Rough set based image segmentation of video sequences

Authors:
Young Sub Song;Hang Joon Kim
Affiliations:
Department of Computer Engineering, Kyungpook National Univ., Daegu, Republic of Korea;Department of Computer Engineering, Kyungpook National Univ., Daegu, Republic of Korea
Venue:
RSCTC'06 Proceedings of the 5th international conference on Rough Sets and Current Trends in Computing
Year:
2006

Citing 3
Cited 0

Rough classification

International Journal of Human-Computer Studies - Special issue: 1969-1999, the 30th anniversary
Context-Based Segmentation of Image Sequences

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiple motion segmentation with level sets

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a rough set based segmentation method of video sequences. In a frame, there are many objects and a background. We represent theses objects and a background by regions. We consider that each object or background is a region. This region is represented by a rough set. Rough set is approximately representation of a crisp set. Our method consists of two phases. First phase is updating regions phase that consist three steps. First step is setting initial parameters. We use previous regions’ parameters to initial parameters. Second step is updating object regions. Updating is by hill climbing method with our evaluation function. Third step is updating a background region. The background region is updated by using other regions. In second phase, we make a segmentation map of frame using the regions. An ambiguous pixel’s label is decided using distance with regions.