The matching of infrared sequence images is a process to search the corresponding relationship between the pixels in a series of infrared images. Since it can directly affect the registration precision of infrared images, it is one of the key techniques for the data processing, such as the recognition, location and tracking of an object in video images. In order to increase the search speed, the Pyramid Strategy is used in image matching. In view of the features such as low S/N ratio of infrared sequence images, the wavelet threshold algorithm is introduced to filter the infrared images in preprocessing. For the infrared sequence images of Unmanned Aerial Vehicles (UAV), the SIFT algorithm is used in image sequence matching and is also combined with the correlation coefficient control method so as to get rid of the wrong matching points. Because the matching is not affected by the rotation of the sensing platform at a large angle, good effectiveness is obtained.