A real time motion estimation for traffic monitoring using sloped diamond search

T. Johri, V. Bahri, R. Sahu
{"title":"A real time motion estimation for traffic monitoring using sloped diamond search","authors":"T. Johri, V. Bahri, R. Sahu","doi":"10.1109/SECON.2008.4494348","DOIUrl":null,"url":null,"abstract":"This paper focus on fast block based motion estimation for traffic monitoring using a stationary camera. As the traffic needs to be monitored continuously a real time motion estimation algorithm is required which could provide good match as well. Most of the existing block matching algorithms fail to give good match when the speed of motion varies too much. This algorithm (RTME-SDS) overcomes this problem by estimating the initial position to be searched using the motion vector of previous frame. At this position we apply sloped diamond search. Since the traffic move along a fixed path at different speed, this algorithm gives a good initial position to continue with the estimation. RTME-SDS improves over the above mentioned algorithm by more than 45% in terms of complexity giving a match close to above mentioned algorithm.","PeriodicalId":188817,"journal":{"name":"IEEE SoutheastCon 2008","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE SoutheastCon 2008","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SECON.2008.4494348","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 focus on fast block based motion estimation for traffic monitoring using a stationary camera. As the traffic needs to be monitored continuously a real time motion estimation algorithm is required which could provide good match as well. Most of the existing block matching algorithms fail to give good match when the speed of motion varies too much. This algorithm (RTME-SDS) overcomes this problem by estimating the initial position to be searched using the motion vector of previous frame. At this position we apply sloped diamond search. Since the traffic move along a fixed path at different speed, this algorithm gives a good initial position to continue with the estimation. RTME-SDS improves over the above mentioned algorithm by more than 45% in terms of complexity giving a match close to above mentioned algorithm.
基于倾斜菱形搜索的交通监控实时运动估计
本文研究了基于快速块的静止摄像机交通监控运动估计方法。由于需要对交通进行连续监控,需要一种能够提供良好匹配的实时运动估计算法。当运动速度变化过大时,现有的块匹配算法大多不能很好地匹配。该算法利用前一帧的运动向量估计待搜索的初始位置,克服了这一问题。在这个位置我们使用倾斜菱形搜索。由于交通以不同的速度沿着固定的路径移动,该算法给出了一个很好的初始位置,可以继续进行估计。RTME-SDS在复杂度方面比上述算法提高了45%以上,并给出了接近上述算法的匹配。
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:481959085
Book学术官方微信