Large-scale UAV image stitching based on global registration optimization and graph-cut method

Abstract

This paper presents a large-scale unmanned aerial vehicle (UAV) image stitching method based on global registration optimization and the graph-cut technique. To minimize cumulative registration errors in large-scale image stitching, we propose a two-step global registration optimization approach, which includes affine transformation optimization followed by projective transformation optimization. Evenly distributed matching points are used to formulate the objective function for registration optimization, with the optimal affine transformation serving as the initial value for projective transformation optimization. Additionally, a rigid constraint is incorporated as the regularization term for projective transformation optimization to preserve shape and prevent unnatural warping of the aligned images. After global registration, the graph-cut method is employed to blend the aligned images and generate the final mosaic. The proposed method is evaluated on five UAV-captured remote sensing image datasets. Experimental results demonstrate that our approach effectively aligns multiple images and produces high-quality, seamless mosaics.