Improving video foreground segmentation and propagation through multifeature fusion

doi:10.1117/1.JEI.24.6.063017

	Improving video foreground segmentation and propagation through multifeature fusion
	Cheng, Xiaoliu 1,2; Wang, Yan 1; Yuan, Xiaobing 1; Li, Baoqing 1; Ding, Yuanyuan 1,2; Zhang, Zebin 1,2
	2015-11-01
发表期刊	JOURNAL OF ELECTRONIC IMAGING
ISSN	1017-9909
卷号	24 期号:6 页码:12
摘要	Video foreground segmentation lays the foundation for many high-level visual applications. However, how to dig up the effective features for foreground propagation and how to intelligently fuse the different information are still challenging problems. We aim to deal with the above-mentioned problems, and the goal is to accurately propagate the object across the rest of the frames given an initially labeled frame. Our contributions are summarized as follows: (1) we describe the object features with superpixel-based appearance and motion clues from both global and local viewpoints. Furthermore, the objective confidences for both the appearance and motion features are also introduced to balance the different clues. (2) All the features and their confidences are intelligently fused by the improved Dempster-Shafer evidence theory instead of the empirical parameters tuning used in many algorithms. Experimental results on the two well-known SegTrack and SegTrack v2 datasets demonstrate that our algorithm can yield high-quality segmentations. (C) 2015 SPIE and IS&T
关键词	video foreground segmentation object propagation superpixels mapping feature confidence feature fusion improved Dempster-Shafer evidence theory
DOI	10.1117/1.JEI.24.6.063017
收录类别	SCI
语种	英语
WOS研究方向	Engineering ; Optics ; Imaging Science & Photographic Technology
WOS类目	Engineering, Electrical & Electronic ; Optics ; Imaging Science & Photographic Technology
WOS记录号	WOS:000375861200010
出版者	IS&T & SPIE
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/8557
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Cheng, Xiaoliu
作者单位	1.Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Wireless Sensor Network Lab, 1455 Pingcheng Rd, Shanghai 201800, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Cheng, Xiaoliu,Wang, Yan,Yuan, Xiaobing,et al. Improving video foreground segmentation and propagation through multifeature fusion[J]. JOURNAL OF ELECTRONIC IMAGING,2015,24(6):12.
APA	Cheng, Xiaoliu,Wang, Yan,Yuan, Xiaobing,Li, Baoqing,Ding, Yuanyuan,&Zhang, Zebin.(2015).Improving video foreground segmentation and propagation through multifeature fusion.JOURNAL OF ELECTRONIC IMAGING,24(6),12.
MLA	Cheng, Xiaoliu,et al."Improving video foreground segmentation and propagation through multifeature fusion".JOURNAL OF ELECTRONIC IMAGING 24.6(2015):12.