基于优化ORB算法的遥感图像精确配准技术  

Optimized ORB algorithm based precise registration technology for remote sensing images

作　　者：黄涛 武卫东[2] HUANG Tao;WU Weidong(Department of Teaching Affairs,Hebei University of Science and Technology,Shijiazhuang 050018,China;School of Information Science and Engineering,Hebei University of Science and Technology,Shijiazhuang 050018,China)

机构地区：[1]河北科技大学教务处,河北石家庄050018 [2]河北科技大学信息科学与工程学院,河北石家庄050018

出　　处：《现代电子技术》2019年第9期35-38,共4页Modern Electronics Technique

基　　金：河北省科技厅项目:基于物联网技术的静电安全监测系统(13200325D)~~

摘　　要：对于遥感图像精准配准技术的问题,提出基于优化ORB算法的遥感图像精准配准技术。首先,实现特征匹配,通过改进ORB算法将特征点进行提取,并且实现描述符的创建及匹配,得到初始控制点;然后,使用随机采样一致性方法和变换参数估计相结合,将可能错误的匹配进行剔除;最后,通过最小二乘法对变换参数进行估计,实现图像的几何纠正。对算法配准技术进行实验,实验结果表明此方法得到的配准精度较高,能够进一步提高配准效率。An optimized ORB algorithm based precise registration technology for remote sensing images is proposed. The feature points are extracted by improved ORB algorithm to realize the creation and matching of the descriptors,and obtain the initial control points. The random sampling consistency method is combined with transformation parameter estimation to eliminate the possible incorrect matching. The least square method is used to estimate the transformation parameters to realize the geometric correction of the images. The experiment was carried out for technology of the algorithm. The experimental results show that the registration accuracy obtained by this method is high,and the registration efficiency can be further improved.

关 键 词：ORB算法 遥感图像 图像配准技术 变换参数估计 互信息计算 特征点匹配 

分 类 号：TN911.73-34[电子电信—通信与信息系统]