Selective Use of Optimal Image Resolution for Depth from Multiple Motions based on Gradient Scheme

Norio Tagawa, Shoei Koizumi

2015

Abstract

The gradient-based depth from motion method is effective for obtaining a dense depth map. However, the accuracy of the depth map recovered only from two successive images is not so high, and hence, to increase the depth information by tracking corresponding image points through an image sequence is often performed by using, for example, the Kalman filter-like technique. Alternatively, multiple image pairs generated by random small camera rotations around a reference direction can be used for gaining much information of depth without such the tracking procedure. In the framework of this strategy, in this study, to further improve the accuracy, we propose a selective use of the optimal image resolution. The appropriate resolution image is required to have a linear intensity pattern which is the most important supposition for the gradient method often used for dense depth recovery based on the theory of “shape from motion.” The performance of our proposal is examined through numerical evaluations using artificial images.

References

  1. Brox, T. and Malik, J. (2011). Large displacement optical flow: descriptor matching in vartional motion estimation. IEEE Trans. Pattern Anal. Machine Intell., 33(3):500-513.
  2. Bruhn, A. and Weickert, J. (2005). Locas/kanade meets horn/schunk: combining local and global optic flow methods. Int. J. Comput. Vision, 61(3):211-231.
  3. Dempster, A. P., Laird, N. M., and Rubin, D. B. (1977). Maximum likelihood from incomplete data. J. Roy. Statist. Soc. B, 39:1-38.
  4. Green, P. J. (1990). On use of the em algorithm for penalized likelihood estimation. J. Roy. Statist. Soc. B, 52:443-452.
  5. Horn, B. P. and Schunk, B. (1981). Determining optical flow. Artif. Intell., 17:185-203.
  6. Ikeda, M., Okubo, K., and Tagawa, N. (2009). Implicit tracking of multiple objects based on bayesian region label assignment. In proc. VISAPP2009, pages 503- 506.
  7. Martinez-Conde, S., Macknik, S. L., and Hubel, D. (2004). The role of fixational eye movements in visual perception. Nature Reviews, 5:229-240.
  8. Ochs, P. and Brox, T. (2012). Higher order motion models and spectral clustering. In proc. CVPR2012, pages 614-621.
  9. Paramanand, C. and Rajagopalan, A. N. (2012). Depth from motion and optical blur with unscented kalman filter. IEEE Trans. Image Processing, 21(5):2798-2811.
  10. Poggio, T., Torre, V., and Koch, C. (1985). Computational vision and regularization theory. Nature, 317:314- 319.
  11. Simoncelli, E. P. (1999). Bayesian multi-scale differential optical flow. In Handbook of Computer Vision and Applications, pages 397-422. Academic Press.
  12. Tagawa, N. (2010). Depth perception model based on fixational eye movements using byesian statistical inference. In proc. ICPR2010, pages 1662-1665.
  13. Tagawa, N., Iida, Y., and Okubo, K. (2012). Depth perception model exploiting blurring caused by random small camera motions. In proc. Int. Conf. on Computer Vision, Theory and Applications, pages 329- 334.
  14. Tagawa, N., Kawaguchi, J., Naganuma, S., and Okubo, K. (2008). Direct 3-d shape recovery from image sequence based on multi-scale bayesian network. In proc. ICPR08, page CD.
  15. Tagawa, N., Koizumi, S., and Okubo, K. (2013). Direct depth recovery from motion blur caused by random camera rotations imitating fixational eye movements. In proc. Int. Conf. on Computer Vision, Theory and Applications, pages 177-186.
Download


Paper Citation


in Harvard Style

Tagawa N. and Koizumi S. (2015). Selective Use of Optimal Image Resolution for Depth from Multiple Motions based on Gradient Scheme . In Proceedings of the 5th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-5, (VISIGRAPP 2015) ISBN 978-989-758-094-9, pages 92-99. DOI: 10.5220/0005462500920099


in Bibtex Style

@conference{imta-515,
author={Norio Tagawa and Shoei Koizumi},
title={Selective Use of Optimal Image Resolution for Depth from Multiple Motions based on Gradient Scheme},
booktitle={Proceedings of the 5th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-5, (VISIGRAPP 2015)},
year={2015},
pages={92-99},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005462500920099},
isbn={978-989-758-094-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-5, (VISIGRAPP 2015)
TI - Selective Use of Optimal Image Resolution for Depth from Multiple Motions based on Gradient Scheme
SN - 978-989-758-094-9
AU - Tagawa N.
AU - Koizumi S.
PY - 2015
SP - 92
EP - 99
DO - 10.5220/0005462500920099