Video object cut and paste

Yin Li, Jian Sun, H. Shum
{"title":"Video object cut and paste","authors":"Yin Li, Jian Sun, H. Shum","doi":"10.1145/1186822.1073234","DOIUrl":null,"url":null,"abstract":"In this paper, we present a system for cutting a moving object out from a video clip. The cutout object sequence can be pasted onto another video or a background image. To achieve this, we first apply a new 3D graph cut based segmentation approach on the spatial-temporal video volume. Our algorithm partitions watershed presegmentation regions into foreground and background while preserving temporal coherence. Then, the initial segmentation result is refined locally. Given two frames in the video sequence, we specify two respective windows of interest which are then tracked using a bi-directional feature tracking algorithm. For each frame in between these two given frames, the segmentation in each tracked window is refined using a 2D graph cut that utilizes a local color model. Moreover, we provide brush tools for the user to control the object boundary precisely wherever needed. Based on the accurate binary segmentation result, we apply coherent matting to extract the alpha mattes and foreground colors of the object.","PeriodicalId":211118,"journal":{"name":"ACM SIGGRAPH 2005 Papers","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2005-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"354","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM SIGGRAPH 2005 Papers","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/1186822.1073234","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 354

Abstract

In this paper, we present a system for cutting a moving object out from a video clip. The cutout object sequence can be pasted onto another video or a background image. To achieve this, we first apply a new 3D graph cut based segmentation approach on the spatial-temporal video volume. Our algorithm partitions watershed presegmentation regions into foreground and background while preserving temporal coherence. Then, the initial segmentation result is refined locally. Given two frames in the video sequence, we specify two respective windows of interest which are then tracked using a bi-directional feature tracking algorithm. For each frame in between these two given frames, the segmentation in each tracked window is refined using a 2D graph cut that utilizes a local color model. Moreover, we provide brush tools for the user to control the object boundary precisely wherever needed. Based on the accurate binary segmentation result, we apply coherent matting to extract the alpha mattes and foreground colors of the object.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
视频对象的剪切和粘贴
在本文中,我们提出了一个从视频剪辑中剪切运动物体的系统。剪切对象序列可以粘贴到另一个视频或背景图像上。为了实现这一点,我们首先对时空视频体积应用了一种新的基于三维图切割的分割方法。该算法将分水岭预分割区域划分为前景和背景,同时保持时间相干性。然后,对初始分割结果进行局部细化。给定视频序列中的两帧,我们指定两个各自感兴趣的窗口,然后使用双向特征跟踪算法进行跟踪。对于这两个给定帧之间的每一帧,每个跟踪窗口中的分割使用利用局部颜色模型的2D图切割进行细化。此外,我们还为用户提供了画笔工具,可以在需要的地方精确地控制物体的边界。基于精确的二值分割结果,应用相干抠图提取目标的阿尔法抠图和前景色。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Session details: I3D (symposium on interactive 3D graphics) Session details: Mesh manipulation Session details: Texture synthesis Session details: Precomputed light transport Session details: Hardware rendering
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1