一种改进的快速特征点匹配方法An improved algorithm for fast feature point matching
李玉潮,杜丙新,黄培之
摘要(Abstract):
如何进行快速特征点匹配是计算机视觉领域研究的热点问题之一,基于层级式K均值聚类的分类树算法能对特征点实现快速分类。然而,当用该方法进行特征点匹配时不仅会产生大量误匹配点,而且还会丢失许多匹配点。本文对该方法进行研究后,从建树和匹配两个方面对算法进行了改进,使其更加适合于特征点匹配。实验结果表明,改进后的分类树算法能够在保持原算法匹配速度快特点的同时还能够有效降低误匹配率和漏匹配率。
关键词(KeyWords): 特征点匹配;分类树;聚类;算法
基金项目(Foundation):
作者(Author): 李玉潮,杜丙新,黄培之
DOI: 10.16251/j.cnki.1009-2307.2010.05.067
参考文献(References):
- [1]张祖勋,张剑清.数字摄影测量学[M].武汉:武汉测绘科技大学出版社,1997.
- [2]D.G.Lowe.Distinctive image features from scale-in-variant key points[J].International Journal of ComputerVision,2004,60(2):91-110.
- [3]Herbert Bay,Andreas Ess,Tinne Tuytelaars,Luc VanGool.SURF:Speeded Up Robust Features[J].Com-puter Vision and Image Understanding,2008,110(3):346-359.
- [4]J S Beis,D G.Lowe.Shape indexing using approximatenearest-neighbor search in high-dimensional spaces[C]//IEEE Computer Society Conference on ComputerVision and Pattern Recognition(CVPR’97),(SanJuan,Puerto Rico),1997,1000-1006.
- [5]D.Nister and H.Stewenius.Scalable recognition with avocabulary tree[J].Computer Vision and Pattern Rec-ognition,2006,2:2161-2168.
- [6]董明利,王振华,祝连庆,等.基于RANSAC算法的立体视觉图像匹配方法[J].北方工业大学报,2009,35(4):452-457.
- [7]Sicong Yue,Qing Wang and Rongchun Zhao.RobustWide Baseline Feature Point Matching Based on Scale In-variant Feature Descriptor[J].Chinese Journal of Aero-nautics,2009,22(1):70-74.