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：110-114
出版社：Copernicus Publications
摘要：Achieving coordinates of object coordinate points with optimum accuracy is one of the most important issues in close range photogrammetry. In this context, network design plays a vital role in determination of angles and distances between imaging stations. This is, however, not a trivial task due to various constraints affecting the geometry of the network. As a result, most camera station networks are defined on a try and error basis based on the user's experience. In this paper, a new fuzzy approach is adopted, in which the constraints affecting the network design are all modeled. As a result, the position of all camera locations are defined based on fuzzy rules. The tests carried out show that by applying fuzzy rules inappropriate images can be defined and eliminated from the process leading to some 20% accuracy in the determination of object coordinates
