Knowledge Commons of Institute of Automation,CAS
Automatic Motion-Blurred Hand Matting for Human Soft Segmentation in Videos | |
Zhao, Xiaomei1,2; Wu, Yihong1,2 | |
2019 | |
会议名称 | 26th IEEE International Conference on Image Processing, ICIP 2019 |
卷号 | 2019-September |
页码 | 1450-1454 |
会议日期 | 2019-09 |
会议地点 | 台北 |
摘要 | Accurate hand segmentation is important for human segmentation. However, in videos, hand regions usually have serious motion blur, which reduces segmentation performance obviously. To solve this problem, we propose an automatic matting network to deal with motion-blurred hands. Then we combine the hand alpha mattes provided by matting network and the human segmentation results provided by segmentation network to generate our final human soft segmentation results. In addition, to train the matting network, we need a huge amount of motion-blurred hand images and their groundtruth alpha mattes. However these images are very difficult to obtain. To solve this problem, we propose an efficient semi-automatic synthetic data generation method and generate 36186 synthetic motion-blurred hand images and their alpha mattes. Experiments on synthetic images and real videos show that our method achieves state-of-art matting performance and successfully solve the problem of bad hand segmentation caused by serious motion blur. |
关键词 | Motion-blurred Hands Matting Synthetic Data Generation Human Soft Segmentation |
DOI | 10.1109/ICIP.2019.8803053 |
收录类别 | EI |
EI入藏号 | 20195207921868 |
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 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/38541 |
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.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China 2.University of Chinese Academy of Sciences, Beijing 100049, 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. Automatic Motion-Blurred Hand Matting for Human Soft Segmentation in Videos[C],2019:1450-1454. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
IEEE ICIP会议-2019-zha(4467KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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