{"title":"Pose and motion estimation of a moving rigid body with few features","authors":"Valentin Borsu, P. Payeur","doi":"10.1109/ROSE.2009.5355973","DOIUrl":null,"url":null,"abstract":"This paper proposes a reliable solution to the problem of estimating the motion of a rigid object moving freely in 3D space, through the use of a passive vision system. The feature-based tracking technique builds upon the selection of a consistent set of features and their tracking on a frame-by-frame basis. A thorough investigation is conducted to determine a proper vision system setup, which results in a configuration that ensures the coverage of the complete patterns of motion that the object may exhibit. While the system relies on low resolution cameras, the proposed algorithm provides subpixel accuracy on the pose estimation of the rigid body and its associated motion. The algorithm is experimentally validated and operates within an execution timeframe that makes it suitable for real-time processing applications.","PeriodicalId":107220,"journal":{"name":"2009 IEEE International Workshop on Robotic and Sensors Environments","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 IEEE International Workshop on Robotic and Sensors Environments","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ROSE.2009.5355973","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6
Abstract
This paper proposes a reliable solution to the problem of estimating the motion of a rigid object moving freely in 3D space, through the use of a passive vision system. The feature-based tracking technique builds upon the selection of a consistent set of features and their tracking on a frame-by-frame basis. A thorough investigation is conducted to determine a proper vision system setup, which results in a configuration that ensures the coverage of the complete patterns of motion that the object may exhibit. While the system relies on low resolution cameras, the proposed algorithm provides subpixel accuracy on the pose estimation of the rigid body and its associated motion. The algorithm is experimentally validated and operates within an execution timeframe that makes it suitable for real-time processing applications.