基于ORB算法和改进KNN-RANSAC算法的无人机遥感影像拼接

UAV remote sensing image stitching based on ORB algorithm and improved KNN-RANSAC algorithm

根据无人机遥感影像自身的特点,提出了一种基于ORB算法和改进KNN-RANSAC算法的无人机遥感影像拼接。该算法首先通过ORB算法对特征点进行提取,然后利用改进的KNN-RANSAC算法进行特征匹配,最后使用加权融合算法对图像进行融合拼接。实验结果表明,ORB算法和改进的KNN-RANSAC算法在保证匹配精度的前提下,提高了匹配速度,有利于无人机遥感影像的拼接。

According to the characteristics of UAV remote sensing image,a UAV remote sensing image mosaic based on ORB algorithm and improved KNN-RANSAC algorithm is proposed. Firstly,the feature points are extracted by the ORB algorithm,then the improved KNN-RANSAC algorithm is used for feature matching. Finally,the image is fused and stitched by the weighted fusion algorithm.The experiment results show that the ORB algorithm and the improved KNN-RANSAC algorithm increase the matching speed by ensuring the matching accuracy,which is beneficial to the splicing of remote sensing images of UAVs.