Three-dimensional Object Recognition via Subspace Representation on a Grassmann Manifold

Ryoma Yataka, Kazuhiro Fukui

2017

Abstract

In this paper, we propose a method for recognizing three-dimensional (3D) objects using multi-view depth images. To derive the essential 3D shape information extracted from these images for stable and accurate 3D object recognition, we need to consider how to integrate partial shapes of a 3D object. To address this issue, we introduce two ideas. The first idea is to represent a partial shape of the 3D object by a three-dimensional subspace in a high-dimensional vector space. The second idea is to represent a set of the shape subspaces as a subspace on a Grassmann manifold, which reflects the 3D shape of the object more completely. Further, we measure the similarity between two subspaces on the Grassmann manifold by using the canonical angles between them. This measurement enables us to construct a more stable and accurate method based on richer information about the 3D shape. We refer to this method based on subspaces on a Grassmann manifold as the Grassmann mutual subspace method (GMSM). To further enhance the performance of the GMSM, we equip it with powerful feature-extraction capabilities. The validity of the proposed method is demonstrated through experimental comparisons with several conventional methods on a hand-depth image dataset.

References

  1. Afriat, S. N. (1957). Orthogonal and oblique projectors and the characteristics of pairs of vector spaces. Proceedings of the Cambridge Philosophical Society, 53:800- 816.
  2. Costeira, Joa˜o, P. and Kanade, T. (1998). A multibody factorization method for independently moving objects. International Journal of Computer Vision, 29(3):159- 179.
  3. Fukui, K. and Maki, A. (2015). Difference subspace and its generalization for subspace-based methods. IEEE Trans. Pattern Anal. Mach. Intell., 37(11):2164-2177.
  4. Fukui, K. and Yamaguchi, O. (2003). Face recognition using multi-viewpoint patterns for robot vision. Proc. 11th International Symposium of Robotics Research, pages 192-201.
  5. Hamm, J. and Lee, Daniel, D. (2008). Grassmann discriminant analysis: A unifying view on subspace-based learning. In Proceedings of the 25th International Conference on Machine Learning, pages 376-383.
  6. Harold, H. (1936). Relations between two sets of variates. Biometrika, 28(3/4):321-377.
  7. Jamie, S., Ross, G., Andrew, F., Toby, S., Mat, C., Mark, F., Richard, M., Pushmeet, K., Antonio, C., Alex, K., and Andrew, B. (2012). Efficient Human Pose Estimation from Single Depth Images, pages 175-192. Springer London.
  8. Jianguo, L., Eric, Lia nd Yurong, C., Lin, X., and Yimin, Z. (2010). Bundled depth-map merging for multiview stereo. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pages 2769- 2776.
  9. Kanade, T., Rander, P., and Narayanan, P. J. (1997). Virtualized reality: Constructing virtual worlds from real scenes. IEEE MultiMedia, 4(1):34-47.
  10. Kawahara, T., Nishiyama, M., Kozakaya, T., and Yamaguchi, O. (2007). Face recognition based on whitening transformation of distribution of subspaces. Proc. ACCV 2007 Workshops, Subspace2007, pages 97- 103.
  11. Lee, K. C., Ho, J., and Kriegman, D. J. (2005). Acquiring linear subspaces for face recognition under variable lighting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(5):684-698.
  12. Maeda, K. and Watanabe, S. (1985). A pattern matching method with local structure. Trans. IEICE, J68- D:345-352.
  13. Michael, A. A. C. and Trevor, F. C. (2008). Multidimensional Scaling, pages 315-347. Springer Berlin Heidelberg.
  14. Ohkawa, Y. and Fukui, K. (2012). Hand shape recognition using the distributions of multi-viewpoint image sets. IEICE Transactions on Information and Systems, E95-D(6):1619-1627.
  15. Paul, J. B. and Neil, D. M. (1992). A method for registration of 3-d shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2):239-256.
  16. Ronen, B. and David, W. J. (2003). Lambertian reflectance and linear subspaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(2):218-233.
  17. Shen, W., Xiao, S., Jiang, N., and Liu, W. (2012). Unsupervised human skeleton extraction from kinect depth images. In Proceedings of the 4th International Conference on Internet Multimedia Computing and Service, pages 66-69.
  18. Song, S. and Xiao, J. (2014). Sliding Shapes for 3D Object Detection in Depth Images, pages 634-651. Springer International Publishing.
  19. Stefania, C., Stefano, R., and Gaetano, S. (2014). Current research results on depth map interpolation techniques. Lecture Notes in Computational Vision and Biomechanics, 15:187-200.
  20. Tomasi, C. and Kanade, T. (1992). Shape and motion from image streams under orthography: a factorization method. International Journal of Computer Vision, 9(2):137-154.
  21. Watanabe, T., Ohtsuka, N., Shibusawa, S., Kamada, M., and Yonekura, T. (2014). Motion detection and evaluation of chair exercise support system with depth image sensor. In Ubiquitous Intelligence and Computing, 2014 IEEE 11th Intl Conf, pages 800-807.
  22. Yamaguchi, O., Fukui, K., and Maeda, K. (1998). Face recognition using temporal image sequence. In Proceedings of the 3rd. International Conference on Face and Gesture Recognition, pages 318-323.
  23. Yoshinuma, T., Hino, H., and Fukui, K. (2015). Personal Authentication Based on 3D Configuration of Micro-feature Points on Facial Surface, pages 433- 446. Springer International Publishing.
  24. Yosuke, I. and Kazuhiro, F. (2011). 3d object recognition based on canonical angles between shape subspaces. In Computer Vision - ACCV 2010 - 10th Asian Conference on Computer Vision, pages 580-591.
  25. Yu, Y., Song, Y., and Zhang, Y. (2014). Real time fingertip detection with kinect depth image sequences. In 2014 22nd International Conference on Pattern Recognition, pages 550-555.
Download


Paper Citation


in Harvard Style

Yataka R. and Fukui K. (2017). Three-dimensional Object Recognition via Subspace Representation on a Grassmann Manifold . In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-222-6, pages 208-216. DOI: 10.5220/0006204702080216


in Bibtex Style

@conference{icpram17,
author={Ryoma Yataka and Kazuhiro Fukui},
title={Three-dimensional Object Recognition via Subspace Representation on a Grassmann Manifold},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2017},
pages={208-216},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006204702080216},
isbn={978-989-758-222-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Three-dimensional Object Recognition via Subspace Representation on a Grassmann Manifold
SN - 978-989-758-222-6
AU - Yataka R.
AU - Fukui K.
PY - 2017
SP - 208
EP - 216
DO - 10.5220/0006204702080216