Vision-Based Shipwreck Mapping: On Evaluating Features Quality and Open Source State Estimation Packages

Alberto Quattrini Li, Adem Coskun, Sean M. Doherty, Shervin Ghasemlou, Apoorv S. Jagtap, MD Modasshir, Sharmin Rahman, Akanksha Singh, Marios Xanthidis, Jason M. O'Kane, Ioannis Rekleitis
In Proc. MTS/IEEE Oceans
2016

Abstract 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 View, contains underwater panoramas from select location 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.

@inproceedings{QuaCos+16b,
  author = {Alberto Quattrini Li and Adem Coskun and Sean M. Doherty and Shervin
            Ghasemlou and Apoorv S. Jagtap and MD Modasshir and
            Sharmin Rahman and Akanksha Singh and Marios Xanthidis and
            Jason M. O'Kane and Ioannis Rekleitis},
  booktitle = {Proc. MTS/IEEE Oceans},
  title = {Vision-Based Shipwreck Mapping: {O}n Evaluating Features Quality and
           Open Source State Estimation Packages},
  year = {2016}
}


O'Kane's home page
O'Kane's publication list

Last updated 2020-09-23.