| Paper: | WP-P3.7 |
| Session: | Video Object Segmentation and Tracking III / Video Shot/Scene Segmentation |
| Time: | Wednesday, September 19, 14:30 - 17:10 |
| Presentation: |
Poster
|
| Title: |
A HIGH DIMENSIONAL FRAMEWORK FOR JOINT COLOR-SPATIAL SEGMENTATION |
| Authors: |
Sylvain Boltz; I3S Laboratory | | |
| | Eric Debreuve; I3S Laboratory | | |
| | Michel Barlaud; I3S Laboratory | | |
| Abstract: |
This paper deals with region-of-interest (ROI) segmentation in video sequences. The goal is to determine in successive frames the region which best matches, in terms of a similarity measure, a ROI defined in a reference frame. Color and geometry can be combined in a joint PDF. However such high-dimensional PDFs being hard to estimate, measures based on PDF distances may lead to incorrect segmentations. Here, we propose to use an estimate of the Kullback-Leibler divergence adapted to high-dimensional PDFs. It is defined from the samples using the kth-nearest neighbor (kNN) framework and it is differentiated for active contour implementation and expressed in both the continuous form and a kNN form. Results are presented on standard sequences. |
