Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (17): 159-162.DOI: 10.3778/j.issn.1002-8331.2009.17.048
• 图形、图像、模式识别 • Previous Articles Next Articles
ZHANG Ting-hou1,TUO Hong-ya2,JING Zhong-liang2
Received:
Revised:
Online:
Published:
Contact:
张庭厚1,庹红娅2,敬忠良2
通讯作者:
Abstract: This paper presents an effective multi-sensor image registration method combining high-pass energy transformation and feature point matching.First,the SUSAN algorithm is used to obtain the corners of the two images.And then,the matching procedure is realized with two stages:For coarse matching,the normalized local cross-correlation based on high-pass energy image is defined as similarity measurement to obtain the original correspondence;For precise matching,the robust RANSAC algorithm is applied to discard the incorrectly matched corner pairs and get the registrationt parameters.The validity and exactness have been shown by the experimental results.
摘要: 针对多源传感器图像的特点,提出了一种结合高通能量变换与角点匹配的图像配准方法。该方法首先利用SUSAN 算法进行角点检测,然后将角点匹配分为粗匹配和精匹配两个阶段实现:粗匹配时,对图像进行高通能量变换,有效减少多传感器图像间的差异,并利用高通能量图上角点邻域间的归一化互相关度量,来建立角点初始对应关系;精匹配时,通过RANSAC算法,进一步筛选出正确的匹配点对,并获取匹配参数。实验证明该方法能快速、准确地配准红外与可见光图像。
ZHANG Ting-hou1,TUO Hong-ya2,JING Zhong-liang2. Multi-sensor image registration based on high-pass energy transformation[J]. Computer Engineering and Applications, 2009, 45(17): 159-162.
张庭厚1,庹红娅2,敬忠良2. 基于高通能量变换的多传感器图像配准[J]. 计算机工程与应用, 2009, 45(17): 159-162.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://cea.ceaj.org/EN/10.3778/j.issn.1002-8331.2009.17.048
http://cea.ceaj.org/EN/Y2009/V45/I17/159