Skip to content
Publications

Talk · International Conference on Developments in eSystems Engineering · October 1, 2019

The Software Tool for Comparison and Configuration of Nonlinear Optimization Techniques in Orb-Slam

Makaev Boris, Ilya M. Afanasyev

Abstract

This paper presents the study on development of a software tool with a graphical user interface (GUI) to compare nonlinear optimization methods in ORB-SLAM library. It uses g2o graph optimization framework to solve five optimization problems while tracking SLAM: (a) Global Bundle Adjustment (GBA), (b) Local Bundle Adjustment (LBA), (c) Relative Simulation Optimization (SO), (d) Pose Graph Optimization over SO(3) Constraints, and (e) Essential Graph Optimization. By default, ORB-SLAM solves these problems using Levenberg- Marquardt method, but our tool allows to select optimization methods between Levenberg-Marquardt, Powell's Dogleg and Gauss-Newton algorithms to result in the best configuration solution when working with a video dataset. The developed application allows a user to configure the optimization tasks in ORB-SLAM and run an experiment to observe the performance evaluation of the current configuration. In addition, the ORBSLAM functionality has been extended using Ceres solver optimization framework. The tests of various datasets showed that the developed application is a convenient and effective tool for comparing different solutions and finding the fastest and most accurate ORB-SLAM configuration.

Robotics and Sensor-Based Localization3D Surveying and Cultural HeritageAdvanced Vision and ImagingORB-SLAMnonlinear programmingbundle adjustment

More by Ilya Afanasyev