{"title":"Moving object velocity estimation by appropriately choosing spatial frequencies in the MixeD domain","authors":"Shengli Wu, N. Hamada","doi":"10.1109/PACRIM.1999.799487","DOIUrl":null,"url":null,"abstract":"To estimate moving objects velocity in an image sequence is useful for a variety of applications, such as computer vision and monitoring systems. An effective way is to approach it in the transform/spatiotemporal mixed domain (MixeD), but it remains a problem how to select several 2-D spatial frequency points in MixeD domain which may influence the accuracy of velocity estimation and object detection. We propose a method to approach the velocity estimation problem by automatically selecting only two appropriate points in 2-D spatial frequency domain, the selection is achieved by using the established evaluation function together with a threshold. The simulation results show that the proposed method is effective on the selection of spatial frequency points.","PeriodicalId":176763,"journal":{"name":"1999 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM 1999). Conference Proceedings (Cat. No.99CH36368)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1999-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"1999 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM 1999). Conference Proceedings (Cat. No.99CH36368)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PACRIM.1999.799487","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
To estimate moving objects velocity in an image sequence is useful for a variety of applications, such as computer vision and monitoring systems. An effective way is to approach it in the transform/spatiotemporal mixed domain (MixeD), but it remains a problem how to select several 2-D spatial frequency points in MixeD domain which may influence the accuracy of velocity estimation and object detection. We propose a method to approach the velocity estimation problem by automatically selecting only two appropriate points in 2-D spatial frequency domain, the selection is achieved by using the established evaluation function together with a threshold. The simulation results show that the proposed method is effective on the selection of spatial frequency points.