Generation of 3D Dense Depth Maps by Dynamic Vision
This paper presents a dynamic 3D Vision system that is able to estimate dense depth maps from an image sequence. The depth maps computed at each time instant are used in an Extended Kaiman filtering structure, that integrates all depth measurements over time, reducing uncertainty. Results with images acquired by an underwater camera, are presented.
KeywordsExtend Kalman Filter Camera Motion Autonomous Underwater Vehicle Depth Estimate Epipolar Line
Unable to display preview. Download preview PDF.
- L. Mathies, T. Kanade, and Szelisky R. Kaiman filter-based algorithms for estimating depth from image sequences. Int. J. of Computer Vision ,4(3):2O9–238, 1989.Google Scholar
- J. Heel. Dynamic motion vision. In Proc. of the DARPA Image Understanding Workshop. Morgan-Kaufman Publishers, May 1989.Google Scholar
- B.K. Horn. Robot Vision. M.I.T.Press, 1986.Google Scholar
- D. Ballard and C. Brown. Computer Vision. Prentice-Hall, London, 1982.Google Scholar
- J. Santos-Victor and J. Sentieiro. A Dynamic 3D Vision System. Technical report, Instituto Superior Técnico, February 1992. Ref. Mobius/rpt/02/92 JASV/JJSS.Google Scholar
- R. Szeliski. Bayesian Modeling of Uncertainty in Low-Level Vision. PhD thesis, Carnegie Mellon University, 1988.Google Scholar