The Effect of Presmoothing Image Sequences on the Computation of Optical Flow

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The computation of optical flow has been proposed as a pre-processing step for many high-level vision algorithms. One of the main approaches to the optical flow problem is the gradient-based approach which differentiates the image intensity to compute the optical flow. Often motion vectors computed using various approaches are not reliable. Spatial smoothing of the image sequence is advisable in order to improve velocity estimates in the presence of noise. That is, the application of some kind of linear operation to the images in the sequence before solving for the flow. The pre-processing typically takes the form of some type of spatial Gaussian smoothing or scale specific band-pass filtering of the input images. The main objectives of such filtering have been to lessen the effects of noise, to isolate image structure of interest and to attenuate temporal aliasing and quantization effects in the input images. This paper investigates the effect of presmoothing on this computation of optical flow. The well known method of Horn and Schunck as well as our own finite element method are implemented and tested for improvements due to presmoothing. Discussions are provided on the effects of presmoothing for a variety of image sequences. In our experiments, smoothing is carried out on a selection of well known sequences in both time and space. Improvements are shown using presmoothing.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages780-791
Number of pages12
Volume4141
Publication statusPublished - 18 Sep 2006
EventImage Analysis and Recognition - The Third International Conference on Image Analysis and Recognition (ICIAR 2006) - Portugal
Duration: 18 Sep 2006 → …

Conference

ConferenceImage Analysis and Recognition - The Third International Conference on Image Analysis and Recognition (ICIAR 2006)
Period18/09/06 → …

Fingerprint

Optical flows
Processing
Finite element method
Experiments

Cite this

@inproceedings{dad060cd63244cfeaedb4aa5a29beb2e,
title = "The Effect of Presmoothing Image Sequences on the Computation of Optical Flow",
abstract = "The computation of optical flow has been proposed as a pre-processing step for many high-level vision algorithms. One of the main approaches to the optical flow problem is the gradient-based approach which differentiates the image intensity to compute the optical flow. Often motion vectors computed using various approaches are not reliable. Spatial smoothing of the image sequence is advisable in order to improve velocity estimates in the presence of noise. That is, the application of some kind of linear operation to the images in the sequence before solving for the flow. The pre-processing typically takes the form of some type of spatial Gaussian smoothing or scale specific band-pass filtering of the input images. The main objectives of such filtering have been to lessen the effects of noise, to isolate image structure of interest and to attenuate temporal aliasing and quantization effects in the input images. This paper investigates the effect of presmoothing on this computation of optical flow. The well known method of Horn and Schunck as well as our own finite element method are implemented and tested for improvements due to presmoothing. Discussions are provided on the effects of presmoothing for a variety of image sequences. In our experiments, smoothing is carried out on a selection of well known sequences in both time and space. Improvements are shown using presmoothing.",
author = "Joan Condell and Bryan Scotney and PJ Morrow",
year = "2006",
month = "9",
day = "18",
language = "English",
isbn = "978-3-540-44891-4",
volume = "4141",
pages = "780--791",
booktitle = "Unknown Host Publication",

}

Condell, J, Scotney, B & Morrow, PJ 2006, The Effect of Presmoothing Image Sequences on the Computation of Optical Flow. in Unknown Host Publication. vol. 4141, pp. 780-791, Image Analysis and Recognition - The Third International Conference on Image Analysis and Recognition (ICIAR 2006), 18/09/06.

The Effect of Presmoothing Image Sequences on the Computation of Optical Flow. / Condell, Joan; Scotney, Bryan; Morrow, PJ.

Unknown Host Publication. Vol. 4141 2006. p. 780-791.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - The Effect of Presmoothing Image Sequences on the Computation of Optical Flow

AU - Condell, Joan

AU - Scotney, Bryan

AU - Morrow, PJ

PY - 2006/9/18

Y1 - 2006/9/18

N2 - The computation of optical flow has been proposed as a pre-processing step for many high-level vision algorithms. One of the main approaches to the optical flow problem is the gradient-based approach which differentiates the image intensity to compute the optical flow. Often motion vectors computed using various approaches are not reliable. Spatial smoothing of the image sequence is advisable in order to improve velocity estimates in the presence of noise. That is, the application of some kind of linear operation to the images in the sequence before solving for the flow. The pre-processing typically takes the form of some type of spatial Gaussian smoothing or scale specific band-pass filtering of the input images. The main objectives of such filtering have been to lessen the effects of noise, to isolate image structure of interest and to attenuate temporal aliasing and quantization effects in the input images. This paper investigates the effect of presmoothing on this computation of optical flow. The well known method of Horn and Schunck as well as our own finite element method are implemented and tested for improvements due to presmoothing. Discussions are provided on the effects of presmoothing for a variety of image sequences. In our experiments, smoothing is carried out on a selection of well known sequences in both time and space. Improvements are shown using presmoothing.

AB - The computation of optical flow has been proposed as a pre-processing step for many high-level vision algorithms. One of the main approaches to the optical flow problem is the gradient-based approach which differentiates the image intensity to compute the optical flow. Often motion vectors computed using various approaches are not reliable. Spatial smoothing of the image sequence is advisable in order to improve velocity estimates in the presence of noise. That is, the application of some kind of linear operation to the images in the sequence before solving for the flow. The pre-processing typically takes the form of some type of spatial Gaussian smoothing or scale specific band-pass filtering of the input images. The main objectives of such filtering have been to lessen the effects of noise, to isolate image structure of interest and to attenuate temporal aliasing and quantization effects in the input images. This paper investigates the effect of presmoothing on this computation of optical flow. The well known method of Horn and Schunck as well as our own finite element method are implemented and tested for improvements due to presmoothing. Discussions are provided on the effects of presmoothing for a variety of image sequences. In our experiments, smoothing is carried out on a selection of well known sequences in both time and space. Improvements are shown using presmoothing.

M3 - Conference contribution

SN - 978-3-540-44891-4

VL - 4141

SP - 780

EP - 791

BT - Unknown Host Publication

ER -