Title | ||
---|---|---|
Robust Global Structure From Motion Pipeline With Parallax On Manifold Bundle Adjustment And Initialization |
Abstract | ||
---|---|---|
In this letter, we present a novel global structure from motion (SfM) pipeline that is particularly effective in dealing with low-parallax scenes and camera motion collinear with the features that represent the environment structure. It is therefore particularly suitable in Urban SLAM, in which frequent road-facing motion poses many challenges to conventional SLAM algorithms. Our pipeline includes a recently explored bundle adjustment (BA) method that exploits a feature parameterization using Parallax angle between on-Manifold observation rays (PMBA). It is demonstrated that this BA stage has a consistently stable optimization configuration for features with any parallax and therefore lowparallax features can stay in reconstruction without pre-filtering. To allow practical usage of PMBA, we provide a compatible initialization stage in the SfM to initialize all camera poses simultaneously, exhibiting friendliness to collinear motion. This is achieved by simplifying PMBA into a hybrid graph problem of high connectivity yet small node set size, solved using a robust linear programming technique. Using simulations and a series of publicly available real datasets including "KITTI" and "Bundle Adjustment in the Large," we demonstrate the robustness of the position initialization stage in handling collinear motion and outlier matches, superior convergence performance of the BA stage in the presence of lowparallax features, and effectiveness of our pipeline to handle many sequential or out-of-order urban scenes. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/LRA.2019.2900756 | IEEE ROBOTICS AND AUTOMATION LETTERS |
Keywords | Field | DocType |
Mapping, SLAM | Convergence (routing),Computer vision,Parallax,Bundle adjustment,Control theory,Outlier,Robustness (computer science),Linear programming,Artificial intelligence,Engineering,Initialization,Simultaneous localization and mapping | Journal |
Volume | Issue | ISSN |
4 | 2 | 2377-3766 |
Citations | PageRank | References |
1 | 0.35 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Liyang Liu | 1 | 2 | 2.13 |
Teng Zhang | 2 | 1 | 1.02 |
Brenton Leighton | 3 | 1 | 0.35 |
Liang Zhao | 4 | 100 | 13.74 |
Shoudong Huang | 5 | 755 | 62.77 |
Gamini Dissanayake | 6 | 2226 | 256.36 |