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

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.

[1]  Evgeni Magid,et al.  Comparative analysis of ROS-based monocular SLAM methods for indoor navigation , 2017, International Conference on Machine Vision.

[2]  Jürgen Sturm,et al.  Evaluating Egomotion and Structure-from-Motion Approaches Using the TUM RGB-D Benchmark , 2012 .

[3]  Ilmir Z. Ibragimov,et al.  Comparison of ROS-based visual SLAM methods in homogeneous indoor environment , 2017, 2017 14th Workshop on Positioning, Navigation and Communications (WPNC).

[4]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[5]  Hujun Bao,et al.  ICE-BA: Incremental, Consistent and Efficient Bundle Adjustment for Visual-Inertial SLAM , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Hugh F. Durrant-Whyte,et al.  Simultaneous localization and mapping: part I , 2006, IEEE Robotics & Automation Magazine.

[7]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Wolfram Burgard,et al.  G2o: A general framework for graph optimization , 2011, 2011 IEEE International Conference on Robotics and Automation.

[9]  Ilya Afanasyev,et al.  Comparison of Various SLAM Systems for Mobile Robot in an Indoor Environment , 2018, 2018 International Conference on Intelligent Systems (IS).

[10]  Andreas Geiger,et al.  Object scene flow for autonomous vehicles , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Davide Scaramuzza,et al.  REMODE: Probabilistic, monocular dense reconstruction in real time , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[12]  Marco Pertile,et al.  An evaluation of ROS-compatible stereo visual SLAM methods on a nVidia Jetson TX2 , 2019, Measurement.

[13]  G. Klein,et al.  Parallel Tracking and Mapping for Small AR Workspaces , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[14]  Ilya Afanasyev,et al.  Analysis of onboard sensor-based odometry for a quadrotor UAV in outdoor environment , 2018 .

[15]  Daniel Cremers,et al.  Direct Sparse Odometry , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Andrew J. Davison,et al.  DTAM: Dense tracking and mapping in real-time , 2011, 2011 International Conference on Computer Vision.

[17]  Vladlen Koltun,et al.  Dense Monocular Depth Estimation in Complex Dynamic Scenes , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  J. M. M. Montiel,et al.  ORB-SLAM: A Versatile and Accurate Monocular SLAM System , 2015, IEEE Transactions on Robotics.

[19]  Konstantin S. Yakovlev,et al.  Original Loop-closure Detection Algorithm for Monocular vSLAM , 2017, AIST.

[20]  Daniel Cremers,et al.  LSD-SLAM: Large-Scale Direct Monocular SLAM , 2014, ECCV.

[21]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.