3D tracking using rectangular regions in structured scenes

Kun Peng, Lulu Hou, Jing Kong, Ren Ren, Xianghua Ying, H. Zha
{"title":"3D tracking using rectangular regions in structured scenes","authors":"Kun Peng, Lulu Hou, Jing Kong, Ren Ren, Xianghua Ying, H. Zha","doi":"10.1109/ICINFA.2011.5949019","DOIUrl":null,"url":null,"abstract":"This paper presents a practical 3D tracking method using rectangular regions in structured scenes. The dominant orthogonal vanishing points and some projections of rectangular regions (PRR) are detected from the first frame of a video sequence. Then the focal length of the camera and the height/width ratios for each rectangle are determined. The full camera position and orientation are tracked using the intensity differences among the frame sequences. The advantage of the method is that it can obtain all initial tracking parameters only from the first frame while previous methods may require the first 100 frames or more for initialization, which makes the proposed method very suitable for real-time applications.","PeriodicalId":299418,"journal":{"name":"2011 IEEE International Conference on Information and Automation","volume":"48 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 IEEE International Conference on Information and Automation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICINFA.2011.5949019","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

This paper presents a practical 3D tracking method using rectangular regions in structured scenes. The dominant orthogonal vanishing points and some projections of rectangular regions (PRR) are detected from the first frame of a video sequence. Then the focal length of the camera and the height/width ratios for each rectangle are determined. The full camera position and orientation are tracked using the intensity differences among the frame sequences. The advantage of the method is that it can obtain all initial tracking parameters only from the first frame while previous methods may require the first 100 frames or more for initialization, which makes the proposed method very suitable for real-time applications.
在结构化场景中使用矩形区域的3D跟踪
提出了一种实用的基于矩形区域的结构化场景三维跟踪方法。从视频序列的第一帧开始检测到优势正交消失点和一些矩形区域的投影(PRR)。然后确定相机的焦距和每个矩形的高/宽比。利用帧序列之间的强度差来跟踪整个摄像机的位置和方向。该方法的优点是只需从第一帧即可获得所有初始跟踪参数,而以前的方法可能需要前100帧或更多帧进行初始化,这使得该方法非常适合实时应用。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信