Snowflake removal for videos via global and local low-rank decomposition
Han Z(韩志); Chen XA(陈希爱); Tang YD(唐延东); Tian JD(田建东); Ren WH(任卫红)
刊名IEEE Transactions on Multimedia
2018
关键词Snowflake removal desnowing low-rank decomposition
ISSN号1520-9210
通讯作者Tian JD(田建东)
产权排序1
中文摘要Falling snow not only blocks human vision, but also significantly degrades the effectiveness of computer vision systems in outdoor environment. In this paper, we aim to remove snowflakes in videos by using the global and local low rank property of snowflake-removed scenes. The stationary background and the mixture of moving foreground as well as falling snowflake are extracted via the global low rank matrix decomposition. Some snowflake features, such as its color and size, are used to separate out the snowflakes from other moving objects. Then, the mean absolute difference based patch matching is applied to align every same moving object over frames to grab its low rank structure. As such, the falling snowflake in front of moving objects can be removed via the local low rank decomposition. Finally, the snowflake removed videos are generated by pasting moving foreground to stationary backgrounds. Experiments show that our method can remove snowflakes effectively and outperforms the comparison methods.
收录类别EI
语种英语
内容类型期刊论文
源URL[http://ir.sia.cn/handle/173321/21578]  
专题沈阳自动化研究所_机器人学研究室
作者单位1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Shenyang China
2.University of Chinese Academy of Sciences, Beijing, China
推荐引用方式
GB/T 7714
Han Z,Chen XA,Tang YD,et al. Snowflake removal for videos via global and local low-rank decomposition[J]. IEEE Transactions on Multimedia,2018.
APA Han Z,Chen XA,Tang YD,Tian JD,&Ren WH.(2018).Snowflake removal for videos via global and local low-rank decomposition.IEEE Transactions on Multimedia.
MLA Han Z,et al."Snowflake removal for videos via global and local low-rank decomposition".IEEE Transactions on Multimedia (2018).
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。


©版权所有 ©2017 CSpace - Powered by CSpace