A Scale, Rotation, and Affine Invariant Line Detection and Matching Algorithm for 3D Reconstruction of Infrastructure

Structure from Motion (SfM) is a well-known approach for extracting the 3D geometry of a structure from 2D images. Despite being inexpensive, simple, and automatic, it has not been widely used in the construction industry, mainly due to challenges in detecting and matching visual features. In built infrastructure scenes, most areas lack distinctive points due to the prevalence of poorly-textured surfaces which obstructs the successful use of SfM. In contrast, an abundant number of straight lines are visible but cannot be fully exploited because of the low performance of existing line-matching algorithms. When applied to infrastructure scenes, such algorithms produce many mismatches because of inaccurate locations of line end-points, fragmented lines, lack of geometric constraints, and lack of distinctive texture in the local neighborhood. This paper presents a novel method for tackling this problem. The key innovations of the proposed method are the joint use of local and global information in the scene and the canonical form representation of the support region of each feature. Using the scale-space theory, lines that are stable with respect to scale variations are first extracted. A dynamic pixel support region is then assigned to each line based on the Laplacian function. Each region is described by an affine-invariant vector. Finally, the Euclidean distance between vectors and global geometric constraints in the scene are applied to determine corresponding pairs. Experimental analyses have shown performance improvement compared to the state-of-the-art algorithms.