摘要
针对基于尺度不变特征变换(SIFT)的合成孔径雷达(SAR)与可见光图像配准存在耗时长、精度不高的问题,提出了SIFT与快速近似最近邻搜索(FLANN)相结合的配准算法。首先,针对SAR图像存在的相干斑噪声做双边滤波(BF),在去噪的同时能够保护图像的边缘避免被高斯函数模糊。其次,在高斯差分尺度空间检测特征点并生成SIFT特征描述向量,利用FLANN算法实现高维向量空间中的快速匹配。最后,采用改进的抽样一致算法(PROSAC)剔除误匹配进一步提高匹配正确率。实验结果表明该算法在配准的精度和速度上都优于原始的SIFT算法。
Registration between SAR and optical images is time-consuming and has poor accuracy when based on the scale-invariant feature transform(SIFT)algorithm.In this letter we propose a novel method to solve this problem.First,we smooth SAR image by using bilateral filter(BF).BF is also good at preserving edges in the image as opposed to Gaussian smoothing,which is used in the original SIFT.Then,keypoints are detected in the Difference-of-Gaussian(DOG)scale space and SIFT descriptors are generated.Next,we adopt the fast library for approximate nearest neighbors(FLANN)algorithm which can search matching points fast in high-dimensional space.Last,progressive sample consensus(PROSAC)algorithm is utilized to exclude false matches.Experimental results show that our approach is significantly more accurate and much faster than the original SIFT.
作者
张皖南
杨学志
董张玉
ZHANG Wannan;YANG Xuezhi;DONG Zhangyu(School of Computer and Information,Hefei University of Technology,Hefei Anhui 230009,China;Anhui Province Key Laboratory of Industry Safety and Emergency Technology,Hefei Anhui 230009,China)
出处
《图学学报》
CSCD
北大核心
2018年第2期209-213,共5页
Journal of Graphics
基金
国家自然科学基金项目(61371154
41601452)
安徽省重点研究与开发计划项目(1704a0802124)
中国博士后科学基金项目(2016M602005)
关键词
合成孔径雷达图像
可见光图像
配准
尺度不变特征变换
快速近似最近邻搜索
synthetic aperture radar image
optical image
registration
scale-invariant feature transform
fast library for approximate nearest neighbors
作者简介
第一作者:张皖南(1993–),女,江苏徐州人,硕士研究生。主要研究方向为遥感信息处理。E-mail:1508622762@qq.com。;通信作者:杨学志(1970–),男,安徽合肥人,教授,博士,博士生导师。主要研究方向为数字图像处理。E-mail:xzyang@hfut.edu.cn。
