Journal of Computer Science and Technology
Quick Search in JCST
 Advanced Search 
      Home | PrePrint | SiteMap | Contact Us | Help
 
Indexed by   SCIE, EI ...
Bimonthly    Since 1986
Journal of Computer Science and Technology 2015, Vol. 30 Issue (3) :467-477    DOI: 10.1007/s11390-015-1537-y
Special Section on Computational Visual Media << Previous Articles | Next Articles >>
基于笔画选取的高效视频对象切割
Yun Zhang1(张赟), Yan-Long Tang2(唐延龙), Ke-Li Cheng2(成可立)
1. Institute of Zhejiang 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
Efficient Video Cutout by Paint Selection
Yun Zhang1(张赟), Yan-Long Tang2(唐延龙), Ke-Li Cheng2(成可立)
1. Institute of Zhejiang 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

摘要
参考文献
相关文章
Download: [PDF 9968KB]  
摘要 视频对象切割是从视频中提取出运动的对象,这是许多视频编辑任务中的重要操作.由于前人提出的算法在效率、交互方式和稳定性方面存在不足,本文提出了用于视频对象逐步提取的新方法.该方法减少了人工交互并能为用户提供快速的结果反馈.通过提取局部和紧凑的视频特征,建立了基于图的优化模型.该模型为视频中所有空域和时域上相邻的块建立了联系.该优化能够通过图割算法高效求解,进而得到视频对象逐步提取的结果.进一步地,本文提出了基于采样的帧间连续的透明值抠图算法来进一步提升视频对象提取的效果.实验结果表明本文提出的基于笔画选取的视频对象切割算法比先前基于笔画交互的方法更加直观和高效,因此能够应用于实际.
关键词视频对象切割   逐步地   图割   笔画选取     
Abstract: Video cutout refers to extracting moving objects from videos, which is an important step in many video editing tasks. Recent algorithms 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, thus could be put into practical use.
Keywordsvideo cutout   progressive   graph cuts   paint selection     
Received 2014-12-08;
本文基金:

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.

About author: Yun Zhang is an assistant professor in Zhejiang University of Media and Communications, Hangzhou. He received his B.S. and M.S. degrees in computer science from Hangzhou Dianzi University, Hangzhou, in 2006 and 2009 respectively, and Ph.D. degree in computer science from Zhejiang University, Hangzhou, in 2013. His research interests include image/video editing and computer vision.
引用本文:   
Yun Zhang, Yan-Long Tang, Ke-Li Cheng.基于笔画选取的高效视频对象切割[J]  Journal of Computer Science and Technology , 2015,V30(3): 467-477
Yun Zhang, Yan-Long Tang, Ke-Li Cheng.Efficient Video Cutout by Paint Selection[J]  Journal of Computer Science and Technology, 2015,V30(3): 467-477
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-015-1537-y
Copyright 2010 by Journal of Computer Science and Technology