ON GENERATING GROUND-TRUTH TIME-LAPSE IMAGE SEQUENCES AND FLOW FIELDS

Vladimír Ulman, Jan Hubený

2007

Abstract

The availability of time-lapse image sequencies accompanied with appropriate ground-truth flow fields is crucial for quantitative evaluation of any optical flow computation method. Moreover, since these methods are often part of automatic object-tracking or motion-detection solutions used mainly in robotics and computer vision, an artificially generated high-fidelity test data is obviously needed. In this paper, we present a framework that allows for automatic generation of such image sequences based on real-world model image together with an artificial flow field. The framework benefits of a two-layered approach in which user-selected foreground is locally moved and inserted into an artificially generated background. The background is visually similar to the input real image while the foreground is extracted from it and so its fidelity is guaranteed. The framework is capable of generating 2D and 3D image sequences of arbitrary length. A brief discussion as well as an example of application in optical microscopy imaging is presented.

References

  1. Barron, J. L., Fleet, D. J., and Beauchemin, S. S. (1994). Performance of optical flow techniques. Int. J. Comput. Vision, 12(1):43-77.
  2. Beauchemin, S. S. and Barron, J. L. (1995). The computation of optical flow. ACM Comput. Surv., 27(3):433- 466.
  3. Cédras, C. and Shah, M. A. (1995). Motion based recognition: A survey. Image and Vision Computing, 13(2):129-155.
  4. Eils, R. and Athale, C. (2003). Computational imaging in cell biology. The Journal of Cell Biology, 161:447- 481.
  5. Galvin, B., McCane, B., Novins, K., Mason, D., and Mills, S. (1998). Recovering motion fields: An evaluation of eight optical flow algorithms. In In Proc. of the 9th British Mach. Vis. Conf. (BMVC 7898), volume 1, pages 195-204.
  6. Gerlich, D., Mattes, J., and Eils, R. (2003). Quantitative motion analysis and visualization of cellular structures. Methods, 29(1):3-13.
  7. Horn, B. K. P. and Schunck, B. G. (1981). Determining optical flow. Artificial Intelligence, 17:185-203.
  8. HubenÉ, J. and Matula, P. (2006). Fast and robust segmentation of low contrast biomedical images. In In Proceedings of the Sixth IASTED International Conference VIIP, page 8.
  9. Lehmussola, A., Selinummi, J., Ruusuvuori, P., Niemisto, A., and Yli-Harja, O. (2005). Simulating fluorescent microscope images of cell populations. In IEEE Engineering in Medicine and Biology 27th Annual Conference, pages 3153-3156.
  10. Lin, T. and Barron, J. (1994). Image reconstruction error for optical flow. In Vision Interface, pages 73-80.
  11. Saito, T. and Toriwaki, J. I. (1994). New algorithms for Euclidean distance transformations of an n-dimensional digitized picture with applications. Pattern Recognition, 27:1551-1565.
  12. Ulman, V. (2005). Mosaicking of high-resolution biomedical images acquired from wide-field optical microscope. In EMBEC'05: Proceedings of the 3rd European Medical & Biological Engineering Conference, volume 11.
  13. Webb, D., Hamilton, M. A., Harkin, G. J., Lawrence, S., Camper, A. K., and Lewandowski, Z. (2003). Assessing technician effects when extracting quantities from microscope images. Journal of Microbiological Methods, 53(1):97-106.
  14. Young, I. (1996). Quantitative microscopy. IEEE Engineering in Medicine and Biology Magazine, 15(1):59-66.
  15. Zitová, B. and Flusser, J. (2003). Image registration methods: a survey. IVC, 21(11):977-1000.
Download


Paper Citation


in Harvard Style

Ulman V. and Hubený J. (2007). ON GENERATING GROUND-TRUTH TIME-LAPSE IMAGE SEQUENCES AND FLOW FIELDS . In Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-972-8865-83-2, pages 234-239. DOI: 10.5220/0001630202340239


in Bibtex Style

@conference{icinco07,
author={Vladimír Ulman and Jan Hubený},
title={ON GENERATING GROUND-TRUTH TIME-LAPSE IMAGE SEQUENCES AND FLOW FIELDS},
booktitle={Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2007},
pages={234-239},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001630202340239},
isbn={978-972-8865-83-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - ON GENERATING GROUND-TRUTH TIME-LAPSE IMAGE SEQUENCES AND FLOW FIELDS
SN - 978-972-8865-83-2
AU - Ulman V.
AU - Hubený J.
PY - 2007
SP - 234
EP - 239
DO - 10.5220/0001630202340239