Velocity tuned generalized Sobel operators for multiresolution computation of optical flow

Optical flow computation may be divided into four processing steps where the first is extraction of image features suitable for flow estimation. Using a generalization of the basic flow constraint it is possible to estimate flow vectors from a set of feature images obtained from the input image sequ...

Full description

Saved in:
Bibliographic Details
Published inProceedings of 1st International Conference on Image Processing Vol. 2; pp. 765 - 769 vol.2
Main Authors Gokstorp, M., Danielsson, P.-E.
Format Conference Proceeding
LanguageEnglish
Published IEEE Comput. Soc. Press 1994
Subjects
Band pass filters
Equations
Feature extraction
Frequency
Gabor filters
Image edge detection
Image motion analysis
Optical computing
Optical filters
Spatial resolution
Online AccessGet full text

Cover

More Information
Summary:Optical flow computation may be divided into four processing steps where the first is extraction of image features suitable for flow estimation. Using a generalization of the basic flow constraint it is possible to estimate flow vectors from a set of feature images obtained from the input image sequence. Generalized Sobel operators provide a suitable set of feature extraction operators. The set of five filters up to second order provides good approximations of ideal edge and line detectors. A review of spatial and frequency constraints on optical flow suggests a multiresolution approach to optical flow where the initial feature extractors consists of velocity tuned operators. We show that two-dimensional generalized Sobel operators may be extended to spatio-temporal velocity tuned filters for optical flow estimation. Experimental results compare well to existing methods.< >
ISBN:0818669527
9780818669521
DOI:10.1109/ICIP.1994.413674