文章基本信息

标题：Pose estimation of image sequence captured from urban environment
本地全文：下载
作者：Mehdi Mazaheri Tehrani ; Mohammad Saadat Seresht
期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2010
卷号：XXXVIII - Part 3B
页码：72-75
出版社：Copernicus Publications
摘要：This paper reviews whole process of long sequence pose estimation and its challenges for urban environment which is considered as complex scene due to moving objects, greens, repetitious features and scene incidental events. In this study, color images are used for point feature selection and green features are filtered using hue values of surrounding window. Pyramidal KLT color feature tracker is used in short and wide base line fashion to investigate their behaviour in long sequence. To detect outliers, RANSAC in conjunction with common relative orientation algorithms (eight point and Nister five point) and space resection is used to compare their performance. Sequential local bundle adjustment estimates approximate camera poses and global bundle adjustment is used to refine the result
关键词：Pose Estimation; Urban Environment; Structure from Motion; Feature Extraction; Long Sequence