3D Representation Models Construction through a Volume Geometric Decomposition Method

Gisele Simas, Rodrigo de Bem, Silvia Botelho

Abstract

Despite the fact of 3D motion tracking has being highly explored in the computer vision researches, it still faces some relevant challenges, such as the tracking of objects using few a priori knowledge. In this context, this work presents the Volume Geometric Decomposition method, capable of constructing representation models of distinct and previously unknown objects. This method is executed over a probabilistic volumetric reconstruction of the interested objects. It adjusts the representation to the reconstructed volume, minimizing the amount of empty space enclosed by the model. Such representation model is composed by an appearance and a kinematic models. The former is comprised of ellipsoids and joints, while the latter is implemented through the Loose-Limbed model, a probabilistic graphical model. The performed experiments and the obtained results shown that the proposed method successfully constructed representation models to highly distinct and a priori unknown objects.

References

  1. Anguelov, D., Koller, D., Pang, H.-C., Srinivasan, P., and Thrun, S. (2004). Recovering articulated object models from 3d range data. In 20th Conf. on Uncertainty in Artificial Intelligence, UAI 7804, pages 18-26.
  2. Banégas, F., Jaeger, M., Michelucci, D., and Roelens, M. (2001). The ellipsoidal skeleton in medical applications. In Sixth ACM Symp. on Solid Modeling and Appl., SMA 7801, pages 30-38.
  3. Caillette, F. (2006). Real-Time Markerless 3D Human Body Tracking. Phd thesis, University of Manchester.
  4. Canton-Ferrer, C., Casas, J., and Pardas, M. (2009). Voxel based annealed particle filtering for markerless 3d articulated motion capture. In 3DTV Conf.: The True Vision - Capture, Transmission and Display of 3D Video, 2009, pages 1 -4.
  5. Cipolla, R., Stenger, B., Thayananthan, A., and Torr, P. (2003). Hand tracking using a quadric surface model and bayesian filtering. In Mathematics of Surfaces, volume 2768 of LNCS, pages 129-141. Springer.
  6. Darby, J., Li, B., and Costen, N. (2008). Behaviour based particle filtering for human articulated motion tracking. In ICPR, 2008, pages 1-4.
  7. de Aguiar, E., Theobalt, C., Magnor, M., Theisel, H., and Seidel, H.-P. (2004). M3: marker-free model reconstruction and motion tracking from 3d voxel data. In Pacific Graphics, 2004, pages 101-110.
  8. de Aguiar, E., Theobalt, C., and Seidel, H.-P. (2006). Automatic learning of articulated skeletons from 3d marker trajectories. In Second Int. Conf. on Advances in Visual Computing, ISVC'06, pages 485-494.
  9. de Aguiar, E., Theobalt, C., Thrun, S., and Seidel, H.-P. (2008). Automatic conversion of mesh animations into skeleton-based animations. Computer Graphics Forum, 27(2):389-397.
  10. Fossati, A., Salzmann, M., and Fua, P. (2009). Observable subspaces for 3d human motion recovery. In CVPR, 2009, pages 1137-1144.
  11. Franco, J.-S. and Boyer, E. (2005). Fusion of multiview silhouette cues using a space occupancy grid. In ICCV, 2005, pages 1747-1753.
  12. Gall, J., Rosenhahn, B., Brox, T., and Seidel, H.-P. (2010). Optimization and filtering for human motion capture. Int. J. of Computer Vision, 87:75-92.
  13. Hasler, N., Rosenhahn, B., Thormahlen, T., Wand, M., Gall, J., and Seidel, H.-P. (2009). Markerless motion capture with unsynchronized moving cameras. In CVPR, 2009, pages 224-231.
  14. Huang, P., Hilton, A., and Starck, J. (2009). Human motion synthesis from 3d video. In CVPR, 2009, pages 1478- 1485.
  15. Inria (2012). 4d repository. Perception Group, Inria RhoˆneAlpes. http://4drepository.inrialpes.fr.
