Hierarchical feature based matching for motion correspondence

V. Venkateswar, R. Chellappa
{"title":"Hierarchical feature based matching for motion correspondence","authors":"V. Venkateswar, R. Chellappa","doi":"10.1109/WVM.1991.212774","DOIUrl":null,"url":null,"abstract":"The authors design a feature based motion correspondence system. They propose a hierarchical grouping process that groups line segments into more complex structures that are easier to match. The hierarchy consists of lines, vertices, edges and surfaces. Matching starts at the highest level of the hierarchy (surfaces) and proceeds to the lowest (lines). Higher level features are easier to match, because they are fewer in number and more distinct in form. These matches then constrain the matches at lower levels. Perceptual and structural relations are used to group matches into islands of certainty. A Truth Maintenance System (TMS) is used to enforce grouping constraints and eliminates inconsistent match groupings. The TMS is also used for reasoning in the presence of uncertainty and to carry out logic revisions necessitated by additions, deletions and confirmations of hypotheses. The hierarchical matching process results in line matches as well as point matches. These then can be used as an input to a motion estimation algorithm.<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"14 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the IEEE Workshop on Visual Motion","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WVM.1991.212774","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 11

Abstract

The authors design a feature based motion correspondence system. They propose a hierarchical grouping process that groups line segments into more complex structures that are easier to match. The hierarchy consists of lines, vertices, edges and surfaces. Matching starts at the highest level of the hierarchy (surfaces) and proceeds to the lowest (lines). Higher level features are easier to match, because they are fewer in number and more distinct in form. These matches then constrain the matches at lower levels. Perceptual and structural relations are used to group matches into islands of certainty. A Truth Maintenance System (TMS) is used to enforce grouping constraints and eliminates inconsistent match groupings. The TMS is also used for reasoning in the presence of uncertainty and to carry out logic revisions necessitated by additions, deletions and confirmations of hypotheses. The hierarchical matching process results in line matches as well as point matches. These then can be used as an input to a motion estimation algorithm.<>
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
基于层次特征的运动对应匹配
作者设计了一个基于特征的运动对应系统。他们提出了一种分层分组过程,将线段分组成更复杂的结构,这样更容易匹配。层次结构由线、顶点、边和面组成。匹配从层次结构的最高级别(面)开始,一直到最低级别(行)。更高级别的功能更容易匹配,因为它们的数量更少,形式更明显。然后,这些匹配将在较低级别约束匹配。感知和结构关系用于将匹配分组为确定性岛屿。真理维护系统(TMS)用于强制分组约束和消除不一致的匹配分组。TMS也用于在不确定性存在的情况下进行推理,并通过添加、删除和确认假设进行必要的逻辑修正。分层匹配过程的结果是行匹配和点匹配。然后,这些可以用作运动估计算法的输入。
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
Incremental estimation of image-flow using a Kalman filter Structure and motion in two dimensions from multiple images: a least squares approach An adaptive multi-scale approach for estimating optical flow: computational theory and physiological implementation Stability of phase information Motion tracking on the spatiotemporal surface
×
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