{"title":"Structure and motion in two dimensions from multiple images: a least squares approach","authors":"Camillo J. Taylor, D. Kriegman, P. Anandan","doi":"10.1109/WVM.1991.212801","DOIUrl":null,"url":null,"abstract":"The authors address a special case of the structure from motion problem for static scenes where the camera positions and feature points are confined to the two-dimensional plane. This problem is relevant to indoor mobile robots that construct a map of their environment from vertical line correspondences. The algorithm is based on the minimization of the mean square difference between the projection of the reconstructed scene and the actual image measurements. The formulation of this objective function allows for an arbitrary number of images and feature points; therefore, the algorithm can take advantage of all of the available image data simultaneously. A fast, effective method for minimizing the resulting non-linear objective function is also presented.<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"39 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"51","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the IEEE Workshop on Visual Motion","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WVM.1991.212801","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 51
Abstract
The authors address a special case of the structure from motion problem for static scenes where the camera positions and feature points are confined to the two-dimensional plane. This problem is relevant to indoor mobile robots that construct a map of their environment from vertical line correspondences. The algorithm is based on the minimization of the mean square difference between the projection of the reconstructed scene and the actual image measurements. The formulation of this objective function allows for an arbitrary number of images and feature points; therefore, the algorithm can take advantage of all of the available image data simultaneously. A fast, effective method for minimizing the resulting non-linear objective function is also presented.<>
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
