Efficient Structure from Motion for Oblique UAV Images Based on Maximal Spanning Tree Expansions

TL;DR

This paper introduces an efficient SfM method for oblique UAV images that leverages a maximal spanning tree expansion to improve match graph construction, resulting in faster processing and reliable orientation accuracy.

Contribution

The paper presents a novel MST-Expansion algorithm for match graph enhancement, improving efficiency in SfM for oblique UAV images using spatial constraints and topological analysis.

Findings

Image matching speed increased by 19 to 35 times.

Achieved competitive orientation accuracy without GCPs.

Successfully oriented images from three UAV datasets.

Abstract

The primary contribution of this paper is an efficient Structure from Motion (SfM) solution for oblique unmanned aerial vehicle (UAV) images. First, an algorithm, considering spatial relationship constrains between image footprints, is designed for match pair selection with assistant of UAV flight control data and oblique camera mounting angles. Second, a topological connection network (TCN), represented by an undirected weighted graph, is constructed from initial match pairs, which encodes overlap area and intersection angle into edge weights. Then, an algorithm, termed MST-Expansion, is proposed to extract the match graph from the TCN where the TCN is firstly simplified by a maximum spanning tree (MST). By further analysis of local structure in the MST, expansion operations are performed on the nodes of the MST for match graph enhancement, which is achieved by introducing critical connections in two expansion directions. Finally, guided by the match graph, an efficient SfM solution is proposed, and its validation is verified through comprehensive analysis and comparison using three UAV datasets captured with different oblique multi-camera systems. Experiment results demonstrate that the efficiency of image matching is improved with a speedup ratio ranging from 19 to 35, and competitive orientation accuracy is achieved from both relative bundle adjustment (BA) without GCPs (Ground Control Points) and absolute BA with GCPs. At the same time, images in the three datasets are successfully oriented. For orientation of oblique UAV images, the proposed method can be a more efficient solution.