Semantic Segmentation and Model Fitting for Triangulated Surfaces using Random Jumps and Graph Cuts

Tilman Wekel, Olaf Hellwich

Abstract

Recent advances in 3D reconstruction allows to acquire highly detailed geometry from a set of images. The outcome of vision-based reconstruction methods is often oversampled, noisy, and without any higher-level information. Further processing such as object recognition, physical measurement, urban modeling, or rendering requires more advanced representations such as computer-aided design (CAD) models. In this paper, we present a global approach that simultaneously decomposes a triangulated surface into meaningful segments and fits a set of bounded geometric primitives. Using the theory of Markov chain Monte Carlo methods (MCMC), a random process is derived to find the solution that most likely explains the measured data. A data-driven approach based on the random sample consensus (RANSAC) paradigm is designed to guide the optimization process with respect to efficiency and robustness. It is shown, that graph cuts allow to incorporate model complexity and spatial regularization into the MCMC process. The algorithm has successfully been implemented and tested on various examples.

References

  1. Attene, M., Falcidieno, B., and Spagnuolo, M. (2006). Hierarchical mesh segmentation based on fitting primitives. The Visual Computer, 22:181-193.
  2. Benhabiles, H., Lavoué, G., Vandeborre, J.-P., and Daoudi, M. (2011). Learning boundary edges for 3D-Mesh segmentation. In Computer Graphics Forum, volume 30, pages 2170-2182. Wiley Online Library.
  3. Cohen-Steiner, D., Alliez, P., and Desbrun, M. (2004). Variational shape approximation. In ACM Transactions on Graphics, volume 23, pages 905-914. ACM.
  4. Delong, A., Osokin, A., Isack, H., and Boykov, Y. (2010). Fast approximate energy minimization with label costs. In 2010 IEEE Conference on Computer Vision and Pattern Recognition, pages 2173-2180.
  5. Ebert, D. S. (2003). Texturing & modeling: a procedural approach. Morgan Kaufmann.
  6. Han, F., Tu, Z., and Zhu, S.-C. (2004). Range image segmentation by an effective jump-diffusion method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(9):1138-1153.
  7. Isack, H. and Boykov, Y. (2012). Energy-based geometric multi-model fitting. International Jorunal of Computer Vision, 97(2):123-147.
  8. Jancosek, M. and Pajdla, T. (2011). Multi-view reconstruction preserving weakly-supported surfaces. In 2011 IEEE Conference on Computer Vision and Pattern Recognition, pages 3121-3128. IEEE.
  9. Kalogerakis, E., Hertzmann, A., and Singh, K. (2010). Learning 3d mesh segmentation and labeling. In ACM SIGGRAPH 2010 Papers, SIGGRAPH 7810, pages 102:1-102:12, New York, NY, USA. ACM.
  10. Lafarge, F., Keriven, R., Brédif, M., and Vu, H.-H. (2013). A hybrid multiview stereo algorithm for modeling urban scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1):5-17.
  11. Lai, Y.-K., Hu, S.-M., Martin, R. R., and Rosin, P. L. (2008). Fast mesh segmentation using random walks. In Proceedings of the 2008 ACM symposium on Solid and physical modeling, pages 183-191. ACM.
  12. Lavoué, G. and Wolf, C. (2008). Markov random fields for improving 3d mesh analysis and segmentation. In 3DOR, pages 25-32.
  13. Li, Y., Wu, X., Chrysathou, Y., Sharf, A., Cohen-Or, D., and Mitra, N. J. (2011). Globfit: Consistently fitting primitives by discovering global relations. In ACM Transactions on Graphics (TOG), volume 30, page 52. ACM.
  14. Longjiang, E., Waseem, S., and Willis, A. (2013). Using a map-mrf model to improve 3d mesh segmentation algorithms. In Southeastcon, 2013 Proceedings of IEEE, pages 1-7. IEEE.
  15. Lv, J., Chen, X., Huang, J., and Bao, H. (2012). Semisupervised mesh segmentation and labeling. In Computer Graphics Forum, volume 31, pages 2241-2248. Wiley Online Library.
  16. Mangan, A. P. and Whitaker, R. T. (1999). Partitioning 3d surface meshes using watershed segmentation. IEEE Transactions on Visualization and Computer Graphics, 5(4):308-321.
  17. Papazov, C. and Burschka, D. (2011). An efficient ransac for 3d object recognition in noisy and occluded scenes. In Kimmel, R., Klette, R., and Sugimoto, A., editors, Computer Vision ACCV 2010, volume 6492 of Lecture Notes in Computer Science, pages 135- 148. Springer Berlin Heidelberg.
  18. Schnabel, R., Wahl, R., and Klein, R. (2007). Efficient ransac for point-cloud shape detection. Computer Graphics Forum, 26(2):214-226.
  19. Suzuki, M. (1993). Quantum Monte Carlo methods in condensed matter physics. World scientific.
  20. Tu, Z. and Zhu, S.-C. (2002). Image segmentation by datadriven markov chain monte carlo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5):657-673.
  21. Várady, T., Facello, M. A., and Terék, Z. (2007). Automatic extraction of surface structures in digital shape reconstruction. Computer Aided Design, 39(5):379-388.
  22. Woodford, O. J., Pham, M.-T., Maki, A., Gherardi, R., Perbet, F., and Stenger, B. (2012). Contraction moves for geometric model fitting. In Proceedings of the 12th European Conference on Computer Vision - Volume Part VII, ECCV'12, pages 181-194, Berlin, Heidelberg. Springer-Verlag.
  23. Wu Leif Kobbelt, J. (2005). Structure recovery via hybrid variational surface approximation. In Computer Graphics Forum, volume 24, pages 277-284. Wiley Online Library.
  24. Yan, D.-M., Wang, W., Liu, Y., and Yang, Z. (2012). Variational mesh segmentation via quadric surface fitting. Computer-Aided Design, 44(11):1072-1082.
Download


Paper Citation


in Harvard Style

Wekel T. and Hellwich O. (2015). Semantic Segmentation and Model Fitting for Triangulated Surfaces using Random Jumps and Graph Cuts . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-091-8, pages 241-250. DOI: 10.5220/0005265102410250


in Bibtex Style

@conference{visapp15,
author={Tilman Wekel and Olaf Hellwich},
title={Semantic Segmentation and Model Fitting for Triangulated Surfaces using Random Jumps and Graph Cuts},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={241-250},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005265102410250},
isbn={978-989-758-091-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)
TI - Semantic Segmentation and Model Fitting for Triangulated Surfaces using Random Jumps and Graph Cuts
SN - 978-989-758-091-8
AU - Wekel T.
AU - Hellwich O.
PY - 2015
SP - 241
EP - 250
DO - 10.5220/0005265102410250