北京航空航天大学学报 ›› 2010, Vol. 36 ›› Issue (7): 785-788.

• 论文 • 上一篇    下一篇

已知初始匹配对的图像四元松弛匹配算法

王华1, 侯相深1, 丛建亭2, 孙金玮2   

  1. 1. 哈尔滨工业大学 交通科学与工程学院, 哈尔滨 150090;
    2. 哈尔滨工业大学 电气工程及自动化学院, 哈尔滨 150001
  • 收稿日期:2009-05-14 出版日期:2010-07-30 发布日期:2010-09-10
  • 作者简介:王 华(1975-),男,黑龙江讷河人,副教授,hitwh@hit.edu.cn.
  • 基金资助:

    国家自然科学基金资助项目(50808057)

Four-element relaxation matching algorithm of images based on known initial matching pairs

Wang Hua1, Hou Xiangshen1, Cong Jianting2, Sun Jinwei2   

  1. 1. School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China;
    2. School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin 150001, China
  • Received:2009-05-14 Online:2010-07-30 Published:2010-09-10

摘要: 提出了已知初始匹配对的四元松弛匹配算法,该算法以向量旋转角的旋转和缩放不变性特征作为匹配对的优化准则,首先计算向量旋转角度差值,然后通过构造支持度函数和剔除策略选出最优匹配对.在初始错误匹配比例较高和游动误差较大的情况下能够实现正确匹配.通过大量图像实验证明,该算法在匹配速度和正确率上优于桑农松弛匹配算法.

Abstract: A four-element relaxation matching algorithm based on known initial matching pairs was proposed. The algorithm with characteristics of anti-rotation and anti-scale of rotating angle of vectors was applied as the optimization criterion of matching pairs. Under the condition of higher initial error matching rate and larger walk errors, the algorithm achieved the matching correctly. The value difference of the rotating angle of vectors was calculated, and the optimal matching pairs was selected by using of the support function and the rules of rejection. Experimental results with large images show that the matching speed and correctness of the algorithm is better than Sangnong relaxation matching algorithm.

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发