An Optimized SIFT-OCT Algorithm for Stitching Aerial Images of a Loblolly Pine Plantation

When producing orthomosaic from aerial images of a forested area, challenges arise when the forest canopy is closed, and tie points are hard to find between images. The recent development in deep leaning has shed some light in tackling this problem with an algorithm that examines each image pixel-by-pixel. The scale-invariant feature transform (SIFT) algorithm and its many variants are widely used in feature-based image stitching, which is ideal for orthomosaic production. However, although feature-based image registration can find many feature points in forest image stitching, the similarity between images is too high, resulting in a low correct matching rate and long splicing time. To counter this problem by considering the characteristics of forest images, the inverse cosine function ratio of the unit vector dot product (arccos) is introduced into the SIFT-OCT (SIFT skipping the first scale-space octave) algorithm to overcome the shortfalls of too long a matching time caused by too many feature points for matching. Then, the fast sample consensus (FSC) algorithm was introduced to realize the deletion of mismatched point pairs and improve the matching accuracy. This optimized method was tested on three sets of forest images, representing the forest core, edge, and road areas of a loblolly pine plantation. The same process was repeated by using the regular SIFT and SIFT-OCT algorithms for comparison. The results showed the optimized SIFT-OCT algorithm not only greatly reduced the splicing time, but also increased the correct matching rate.