INTERPRETING STRUCTURES IN MAN-MADE SCENES - Combining Low-Level and High-Level Structure Sources

Kasim Terzić, Lothar Hotz, Jan Šochman

2010

Abstract

Recognizing structure is an important aspect of interpreting many computer vision domains. Structure can manifest itself both visually, in terms of repeated low-level phenomena, and conceptually, in terms of a highlevel compositional hierarchy. In this paper, we demonstrate an approach for combining a low-level repetitive structure detector with a logical high-level interpretation system. We evaluate the performance on a set of images from the building façade domain.

References

  1. Freund, Y. and Schapire, R. (1997). A Decision-theoretic Generalization of On-line Learning and an Application to Boosting. Journal of Computer and System Sciences, 55(1):119-139.
  2. Friedman, J., Hastie, T., and Tibshirani, R. (1998). Additive logistic regression: a statistical view of boosting. Technical report, Department of Statistics, Sequoia Hall, Stanford Univerity.
  3. Fusier, F., Valentin, V., Bremond, F., Thonnat, M., Borg, M., Thirde, D., and Ferryman, J. (2007). Video understanding for complex activity recognition. Machine Vision and Applications (MVA), 18:167-188.
  4. Grabner, H., Grabner, M., and Bischof, H. (2006). Realtime tracking via on-line boosting. In British Machine Vision Conference, volume 1, pages 47-56.
  5. Hartz, J., Hotz, L., Neumann, B., and Terzic, K. (2009). Automatic incremental model learning for scene interpretation. In Proc. of the Fourth IASTED International Conference on Computational Intelligence, Honolulu, Hawaii.
  6. Hotz, L. and Neumann, B. (2005). Scene Interpretation as a Configuration Task. Künstliche Intelligenz, 3:59-65.
  7. Hotz, L., Neumann, B., and Terzic, K. (2008). Highlevel expectations for low-level image processing. In KI 2008: Advances in Artificial Intelligence, volume 5243 of Springer Lecture Notes in Computer Science, pages 87-94.
  8. Hummel, B., Thiemann, W., and Lulcheva, I. (2008). Scene understanding of urban road intersections with description logic. In Cohn, A. G., Hogg, D. C., Möller, R., and Neumann, B., editors, Logic and Probability for Scene Interpretation, number 08091 in Dagstuhl Seminar Proceedings, Dagstuhl, Germany. Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany.
  9. Mohnhaupt, M. and Neumann, B. (1993). Understanding object motion: recognition, learning and spatiotemporal reasoning. Robotics and Autonomous Systems, pages 65-91.
  10. Russel, S. and Norvig, P. (2003). Artificial Intelligence - A Modern Approach. Prentice-Hall.
  11. Seo, Y.-W., Ratliff, N., and Urmson, C. (2009). Selfsupervised aerial image analysis for extracting parking lot structure. In Proc. of Twenty-First Int. Joint Conf. on AI IJCAI-09, pages 1837-1842, Pasadena.
  12. Soininen, T., Tiihonen, J., Männistö, T., and Sulonen, R. (1998). Towards a General Ontology of Configuration. Artificial Intelligence for Engineering Design, Analysis and Manufacturing (1998), 12, pages 357- 372.
  13. Terzic, K., Hotz, L., and Neumann, B. (2007). Division of Work During Behaviour Recognition - The SCENIC Approach. In Schuldt, A., editor, Behaviour Monitoring and Interpretation, Workshop Proceedings KI, Universität Bremen.
  14. C?ech, J. and S? ára, R. (2007). Language of the structural models for constrained image segmentation. Technical Report Technical Report TN-eTRIMS-CMP-03- 2007, Czech Technical University, Prague.
  15. Yang, C. and Yang, M.-H. (1997). Constraint Networks: A Survey. In Proc. of the IEEE International Conference on Systems, Man and Cybernetics, volume 2, Orlando, Florida, USA. Institute of Electrical and Electronics Engineers (IEEE).
  16. Zhu, S. and Mumford, D. (2006). A Stochastic Grammar of Images. Foundations and Trends in Computer Graphics and Vision. Prentice-Hall.
Download


Paper Citation


in Harvard Style

Terzić K., Hotz L. and Šochman J. (2010). INTERPRETING STRUCTURES IN MAN-MADE SCENES - Combining Low-Level and High-Level Structure Sources . In Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-674-021-4, pages 357-364. DOI: 10.5220/0002735303570364


in Bibtex Style

@conference{icaart10,
author={Kasim Terzić and Lothar Hotz and Jan Šochman},
title={INTERPRETING STRUCTURES IN MAN-MADE SCENES - Combining Low-Level and High-Level Structure Sources},
booktitle={Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2010},
pages={357-364},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002735303570364},
isbn={978-989-674-021-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - INTERPRETING STRUCTURES IN MAN-MADE SCENES - Combining Low-Level and High-Level Structure Sources
SN - 978-989-674-021-4
AU - Terzić K.
AU - Hotz L.
AU - Šochman J.
PY - 2010
SP - 357
EP - 364
DO - 10.5220/0002735303570364