摘要
提出一种基于SURF特征点的图像自动配准方法。首先在图像的尺度空间中提取特征点,然后对特征点进行亚像素定位,并赋予主方向。根据特征点邻域信息分布计算得到特征向量后,利用最近邻特征点距离与次近邻特征点距离之比得到初始匹配点对。然后使用RANSAC算法剔除错误匹配特征点对,同时计算得到图像之间的变换参数。实验结果表明该方法能够实现不同分辨率图像的自动配准。
An automatic image registration method based on SURF feature points was proposed.First,extracts the feature points from the scale space of the image,then locates feature points on the sub-pixel coordinates,and gives the main orientation.Initial feature points matching can be calculated by using the distance ratio of the nearest neighbor feature point and the next nearest neighbor feature point.Then RANSAC（Random Sample Consensus） algorithm was used to match the initial feature points set,while calculating transformation parameters between the two images.The results show that the method can achieve robust automatic image registration between different resolution images.
出处
《计算机应用》
CSCD
北大核心
2011年第A01期73-75,共3页
journal of Computer Applications
基金
云南省自然科学基金资助项目(2000YP20)
西南林业大学面上基金资助项目(200616M)
关键词
图像配准
特征匹配
鲁棒估计
image registration
feature matching
robust estimation
