{"title":"Tracking points and line segments in image sequences","authors":"J. Gambotto","doi":"10.1109/WVM.1989.47092","DOIUrl":null,"url":null,"abstract":"The author examines different constraints which can be used to find the correspondences between line segments in an image sequence. These constraints are imposed by the continuity of the 3-D motion and also by certain types of motions. The author derives simple equations which relate corresponding tokens in three consecutive images when the 3-D motion is a translation. Next, he describes an algorithm for matching line segments when the motion of the camera is approximately known and presents some experimental results. If a camera moving in a stationary environment is considered, an image motion is related to the location of the corresponding object in space with respect to the instantaneous axis of translation. The author performs a geometrical analysis of this relationship and introduces concepts for this analysis. It is noted that this relationship is useful for tracking objects in the field of view.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"14 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1989-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"[1989] Proceedings. Workshop on Visual Motion","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WVM.1989.47092","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
The author examines different constraints which can be used to find the correspondences between line segments in an image sequence. These constraints are imposed by the continuity of the 3-D motion and also by certain types of motions. The author derives simple equations which relate corresponding tokens in three consecutive images when the 3-D motion is a translation. Next, he describes an algorithm for matching line segments when the motion of the camera is approximately known and presents some experimental results. If a camera moving in a stationary environment is considered, an image motion is related to the location of the corresponding object in space with respect to the instantaneous axis of translation. The author performs a geometrical analysis of this relationship and introduces concepts for this analysis. It is noted that this relationship is useful for tracking objects in the field of view.<>