Improving video foreground segmentation and propagation through multifeature fusion
文献类型:期刊论文
作者 | Cheng, Xiaoliu1,2; Wang, Yan1; Yuan, Xiaobing1; Li, Baoqing1; Ding, Yuanyuan1,2; Zhang, Zebin1,2 |
刊名 | JOURNAL OF ELECTRONIC IMAGING
![]() |
出版日期 | 2015-11-01 |
卷号 | 24期号:6页码:12 |
关键词 | video foreground segmentation object propagation superpixels mapping feature confidence feature fusion improved Dempster-Shafer evidence theory |
ISSN号 | 1017-9909 |
DOI | 10.1117/1.JEI.24.6.063017 |
英文摘要 | 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 |
WOS研究方向 | Engineering ; Optics ; Imaging Science & Photographic Technology |
语种 | 英语 |
WOS记录号 | WOS:000375861200010 |
出版者 | IS&T & SPIE |
源URL | [http://119.78.100.204/handle/2XEOYT63/8556] ![]() |
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. |
入库方式: OAI收割
来源:计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。