Abstract
We have proposed a novel approach to the tracking of multiple people before, during and after occlusions. The method is intended to deliver better segmentation from low resolution and noisy data using any background subtraction algorithm. A simple and novel tracking algorithm based on the region segmentation is presented. This can track clearly visible targets and occluded targets, even when the occlusion involves several people. We have also proposed a novel testing criterion for checking the effectiveness of any tracking algorithm during occlusions. Sample results are presented indicating the effectiveness of the algorithm.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing|Proc. Fourth IASTED Int. Conf. Visual. Imaging Imag. Process. |
| Editors | J.J. Villanueva |
| Pages | 670-675 |
| Number of pages | 5 |
| Publication status | Published - 2004 |
| Event | Proceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing - Marbella Duration: 1 Jul 2004 → … |
Conference
| Conference | Proceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing |
|---|---|
| City | Marbella |
| Period | 1/07/04 → … |
Keywords
- Histogram matching and computer vision
- Occlusion
- Tracking