基于改进SIFT的无人机航拍图像快速匹配  

Fast Matching of UAV Aerial Image Based on SIFT

作　　者：韩宇[1] 宗群[1] 邢娜[1] Han Yu;Zong Qun;Xing Na(School of Electronic Information Engineering,Tianjin University,Tianjin 300072,China)

机构地区：[1]天津大学电子信息工程学院,天津300072

出　　处：《南开大学学报（自然科学版）》2019年第1期5-9,共5页Acta Scientiarum Naturalium Universitatis Nankaiensis

基　　金：国家863计划资助项目(2013AA122602);国家自然科学基金(61673294)

摘　　要：针对无人机航拍图像快速匹配问题,传统的SIFT算法复杂度高,处理时间长,为了满足实时性的要求,提出一种改进的SIFT算法.首先将特征点的矩形区域改为圆形区域,对描述子进行降维,然后借助绝对距离和余弦相似度进行双重匹配,最后再通过RANSAC算法剔除误匹配点.实验证明,改进的SIFT算法在尺度缩放、旋转、光照等情况下均有良好的匹配效果,与原算法相比,在保证匹配精度的同时很好的提高了匹配速率,验证了算法的实时性、有效性.To realize fast matching of UAV aerial images, the traditional SIFT algorithm has high complexity and long processing time, which cannot meet the requirements of real-time. A improved SIFT algorithm is proposed. The improved SIFT algorithm changes the rectangular area of the feature point into circular area and reduces the Dimensions of descriptor at first, and then do the match by means of the absolute distance and cosine similarity. Finally, the RANSAC algorithm is used to eliminate the false matching points. The experimental results show that the improved SIFT algorithm has a good matching result on the conditions of image zooming, rotating, lighting. Compared with the original algorithm, the matching speed is improved while the matching accuracy is ensured, which verifies the real-time and effectiveness of the improved algorithm.

关 键 词：无人机 图像匹配 SIFT 余弦相似度 RANSAC 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]