Exploiting ramp structures for improving optical flow estimation

Abhishek Singh, Narendra Ahuja

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

Abstract

The underlying principle behind most optical flow algorithms is that the brightness of a pixel remains the same as it flows from one frame to the next. The first order Taylor approximation used in formulating this brightness constancy principle may not be accurate when intensity profiles change non-linearly. In this paper, we propose a method of alleviating the effect of this approximation. Instead of computing image gradients using conventional horizontal and vertical filters of fixed coefficients and sizes, we propose to obtain the gradient information by an explicit examination of ramp profiles at a given location, in all directions. The gradient information obtained using the proposed analysis is more robust under non-linear changes in intensity profiles. Our results demonstrate that by incorporating the ramp structure information as proposed, we are able to improve existing optical flow algorithms.

Original languageEnglish (US)
Title of host publicationICPR 2012 - 21st International Conference on Pattern Recognition
Pages2504-2507
Number of pages4
StatePublished - Dec 1 2012
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: Nov 11 2012Nov 15 2012

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Other

Other21st International Conference on Pattern Recognition, ICPR 2012
CountryJapan
CityTsukuba
Period11/11/1211/15/12

Fingerprint

Optical flows
Luminance
Pixels

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Singh, A., & Ahuja, N. (2012). Exploiting ramp structures for improving optical flow estimation. In ICPR 2012 - 21st International Conference on Pattern Recognition (pp. 2504-2507). [6460676] (Proceedings - International Conference on Pattern Recognition).

Exploiting ramp structures for improving optical flow estimation. / Singh, Abhishek; Ahuja, Narendra.

ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. p. 2504-2507 6460676 (Proceedings - International Conference on Pattern Recognition).

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

Singh, A & Ahuja, N 2012, Exploiting ramp structures for improving optical flow estimation. in ICPR 2012 - 21st International Conference on Pattern Recognition., 6460676, Proceedings - International Conference on Pattern Recognition, pp. 2504-2507, 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, 11/11/12.
Singh A, Ahuja N. Exploiting ramp structures for improving optical flow estimation. In ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. p. 2504-2507. 6460676. (Proceedings - International Conference on Pattern Recognition).
Singh, Abhishek ; Ahuja, Narendra. / Exploiting ramp structures for improving optical flow estimation. ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. pp. 2504-2507 (Proceedings - International Conference on Pattern Recognition).
@inproceedings{1292abecce0d4456913257886e57ae9a,
title = "Exploiting ramp structures for improving optical flow estimation",
abstract = "The underlying principle behind most optical flow algorithms is that the brightness of a pixel remains the same as it flows from one frame to the next. The first order Taylor approximation used in formulating this brightness constancy principle may not be accurate when intensity profiles change non-linearly. In this paper, we propose a method of alleviating the effect of this approximation. Instead of computing image gradients using conventional horizontal and vertical filters of fixed coefficients and sizes, we propose to obtain the gradient information by an explicit examination of ramp profiles at a given location, in all directions. The gradient information obtained using the proposed analysis is more robust under non-linear changes in intensity profiles. Our results demonstrate that by incorporating the ramp structure information as proposed, we are able to improve existing optical flow algorithms.",
author = "Abhishek Singh and Narendra Ahuja",
year = "2012",
month = "12",
day = "1",
language = "English (US)",
isbn = "9784990644109",
series = "Proceedings - International Conference on Pattern Recognition",
pages = "2504--2507",
booktitle = "ICPR 2012 - 21st International Conference on Pattern Recognition",

}

TY - GEN

T1 - Exploiting ramp structures for improving optical flow estimation

AU - Singh, Abhishek

AU - Ahuja, Narendra

PY - 2012/12/1

Y1 - 2012/12/1

N2 - The underlying principle behind most optical flow algorithms is that the brightness of a pixel remains the same as it flows from one frame to the next. The first order Taylor approximation used in formulating this brightness constancy principle may not be accurate when intensity profiles change non-linearly. In this paper, we propose a method of alleviating the effect of this approximation. Instead of computing image gradients using conventional horizontal and vertical filters of fixed coefficients and sizes, we propose to obtain the gradient information by an explicit examination of ramp profiles at a given location, in all directions. The gradient information obtained using the proposed analysis is more robust under non-linear changes in intensity profiles. Our results demonstrate that by incorporating the ramp structure information as proposed, we are able to improve existing optical flow algorithms.

AB - The underlying principle behind most optical flow algorithms is that the brightness of a pixel remains the same as it flows from one frame to the next. The first order Taylor approximation used in formulating this brightness constancy principle may not be accurate when intensity profiles change non-linearly. In this paper, we propose a method of alleviating the effect of this approximation. Instead of computing image gradients using conventional horizontal and vertical filters of fixed coefficients and sizes, we propose to obtain the gradient information by an explicit examination of ramp profiles at a given location, in all directions. The gradient information obtained using the proposed analysis is more robust under non-linear changes in intensity profiles. Our results demonstrate that by incorporating the ramp structure information as proposed, we are able to improve existing optical flow algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84874568773&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874568773&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84874568773

SN - 9784990644109

T3 - Proceedings - International Conference on Pattern Recognition

SP - 2504

EP - 2507

BT - ICPR 2012 - 21st International Conference on Pattern Recognition

ER -