Approximation to the Fisher-Rao metric for the focus of expansion

被引:1
|
作者
Maybank, S. J. [1 ]
机构
[1] Univ London Birkbeck Coll, Sch Comp Sci & Informat Syst, London WC1E 7HX, England
关键词
false detection; Fisher-Rao metric; focus of expansion; Riemannian metric; translation;
D O I
10.1016/j.neucom.2007.07.040
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The Fisher-Rao metric for the focus of expansion is approximated, under the assumption that the focus is estimated from correspondences between two images taken by a translating camera. The approximation is accurate if the errors in the image correspondences are small. The parameter space for the focus of expansion is sampled at a finite set of points chosen such that every point in the space is near to at least one sample point. A focus of expansion is detected by checking each sample point in turn to see if it is supported by the image correspondences. (C) 2008 Elsevier B.V. All rights reserved.
引用
收藏
页码:2037 / 2045
页数:9
相关论文
共 50 条