A fast, accurate and dense feature matching algorithm for aerial images

作     者：LI Ying GONG Guanghong SUN Lin LI Ying;GONG Guanghong;SUN Lin

作者机构：School of Automation Science and Electrical EngineeringBeihang UniversityBeijing 100191China 

出 版 物：《Journal of Systems Engineering and Electronics》 (系统工程与电子技术（英文版）)

年 卷 期：2020年第31卷第6期

页      面：1128-1139页

核心收录：

学科分类：083002[工学-环境工程] 0830[工学-环境科学与工程（可授工学、理学、农学学位）] 081802[工学-地球探测与信息技术] 08[工学] 080203[工学-机械设计及理论] 0818[工学-地质资源与地质工程] 081602[工学-摄影测量与遥感] 0816[工学-测绘科学与技术] 0802[工学-机械工程] 

基　　金：This work was supported by the Equipment Pre-Research Foundation of China(6140001020310) 

主　　题：feature matching feature screening feature fusion aerial image three-dimensional(3D)reconstruction 

摘      要：Three-dimensional(3D)reconstruction based on aerial images has broad prospects,and feature matching is an important step of ***,for high-resolution aerial images,there are usually problems such as long time,mismatching and sparse feature pairs using traditional ***,an algorithm is proposed to realize fast,accurate and dense feature *** algorithm consists of four ***,we achieve a balance between the feature matching time and the number of matching pairs by appropriately reducing the image ***,to realize further screening of the mismatches,a feature screening algorithm based on similarity judgment or local optimization is ***,to make the algorithm more widely applicable,we combine the results of different algorithms to get dense ***,all matching feature pairs in the low-resolution images are restored to the original *** between the original algorithms and our algorithm show that the proposed algorithm can effectively reduce the matching time,screen out the mismatches,and improve the number of matches.