Associating UAS images through a graph-based guiding strategy for boosting structure from motion

Structure from motion (SfM) using optical images has been an important prerequisite for reconstructing three-dimensional (3D) landforms. Although various algorithms have been developed in the past, they suffer from many image pairs for feature matching and recursive searching for the most suitable image to add to SfM reconstruction. Thus, carrying out SfM is computationally costly. This research proposes a boosting SfM (B-SfM) pipeline containing two phases, indexing graph network (IGN) and graph tracking, to accelerate SfM reconstruction. The IGN intends to form image pairs presenting desirable spatial correlation to reduce the time costs spent for feature matching. Building on the IGN, graph tracking integrates ant colony optimisation and greedy sorting algorithms to encode an optimum image sequence to boost SfM reconstruction. Compared to the results derived from other available means, the experimental results show that the proposed approach can accelerate the two phases, feature matching and 3D reconstruction, by up to 14 times faster. The quality of the camera poses recovered is retained or even slightly improved. As a result, the developed B-SfM can efficiently achieve SfM reconstruction by suppressing the time cost in the fashion of image pair selection for feature matching and image order determination for more efficient SfM reconstruction.