A Line Feature-Based Rotation Invariant Method for Pre- and Post-Damage Remote Sensing Image Registration

The accurate registration of pre- and post-damage images plays a vital role in the change analysis of the target area and the subsequent work of damage effect assessment. However, due to the impact of shooting time and damaged areas, there are large background and regional differences between pre- and post-damage remote sensing images, and the existing image registration methods do not perform well. In this paper, a line feature-based rotation invariant image registration method is proposed for pre- and post-damage remote sensing images. First, we extract and screen straight line segments from the images before and after damage. Then, we design a new method to calculate the main direction of each line segment and rotate the image based on the current line segment’s main direction and the center coordinates. According to the spatial distribution (distance and angle) of the reference line segment relative to the remaining line segments, a line feature descriptor vector is constructed and matched for each line segment on the rotated image. Since the main edge contour can preserve more invariant features, this descriptor can be better applied to the registration of pre- and post-damage remote sensing images. Finally, we cross-pair the midpoints and endpoints of the matched line segments to improve the accuracy of subsequent affine transformation parameter calculations. In remote sensing images with large background and regional differences, the average registration precision of our method is close to 100%, and the root mean square error is about 1 pixel. At the same time, the rotation invariance of our method is verified by rotating the test images. In addition, the results of the comparative experiments show that the registration precision and error of the proposed method are better than those of the existing typical representative algorithms.