OSA's Digital Library

Journal of the Optical Society of America A

Journal of the Optical Society of America A

| OPTICS, IMAGE SCIENCE, AND VISION

  • Vol. 20, Iss. 8 — Aug. 1, 2003
  • pp: 1505–1515

Fast two-frame multiscale dense optical flow estimation using discrete wavelet filters

Haiying Liu, Rama Chellappa, and Azriel Rosenfeld  »View Author Affiliations


JOSA A, Vol. 20, Issue 8, pp. 1505-1515 (2003)
http://dx.doi.org/10.1364/JOSAA.20.001505


View Full Text Article

Enhanced HTML    Acrobat PDF (1167 KB)





Browse Journals / Lookup Meetings

Browse by Journal and Year


   


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools

Share
Citations

Abstract

A multiscale algorithm with complexity O(N) (where N is the number of pixels in one image) using wavelet filters is proposed to estimate dense optical flow from two frames. Hierarchical image representation by wavelet decomposition is integrated with differential techniques in a new multiscale framework. It is shown that if a compactly supported wavelet basis with one vanishing moment is carefully selected, hierarchical image, first-order derivative, and corner representations can be obtained from the wavelet decomposition. On the basis of this result, three of the four components of the wavelet decomposition are employed to estimate dense optical flow with use of only two frames. This overcomes the “flattening-out” problem in traditional pyramid methods, which produce large errors when low-texture regions become flat at coarse levels as a result of blurring. A two-dimensional affine motion model is used to formulate the optical flow problem as a linear system, with all resolutions simultaneously (i.e., coarse-and-fine) rather than the traditional coarse-to-fine approach, which unavoidably propagates errors from the coarse level. This not only helps to improve the accuracy but also makes the hardware implementation of our algorithm simple. Experiments on different types of image sequences, together with quantitative and qualitative comparisons with several other optical flow methods, are given to demonstrate the effectiveness and the robustness of our algorithm.

© 2003 Optical Society of America

OCIS Codes
(100.2000) Image processing : Digital image processing
(100.2960) Image processing : Image analysis
(150.4620) Machine vision : Optical flow

History
Original Manuscript: October 10, 2002
Revised Manuscript: April 1, 2003
Manuscript Accepted: April 1, 2003
Published: August 1, 2003

Citation
Haiying Liu, Rama Chellappa, and Azriel Rosenfeld, "Fast two-frame multiscale dense optical flow estimation using discrete wavelet filters," J. Opt. Soc. Am. A 20, 1505-1515 (2003)
http://www.opticsinfobase.org/josaa/abstract.cfm?URI=josaa-20-8-1505

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Article level metrics are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

« Previous Article  |  Next Article »

OSA is a member of CrossRef.

CrossCheck Deposited