Image Stitching Algorithm for Drones Based on SURF-GHT

Abstract

Aiming at the problem that the amount of single remote sensing picture information is limited due to the limited angular range of single drone, this paper proposes SURF-GHT algorithm based on SURF algorithm and generalized Hough transform based on the existing image stitching algorithm. After the feature points are extracted by the SURF algorithm for the pictures to be spliced, the decision tree forest in the generalized Hough transform is used to filter the set of feature points, and then the fading image fusion algorithm is used for image splicing. The experimental results show that the SURF-GHT algorithm improves the quality of image stitching on the basis of higher stitching efficiency, and better satisfies the subsequent identification of remote sensing images of drones.