针对目前已有的航空影像拼接技术中,变换参数仅仅依据拼接顺序独立求解,而未考虑到待拼接影像的整体关系的问题,提出一种用于航空影像拼接的整体平差算法。对所有具有重叠区域的待拼接影像进行匹配,以多项式变换为模型,利用最小二乘原理整体解求待拼接影像的变换参数。实验结果表明,该算法能较好地解决拼接误差随拼接次数增多而累积的问题,提高影像拼接的精度。 Aiming at the existing aerial video mosaic technology, the transformation parameters are solved independently only according to the order of splicing without considering the overall relationship of the images to be spliced, a global adjustment algorithm for aerial video mosaic is proposed. Matching all the images to be spliced ​​with overlapping regions, transforming them into polynomials and using the least squares principle to solve the transformation parameters of the spliced ​​images. Experimental results show that this algorithm can better solve the problem that the stitching error accumulates with the increase of the number of splicing and improve the accuracy of the image stitching.