Augmented Reality by Integrating Multiple Sensory Modalities for Underwater Scene Understanding
This chapter proposes a method for the integration of acoustic and optical data to enhance the perception of an underwater environment in teleoperation tasks. Off-shore applications are addressed, in which an underwater remotely operated vehicle is approaching an oil rig for inspection, maintenance and repairing tasks. A technique is presented which takes advantage of optical features to segment an acoustic three-dimensional (3-D) image. Cylindrical surfaces are than extracted from 3-D points, and complete cylinders are reconstructed. The final step is to present useful information to the human operator, by displaying the superposition of measured acoustic data and geometric primitives fitted to parts of it, i.e., an augmented reality view. Experimental results with real data are reported showing the effectiveness of the proposed approach.
KeywordsAugmented Reality Markov Random Field Acoustic Data Complete Subgraph Optical Camera
Unable to display preview. Download preview PDF.
- D. H. Ballard and Brown C. M. Computer Vision. Prentice-Hall Inc., 1982.Google Scholar
- R. R. Brooks and S.S. Iyengar. Multi-Sensor Fusion. Prentice Hall, Upper Saddle River, USA, 1998.Google Scholar
- A. Fusiello, R. Giannitrapani, V. Isaia, and V. Murino. Virtual environment modeling by integrated optical and acoustic sensing. In Second International Conference on 3-D Digital Imaging and Modeling (3DIM99), pages 437–446, Ottawa, Canada, 4–8 October 1999. IEEE Computer Society Press.CrossRefGoogle Scholar
- A. Fusiello and V. Murino. Calibration of an optical/acoustic sensor. In 6th International Conference on Computer Graphics and Image Processing (GKPO2000), 2000. To appear.Google Scholar
- R. Giannitrapani, A. Trucco, and V. Murino. Segmentation of underwater 3-D acoustical images for augmented and virtual reality applications. In Proceedings of the OCEANS’99 Conference, pages 459–465, Seattle (USA), September 1999. MTS/IEEE.Google Scholar
- F. Goulette. Automatic CAD modeling of industrial pipes from range images. In International Conference on Recent Advances in 3-D Digital Imaging and Modeling, pages 229–233, May 1997.Google Scholar
- B. Gunsel, A. K. Jain, and E. Panayirci. Reconstruction and boundary detection of range and intensity images using multiscale MRF representations. CVGIP: Image Understanding, 63(2):353–366, March 1996.Google Scholar
- M. Hebert, R. Hoffman, A. Johnson, and J. Osborn. Sensor based interior modeling. In American Nuclear Society 6th Topical Meeting on Robotics and Remote Systems (ANS ’95), pages 731–737, February 1995.Google Scholar
- A. Johnson, P. Leger, R. Hoffman, M. Hebert, and J. Osborn. 3-D object modeling and recognition for telerobotic manipulation. In Proc. IEEE Intelligent Robots and Systems, volume 1, pages 103–110, August 1995.Google Scholar
- D. Dion Jr. and D. Laurendeau. Generalized cylinders extraction in a range image. In International Conference on Recent Advances in 3-D Digital Imaging and Modeling, pages 141–147, May 1997.Google Scholar
- M. Maimone, L. Matthies, J. Osborn, E. Rollins, J. Teza, and S. Thayer. A photo-realistic 3-D mapping system for extreme nuclear environments: Chornobyl. In Proceedings of the 1998 IEEE/RS J International Conference on Intelligent Robotic Systems (IROS ’98). IEEE, 1998.Google Scholar
- G. Scott and H. Longuet-Higgins. An algorithm for associating the features of two images. In Proceedings of the Royal Society of London B, volume 244, pages 21–26, 1991.Google Scholar