Key-segments for video object segmentation

Yong Jae Lee, Jaechul Kim, Kristen Grauman
2011 2011 International Conference on Computer Vision  
We present an approach to discover and segment foreground object(s) in video. Given an unannotated video sequence, the method first identifies object-like regions in any frame according to both static and dynamic cues. We then compute a series of binary partitions among those candidate "key-segments" to discover hypothesis groups with persistent appearance and motion. Finally, using each ranked hypothesis in turn, we estimate a pixel-level object labeling across all frames, where (a) the
more » ... und likelihood depends on both the hypothesis's appearance as well as a novel localization prior based on partial shape matching, and (b) the background likelihood depends on cues pulled from the key-segments' (possibly diverse) surroundings observed across the sequence. Compared to existing methods, our approach automatically focuses on the persistent foreground regions of interest while resisting oversegmentation. We apply our method to challenging benchmark videos, and show competitive or better results than the state-of-the-art. part by DARPA Mind's Eye W911NF-10-2-0059, LLNL B594497, and CSSG N11AP20004. Key-segments (1) Key-segments (1) Key-segments (2) Key-segments (4) Key-segments (1) Key-segments (1) Key-segments (1) Key-segments (1)
doi:10.1109/iccv.2011.6126471 dblp:conf/iccv/LeeKG11 fatcat:722kgevi5jhipdcad2m6nafz5q