Sciweavers

ICCV
2009
IEEE

Video object segmentation by tracking regions

13 years 9 months ago
Video object segmentation by tracking regions
This paper presents an approach to unsupervised segmentation of moving and static objects occurring in a video. Objects are, in general, spatially cohesive and characterized by locally smooth motion trajectories. Therefore, they occupy regions within each frame. The shape and location of these regions vary slowly from frame to frame. Thus, video segmentation can be done by tracking regions across the frames such that the resulting tracks are locally smooth. To this end, we use a low-level segmentation to extract regions in all frames. Then, similar regions are transitively matched and clustered across the video. Region similarity is defined with respect to geometric and motion properties of region contours. To match region contours, we formulate a new circular dynamic-time warping (CDTW) algorithm that generalizes DTW to closed contours, without compromising the optimality and low complexity of DTW. Our quantitative evaluation and comparison with the state of the art suggest that the ...
William Brendel, Sinisa Todorovic
Added 18 Feb 2011
Updated 18 Feb 2011
Type Journal
Year 2009
Where ICCV
Authors William Brendel, Sinisa Todorovic
Comments (0)