  16. Isard, M. (2003). Pampas: real-valued graphical models for computer vision. In CVPR, 2003, pages 613-620.
  17. James, D. L. and Twigg, C. D. (2005). Skinning mesh animations. ACM Trans. Graph., 24(3):399-407.
  18. Mian, A., Bennamoun, M., and Owens, R. (2006). Threedimensional model-based object recognition and segmentation in cluttered scenes. IEEE Trans. Pattern Anal. Machine Intell., 28(10):1584 -1601.
  19. Mikic, I., Trivedi, M., Hunter, E., and Cosman, P. (2003). Human body model acquisition and tracking using voxel data. Int. J. of Computer Vision, 53:199-223.
  20. Ross, D., Lim, J., Lin, R.-S., and Yang, M.-H. (2008). Incremental learning for robust visual tracking. Int. J. of Computer Vision, 77:125-141.
  21. Ross, D., Tarlow, D., and Zemel, R. (2010). Learning articulated structure and motion. Int. J. of Computer Vision, 88:214-237.
  22. Schaefer, S. and Yuksel, C. (2007). Example-based skeleton extraction. In Fifth Eurographics Symp. on Geometry Processing, SGP 7807, pages 153-162.
  23. Sigal, L. and Black, M. (2010). Guest editorial: State of the art in image- and video-based human pose and motion estimation. Int. J. of Computer Vision, 87:1-3.
  24. Sigal, L., Isard, M., Sigelman, B. H., and Black, M. J. (2003). Attractive people: Assembling loose-limbed models using non-parametric belief propagation. In NIPS, 2003, pages 1539-1546.
  25. Song, Y., Goncalves, L., and Perona, P. (2003). Unsupervised learning of human motion. IEEE Trans. Pattern Anal. Machine Intell., 25(7):814 - 827.
  26. Starck, J. and Hilton, A. (2003). Model-based multiple view reconstruction of people. In ICCV, 2003, pages 915- 922.
  27. Starck, J. and Hilton, A. (2007). Surface capture for performance-based animation. IEEE Comput. Graph. Appl., 27:21-31.
  28. Sudderth, E., Ihler, A., Freeman, W., and Willsky, A. (2003). Nonparametric belief propagation. In CVPR, 2003., pages 605-612.
  29. Sudderth, E. B., Ihler, A. T., Isard, M., Freeman, W. T., and Willsky, A. S. (2010). Nonparametric belief propagation. Commun. ACM, 53(10):95-103.
  30. Sundaresan, A. and Chellappa, R. (2009). Multicamera tracking of articulated human motion using shape and motion cues. IEEE Trans. on Image Processing, 18(9):2114 -2126.
  31. Theobalt, C., de Aguiar, E., Magnor, M. A., Theisel, H., and Seidel, H.-P. (2004). Marker-free kinematic skeleton estimation from sequences of volume data. In ACM Symp. on Virtual Reality Software and Technology, 2004, VRST 7804, pages 57-64. ACM.
  32. Toshev, A., Makadia, A., and Daniilidis, K. (2009). Shapebased object recognition in videos using 3d synthetic object models. In CVPR, 2009, pages 288 -295.
  33. Ukita, N., Hirai, M., and Kidode, M. (2009). Complex volume and pose tracking with probabilistic dynamical models and visual hull constraints. In ICCV, 2009, pages 1405 -1412.
Download


Paper Citation


in Harvard Style

Simas G., de Bem R. and Botelho S. (2013). 3D Representation Models Construction through a Volume Geometric Decomposition Method . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-48-8, pages 274-279. DOI: 10.5220/0004288502740279


in Bibtex Style

@conference{visapp13,
author={Gisele Simas and Rodrigo de Bem and Silvia Botelho},
title={3D Representation Models Construction through a Volume Geometric Decomposition Method},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={274-279},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004288502740279},
isbn={978-989-8565-48-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)
TI - 3D Representation Models Construction through a Volume Geometric Decomposition Method
SN - 978-989-8565-48-8
AU - Simas G.
AU - de Bem R.
AU - Botelho S.
PY - 2013
SP - 274
EP - 279
DO - 10.5220/0004288502740279