Shape-from-Silhouettes Algorithm with Built-in Occlusion Detection and Removal

Maarten Slembrouck, Dimitri Van Cauwelaert, Peter Veelaert, Wilfried Philips

2015

Abstract

Occlusion and inferior foreground/background segmentation still poses a big problem to 3D reconstruction from a set of images in a multi-camera system because it has a destructive nature on the reconstruction if one or more of the cameras do not see the object properly. We propose a method to obtain a 3D reconstruction which takes into account the possibility of occlusion by combining the information of all cameras in the multicamera setup. The proposed algorithm tries to find a consensus of geometrical predicates that most cameras can agree on. The results show a performance with an average error lower than 2cm on the centroid of a person in case of perfect input silhouettes. We also show that tracking results are significantly improved in a room with a lot of occlusion.

References

  1. Allied Vision Technologies. Manta G-046C. http:// www.alliedvisiontec.com/us/products/cameras/gigabitethernet/manta/g-046bc.html. Accessed: 2014-09-14.
  2. Guan, L., Sinha, S., Franco, J.-S., and Pollefeys, M. (2006). Visual hull construction in the presence of partial occlusion. In 3D Data Processing, Visualization, and Transmission, Third International Symposium on, pages 413-420. IEEE.
  3. Laurentini, A. (1994). The visual hull concept for silhouette-based image understanding. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 16(2):150-162.
  4. Laurentini, A. (1997). How many 2d silhouettes does it take to reconstruct a 3d object? Computer Vision and Image Understanding, 67(1):81-87.
  5. Laurentini, A. (1999). The visual hull of curved objects. In In Proceedings of ICCV99, Corfu, pages 356-361.
  6. Ober-Gecks, A., Haenel, M., Werner, T., and Henrich, D. (2014). Fast multi-camera reconstruction and surveillance with human tracking and optimized camera configurations. In ISR/Robotik 2014; 41st International Symposium on Robotics; Proceedings of, pages 1-8. VDE.
  7. Slembrouck, M., Van Cauwelaert, D., Van Hamme, D., Van Haerenborgh, D., Van Hese, P., Veelaert, P., and Philips, W. (2014). Self-learning voxel-based multicamera occlusion maps for 3d reconstruction. In 9th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP-2014). SCITEPRESS.
  8. St-Charles, P.-L., Bilodeau, G.-A., and Bergevin, R. (2014). Flexible background subtraction with self-balanced local sensitivity. In Proceedings of IEEE Workshop on Change Detection.
  9. Stengel, D., Wiedemann, T., and Vogel-Heuser, B. (2012). Efficient 3d voxel reconstruction of human shape within robotic work cells. In Mechatronics and Automation (ICMA), 2012 International Conference on, pages 1386-1392. IEEE.
  10. Toth, C., O'Rourke, J., and Goodman, J. (2004). Handbook of Discrete and Computational Geometry, Second Edition. Discrete and Combinatorial Mathematics Series. Taylor & Francis.
  11. Wang, Y., Jodoin, P.-M., Porikli, F., Konrad, J., Benezeth, Y., and Ishwar, P. (2014). Cdnet 2014: An expanded change detection benchmark dataset. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 387-394.
Download


Paper Citation


in Harvard Style

Slembrouck M., Van Cauwelaert D., Veelaert P. and Philips W. (2015). Shape-from-Silhouettes Algorithm with Built-in Occlusion Detection and Removal . 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 635-642. DOI: 10.5220/0005355506350642


in Bibtex Style

@conference{visapp15,
author={Maarten Slembrouck and Dimitri Van Cauwelaert and Peter Veelaert and Wilfried Philips},
title={Shape-from-Silhouettes Algorithm with Built-in Occlusion Detection and Removal},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={635-642},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005355506350642},
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 - Shape-from-Silhouettes Algorithm with Built-in Occlusion Detection and Removal
SN - 978-989-758-091-8
AU - Slembrouck M.
AU - Van Cauwelaert D.
AU - Veelaert P.
AU - Philips W.
PY - 2015
SP - 635
EP - 642
DO - 10.5220/0005355506350642