Robust motion and correspondence of noisy 3-D point sets with missing data

被引：74

作者：

Trucco, E

Fusiello, A ^{[1
]}

Roberto, V

机构：

[1] Univ Udine, Dipartimento Matemat & Informat, Lab Immagini, I-33100 Udine, Italy

[2] Heriot Watt Univ, Dept Elect & Comp Engn, Edinburgh, Midlothian, Scotland

来源：

PATTERN RECOGNITION LETTERS | 1999年 / 20卷 / 09期

关键词：

ICP; registration; CAD-based vision; motion estimation; reverse engineering;

D O I：

10.1016/S0167-8655(99)00055-0

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We describe RICP, a robust algorithm for registering and finding correspondences in sets of 3-D points with significant percentages of missing data, and therefore useful for both motion analysis and reverse engineering. RICP exploits LMedS robust estimation to withstand the effect of outliers. Our extensive experimental comparison of RICP with ICP shows RICP's superior robustness and reliability. (C) 1999 Elsevier Science B.V. All rights reserved.

引用

页码：889 / 898

页数：10

共 20 条

[1] A METHOD FOR REGISTRATION OF 3-D SHAPES [J].