Title :
An interactive video segmentation approach based on GrabCut algorithm
Author :
Yang, Lei ; Guo, Yiming ; Wu, Xiaoyu ; Li, Shaobin
Author_Institution :
Digital Media Dept., Commun. Univ. of China, Beijing, China
Abstract :
GrabCut is a classical efficient algorithm used in image segmentation. In this paper we apply the approach to video matting in respects as follow: First, user scribbles interactive information in the key frame, which is similar to the interactive segmentation method GrabCut algorithm. Secondly, estimate the probable foreground region by block-matching and then get the segmentation result by GrabCut operator. In addition, morphological approaches are used to make the extracted foreground smooth. Experiments result is demonstrated at the end of this paper, proving the method is efficient, especially to the video in which foreground object moves.
Keywords :
feature extraction; graph theory; image matching; image segmentation; video signal processing; GrabCut algorithm; block-matching; foreground smooth extraction; image segmentation; interactive video segmentation method; video matting; Algorithm design and analysis; Educational institutions; Image color analysis; Image segmentation; Motion estimation; Motion segmentation; Signal processing algorithms; Block matching; GrabCut; Interactive video segmentation; Motion estimation; Open operation;
Conference_Titel :
Image and Signal Processing (CISP), 2011 4th International Congress on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-9304-3
DOI :
10.1109/CISP.2011.6100014