University of Wollongong
Browse

Fast digital optical flow estimation based on EMD

Download (843.02 kB)
conference contribution
posted on 2024-11-13, 20:15 authored by Mickael Quelin, Abdesselam BouzerdoumAbdesselam Bouzerdoum, Son Lam PhungSon Lam Phung
This paper presents an optical flow estimation technique based on the so called Elementary Motion Detector (EMD). The aim is to provide a fast but not necessarily very accurate system to be used for specific post processing purposes. This model uses a low complexity algorithm for detecting motion in four directions by identifying specific motion templates. By extending the motion templates to different scales of the input video, an Elementary Velocity Detector (EVD) is created. This one can save computation time by estimating different speeds in parallel. Information from the EVD outputs is then used to generate an estimate of the optical flow along edges and other intensity transitions. Experimen- tal results are presented, which show the effectiveness of the proposed model. Furthermore, the robustness of the model can be enhanced by using pre-filtering.

History

Citation

Quelin, M., Bouzerdoum, A. & Phung, S. (2010). Fast digital optical flow estimation based on EMD. 2nd European Workshop on Visual Information Processing (pp. 155-158). USA: IEEE.

Parent title

2010 2nd European Workshop on Visual Information Processing, EUVIP2010

Pagination

155-158

Language

English

RIS ID

33613

Usage metrics

    Categories

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC