DEPTH PREDICTION AT HOMOGENEOUS IMAGE STRUCTURES

Sinan Kalkan, Florentin Wörgötter, Norbert Krüger

Abstract

This paper proposes a voting-based model that predicts depth at weakly-structured image areas from the depth that is extracted using a feature-based stereo method. We provide results, on both real and artificial scenes, that show the accuracy and robustness of our approach. Moreover, we compare our method to different dense stereo algorithms to investigate the effect of texture on performance of the two different approaches. The results confirm the expectation that dense stereo methods are suited better for textured image areas and our method for weakly-textured image areas.

References

  1. Brown, M. Z., Burschka, D., and Hager, G. D. (2003). Advances in computational stereo. IEEE Trans. Pattern Anal. Mach. Intell., 25(8):993-1008.
  2. Grimson, W. E. L. (1982). A Computational Theory of Visual Surface Interpolation. Royal Society of London Philosophical Transactions Series B, 298:395-427.
  3. Guy, G. and Medioni, G. (1994). Inference of surfaces from sparse 3-d points. In ARPA94, pages II:1487-1494.
  4. Hoff, W. A. and Ahuja, N. (1989). Surfaces from stereo: Integrating feature matching, disparity estimation, and contour detection. IEEE Trans. Pattern Anal. Mach. Intell., 11(2):121-136.
  5. Kalkan, S., W örgötter, F., and Krüger, N. (2006). Statistical analysis of local 3d structure in 2d images. CVPR, pages 1114-1121.
  6. Kalkan, S., W örgötter, F., and Krüger, N. (2007). Firstorder and second-order statistical analysis of 3d and 2d structure. Network: Computation in Neural Systems, 18(2):129-160.
  7. Krüger, N., Lappe, M., and W örgötter, F. (2004). Biologically motivated multi-modal processing of visual primitives. The Interdisciplinary Journal of Artificial Intelligence and the Simulation of Behaviour, 1(5):417-428.
  8. Lee, M. S. and Medioni, G. (1998). Inferring segmented surface description from stereo data. In CVPR.
  9. Lee, M.-S., Medioni, G., and Mordohai, P. (2002). Inference of segmented overlapping surfaces from binocular stereo. IEEE Trans. Pattern Anal. Mach. Intell., 24(6):824-837.
  10. Pugeault, N. and Krüger, N. (2003). Multi-modal matching applied to stereo. Proceedings of the BMVC 2003, pages 271-280.
  11. Sabatini, S. P., Gastaldi, G., Solari, F., Diaz, J., Ros, E., Pauwels, K., Hulle, K. M. M. V., Pugeault, N., and Krüger, N. (2007). Compact and accurate early vision processing in the harmonic space. VISAPP, Barcelona.
  12. Scharstein, D. and Szeliski, R. (2001). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Technical Report MSR-TR-2001-81, Microsoft Research, Microsoft Corporation.
  13. Terzopoulos, D. (1988). The computation of visible-surface representations. IEEE Trans. Pattern Anal. Mach. Intell., 10(4):417-438.
Download


Paper Citation


in Harvard Style

Kalkan S., Wörgötter F. and Krüger N. (2008). DEPTH PREDICTION AT HOMOGENEOUS IMAGE STRUCTURES . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 520-527. DOI: 10.5220/0001079005200527


in Bibtex Style

@conference{visapp08,
author={Sinan Kalkan and Florentin Wörgötter and Norbert Krüger},
title={DEPTH PREDICTION AT HOMOGENEOUS IMAGE STRUCTURES},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={520-527},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001079005200527},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - DEPTH PREDICTION AT HOMOGENEOUS IMAGE STRUCTURES
SN - 978-989-8111-21-0
AU - Kalkan S.
AU - Wörgötter F.
AU - Krüger N.
PY - 2008
SP - 520
EP - 527
DO - 10.5220/0001079005200527