【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。更多还原

【Abstract】 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.更多还原