A Hybrid Global Image Orientation Method for Simultaneously Estimating Global Rotations and Global Translations

Abstract

Abstract. In recent years, the determination of global image orientation, i.e. global SfM, has gained a lot of attentions from researchers, mainly due to its time efficiency. Most of the global methods take relative rotations and translations as input for a two-step strategy comprised of global rotation averaging and global translation averaging. This paper by contrast presents a hybrid approach that aims to solve global rotations and translations simultaneously, but hierarchically. We first extract an optimal minimum cover connected image triplet set (OMCTS) which includes all available images with a minimum number of triplets, all of them with the three related relative orientations being compatible to each other. For non-collinear triplets in the OMCTS, we introduce some basic characterizations of the corresponding essential matrices and solve for the image pose parameters by averaging the constrained essential matrices. For the collinear triplets, on the other hand, the image pose parameters are estimated by relative orientation using the depth of object points from individual local spatial intersection. Finally, all image orientations are estimated in a common coordinate frame by traversing every solved triplet using a similarity transformation. We show results of our method on different benchmarks and demonstrate the performance and capability of the proposed approach by comparing with other global SfM methods.

An Efficient and Robust Hybrid SfM Method for Large-Scale Scenes

“…SfM includes three parts: feature extraction and matching, initial camera pose estimation, and bundle adjustment. According to the different initial camera pose estimation methods, SfM methods can be roughly divided into incremental [12][13][14][15], global [16][17][18][19], and hybrid [20][21][22][23] methods. The hybrid method combines incremental and global methods, that is, the partition-merge strategy [22], which has the characteristics of high efficiency and the ability to process large-scale scenes composed of tens of thousands or even hundreds of thousands of image data, and it effectively prevents error accumulation, drift problems, and memory bottlenecks [24,25].…”