Video magnification in presence of large motions

Mohamed Elgharib, Mohamed Hefeeda, Frédo Durand, William T. Freeman

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

37 Citations (Scopus)

Abstract

Video magnification reveals subtle variations that would be otherwise invisible to the naked eye. Current techniques require all motion in the video to be very small, which is unfortunately not always the case. Tiny yet meaningful motions are often combined with larger motions, such as the small vibrations of a gate as it rotates, or the microsaccades in a moving eye. We present a layer-based video magnification approach that can amplify small motions within large ones. An examined region/layer is temporally aligned and subtle variations are magnified. Matting is used to magnify only region of interest while maintaining integrity of nearby sites. Results show handling larger motions, larger amplification factors and significant reduction in artifacts over state of the art.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
Pages4119-4127
Number of pages9
Volume07-12-June-2015
ISBN (Print)9781467369640
DOIs
Publication statusPublished - 14 Oct 2015
EventIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States
Duration: 7 Jun 201512 Jun 2015

Other

OtherIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
CountryUnited States
CityBoston
Period7/6/1512/6/15

Fingerprint

Amplification

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Elgharib, M., Hefeeda, M., Durand, F., & Freeman, W. T. (2015). Video magnification in presence of large motions. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 07-12-June-2015, pp. 4119-4127). [7299039] IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7299039

Video magnification in presence of large motions. / Elgharib, Mohamed; Hefeeda, Mohamed; Durand, Frédo; Freeman, William T.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 07-12-June-2015 IEEE Computer Society, 2015. p. 4119-4127 7299039.

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

Elgharib, M, Hefeeda, M, Durand, F & Freeman, WT 2015, Video magnification in presence of large motions. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. vol. 07-12-June-2015, 7299039, IEEE Computer Society, pp. 4119-4127, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 7/6/15. https://doi.org/10.1109/CVPR.2015.7299039
Elgharib M, Hefeeda M, Durand F, Freeman WT. Video magnification in presence of large motions. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 07-12-June-2015. IEEE Computer Society. 2015. p. 4119-4127. 7299039 https://doi.org/10.1109/CVPR.2015.7299039
Elgharib, Mohamed ; Hefeeda, Mohamed ; Durand, Frédo ; Freeman, William T. / Video magnification in presence of large motions. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 07-12-June-2015 IEEE Computer Society, 2015. pp. 4119-4127
@inproceedings{702541b892bd48c1b651519b3356fb48,
title = "Video magnification in presence of large motions",
abstract = "Video magnification reveals subtle variations that would be otherwise invisible to the naked eye. Current techniques require all motion in the video to be very small, which is unfortunately not always the case. Tiny yet meaningful motions are often combined with larger motions, such as the small vibrations of a gate as it rotates, or the microsaccades in a moving eye. We present a layer-based video magnification approach that can amplify small motions within large ones. An examined region/layer is temporally aligned and subtle variations are magnified. Matting is used to magnify only region of interest while maintaining integrity of nearby sites. Results show handling larger motions, larger amplification factors and significant reduction in artifacts over state of the art.",
author = "Mohamed Elgharib and Mohamed Hefeeda and Fr{\'e}do Durand and Freeman, {William T.}",
year = "2015",
month = "10",
day = "14",
doi = "10.1109/CVPR.2015.7299039",
language = "English",
isbn = "9781467369640",
volume = "07-12-June-2015",
pages = "4119--4127",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Video magnification in presence of large motions

AU - Elgharib, Mohamed

AU - Hefeeda, Mohamed

AU - Durand, Frédo

AU - Freeman, William T.

PY - 2015/10/14

Y1 - 2015/10/14

N2 - Video magnification reveals subtle variations that would be otherwise invisible to the naked eye. Current techniques require all motion in the video to be very small, which is unfortunately not always the case. Tiny yet meaningful motions are often combined with larger motions, such as the small vibrations of a gate as it rotates, or the microsaccades in a moving eye. We present a layer-based video magnification approach that can amplify small motions within large ones. An examined region/layer is temporally aligned and subtle variations are magnified. Matting is used to magnify only region of interest while maintaining integrity of nearby sites. Results show handling larger motions, larger amplification factors and significant reduction in artifacts over state of the art.

AB - Video magnification reveals subtle variations that would be otherwise invisible to the naked eye. Current techniques require all motion in the video to be very small, which is unfortunately not always the case. Tiny yet meaningful motions are often combined with larger motions, such as the small vibrations of a gate as it rotates, or the microsaccades in a moving eye. We present a layer-based video magnification approach that can amplify small motions within large ones. An examined region/layer is temporally aligned and subtle variations are magnified. Matting is used to magnify only region of interest while maintaining integrity of nearby sites. Results show handling larger motions, larger amplification factors and significant reduction in artifacts over state of the art.

UR - http://www.scopus.com/inward/record.url?scp=84959214453&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959214453&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7299039

DO - 10.1109/CVPR.2015.7299039

M3 - Conference contribution

SN - 9781467369640

VL - 07-12-June-2015

SP - 4119

EP - 4127

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

PB - IEEE Computer Society

ER -