摘要
针对尺度不变特征变换算法应用于多源遥感影像配准时面临的低效率和误匹配问题,从特征点提取和特征点匹配两个方面对其进行改进。在特征点提取阶段,通过控制特征点数量和分布情况获取均匀分布的特征点;在特征点匹配阶段,采用特征点仿射变换粗匹配、精匹配和误匹配点剔除策略,由粗到精地获取准确的同名点。对多源遥感影像进行配准实验,结果表明,此方法在匹配效率及匹配性能上均优于原始SIFT算法,且配准精度更高。
Considering the low efficency and mismatching in SIFT-based multi-source remote sensing image registration, we improve the SIFT algorithm through two aspects of point fea- ture extraction and point feature matching. Firstly, we acquire an appropriate number of well-distributed point features by controlling their number and distribution. Secondly, an optimized strategy is adopted to realize a coarse-to-fine feature point matching approach by applying the initial affine matching, precise matching and mismatching elimination proces- ses. Experiments on several multi-source data sets show that the proposed algorithm per- forms better than the SIFT algorithm on both efficiency and accuracy.
出处
《武汉大学学报（信息科学版）》
EI
CSCD
北大核心
2013年第4期455-459,共5页
Geomatics and Information Science of Wuhan University
基金
国家科技支撑计划资助项目(2011BAB01B05)
中央高校基本科研业务费专项资金资助项目(201121302020003)
关键词
尺度不变特征
影像配准
影像匹配
多源遥感影像
SIFT
image registration
image matching
multi-source remote sending image
