Efficient Video Cutout by Paint Selection  

作　　者：张赟 唐延龙 成可立 

机构地区：[1]Institute of Zhejian9 Radio and TV Technology, Zhejiang University of Media and Communications Hangzhou 310018, China [2]College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China

出　　处：《Journal of Computer Science & Technology》2015年第3期467-477,共11页计算机科学技术学报（英文版）

基　　金：This work was supported by the National High Technology Research and Development 863 Program of China under Grant No. 2013AA013903, the Zhejiang Provincial Natural Science Foundation of China under Grant No. LY14F020050, and the National Basic Research 973 Program of China under Grant No. 2011CB302205. Acknowledgement The authors would like to thank anonymous reviewers and editors for their valuable comments.

摘　　要：Video cutout refers to extracting moving objects from videos, which is an important step in many video editing tasks. Recent Mgorithms have limitations in terms of efficiency interaction style and robustness. This paper presents a novel method for progressive video cutout with less user interaction and fast feedback. By exploring local and compact features, an optimization is constructed based on a graph model which establishes spatial and temporal relationship of neighboring patches in video frames. This optimization enables an efficient solution for progressive video cutout using graph cuts. Furthermore, a sampling-based method for temporally coherent matting is proposed to further refine video cutout results. Experiments demonstrate that our video cutout by paint selection is more intuitive and efficient for users than previous stroke-based methods, and thus could be put into practical use.Video cutout refers to extracting moving objects from videos, which is an important step in many video editing tasks. Recent Mgorithms have limitations in terms of efficiency interaction style and robustness. This paper presents a novel method for progressive video cutout with less user interaction and fast feedback. By exploring local and compact features, an optimization is constructed based on a graph model which establishes spatial and temporal relationship of neighboring patches in video frames. This optimization enables an efficient solution for progressive video cutout using graph cuts. Furthermore, a sampling-based method for temporally coherent matting is proposed to further refine video cutout results. Experiments demonstrate that our video cutout by paint selection is more intuitive and efficient for users than previous stroke-based methods, and thus could be put into practical use.

关 键 词：video cutout PROGRESSIVE graph cut paint selection 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论] TU561[自动化与计算机技术—计算机科学与技术]