et al.  Real-time tracking of non-rigid objects using mean shift , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[3]  Robert T. Collins,et al.  Mean-shift blob tracking through scale space , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[4]  Stan Birchfield,et al.  Spatial Histograms for Region‐Based Tracking , 2007 .

[5]  Ehud Rivlin,et al.  Robust Fragments-based Tracking using the Integral Histogram , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[6]  Ingvar Claesson,et al.  On histograms and spatiograms - introduction of the mapogram , 2008, 2008 15th IEEE International Conference on Image Processing.

[7]  Hanqing Lu,et al.  Probabilistic tracking on Riemannian manifolds , 2008, 2008 19th International Conference on Pattern Recognition.

[8]  Dorin Comaniciu,et al.  Kernel-Based Object Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..