DEPTH GRADIENT IMAGE BASED ON SILHOUETTE - A Solution for Reconstruction of Scenes in 3D Environments

Pilar Merchán, Antonio Adán, Santiago Salamanca

Abstract

Greatest difficulties arise in 3D environments when we have to deal with a scene with dissimilar objects without pose restrictions and where contacts and occlusions are allowed. This work tackles the problem of correspondence and alignment of surfaces in such a kind of scenes. The method presented in this paper is based on a new representation model called Depth Gradient Image Based on Silhouette (DGI-BS) which synthesizes object surface information (through depth) and object shape information (through contour). Recognition and pose problems are efficiently solved for all objects of the scene by using a simple matching algorithm in the DGI-BS space. As a result of this the scene can be virtually reconstructed. This work is part of a robot intelligent manipulation project. The method has been successfully tested in real experimentation environments using range sensors.

References

  1. Antonio Adán and Miguel Adán, 2004. A flexible similarity measure for 3D shapes recognition. In IEEE TPMI, 26(11), 1507-1520.
  2. A. Adán, P. Merchán, S. Salamanca, A. Vázquez , M. Adán, C. Cerrada, 2005.Objects Layout Graph for 3D Complex Scenes. In Proc. of ICIP'05.
  3. A. Ashbrook, R. Fisher, N. Werghi, C. Robertson, 1998. Aligning arbitrary surfaces using pairwise geometric histograms. In Proc. Noblesse Workshop on No-linear Model Based Image Analysis, 103-108.
  4. Alferez, R., Wang,Y.F., 1999.Geometric and illumination invariants for object recognition. In IEEE TPAMI 21, 505-535
  5. Bamieh, B., De Figuereido, R.J.P., 1986. A general moment-invariants/attributed graph method for threedimensional object recognition from single image. In IEEE T. Rob. Aut., RA-2, 31-41
  6. Besl, P. and McKay, N., 1992. A method for registration of 3-D shapes. In IEEE TPAMI, 14 (2), 239-256.
  7. R. Campbell, P. J. Flynn, 2002. Recognition of Free-Form Objects in Dense Range Data Using Local Features. In 16th International Conference on Pattern Recognition.
  8. C.M. Cyr and B.B. Kimia, 2004. A similarity-based aspect-graph approach to 3D object recognition. In Int. Journal of Computer Vision, 57(1), 5-22.
  9. Ching S. Chua, Ray Jarvis, 1997. Point signatures: A new representation for 3D object recognition. In International J. of Comp. Vision, 25(1), 63-85.
  10. Horn, B., 1988. Closed-Form Solution of absolute orientation using orthonormal matrices. In Journal of the Optical Society A. 5 (7).
  11. Andrew E. Johnson and Martial Hebert. 1999. Using spin images for efficient object recognition in cluttered 3d scenes. In IEEE TPAMI, 21(5), 433-449.
  12. Lee, J.D., 2000. A new scheme for planar shape recognition using wavelets. In Comp. Mach. Appl. 39 201-216
  13. Merchán, P., Adán, A., Salamanca, S., Cerrada, C., 2002. 3D complex scenes segmentation from a single range image using virtual exploration. In LNAI, 2527, 923- 932.
  14. Mokhararian, F. S., 1997. Silhouette-based occluded object recognition through curvature scale space. In Mach. Vis. Appl. 10, 87-97
  15. B.M. Planitz, A.J. Maeder, J.A. Williams, 2005. The correspondence framework for 3D surface matching algorithms. In Comp. Vis. Image Underst. 97,347-383.
  16. Roh, K.C., Kweon, I. S., 2000. 3-D object recognition using a new invariant relationship by single view. In Pattern Recognition 33, 741-754.
  17. Rothwell, C.A., Zisserman, A., Forsyth, D.A., Mundy, J.L., 1995. Planar object recognition using projective shape representation. In Int. J. Com. Vision 12, 57-59
  18. Rusinkiewicz, S., and Levoy, M., 2001. Efficient variant of the ICP algorithm. In Proc. of 3DIM'01. 145-152.
  19. Trazegnies,C.,Urdiales,C., Bandera,A., Sandoval,F., 2003. 3D object recognition based on curvature information of planar views. In Pattern Rec. 36, 2571-2584.
  20. Xinguo Liu, Robin Sun, Sing Bing Kang, and HeungYeung Shum, 2003. Directional histogram for threedimensional shape similarity. In Proc. of the IEEE Conference on CVPR, I, 813-820,.
  21. Xu, D., Xu,W., 2005. Description and Recognition of object contours using arc length and tangent orientation. In Pattern Rec. Letters 26, 855-864
  22. Sameh Yamany and Aly Farag, 2002.Surfacing signatures: An orientation independent free-form surface representation scheme for the purpose of objects registration and matching. In IEEE TPAMI, 24(8),1105-1120.
  23. Zabulis, X., Sporring, J., Orphanoudakis, S.C., 2005. Perceptually relevant and piecewise linear matching of silhouettes.In Pattern Recognition 38, 75-93
  24. Zahn, C.T., Roskies, R.C., 1972. Fourier descriptors for plane closed curve. In IEEE T. Comp. 21,195-281
  25. Zhang, Z., 1994. Iterative point matching for registration of free-form curves and surfaces. In International Journal of Computer Vision, 13 (2), 119-152.
  26. Zhang, 1999. Harmonic Shape Images: A 3D free form representation and its applications in surface matching. In PhD thesis CMU. Pennsylvania. USA.
Download


Paper Citation


in Harvard Style

Merchán P., Adán A. and Salamanca S. (2006). DEPTH GRADIENT IMAGE BASED ON SILHOUETTE - A Solution for Reconstruction of Scenes in 3D Environments . In Proceedings of the Third International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-972-8865-60-3, pages 112-119. DOI: 10.5220/0001214401120119


in Bibtex Style

@conference{icinco06,
author={Pilar Merchán and Antonio Adán and Santiago Salamanca},
title={DEPTH GRADIENT IMAGE BASED ON SILHOUETTE - A Solution for Reconstruction of Scenes in 3D Environments},
booktitle={Proceedings of the Third International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2006},
pages={112-119},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001214401120119},
isbn={978-972-8865-60-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - DEPTH GRADIENT IMAGE BASED ON SILHOUETTE - A Solution for Reconstruction of Scenes in 3D Environments
SN - 978-972-8865-60-3
AU - Merchán P.
AU - Adán A.
AU - Salamanca S.
PY - 2006
SP - 112
EP - 119
DO - 10.5220/0001214401120119