《Ecient Video Cutout by Paint Selection》.pdfVIP

Zhang Y, Tang YL, Cheng KL. Efficient video cutout by paint selection. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 30(3): 467–477 May 2015. DOI 10.1007/s11390-015-1537-y Efficient Video Cutout by Paint Selection Yun Zhang 1 (Ü ! ), Yan-Long Tang 2 (/ò9 ), and Ke-Li Cheng 2 (¤Œá ) 1Institute 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 E-mail: zhangyun zju@; yanlongtang@; chengkeli@ Received December 8, 2014; revised March 6, 2015. 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, and thus could be put into practical use. Keywords video cutout, progressive, graph cut, paint selection 1 Introduction frames, users always have to repair the propagation re- sults frame by frame, which is