CONSTRAIN PROPAGATION FOR GHOST REMOVAL IN HIGH DYNAMIC RANGE IMAGES

Matteo Pedone, Janne Heikkilä

Abstract

Creating high dynamic range images of non-static scenes is a challenging task. Carefully preventing strong camera shakes during shooting and performing image-registration before combining the exposures cannot ensure that the resulting HDR image is consistent. This is eventually due to the presence of moving objects in the scene that causes the so called ghosting artifacts. Currently there is no robust solution that produces satisfactory results in any circumstance. Our method consists of two main steps. First, the probability of belonging to the static part of the scene is estimated for each pixel of the N exposures, yielding N weight images. In the second phase, we segment the areas of the weight-images with lower and higher probability values, and smoothly propagate their influence until a significant change in luminosity is detected or a pixel with a corresponding high probability of belonging to the background is approached. This represents an attempt to spread the influence of lower weights to the surrounding pixels of the same object. Results produced with our technique show a significant reduction or total removal of ghosting artifacts.

References

  1. Bogoni, L. (2000). Extending dynamic range of monochrome and color images through fusion. In International Conference on Pattern Recognition, 2000, vol. 3, pp. 7-12.
  2. Debevec, P. and Malik, J. (1997). Recovering high dynamic range radiance maps from photograph. In SIGGRAPH 97, August 1997.
  3. Grosch, T. (2006). Fast and robust high dynamic range image generation with camera and object movement. In Vision, Modeling and Visualization (VMV), RWTH Aachen, 22.11 - 24.11.2006.
  4. Grossberg, M. D. and Nayar, S. K. (2003). Determining the camera response from images: What is knowable? In IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.25, No.11, pp.1455-1467, Nov, 2003.
  5. Jacobs, K., Ward, G., and Loscos, C. (2005). Automatic hdri generation of dynamic environments. In ACM SIGGRAPH 2005 Sketches.
  6. Khan, E. A., Akyuz, A. O., and Reinhard, E. (2006). Ghost removal in high dynamic range images. In IEEE International Conference on Image Processing, Atlanta, USA, August 2006.
  7. Kim, S. J. and Pollefeys, M. (2004). Radiometric alignment of image sequences. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) - Volume 1, pp. 645-651.
  8. Lischinski, D., Farbman, Z., Uyttendaele, M., and Szeliski, R. (2006). Interactive local adjustment of tonal values. In ACM Transactions on Graphics, ACM SIGGRAPH 2006 Papers SIGGRAPH 7806, Volume 25 Issue 3. ACM Press.
  9. Raykar, V. C. and Duraiswami, R. (2006). Very fast optimal bandwidth selection for univariate kernel density estimation. In CS-TR-4774, Department of Computer Science, University of Maryland, Collegepark.
  10. Reinhard, E., Stark, M., Shirley, P., and Ferwerda, J. (2002). Photographic tone reproduction for digital images. In ACM Transactions on Graphics, 21(3), pp 267-276, Proceedings of SIGGRAPH 2002.
  11. Reinhard, E., Ward, G., Pattanaik, S., and Debevec, P. (2005). High Dynamic Range Imaging: Acquisition, Display and Image-Based-Lighting. Morgan Kaufmann.
  12. Scott, D. W. (1992). Multivariate Density Estimation: Theory, Practice, and Visualization. John Wiley.
  13. Silverman, B. W. (1986). Density Estimation for Statistics and Data Analysis. Chapman and Hall.
  14. Zhang, X., King, M. L., and Hyndman, R. J. (2004). Bandwidth selection for multivariate kernel density estimation using mcmc. In Monash Econometrics and Business Statistics Working Papers 9/04.
Download


Paper Citation


in Harvard Style

Pedone M. and Heikkilä J. (2008). CONSTRAIN PROPAGATION FOR GHOST REMOVAL IN HIGH DYNAMIC RANGE IMAGES . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 36-41. DOI: 10.5220/0001076300360041


in Bibtex Style

@conference{visapp08,
author={Matteo Pedone and Janne Heikkilä},
title={CONSTRAIN PROPAGATION FOR GHOST REMOVAL IN HIGH DYNAMIC RANGE IMAGES},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={36-41},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001076300360041},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - CONSTRAIN PROPAGATION FOR GHOST REMOVAL IN HIGH DYNAMIC RANGE IMAGES
SN - 978-989-8111-21-0
AU - Pedone M.
AU - Heikkilä J.
PY - 2008
SP - 36
EP - 41
DO - 10.5220/0001076300360041