摘要
本文基于SIFT算法进行无人机高分影像自动特征点匹配,在实现影像特征点自动匹配的基础上采用二次多项式模型进行影像几何配准,并且重点考察影像配准过程中匹配特征点数目对几何配准精度的影响,最后进行精度评价。结果表明:在影像特征点匹配结果正确、匹配点分布合理的情况下,匹配点数目越多,利用二次多项式进行影像几何配准的精度越高;无人机航向方向影像配准残差大于旁向残差。
In this paper, SIFT algorithm was used for automatic feature point matching of UAV high-resolution images, image geometry registration was carried out by quadratic polynomial model, and the effect of number of feature points on geometric registration accuracy in image registration was investigated. Finally, the accuracy was evaluated. The results show that: The higher the number of matching points, the higher the accuracy of image geometric registration when the matching result was correct and the matching point distribution was reasonable. Image geometric registration residuals were larger in the flight direction than in the vertical direction.
引文
[1] 李德仁,李明.无人机遥感系统的研究进展与应用前景[J].武汉大学学报(信息科学版),2014,39(5):505-513.
[2] 陈晓龙,陈显龙,彭瑶瑶.无人机影像处理关键技术研究[J].北京测绘,2016(3):24-27.
[3] 谢仁伟,牛铮,王力.基于控制点库的SIFT多源影像自动配准方法[J].测绘科学,2011,36(4):35-38.
[4] LOWE D G. Object Recognition from Local Scale-invariant Features[C]. International Conference on Computer Vision,1999:1150-1157.
[5] LOWE D G. Distinctive Image Features from Scale-invariant Keypoints[J]. International Journal of Computer Vision,2004,60(2):91-110.
[6] 李晓明,郑链,胡占义.基于SIFT特征的遥感影像自动配准[J].遥感学报,2006,10(6):885-892.
[7] 刘小军,杨杰,孙坚伟,等.基于SIFT的图像配准方法[J].红外与激光工程,2008,37(1):156-160.
[8] 索春宝,杨东清,刘云鹏.多种角度比较SIFT、SURF、BRISK、ORB、FREAK算法[J].北京测绘,2014(4):23-26.
[9] 胡佳怡,赵栋梁,刘荣,等.基于特征的影像匹配算法性能评估[J].北京测绘,2018(2):179-185.
[10] 张谦,贾永红,胡忠文.多源遥感影像配准中的SIFT特征匹配改进[J].武汉大学学报(信息科学版),2013,38(4):455-459.
[11] 邵奎.基于高分辨率遥感影像土地覆盖变化检测研究[D].湖北武汉:华中科技大学,2013.
[12] 宋洁.遥感影像几何纠正的模型研究与应用[D].陕西西安:西安科技大学,2013.