A PRACTICAL STEREO SYSTEM BASED ON REGULARIZATION AND TEXTURE PROJECTION

Federico Tombari, Kurt Konolige

Abstract

In this paper we investigate the suitability of stereo vision for robot manipulation tasks, which require high-fidelity real-time 3D information in the presence of motion. We compare spatial regularization methods for stereo and spacetime stereo, the latter relying on integration of information over time as well as space. In both cases we augment the scene with textured projection, to alleviate the well-known problem of noise in low-textured areas. We also propose a new spatial regularization method, local smoothing, that is more efficient than current methods, and produces almost equivalent results. We show that in scenes with moving objects spatial regularization methods are more accurate than spacetime stereo, while remaining computationally simpler. Finally, we propose an extension of regularization-based algorithms to the temporal domain, so to further improve the performance of regularization methods within dynamic scenes.

References

  1. Anderson, D., Herman, H., and Kelly, A. (2005). Experimental characterization of commercial flash ladar devices. In Int. Conf. of Sensing and Technology.
  2. Curless, B. and Levoy, M. (1995). Better optical triangulation through spacetime analysis. In ICCV.
  3. Davis, J., Nehab, D., Ramamoorthi, R., and Rusinkiewicz, S. (2005). Spacetime stereo: a unifying framework dor depth from triangulation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(2).
  4. Felzenszwalb, P. and Huttenlocher, D. (2004). Efficient belief propagation for early vision. In Proc. CVPR, volume 1, pages 261-268.
  5. Gong, M. and Yang, Y. (2005). Near real-time reliable stereo matching using programmable graphics hardware. In Proc. CVPR, volume 1, pages 924-931.
  6. Hirschmuller, H. (2005). Accurate and efficient stereo processing by semi-global matching and mutual information. In Proc. CVPR, volume 2, pages 807-814.
  7. Kim, J., Lee, K., Choi, B., and Lee, S. (2005). A dense stereo matching using two-pass dynamic programming with generalized ground control points. In Proc. CVPR, pages 1075-1082.
  8. Klaus, A., Sormann, M., and Karner, K. (2006). Segmentbased stereo matching using belief propagation and a self-adapting dissimilarity measure. In Proc. ICPR, volume 3, pages 15-18.
  9. Kolmogorov, V. and Zabih, R. (2001). Computing visual correspondence with occlusions via graph cuts. In Proc. ICCV, volume 2, pages 508-515.
  10. Konolige, K. (1997). Small vision systems: hardware and implementation. In Eighth International Symposium on Robotics Research, pages 111-116.
  11. M. Bleyer, M, G. (2008). Simple but effective tree structures for dynamic programming-based stereo matching. In Proc. Int. Conf. on Computer Vision Theory and Applications (VISAPP), volume 2.
  12. Nishihara, H. K. (1984). Prism: A practical real-time imaging stereo matcher. Technical report, Cambridge, MA, USA.
  13. Potts, R. (1995). Some generalized order-disorder transitions. In Proc. Cambridge Philosophical Society, volume 48, pages 106-109.
  14. Salvi, J., Pages, J., and Batlle, J. (2004). Pattern docification strategies in structured light systems. Pattern Recognition, 37(4).
  15. Scharstein, D. and Szeliski, R. (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Computer Vision, 47(1/2/3):7-42.
  16. Williams, O., Isard, M., and MacCormick, J. (2005). Estimating disparity and occlusions in stereo video sequences. In Proc. CVPR.
  17. Yang, Q., Wang, L., Yang, R., Wang, S., Liao, M., and Nister, D. (2006). Real-time global stereo matching using hierarchical belief propagation. In Proc. British Machine Vision Conference.
  18. Yang, Q. e. a. (2006). Stereo matching with color-weighted correlation, hierachical belief propagation and occlusion handling. In Proc. CVPR, volume 2, pages 2347 - 2354.
  19. Zhang, L., Curless, B., and Seitz, S. (2003). Spacetime stereo: shape recovery for dynamic scenes. In Proc. CVPR.
  20. Zhao, J. and Katupitiya, J. (2006). A fast stereo vision algorithm with improved performance at object borders. In Proc. Int. Conf. on Intelligent Robots and Systems (IROS), pages 5209-5214.
Download


Paper Citation


in Harvard Style

Tombari F. and Konolige K. (2009). A PRACTICAL STEREO SYSTEM BASED ON REGULARIZATION AND TEXTURE PROJECTION . In Proceedings of the 6th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-674-000-9, pages 5-12. DOI: 10.5220/0002167800050012


in Bibtex Style

@conference{icinco09,
author={Federico Tombari and Kurt Konolige},
title={A PRACTICAL STEREO SYSTEM BASED ON REGULARIZATION AND TEXTURE PROJECTION},
booktitle={Proceedings of the 6th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2009},
pages={5-12},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002167800050012},
isbn={978-989-674-000-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - A PRACTICAL STEREO SYSTEM BASED ON REGULARIZATION AND TEXTURE PROJECTION
SN - 978-989-674-000-9
AU - Tombari F.
AU - Konolige K.
PY - 2009
SP - 5
EP - 12
DO - 10.5220/0002167800050012