A Computer Vision-Based Approach for Simultaneous Localization and Mapping of Underwater Robots

• Paulo Drews Jr FURG
• Silvia Botelho FURG

Abstract

The use of autonomous underwater vehicles for visual inspection tasks is a promising robotic field. Due to the difficulty of simultaneous robot localization and mapping (SLAM), this paper proposes a solution based on computer vision and topological maps. By means of an inspection camera as sensorial source, this approach is composed by two main stages: i) the application of SIFT to extract the features in underwater image sequences and ii) the use of self-organized maps. The developed system was validated in real and simulated environments, using real robots in online tests. Both accuracy and robustness attained in unfavorable underwater conditions, such as illumination variation and noise, lead to an original and efficient SLAM technique.

References

Arredondo, M. and Lebart, K. (2005). A methodology for the systematic assessment of underwater video processing algorithms. In IEEE/OES Oceans, volume 1, pages 362–367.

Birchfield, S. (2007). KLT 1.3.4 : A C implementation of KLT tracker. [link]. [Acessado em 12 de Março de 2008.].

Booij, O., Terwijn, B., Zivkovic, Z., and Krose, B. (2007). Navigation using an appearance based topological map. In IEEE ICRA, pages 3927–3932.

Fritzke, B. (1993). Growing cell structures - a self-organizing network for unsupervised and supervised learning. Technical report, University of California.

Garcia, R. (2001). A Proposal to Estimate the Motion of an Underwater Vehicle Through Visual Mosaicking. PhD thesis, Universitat de Girona.

Gracias, N., Van der Zwaan, S., Bernardino, A., and Santos-Vitor, J. (2002). Results on underwater mosaic-based navigation. In MTS/IEEE Oceans, volume 3, pages 1588–1594.

Kohonen, T. (2001). Self-Organizing Maps. Springer-Verlag New York, Inc., Secaucus, NJ, USA.

Lowe, D. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2):91–110.

Mahon, I. and Williams, S. (2004). SLAM using natural features in an underwater environment. In IEEE ICARCV, volume 3, pages 2076–2081.

Marks, R., Rock, S., and Lee, M. (1995). Real-time video mosaicking of the ocean floor. IEEE Journal of Oceanic Engineering, 20(3):229–241.

McFarlane, J. R. (2000). Underwater technology 2000 rovs and auvs: tools for exploring, exploiting and defending the ocean frontier. Underwater Technology, pages 465–471.

Negahdaripour, S. and Khamene, A. (2000). Motion-based compression of underwater video imagery for the operations of unmanned submersible vehicles. Computer Vision and Image Understanding, 79(1):162–183.

Plakas, K. and Trucco, E. (2000). Developing a real-time, robust, video tracker. In MTS/IEEE Oceans, volume 2, pages 1345–1352.

Se, S., Lowe, D., and Little, J. (2005). Vision-based global localization and mapping for mobile robots. IEEE Transactions on Robotics, 21(3):364–375.

Shi, J. and Tomasi, C. (1994). Good features to track. In IEEE Conference on Computer Vision and Pattern Recognition, pages 593–600.

Stewart, C. V. (1999). Robust parameter estimation in computer vision. Society for Industrial and Applied Mathematics Review, 41(3):513–537.

Xu, X. and Negahdaripour, S. (1997). Vision-based motion sensing for underwater navigation and mosaicing of ocean floor images. In MTS/IEEE Oceans, volume 2, pages 1412–1417.