遥感影像的自动配准是长期以来一直未能很好解决的一个重要问题。本文将视频图像匹配中获得巨大成功的SIFT( Scale Invariant Feature Transform)特征应用于遥感影像的自动配准问题中,并且针对遥感影像的成像特点,给出了一种具体的特征匹配方法。对航空和航天遥感影像在不同的变形、不同的光照变化和不同的分辨率下进行的大量实验表明,该方法具有稳定、可靠、快速等特点。-remote sensing images automatic registration is not very good for a long time have been resolved a key issue. Video images of this match was the great success sciences (Scale Invariant Feat ure Transform) of remote sensing images used in the automatic registration problems, remote sensing and imaging characteristics of the image is given a specific feature matching methods. For the aviation and aerospace remote sensing images in different deformation, changes in different light and different resolutions for the large number of experiments show that the method is stable, reliable, quick.