中文摘要：

由于多视无人机影像拼接时误差的传播和累计经常导致拼接图扭曲偏斜或者拼接的失败.针对这个问题提出了构建拼接环并以多级拼接作为辅助的拼接策略.首先将待拼接图像分为多组,每组中以环形方式进行拼接,然后利用SIFT进行匹配,RANSAC实现误匹配的去除,而后计算透视变换关系,最后通过平差方程将误差削弱.通过实拍无人机影像进行的拼接实验表明该方式可以有效减少累计误差的影响,提高拼接精度.该方法的提出可以作为影像拼接消除累计误差的有效方式之一.

英文摘要：

The spread of the error and accumulation often lead to distortion or failure of image mosaic during the multi-view UAV images stitching. In this paper, in orden to solve the problem a mosaic strategy to construct a mosaic ring and multi-level grouping is proposed as an auxiliary. First, the input images will be divided into several groups, each group in the ring way to stitch. Then, SIFT is used for matching, and RANSAC is carried out to remove the wrong matching points. And then the perspective transformation matrix is calculated. Finally the error is weakened by using the adjustment equation. By using real UAV images, the experiment results show that this method can effectively reduce the influence of accumulative error, improve the precision of mosaic. The proposed method can be used as one of the effective ways to minimize the accumulative error.