Full reference video quality estimation for videos with different spatial resolutions

Author

Demirtas, A.M. ; Reibman, A.R. ; Jafarkhani, H.

Author_Institution

Center for Pervasive Commun. & Comput., Univ. of California, Irvine, Irvine, CA, USA

fYear

2014

fDate

27-30 Oct. 2014

Firstpage

1997

Lastpage

2001

Abstract

Full reference video quality estimators (QEs) either resize the input video or the reference video to compute the quality when these videos have different spatial resolutions. This resizing operation causes several limitations. Multiscale Image Quality Estimator (MIQE) [1] overcomes those limitations for images but it does not consider the temporal characteristics of video. In this work, we develop a video quality estimator that integrates MIQE with the motion information to estimate the quality. We also perform subjective tests to compare the proposed algorithm with the existing QEs. Test results show that the proposed algorithm outperforms other QEs.

Keywords

image motion analysis; image resolution; video signal processing; MIQE; different spatial resolutions; full reference video quality estimation; input video; motion information; multiscale image quality estimator; video temporal characteristics; Bit rate; Correlation; Estimation; Indexes; Quality assessment; Spatial resolution; Video recording; human visual system; motion; spatial resolution; subjective tests; video quality estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2014 IEEE International Conference on

Conference_Location

Paris

Type

conf

DOI

10.1109/ICIP.2014.7025400

Filename

7025400