Improved Kernel-Based Object Tracking Under Occluded Scenarios
A successful approach for object tracking has been kernel based object tracking  by Comaniciu et al.. The method provides an effective solution to the problems of representation and localization in tracking. The method involves representation of an object by a feature histogram with an isotropic kernel and performing a gradient based mean shift optimization for localizing the kernel. Though robust, this technique fails under cases of occlusion. We improve the kernel based object tracking by performing the localization using a generalized (bidirectional) mean shift based optimization. This makes the method resilient to occlusions. Another aspect related to the localization step is handling of scale changes by varying the bandwidth of the kernel. Here, we suggest a technique based on SIFT features  by Lowe to enable change of bandwidth of the kernel even in the presence of occlusion. We demonstrate the effectiveness of the techniques proposed through extensive experimentation on a number of challenging data sets.
KeywordsTarget Model Scale Invariant Feature Transform Scale Change Partial Occlusion Scale Invariant Feature Transform Feature
Unable to display preview. Download preview PDF.
- 4.Babu, V., Perez, P., Bouthemy, P.: Kernel-based robust tracking for objects. In: Proc. Asian Conference on Computer Vision, Hyderabad India, Part II, pp. 353–362 (2006)Google Scholar
- 5.Isard, M., MacCormick, J.: Bramble: A bayesian multiple-blob tracker. In: Proc.IEEE International Conf. on Computer Vision (ICCV), vol. 2, pp. 34–41 (2001)Google Scholar
- 6.Comaniciu, D., Ramesh, V., Meer, P.: The variable bandwidth mean shift and data-driven scale selection. In: Proceedings of IEEE International Conference on Computer Vision, Vancouver, Canada, vol. 1, pp. 438–445 (2001)Google Scholar
- 8.Collins, R.T.: Mean shift blob tracking through scale space. In: CVPR 2003 Conference Proceedings, Madison, Wisconsin, June 2003, pp. 234–240 (2003)Google Scholar
- 10.Namboodiri, V.P., Chaudhuri, S.: Shock filters based on implicit cluster separation. In: Proc. Conference on Computer Vision and Pattern Recognition (CVPR 2005), San Diego, CA, USA, June 20-26, 2005, pp. 82–87 (2005)Google Scholar
- 11.Fisher, R.B.: Pets04 surveillance ground truth data set. In: Proc. Sixth IEEE Int. Work. on Performance Evaluation of Tracking and Surveillance, pp. 1–5 (2004)Google Scholar
- 12.Jojic, N., Frey, B.: Learning flexible sprites in video layers. In: Proc.IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 199–206 (2001)Google Scholar