基于特定目标的多模板分解多视点视频跟踪方法及路径方案

Jun Wang, Jinyong Wu, Yike Wang, Z. Gong, Dejian Liu
{"title":"基于特定目标的多模板分解多视点视频跟踪方法及路径方案","authors":"Jun Wang, Jinyong Wu, Yike Wang, Z. Gong, Dejian Liu","doi":"10.1109/GCIS.2012.24","DOIUrl":null,"url":null,"abstract":"According to the need of specific object's tracking of multi-viewpoint video, a specific object's tracking method of multi-viewpoint video based on multi-template decomposed tracking and route scheme has been put forward in this paper. First, the route may be schemed by gridding search in this method. Then the object area from motion detection can be blew up, subsequently subtle location should be done again by integration chart. Last, the object from subtle location and the image templates from each angle should be matched. When matching the templates, the features can be extracted by up and down decomposition to the objects. The object with best match and over the threshold can be set as the object to be tracked further. Experiments show that the amount of computation can be reduced greatly and the speed can be improved by the route scheme. The tracking precision has been improved by the precision location of integration chart and the match of multi-template. The method in this paper can become a new method to effectively tracking the specific object of multi-viewpoint video.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"237 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Multi-template Decomposed Tracking Method Based on Specific Object of Multi-viewpoint Video and Route Scheme\",\"authors\":\"Jun Wang, Jinyong Wu, Yike Wang, Z. Gong, Dejian Liu\",\"doi\":\"10.1109/GCIS.2012.24\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"According to the need of specific object's tracking of multi-viewpoint video, a specific object's tracking method of multi-viewpoint video based on multi-template decomposed tracking and route scheme has been put forward in this paper. First, the route may be schemed by gridding search in this method. Then the object area from motion detection can be blew up, subsequently subtle location should be done again by integration chart. Last, the object from subtle location and the image templates from each angle should be matched. When matching the templates, the features can be extracted by up and down decomposition to the objects. The object with best match and over the threshold can be set as the object to be tracked further. Experiments show that the amount of computation can be reduced greatly and the speed can be improved by the route scheme. The tracking precision has been improved by the precision location of integration chart and the match of multi-template. The method in this paper can become a new method to effectively tracking the specific object of multi-viewpoint video.\",\"PeriodicalId\":337629,\"journal\":{\"name\":\"2012 Third Global Congress on Intelligent Systems\",\"volume\":\"237 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-11-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2012 Third Global Congress on Intelligent Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/GCIS.2012.24\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 Third Global Congress on Intelligent Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/GCIS.2012.24","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

根据多视点视频特定目标跟踪的需要,提出了一种基于多模板分解跟踪和路由方案的多视点视频特定目标跟踪方法。首先,该方法可以通过网格搜索对路径进行规划。然后对运动检测得到的目标区域进行放大,再通过积分图进行精细定位。最后,将细微位置的目标与各个角度的图像模板进行匹配。匹配模板时,可以通过对对象的上下分解提取特征。将匹配最佳且超过阈值的对象设置为进一步跟踪的对象。实验表明,该路由方案可以大大减少计算量,提高速度。通过积分图的精确定位和多模板的匹配,提高了跟踪精度。本文所提出的方法可以成为一种有效跟踪多视点视频中特定目标的新方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Multi-template Decomposed Tracking Method Based on Specific Object of Multi-viewpoint Video and Route Scheme
According to the need of specific object's tracking of multi-viewpoint video, a specific object's tracking method of multi-viewpoint video based on multi-template decomposed tracking and route scheme has been put forward in this paper. First, the route may be schemed by gridding search in this method. Then the object area from motion detection can be blew up, subsequently subtle location should be done again by integration chart. Last, the object from subtle location and the image templates from each angle should be matched. When matching the templates, the features can be extracted by up and down decomposition to the objects. The object with best match and over the threshold can be set as the object to be tracked further. Experiments show that the amount of computation can be reduced greatly and the speed can be improved by the route scheme. The tracking precision has been improved by the precision location of integration chart and the match of multi-template. The method in this paper can become a new method to effectively tracking the specific object of multi-viewpoint video.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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