Skip to main content
SpringerLink
Log in

Optical Flow

  • Reference work entry
  • First Online:
Computer Vision

Synonyms

Optic flow

Related Concepts

Rigid Registration

Definition

Optical flow is the vector field that describes the perceived motion of points in the image plane.

Background

When working with image sequences, analyzing the change of the image over time provides valuable information about the scene. The motion of points in the image, as described by the optical flow field, is an important cue in many computer vision tasks, such as tracking, motion segmentation, and structure-from-motion.

Estimating the optical flow from pairs of images is a classical computer vision task. The problem is approached by matching certain image structures, which are assumed to be more or less stable over time, between two successive images. While earlier estimation methods could only provide sparse optical flow fields, nowadays it is common to estimate a dense optical flow field that provides a displacement vector for each pixel in the first image, describing where this pixel went in the second image.

Opti...

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 649.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 899.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. . Lucas B, Kanade T (1981) An iterative image registration technique with an application to stereo vision. In: Proceedings of the seventh international joint conference on artificial intelligence, Vancouver, pp 674–679

    Google Scholar 

  2. Horn B, Schunck B (1981) Determining optical flow. Artif Intell 17:185–203

    Article  Google Scholar 

  3. Black MJ, Anandan P (1996) The robust estimation of multiple motions: parametric and piecewise smooth flow fields. Comput Vis Image Underst 63(1):75–104

    Article  Google Scholar 

  4. Mémin E, Pérez P (1998) Dense estimation and object-based segmentation of the optical flow with robust techniques. IEEE Trans Image Process 7(5):703–719

    Article  Google Scholar 

  5. Brox T, Bruhn A, Papenberg N, Weickert J (2004) High accuracy optical flow estimation based on a theory for warping. In: European conference on computer vision (ECCV). Volume 3024 of LNCS. Springer, Berlin/New York, pp 25–36

    Google Scholar 

  6. Alvarez L, Weickert J, Sánchez J (2000) Reliable estimation of dense optical flow fields with large displacements. Int J Comput Vis 39(1):41–56

    Article  MATH  Google Scholar 

  7. Papenberg N, Bruhn A, Brox T, Didas S, Weickert J (2006) Highly accurate optic flow computation with theoretically justified warping. Int J Comput Vis 67:141–158

    Article  Google Scholar 

  8. Zimmer H, Bruhn A, Weickert J, Valgaerts L, Salgado A, Rosenhahn B, Seidel HP (2009) Complementary optic flow. In: Proceedings of the 7th international conference on energy minimization methods in computer vision and pattern recognition. Volume 5681 of LNCS. Springer, Berlin/Heidelberg/New York, pp 207–220

    Google Scholar 

  9. . Werlberger M, Pock T, Bischof H (2010) Motion estimation with non-local total variation regularization. In: International conference on computer vision and pattern recognition, San Francisco

    Book  Google Scholar 

  10. . Bruhn A (2006) Variational optic flow computation: accurate modelling and efficient numerics. PhD thesis, Faculty of Mathematics and Computer Science, Saarland University, Germany

    Google Scholar 

  11. Zach C, Pock T, Bischof H (2007) A duality based approach for realtime TV-L1 optical flow. In: Pattern recognition – proceeding DAGM. Volume 4713 of LNCS. Springer, Heidelberg pp 214–223

    Google Scholar 

  12. . Shekhovtsov A, Kovtun I, Hlaváč VV (2007) Efficient MRF deformation model for non-rigid image matching. In: International conference on computer vision and pattern recognition (CVPR), Minneapolis

    Google Scholar 

  13. . Glocker B, Paragios N, Komodakis N, Tziritas G, Navab N (2008) Optical flow estimation with uncertainties through dynamic MRFs. In: International conference on computer vision and pattern recognition (CVPR), Anchorage

    Google Scholar 

  14. . Brox T, Malik J (2011) Large displacement optical flow: descriptor matching in variational motion estimation. In: IEEE transactions on pattern analysis and machine intelligence 33(3):500–513

    Article  Google Scholar 

  15. . Shi J, Tomasi C (1994) Good features to track. In: International conference on computer vision and pattern recognition (CVPR), Seattle, pp 593–600

    Google Scholar 

  16. Sand P, Teller S (2008) Particle video: long-range motion estimation using point trajectories. Int J Comput Vis 80(1):72–91

    Article  Google Scholar 

  17. Sundaram N, Brox T, Keutzer K (2010) Dense point trajectories by GPU-accelerated large displacement optical flow. In: European conference on computer vision (ECCV). LNCS. Springer, Berlin/New York

    Google Scholar 

  18. Wang JYA, Adelson EH (1994) Representing moving images with layers. IEEE Trans Image Process 3(5): 625–638

    Article  Google Scholar 

  19. . Weiss Y (1997) Smoothness in layers: motion segmentation using nonparametric mixture estimation. In: International conference on computer vision and pattern recognition (CVPR), San Juan, Puerto Rico, pp 520–527

    Google Scholar 

  20. Cremers D, Soatto S (2005) Motion competition: a variational framework for piecewise parametric motion segmentation. Int J Comput Vis 62(3):249–265

    Article  Google Scholar 

  21. . Efros A, Berg A, Mori G, Malik J (2003) Recognizing action at a distance. In: International conference on computer vision, Nice, pp 726–733

    Google Scholar 

  22. . Middlebury optical flow benchmark. vision.middlebury.edu

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Freiburg, Freiburg, Germany

    Thomas Brox

Authors
  1. Thomas Brox
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Institute of Industrial Science, The University of Tokyo, Tokyo, Japan

    Katsushi Ikeuchi

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer Science+Business Media New York

About this entry

Cite this entry

Brox, T. (2014). Optical Flow. In: Ikeuchi, K. (eds) Computer Vision. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-31439-6_600

Download citation

Publish with us

Policies and ethics

Search

Navigation