Video sharpness prediction based on motion blur analysis

Jongyoo Kim, Junghwan Kim, Woojae Kim, Jisoo Lee, Sanghoon Lee

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

1 Citation (Scopus)

Abstract

For high bit rate video, it is important to acquire the video contents with high resolution, the quality of which may be degraded due to the motion blur from the movement of an object(s) or the camera. However, conventional sharpness assessments are designed to find focal blur caused either by defocusing or by compression distortion targeted for low bit rates. To overcome this limitation, we present a no-reference framework of a visual sharpness assessment (VSA) for high-resolution video based on the motion and scene classification. In the proposed framework, the accuracy of the sharpness estimation can be improved via pooling weighted by the visual perception from the object and camera movements and by the strong influence from the region with the highest sharpness. Based on the motion blur characteristics, the variance and the contrast over the spectral domain are used to quantify the perceived sharpness. Moreover, for the VSA, we extract the highly influential sharper regions and emphasize them by utilizing the scene adaptive pooling.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Multimedia and Expo, ICME 2015
PublisherIEEE Computer Society
ISBN (Electronic)9781479970827
DOIs
Publication statusPublished - 2015 Aug 4
EventIEEE International Conference on Multimedia and Expo, ICME 2015 - Turin, Italy
Duration: 2015 Jun 292015 Jul 3

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2015-August
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Other

OtherIEEE International Conference on Multimedia and Expo, ICME 2015
CountryItaly
CityTurin
Period15/6/2915/7/3

Fingerprint

Cameras
Motion analysis

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Kim, J., Kim, J., Kim, W., Lee, J., & Lee, S. (2015). Video sharpness prediction based on motion blur analysis. In 2015 IEEE International Conference on Multimedia and Expo, ICME 2015 [7177424] (Proceedings - IEEE International Conference on Multimedia and Expo; Vol. 2015-August). IEEE Computer Society. https://doi.org/10.1109/ICME.2015.7177424
Kim, Jongyoo ; Kim, Junghwan ; Kim, Woojae ; Lee, Jisoo ; Lee, Sanghoon. / Video sharpness prediction based on motion blur analysis. 2015 IEEE International Conference on Multimedia and Expo, ICME 2015. IEEE Computer Society, 2015. (Proceedings - IEEE International Conference on Multimedia and Expo).
@inproceedings{7e0b99534a9942e09f3eea620b13b346,
title = "Video sharpness prediction based on motion blur analysis",
abstract = "For high bit rate video, it is important to acquire the video contents with high resolution, the quality of which may be degraded due to the motion blur from the movement of an object(s) or the camera. However, conventional sharpness assessments are designed to find focal blur caused either by defocusing or by compression distortion targeted for low bit rates. To overcome this limitation, we present a no-reference framework of a visual sharpness assessment (VSA) for high-resolution video based on the motion and scene classification. In the proposed framework, the accuracy of the sharpness estimation can be improved via pooling weighted by the visual perception from the object and camera movements and by the strong influence from the region with the highest sharpness. Based on the motion blur characteristics, the variance and the contrast over the spectral domain are used to quantify the perceived sharpness. Moreover, for the VSA, we extract the highly influential sharper regions and emphasize them by utilizing the scene adaptive pooling.",
author = "Jongyoo Kim and Junghwan Kim and Woojae Kim and Jisoo Lee and Sanghoon Lee",
year = "2015",
month = "8",
day = "4",
doi = "10.1109/ICME.2015.7177424",
language = "English",
series = "Proceedings - IEEE International Conference on Multimedia and Expo",
publisher = "IEEE Computer Society",
booktitle = "2015 IEEE International Conference on Multimedia and Expo, ICME 2015",
address = "United States",

}

Kim, J, Kim, J, Kim, W, Lee, J & Lee, S 2015, Video sharpness prediction based on motion blur analysis. in 2015 IEEE International Conference on Multimedia and Expo, ICME 2015., 7177424, Proceedings - IEEE International Conference on Multimedia and Expo, vol. 2015-August, IEEE Computer Society, IEEE International Conference on Multimedia and Expo, ICME 2015, Turin, Italy, 15/6/29. https://doi.org/10.1109/ICME.2015.7177424

Video sharpness prediction based on motion blur analysis. / Kim, Jongyoo; Kim, Junghwan; Kim, Woojae; Lee, Jisoo; Lee, Sanghoon.

2015 IEEE International Conference on Multimedia and Expo, ICME 2015. IEEE Computer Society, 2015. 7177424 (Proceedings - IEEE International Conference on Multimedia and Expo; Vol. 2015-August).

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

TY - GEN

T1 - Video sharpness prediction based on motion blur analysis

AU - Kim, Jongyoo

AU - Kim, Junghwan

AU - Kim, Woojae

AU - Lee, Jisoo

AU - Lee, Sanghoon

PY - 2015/8/4

Y1 - 2015/8/4

N2 - For high bit rate video, it is important to acquire the video contents with high resolution, the quality of which may be degraded due to the motion blur from the movement of an object(s) or the camera. However, conventional sharpness assessments are designed to find focal blur caused either by defocusing or by compression distortion targeted for low bit rates. To overcome this limitation, we present a no-reference framework of a visual sharpness assessment (VSA) for high-resolution video based on the motion and scene classification. In the proposed framework, the accuracy of the sharpness estimation can be improved via pooling weighted by the visual perception from the object and camera movements and by the strong influence from the region with the highest sharpness. Based on the motion blur characteristics, the variance and the contrast over the spectral domain are used to quantify the perceived sharpness. Moreover, for the VSA, we extract the highly influential sharper regions and emphasize them by utilizing the scene adaptive pooling.

AB - For high bit rate video, it is important to acquire the video contents with high resolution, the quality of which may be degraded due to the motion blur from the movement of an object(s) or the camera. However, conventional sharpness assessments are designed to find focal blur caused either by defocusing or by compression distortion targeted for low bit rates. To overcome this limitation, we present a no-reference framework of a visual sharpness assessment (VSA) for high-resolution video based on the motion and scene classification. In the proposed framework, the accuracy of the sharpness estimation can be improved via pooling weighted by the visual perception from the object and camera movements and by the strong influence from the region with the highest sharpness. Based on the motion blur characteristics, the variance and the contrast over the spectral domain are used to quantify the perceived sharpness. Moreover, for the VSA, we extract the highly influential sharper regions and emphasize them by utilizing the scene adaptive pooling.

UR - http://www.scopus.com/inward/record.url?scp=84946085688&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946085688&partnerID=8YFLogxK

U2 - 10.1109/ICME.2015.7177424

DO - 10.1109/ICME.2015.7177424

M3 - Conference contribution

AN - SCOPUS:84946085688

T3 - Proceedings - IEEE International Conference on Multimedia and Expo

BT - 2015 IEEE International Conference on Multimedia and Expo, ICME 2015

PB - IEEE Computer Society

ER -

Kim J, Kim J, Kim W, Lee J, Lee S. Video sharpness prediction based on motion blur analysis. In 2015 IEEE International Conference on Multimedia and Expo, ICME 2015. IEEE Computer Society. 2015. 7177424. (Proceedings - IEEE International Conference on Multimedia and Expo). https://doi.org/10.1109/ICME.2015.7177424