Underwater inspection using sonar-based volumetric submaps
| Autor: | John J. Leonard, Michael Kaess, Pedro V. Teixeira, Franz S. Hover |
|---|---|
| Přispěvatelé: | Massachusetts Institute of Technology. Department of Mechanical Engineering, Teixeira, Pedro V., Hover, Franz S, Leonard, John J |
| Rok vydání: | 2016 |
| Předmět: |
0106 biological sciences
0209 industrial biotechnology Engineering business.industry 010604 marine biology & hydrobiology Probabilistic logic 02 engineering and technology Bulbous bow 01 natural sciences Sonar Computer Science::Robotics 020901 industrial engineering & automation Robustness (computer science) Outlier Synthetic aperture sonar Computer vision Artificial intelligence Underwater business Factor graph |
| Zdroj: | IROS Other univ. web domain |
| DOI: | 10.1109/iros.2016.7759631 |
| Popis: | We propose a submap-based technique for mapping of underwater structures with complex geometries. Our approach relies on the use of probabilistic volumetric techniques to create submaps from multibeam sonar scans, as these offer increased outlier robustness. Special attention is paid to the problem of denoising/enhancing sonar data. Pairwise submap alignment constraints are used in a factor graph framework to correct for navigation drift and improve map accuracy. We provide experimental results obtained from the inspection of the running gear and bulbous bow of a 600-foot, Wright-class supply ship. United States. Office of Naval Research (N00014-12-1-0093) United States. Office of Naval Research (N00014-14-1-0373) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|