图像配准是图像处理工作(图像融合、图像镶嵌等)的核心技术。本文提出了一种有效的遥感图像自动配准算法,该算法采用改进的Harris算子提取角点特征,利用待配准图像之间的灰度相关性进行粗匹配,然后运用虚拟三角形对全等的准则进行精匹配得到最终的匹配角点,最后通过这些角点求得刚体变换模型参数。实验结果表明:该算法是正确和有效的。 Image registration is the core technology of image processing (image fusion, image mosaic, etc.). In this paper, an effective remote sensing image registration algorithm is proposed. This algorithm uses the improved Harris operator to extract corner features, uses the gray correlation between the images to be registered for rough matching, and then uses the virtual triangles to achieve congruent Finally, the rigid body transformation model parameters are obtained through these corner points. Experimental results show that the algorithm is correct and effective.