Wavelet-based optical flow estimation

Li Fen Chen*, Chih-Ching Lin, Hong Yuan Mark Liao

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations


In this paper, a new algorithm for accurate optical flow estimation using discrete wavelet approximation is proposed. In traditional gradient-based approaches, the computation of optical flow depends on minimizing the image and smoothness constraints. The proposed method takes advantages of the nature of wavelet theory, which can efficiently and accurately represent "things" to model optical flow vectors and image related functions. Each flow vector and image function will be represented by linear combinations of wavelet basis functions. From such wavelet-based approximation, the leading coefficients of these basis functions carry the global information of the approximated "things". The proposed method can successfully convert the problem of minimizing a constraint function into that of solving a linear system of a quadratic and convex function of wavelet coefficients. Once all the corresponding coefficients are decided, the flow vectors can be determined accordingly. Experiments have been conducted on both synthetic and real image sequences and the results have reflected that our approach outperformed the existing methods in terms of accuracy.

Original languageEnglish
Title of host publicationProceedings 15th International Conference on Pattern Recognition. ICPR-2000
Number of pages4
StatePublished - 3 Sep 2000
Event15th International Conference on Pattern Recognition. ICPR-2000 - Barcelona, Spain
Duration: 3 Sep 20007 Sep 2000

Publication series

NameProceedings - International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISSN (Print)1051-4651


Conference15th International Conference on Pattern Recognition. ICPR-2000

Fingerprint Dive into the research topics of 'Wavelet-based optical flow estimation'. Together they form a unique fingerprint.

Cite this