Skip to main content
SpringerLink
Log in

A robust optical flow computation

  • Published:
Journal of Electronics (China)

Abstract

This paper presents a new method for robust and accurate optical flow estimation. The significance of this work is twofold. Firstly, the idea of bi-directional scheme is adopted to reduce the model error of optical flow equation, which allows the second order Taylor’s expansion of optical flow equation for accurate solution without much extra computational burden; Secondly, this paper establishs a new optical flow equation based on LSCM (Local Structure Constancy Model) instead of BCM (Brightness Constancy Model), namely the optical flow equation does not act on scalar but on tensor-valued (matrix-valued) field, due to the two reason: (1) structure tensor-value contains local spatial structure information, which provides us more useable cues for computation than scalar; (2) local image structure is less sensitive to illumination variation than intensity, which weakens the disturbance of non-uniform illumination in real sequences. Qualitative and quantitative results for synthetic and real-world scenes show that the new method can produce an accurate and robust results.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. B. K. P. Horn. Robot Vision. Cambridge, MIT Press, 1986, ch.3.

    Google Scholar 

  2. B. Horn, B. Schunck. Determining optical flow. Artificial Intelligence, 17(1981), 185–203.

    Article  Google Scholar 

  3. B. Lucas, T. Kanade. An iterative image registration technique with an application to stereo vision. In Proc. Seventh International Joint Conference on Artificial Intelligence, Vancouver, Canada, Aug. 1981, 674–679.

  4. F. Lauze, P. Kornprobst, E. Mémim. A coarse to fine multiscale approach for linear least squares optical flow estimation. Proceedings of the British Machine Vision Conference, Kingston University, London, U.K., Sept. 2004, 767–776.

  5. L. Alvarez, J. Weickert, J. Sánchez. Reliable estimation of dense optical flow fields with large displacements. International Journal of Computer Vision, 39(2000)1, 41–56.

    Article  MATH  Google Scholar 

  6. M. J. Black, D. J. Fleet. Probabilistic detection and tracking of motion boundaries. International Journal of Computer Vision, 38(2000)3, 231–245.

    Article  MATH  Google Scholar 

  7. F. Heitz, W. Enkemmann. Multimodal estimation of discontinuous optical flow using Markov random fields. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(1993) 12, 1217–1232.

    Article  Google Scholar 

  8. A. Bab-Hadiashar, D. Suter. Robust optical flow estimation. International Journal of Computer Vision, 29(1998)1, 59–77.

    Article  Google Scholar 

  9. S. H. Lai. Adaptive motion estimation for image sequences under non-uniform illumination variations. In Proceedings International Computer Symposium: Workshop on Image Processing and Pattern Recognition, Chiayi, Taiwan, 2000, 223–230.

  10. S. Negahdaripour, C. H. Yu. A generalized brightness change model for computing optical flow. In Proceedings International Conference on Computer Vision, Germany, 1993, 2–11.

  11. H. W. Haussecker, D. J. Fleet. Computing optical flow with physical models of brightness variation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 23(2001)6, 661–673.

    Article  Google Scholar 

  12. K. P. Lim, A. Das, M. N. Chong. Estimation of occlusion and dense motion fields in a bidirectional bayesian framework. IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(2002)5, 712–718.

    Article  Google Scholar 

  13. Yosi Keller, Amir Averbuch. Fast motion estimation using bidirectional gradient methods. IEEE Trans. on Image Processing, 13(2004)8, 1042–1053.

    Article  Google Scholar 

  14. D. J. Fleet, A. D. Jepson. Computation of component image velocity from local phase information. International Journal of Computer Vision, 5(1990)1, 77–104.

    Article  Google Scholar 

  15. M. Nicolescu, M. Medioni. Motion segmentation with accurate boundaries-a tensor voting approach. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, USA, 2003, vol.1, 382–389.

    Google Scholar 

  16. H. Liu, R. Chellappa, A. Rosenfeld. Accurate dense optical flow estimation using adaptive structure tensors and a parametric model. IEEE Trans. on Image Processing, 12(2003)10, 1170–1179.

    Article  Google Scholar 

  17. C. Pierpaoli, P. Jezzard, P. J. Basser, A. Barnett, G. Di Chiro. Diffusion tensor MR imaging of the human brain. Radiology, 201(1996)3, 637–648.

    Google Scholar 

  18. D. Gibson, M. Spann. Robust optical flow estimation based on a sparse motion trajectory set. IEEE Trans. on Image Processing, 12(2003)4, 431–445.

    Article  Google Scholar 

  19. G. Farnebäck. Fast and accurate motion estimation using orientation tensors and parametric motion models. In Proc. Int. Conf. Pattern Recognition, Barcelona, Spain, 2000, vol.1, 135–139.

    Google Scholar 

  20. A. Bruhn, J. Weickert, C. Schnörr. Lucas/Kanade meets Horn/Schunck: Combining local and global optical flow methods. International Journal of Computer Vision, 61(2005)3, 211–231.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Electronic Engineering, Xidian University, Xi’an, 710071, China

    Lu Zongqing, Xie Weixin & Pei Jihong

  2. Key Lab for Intelligent Information Processing, Shenzhen University, Shenzhen, 518060, China

    Xie Weixin & Pei Jihong

Authors
  1. Lu Zongqing
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xie Weixin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Pei Jihong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lu Zongqing.

Additional information

Supported by the National Natural Science Foundation of China (No.60672153) and the Shenzhen Science & Technology Project (No.200424).

Communication author: Lu Zongqing, born in 1975, male, Ph.D. candidate. Xidian University. Current address: P.O. Box. 2-603, Shenzhen University, Shenzhen 518060, China.

About this article

Cite this article

Lu, Z., Xie, W. & Pei, J. A robust optical flow computation. J. of Electron.(China) 24, 635–641 (2007). https://doi.org/10.1007/s11767-006-0004-x

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11767-006-0004-x

Key words

CLC index

Search

Navigation