GSLAM: Initialization-robust Monocular Visual SLAM via Global Structure-from-Motion

GSLAM: Initialization-robust Monocular Visual SLAM via
Global Structure-from-Motion

3DV 2017
Chengzhou Tang1 Oliver Wang2 Ping Tan1
1Simon Fraser University 2Adobe Research
Teaser

Abstract

Many monocular visual SLAM algorithms are derived from incremental structure-from-motion (SfM) methods. This work proposes a novel monocular SLAM method which integrates recent advances made in global SfM. In particular, we present two main contributions to visual SLAM. First, we solve the visual odometry problem by a novel rank-1 matrix factorization technique which is more robust to the errors in map initialization. Second, we adopt a recent global SfM method for the pose-graph optimization, which leads to a multi-stage linear formulation and enables L1 optimization for better robustness to false loops. The combination of these two approaches generates more robust reconstruction and is significantly faster (4X) than recent state-of-the-art SLAM systems. We also present a new dataset recorded with ground truth camera motion in a Vicon motion capture room, and compare our method to prior systems on it and established benchmark datasets.

Paper Data and Evaluation Tools (coming soon) Code

Supplemental Video


Acknowledgements

We thank Zhaopeng Cui for a lot of helps and discussions. This work is supported by the NSERC Discovery grant 611664, Discovery Acceleration Supplements 611663, and a research gift from Adobe.