Title :
The Research of Video Object Segmentation Based on Shape Confidence
Author :
Li, Shaobin ; Wang, Xiaomeng
Author_Institution :
Radio & Telev. Eng. Dept., Commun. Univ. of China, Beijing, China
Abstract :
This paper advanced a kind of video object segmentation arithmetic. This arithmetic first segmented the video reference frame by Graph cuts with user interactive behaviors, got accurate object contour. Then, it calculated shape confidence with geodesic distance, and combined color model with shape model adaptively. Finally, it constructed Graph energy function, and segments with Graph Cuts. This arithmetic can provide satisfied segmentation result when there is very little difference between foreground and background.
Keywords :
differential geometry; graph theory; image colour analysis; image segmentation; video signal processing; color model; geodesic distance; graph cuts; graph energy function; shape confidence; shape model; user interactive behaviors; video object segmentation arithmetic; video reference frame; Adaptation models; Color; Computer vision; Image color analysis; Motion segmentation; Object segmentation; Shape; GMM; Graph Cuts; geodesic distance; object segmentation; shape confidence;
Conference_Titel :
Computer Science & Service System (CSSS), 2012 International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4673-0721-5
DOI :
10.1109/CSSS.2012.452