Benchmark of Visual SLAM Algorithms: ORB-SLAM2 vs RTAB-Map*

This works deals with a benchmark of two well-known visual Simultaneous Localization and Mapping (vSLAM) algorithms: ORB-SLAM2 proposed by Mur-Atal & al in 2015 [7] and RTAB-Map proposed by [8]. The benchmark has been carried out with an Intel real-sense camera 435D mounted on top of a robotics electrical powered wheelchair running a ROS platform. The ORB SLAM has been implemented taking into account a monocular, stereo and RGB-D camera. RTAB SLAM, meanwhile, has only implemented with monocular and RGB-D camera. Several experiments have been carried out in a controlled indoor environment at the ESIGELEC's Autonomous Navigation Laboratory. These experiments are supported by the use of the VICON motion capture system used as a ground-truth to validate our results [1]. Different motion scenarios are used to test and benchmark the SLAM algorithms in various configurations: straight-line, straight-line and back, circular path with loop closure, etc.

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

[2]  Gordon Wyeth,et al.  SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights , 2012, 2012 IEEE International Conference on Robotics and Automation.

[3]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[4]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

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

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

[7]  Sei Ikeda,et al.  Visual SLAM algorithms: a survey from 2010 to 2016 , 2017, IPSJ Transactions on Computer Vision and Applications.

[8]  Laurent Itti,et al.  Biologically Inspired Mobile Robot Vision Localization , 2009, IEEE Transactions on Robotics.

[9]  Paul Newman,et al.  Appearance-only SLAM at large scale with FAB-MAP 2.0 , 2011, Int. J. Robotics Res..

[10]  Michael Milford,et al.  2D visual place recognition for domestic service robots at night , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Junichi Meguro,et al.  A Low-Cost Solution for Automatic Lane-Level Map Generation Using Conventional In-Car Sensors , 2016, IEEE Transactions on Intelligent Transportation Systems.

[12]  Paul Newman,et al.  FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance , 2008, Int. J. Robotics Res..

[13]  Yohan Dupuis,et al.  A Study of Vicon System Positioning Performance , 2017, Sensors.

[14]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[15]  Davide Scaramuzza,et al.  SVO: Fast semi-direct monocular visual odometry , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[16]  Albert S. Huang,et al.  Visual Odometry and Mapping for Autonomous Flight Using an RGB-D Camera , 2011, ISRR.

[17]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[18]  Antonio Torralba,et al.  Building the gist of a scene: the role of global image features in recognition. , 2006, Progress in brain research.

[19]  Friedrich Fraundorfer,et al.  Visual Odometry Part I: The First 30 Years and Fundamentals , 2022 .

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

[21]  David W. Murray,et al.  Parallel Tracking and Mapping on a camera phone , 2009, 2009 8th IEEE International Symposium on Mixed and Augmented Reality.

[22]  Juan D. Tardós,et al.  ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras , 2016, IEEE Transactions on Robotics.