We present a technique for the computation of 2D component velocity from image sequences. Initially, the image sequence is represented by a family of spatiotemporal velocity-tuned linear filters. Component velocity, computed from spatiotemporal responses of identically tuned filters, is expressed in terms of the local first-order behavior of surfaces of constant phase. Justification for this definition is discussed from the perspectives of both 2D image translation and deviations from translation that are typical in perspective projections of 3D scenes. The resulting technique is predominantly linear, efficient, and suitable for parallel processing. Moreover, it is local in space-time, robust with respect to noise, and permits multiple estimates within a single neighborhood. Promising quantiative results are reported from experiments with realistic image sequences, including cases with sizeable perspective deformation.
Description
Computation of component image velocity from local phase information - Springer
%0 Journal Article
%1 year=1990
%A Fleet, DavidJ.
%A Jepson, AllanD.
%D 1990
%I Kluwer Academic Publishers
%J International Journal of Computer Vision
%K optical_flow
%N 1
%P 77-104
%R 10.1007/BF00056772
%T Computation of component image velocity from local phase information
%U http://dx.doi.org/10.1007/BF00056772
%V 5
%X We present a technique for the computation of 2D component velocity from image sequences. Initially, the image sequence is represented by a family of spatiotemporal velocity-tuned linear filters. Component velocity, computed from spatiotemporal responses of identically tuned filters, is expressed in terms of the local first-order behavior of surfaces of constant phase. Justification for this definition is discussed from the perspectives of both 2D image translation and deviations from translation that are typical in perspective projections of 3D scenes. The resulting technique is predominantly linear, efficient, and suitable for parallel processing. Moreover, it is local in space-time, robust with respect to noise, and permits multiple estimates within a single neighborhood. Promising quantiative results are reported from experiments with realistic image sequences, including cases with sizeable perspective deformation.
@article{year={1990},
abstract = {We present a technique for the computation of 2D component velocity from image sequences. Initially, the image sequence is represented by a family of spatiotemporal velocity-tuned linear filters. Component velocity, computed from spatiotemporal responses of identically tuned filters, is expressed in terms of the local first-order behavior of surfaces of constant phase. Justification for this definition is discussed from the perspectives of both 2D image translation and deviations from translation that are typical in perspective projections of 3D scenes. The resulting technique is predominantly linear, efficient, and suitable for parallel processing. Moreover, it is local in space-time, robust with respect to noise, and permits multiple estimates within a single neighborhood. Promising quantiative results are reported from experiments with realistic image sequences, including cases with sizeable perspective deformation.},
added-at = {2013-05-20T17:23:27.000+0200},
author = {Fleet, DavidJ. and Jepson, AllanD.},
biburl = {https://www.bibsonomy.org/bibtex/26f04dd86d2effa7750d6ed0848b005b4/alex_ruff},
description = {Computation of component image velocity from local phase information - Springer},
doi = {10.1007/BF00056772},
interhash = {f9ad68adf8222054281b7d491b560782},
intrahash = {6f04dd86d2effa7750d6ed0848b005b4},
issn = {0920-5691},
journal = {International Journal of Computer Vision},
keywords = {optical_flow},
language = {English},
number = 1,
pages = {77-104},
publisher = {Kluwer Academic Publishers},
timestamp = {2013-05-20T17:23:27.000+0200},
title = {Computation of component image velocity from local phase information},
url = {http://dx.doi.org/10.1007/BF00056772},
volume = 5,
year = 1990
}