基于改进ORB的无人机影像拼接算法  

UAV Image Mosaic Algorithm Based on Improved ORB

作　　者：张平[1] 孙林[1] 何显辉 ZHANG Ping;SUN Lin;HE Xian-hui(College of Geodesy and Geomatics,Shandong University of Science and Technology,Qingdao 266590,China)

机构地区：[1]山东科技大学测绘与空间信息学院,山东青岛266590

出　　处：《软件导刊》2023年第4期156-161,共6页Software Guide

基　　金：科学技术部高端外国专家引进计划项目(G2021025006L)。

摘　　要：针对传统图像拼接算法在无人机遥感影像拼接过程中速度慢、效率低、无法满足实时准确拼接要求的问题,提出一种改进ORB的图像拼接算法。首先构建尺度金字塔并利用ORB算法提取特征点,利用BEBLID描述符对特征点进行特征描述,采用最近邻比值(NNDR)算法进行粗匹配;然后基于特征点投票构建最优化几何约束对特征点进一步优化,利用随机采样一致性(RANSAC)算法计算变换矩阵,获取高精度变换矩阵;最后利用改进的渐入渐出加权融合算法实现图像拼接。实验结果表明,所提算法配准精度最高达到100%,配准耗时低于0.91s,拼接图像信息熵达到6.8079。相较于传统算法,所提算法具有更高的拼接效率,在降低图像拼接时间的同时能够获取更高质量的拼接图像,性能显著提升。Aiming at the problems of slow speed and low efficiency of traditional image stitching algorithm in UAV remote sensing image stitching process,which cannot meet the requirements of real-time and accurate stitching,an improved ORB image stitching algorithm is pro⁃posed.Firstly,the scale pyramid is constructed and the feature points are extracted by ORB algorithm,and then the feature points are de⁃scribed by BEBLID descriptor;The nearest neighbor ratio(NNDR)algorithm is used for rough matching,and then the optimal geometric con⁃straints are constructed based on the feature point voting to further optimize the feature points.The random sampling consistency(RANSAC)algorithm is used to calculate the transformation matrix and obtain the high-precision transformation matrix;Finally,the improved gradual in and gradual out weighted fusion algorithm is used to realize image mosaic.The experimental results show that the registration accuracy of the proposed algorithm reaches 100%at the highest,the registration time is less than 0.91s,and the information entropy of mosaic image reaches 6.8079.Compared with the traditional algorithm,the algorithm in this paper has higher splicing efficiency,and can obtain higher quality splicing images while reducing the image splicing time.The algorithm performance is significantly improved.

关 键 词：图像拼接 多尺度FAST检测 BEBLID特征 最优化几何约束 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]