改进SIFT的特征提取与图像拼接方法  

Image mosaic method based on improved SIFT feature extraction

作　　者：杨祥[1] 周楠 YANG Xiang;ZHOU Nan(College of Information Science and Engineering,Guilin University of Technology,Guilin 541006,China)

机构地区：[1]桂林理工大学信息科学与工程学院,广西桂林541006

出　　处：《桂林理工大学学报》2023年第1期131-136,共6页Journal of Guilin University of Technology

基　　金：广西自然科学基金项目(2018GXNSFBA281081)。

摘　　要：针对无人机影像拼接存在拼接痕迹的问题,提出了一种结合分块SIFT特征点提取和拉普拉斯金字塔融合的无人机图像拼接方法。该方法首先对SIFT的特征点提取方式进行了改善,将原有的图像均匀分块,再采用SIFT算法将每一个子块区域的特征点提取了出来,保留其中对比度较高的特征点;利用RANSAC算法去除错误的匹配点,以避免因特征点过多而造成匹配效率低;在提取到匹配点后,利用拉普拉斯金字塔融合算法将图像进行拼接。结果表明,该方法可以极大地减少匹配点的数量,并提高匹配效率,能够获得良好的拼接图像。Aiming at the research of UAV image mosaic technology,UAV image mosaic method based on block SIFT feature point extraction and Laplace pyramid fusion proposed.Firstly,the original image is segmented,and the SIFT algorithm is used to extract the feature points of each sub block,and the feature points with high contrast are retained.Then the RANSAC algorithm is used to eliminate the mismatched points,so as to prevent the low matching efficiency caused by too many feature points.Finally,the Laplace pyramid fusion algorithm is used to splice the image.Experimental results show that this method can greatly reduce the number of matching points,improve the matching efficiency,and obtain good mosaic images.

关 键 词：特征点检测 图像拼接 拉普拉斯金字塔融合算法 SIFT算法 无人机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]