Omni-directional Reconstruction of Human Figures from Depth Data using Mirrors

Tanwi Mallick, Rishabh Agrawal, Partha Pratim Das, Arun Kumar Majumdar

Abstract

In this paper we present a method for omni-directional 3D reconstruction of a human figure using a single Kinect while two mirrors provide the 360o view. We get three views from a single depth (and its corresponding RGB) frame – one is the real view of the human and other two are the virtual views generated through the mirrors. Using these three views our proposed system reconstruct 360o view of a human. The reconstruction system is robust as it can reconstruct the 360o view of any object (though it is particularly designed for human figures) from single depth and RGB images. These system overcomes the difficulties of synchronization and removes the problem of interference noise of multi-Kinect system. The methodology can be used for a nonKinect RGB-D camera and can be improved in several ways in future.

References

  1. Ahmed, N. (2012). A system for 360 acquisition and 3D animation reconstruction using multiple RGBD cameras. URL: http://www.mpi-inf.mpg.de/˜- nahmed/casa2012.pdf. Unpublished article.
  2. Akay, A. and Akgul, Y. S. (2014). 3D reconstruction with mirrors and RGB-D cameras. In Computer Vision Theory and Applications (VISAPP), 9th International Conference on.
  3. Besl, P. J. and McKay, N. D. (1992). A method for registration of 3-D shapes. In Pattern Analysis and Machine Intelligence, IEEE Transactions on, pages 239-256.
  4. Hu, B., Brown, C., and Nelson, R. (2005). Multiple-view 3-D reconstruction using a mirror. Technical report, University of Rochester.
  5. Khoshelham, K. and Elberink, S. O. (2012). Accuracy and resolution of Kinect depth data for indoor mapping applications. Sensors, 12:1437-1454.
  6. Lanman, D., Crispell, D., and Taubin, G. (2007). Surround structured lighting for full object scanning. In 3-D Digital Imaging and Modeling, 2007. 3DIM 7807. Sixth International Conference on, pages 107-116. IEEE.
  7. Mallick, T., Das, P. P., and Majumdar, A. K. (2013a). Estimation of the orientation and distance of a mirror from Kinect depth data. In Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG 2013). Proc. 4th National Conference on, pages 1-4. IEEE.
  8. Mallick, T., Das, P. P., and Majumdar, A. K. (2013b). Study of interference noise in multi-Kinect set-up. In Computer Vision Theory and Applications (VISAPP 2013). Proc. of the 9th International Conference on, pages 173-178. SciTePress.
  9. Mallick, T., Das, P. P., and Majumdar, A. K. (2014). Characterizations of noise in kinect depth images: A review. IEEE SENSORS JOURNAL, 14:1731-1740.
  10. Mitsumoto, H., Tamura, S., Okazaki, K., Kajimi, N., and Fukui, Y. (1992). 3-D reconstruction using mirror images based on a plane symmetry recovering method. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 14(9):941-946.
  11. Murray, R. M., Li, Z., and Sastry, S. S. (1994). A Mathematical Introduction to Robotic Manipulation.
  12. Rodrigues, R., Barreto, J. P., and Nunes, U. (2010). Camera pose estimation using images of planar mirror reflections. In Computer Vision-ECCV 2010, pages 382- 395. Springer.
  13. Tomasi, C. and Manduchi, R. (1998). Bilateral filtering for gray and color images. In Computer Vision, 1998. Sixth International Conference on, pages 839-846. IEEE.
  14. Tong, J., Zhou, J., Liu, L., Pan, Z., and Yan, H. (2012). Scanning 3D full human bodies using Kinects. Visualization and Computer Graphics, IEEE Transactions on, 18:643-650.
  15. Zhang, Z.-Y. and Tsui, H.-T. (1998). 3D reconstruction from a single view of an object and its image in a plane mirror. In Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on, volume 2, pages 1174-1176. IEEE.
Download


Paper Citation


in Harvard Style

Mallick T., Agrawal R., Das P. and Majumdar A. (2015). Omni-directional Reconstruction of Human Figures from Depth Data using Mirrors . 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 559-566. DOI: 10.5220/0005306905590566


in Bibtex Style

@conference{visapp15,
author={Tanwi Mallick and Rishabh Agrawal and Partha Pratim Das and Arun Kumar Majumdar},
title={Omni-directional Reconstruction of Human Figures from Depth Data using Mirrors},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={559-566},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005306905590566},
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 - Omni-directional Reconstruction of Human Figures from Depth Data using Mirrors
SN - 978-989-758-091-8
AU - Mallick T.
AU - Agrawal R.
AU - Das P.
AU - Majumdar A.
PY - 2015
SP - 559
EP - 566
DO - 10.5220/0005306905590566