Knowledge Commons of Institute of Automation,CAS
Automatically Extract Semi-Transparent Motion-Blurred Hand From a Single Image | |
Zhao, Xiaomei1,2; Wu, Yihong1,2 | |
发表期刊 | IEEE SIGNAL PROCESSING LETTERS |
ISSN | 1070-9908 |
2019-11 | |
卷号 | 26期号:11页码:1598-1602 |
摘要 | When we use video chat, video game, or other video applications, motion-blurred hands often appear. Accurately extracting these hands is very useful for video editing and behavior analysis. However, existing motion-blurred object extraction methods either need user interactions, such as user supplied trimaps and scribbles, or need additional information, such as background images. In this letter, a novel method which can automatically extract the semi-transparent motion-blurred hand just according to the original RGB image is proposed. The proposed method separates the extraction task into two subtasks: alpha matte prediction and foreground prediction. These two subtasks are implemented by Xception based encoder-decoder networks. The images of extracted motion-blurred hands are calculated by multiplying the predicted alpha mattes and foreground images. Experiments on synthetic and real datasets show that the proposed method has promising performance. |
关键词 | Motion blurred hand semi-transparent alpha matte prediction foreground prediction automatically |
DOI | 10.1109/LSP.2019.2939754 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61572499] ; National Natural Science Foundation of China[61836015] ; National Natural Science Foundation of China[61421004] ; National Natural Science Foundation of China[61421004] ; National Natural Science Foundation of China[61836015] ; National Natural Science Foundation of China[61572499] |
WOS研究方向 | Engineering |
WOS类目 | Engineering, Electrical & Electronic |
WOS记录号 | WOS:000487213400006 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 图像视频处理与分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/26987 |
专题 | 多模态人工智能系统全国重点实验室_机器人视觉 |
通讯作者 | Wu, Yihong |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhao, Xiaomei,Wu, Yihong. Automatically Extract Semi-Transparent Motion-Blurred Hand From a Single Image[J]. IEEE SIGNAL PROCESSING LETTERS,2019,26(11):1598-1602. |
APA | Zhao, Xiaomei,&Wu, Yihong.(2019).Automatically Extract Semi-Transparent Motion-Blurred Hand From a Single Image.IEEE SIGNAL PROCESSING LETTERS,26(11),1598-1602. |
MLA | Zhao, Xiaomei,et al."Automatically Extract Semi-Transparent Motion-Blurred Hand From a Single Image".IEEE SIGNAL PROCESSING LETTERS 26.11(2019):1598-1602. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
IEEE Signal Processi(1662KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Zhao, Xiaomei]的文章 |
[Wu, Yihong]的文章 |
百度学术 |
百度学术中相似的文章 |
[Zhao, Xiaomei]的文章 |
[Wu, Yihong]的文章 |
必应学术 |
必应学术中相似的文章 |
[Zhao, Xiaomei]的文章 |
[Wu, Yihong]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论