Vision-based shipwreck mapping: On evaluating features quality and open source state estimation packages

Historical shipwrecks are important for many reasons, including historical, touristic, and environmental. Currently, limited efforts for constructing accurate models are performed by divers that need to take measurements manually using a grid and measuring tape, or using handheld sensors. A commercial product, Google Street View1, contains underwater panoramas from select locations around the planet including a few shipwrecks, such as the SS Antilla in Aruba and the Yongala at the Great Barrier Reef. However, these panoramas contain no geometric information and thus there are no 3D representations available of these wrecks. This paper provides, first, an evaluation of visual features quality in datasets that span from indoor to underwater ones. Second, by testing some open-source vision-based state estimation packages on different shipwreck datasets, insights on open challenges for shipwrecks mapping are shown. Some good practices for replicable results are also discussed.

[1]  Hanumant Singh,et al.  Robotic tools for deep water archaeology: Surveying an ancient shipwreck with an autonomous underwater vehicle , 2010, J. Field Robotics.

[2]  Reinhard Koch,et al.  3D reconstruction based on underwater video from ROV Kiel 6000 considering underwater imaging conditions , 2009, OCEANS 2009-EUROPE.

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

[4]  Matthew Johnson-Roberson,et al.  Mapping Submerged Archaeological Sites using Stereo‐Vision Photogrammetry , 2013 .

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

[6]  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.

[7]  Stefan B. Williams,et al.  Return to Antikythera: Multi-session SLAM Based AUV Mapping of a First Century B.C. Wreck Site , 2015, FSR.

[8]  Asgeir J. Sørensen,et al.  Underwater Photogrammetric Mapping of an Intact Standing Steel Wreck with ROV , 2015 .

[9]  Mariette Yvinec,et al.  A surface reconstruction method for in-detail underwater 3D optical mapping , 2015, Int. J. Robotics Res..

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

[11]  Dimitrios G. Kottas,et al.  Consistency Analysis and Improvement of Vision-aided Inertial Navigation , 2014, IEEE Transactions on Robotics.

[12]  Jason M. O'Kane,et al.  Experimental Comparison of Open Source Vision-Based State Estimation Algorithms , 2016, ISER.

[13]  Carrick Detweiler,et al.  Color-accurate underwater imaging using perceptual adaptive illumination , 2010, Auton. Robots.

[14]  Chris Roman,et al.  Application of structured light imaging for high resolution mapping of underwater archaeological sites , 2010, OCEANS'10 IEEE SYDNEY.

[15]  Pere Ridao,et al.  Creating 360° underwater virtual tours using an omnidirectional camera integrated in an AUV , 2015, OCEANS 2015 - Genova.

[16]  M. Carreras,et al.  Mapping the Moon: Using a lightweight AUV to survey the site of the 17th century ship ‘La Lune’ , 2013, 2013 MTS/IEEE OCEANS - Bergen.

[17]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[18]  Andrew Hogue,et al.  Underwater environment reconstruction using stereo and inertial data , 2007, 2007 IEEE International Conference on Systems, Man and Cybernetics.

[19]  Alberto Quattrini Li,et al.  Shallow coral reef surveying by inexpensive drifters , 2016, OCEANS 2016 - Shanghai.

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

[21]  F. Soreide,et al.  Ormen Lange: investigation and excavation of a shipwreck in 170m depth , 2005, Proceedings of OCEANS 2005 MTS/IEEE.

[22]  Gregory Dudek,et al.  Enabling autonomous capabilities in underwater robotics , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  Gregory Dudek,et al.  Feature Tracking Evaluation for Pose Estimation in Underwater Environments , 2011, 2011 Canadian Conference on Computer and Robot Vision.

[24]  John Enright,et al.  The Devon Island rover navigation dataset , 2012, Int. J. Robotics Res..

[25]  Weilin Hou,et al.  Image feature detection and matching in underwater conditions , 2010, Defense + Commercial Sensing.

[26]  Janet Wiles,et al.  OpenRatSLAM: an open source brain-based SLAM system , 2013, Autonomous Robots.

[27]  L. Neumann,et al.  a New Color Correction Method for Underwater Imaging , 2015 .

[28]  M. Carreras,et al.  Feature extraction for underwater visual SLAM , 2011, OCEANS 2011 IEEE - Spain.