摘要
图像融合是影响图像拼接算法的关键步骤,融合算法的优劣决定拼接图像的质量.基本的融合算法在处理图像时,未考虑在拼接应用中边缘处图像像素灰度值的过渡情况,导致拼接图像质量较差.本文针对现有图像融合算法在拼接过程中存在的不足,提出将空间域融合算法优势应用于小波变换分解系数融合规则中,利用两者算法结合得到效果好的拼接图像.通过对航拍图像的融合拼接实验,证明本文改进的融合算法对于在图像拼接技术中的应用有较好的效果.
Image fusion is a key step of the image stitching algorithm.The quality of the fusion algorithm determines the quality of the stitched image.When the basic fusion algorithm processes the images,it does not consider the transition of the image pixel gray value at the edges in the stitching applications,resulting in poor quality of the stitched image.In view of the shortcomings of the existing image fusion algorithms in the stitching process,this paper proposes to apply the advantages of the spatial domain fusion algorithm to the wavelet transform decomposition coefficient fusion rules,and use the combination of the two algorithms to obtain a good stitched image.Through the fusion stitching experiments on aerial images,it is proved that the improved fusion algorithm proposed in this paper has a better effect for the applications of image stitching technology.
作者
张妍
宋丽丽
韩建峰
ZHANG Yan;SONG Li-li;HAN Jian-feng(College of Information Engineering,Inner Mongolia University of Technology,Hohhot,Inner Mongolia 010080,China;Inner Mongolia Key Laboratory of Perception Technology and Intelligent Systems,Hohhot,Inner Mongolia 010080,China)
出处
《内蒙古工业大学学报（自然科学版）》
2020年第4期265-272,共8页
Journal of Inner Mongolia University of Technology：Natural Science Edition
基金
内蒙古自治区关键技术攻关计划项目(2019GG271)
内蒙古自治区高等学校科学研究重点项目(NJZZ19068)。
关键词
航拍图像处理
图像拼接
图像融合
小波变换
aerial image processing
image stitching
image fusion
wavelet transform
