Advanced search
1 file | 1.33 MB

A full reference video quality measure based on motion differences and saliency maps evaluation

Benhur Ortiz Jaramillo (UGent) , Asli Kumcu (UGent) , Ljiljana Platisa (UGent) and Wilfried Philips (UGent)
Author
Organization
Project
PANORAMA project
Project
iMinds ICON Telesurgery project
Abstract
While subjective assessment is recognized as the most reliable means of quantifying video quality, objective assessment has proven to be a desirable alternative. Existing video quality indices achieve reasonable prediction of human quality scores, and are able to well predict quality degradation due to spatial distortions but not so well those due to temporal distortions. In this paper, we propose a perception-based quality index in which the novelty is the direct use of motion information to extract temporal distortions and to model the human visual attention. Temporal distortions are computed from optical flow and common vector metrics. Results of psychovisual experiments are used for modeling the human visual attention. Results show that the proposed index is competitive with current quality indices presented in the state of art. Additionally, the proposed index is much faster than other indices also including a temporal distortion measure.
Keywords
saliency maps, temporal distortions, video quality assessment., Dense optical flow, psychophysics

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.33 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Ortiz Jaramillo, Benhur, Asli Kumcu, Ljiljana Platisa, and Wilfried Philips. 2014. “A Full Reference Video Quality Measure Based on Motion Differences and Saliency Maps Evaluation.” In Proceedings of the 9th International Conference on Computer Vision Theory and Applications, ed. Sebastiano Battiato and José Braz, 2:714–722. SCITEPRESS Digital Library.
APA
Ortiz Jaramillo, B., Kumcu, A., Platisa, L., & Philips, W. (2014). A full reference video quality measure based on motion differences and saliency maps evaluation. In S. Battiato & J. Braz (Eds.), Proceedings of the 9th International Conference on Computer Vision Theory and Applications (Vol. 2, pp. 714–722). Presented at the International Conference on Computer Vision Theory and Applications, SCITEPRESS Digital Library.
Vancouver
1.
Ortiz Jaramillo B, Kumcu A, Platisa L, Philips W. A full reference video quality measure based on motion differences and saliency maps evaluation. In: Battiato S, Braz J, editors. Proceedings of the 9th International Conference on Computer Vision Theory and Applications. SCITEPRESS Digital Library; 2014. p. 714–22.
MLA
Ortiz Jaramillo, Benhur, Asli Kumcu, Ljiljana Platisa, et al. “A Full Reference Video Quality Measure Based on Motion Differences and Saliency Maps Evaluation.” Proceedings of the 9th International Conference on Computer Vision Theory and Applications. Ed. Sebastiano Battiato & José Braz. Vol. 2. SCITEPRESS Digital Library, 2014. 714–722. Print.
@inproceedings{4233401,
  abstract     = {While subjective assessment is recognized as the most reliable means of quantifying video quality, objective assessment has proven to be a desirable alternative. Existing video quality indices achieve reasonable prediction of human quality scores, and are able to well predict quality degradation due to spatial distortions but not so well those due to temporal distortions. In this paper, we propose a perception-based quality index in which the novelty is the direct use of motion information to extract temporal distortions and to model the human visual attention. Temporal distortions are computed from optical flow and common vector metrics. Results of psychovisual experiments are used for modeling the human visual attention. Results show that the proposed index is competitive with current quality indices presented in the state of art. Additionally, the proposed index is much faster than other indices also
including a temporal distortion measure.},
  author       = {Ortiz Jaramillo, Benhur and Kumcu, Asli and Platisa, Ljiljana and Philips, Wilfried},
  booktitle    = {Proceedings of the 9th International Conference on Computer Vision Theory and Applications},
  editor       = {Battiato, Sebastiano and Braz, Jos{\'e}},
  isbn         = {9789897580048},
  keyword      = {saliency maps,temporal distortions,video quality assessment.,Dense optical flow,psychophysics},
  language     = {eng},
  location     = {Lisbon, Portugal},
  pages        = {714--722},
  publisher    = {SCITEPRESS Digital Library},
  title        = {A full reference video quality measure based on motion differences and saliency maps evaluation},
  url          = {http://dx.doi.org/10.5220/0004870607140722},
  volume       = {2},
  year         = {2014},
}

Altmetric
View in Altmetric