A regression-based framework for estimating the objective quality of HEVC coding units and video frames

A no-reference objective quality estimation framework is proposed. The framework is suitable for any block-based video codec. In the proposed solution, features are extracted from coding units and summarized to form features at frame levels. Stepwise regression is used to select the important featur...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Shanableh, Tamer (author)
التنسيق: article
منشور في: 2015
الموضوعات:
الوصول للمادة أونلاين:http://hdl.handle.net/11073/8819
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513435850506240
author Shanableh, Tamer
author_facet Shanableh, Tamer
author_role author
dc.creator.none.fl_str_mv Shanableh, Tamer
dc.date.none.fl_str_mv 2015-05
2017-05-01T05:56:40Z
2017-05-01T05:56:40Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Shanableh, T. (2015). A regression-based framework for estimating the objective quality of hEVC coding units and video frames. Signal Processing: Image Communication, 34, 22-31. doi:10.1016/j.image.2015.02.008
1879-2677
http://hdl.handle.net/11073/8819
10.1016/j.image.2015.02.008
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv Elsevier
dc.relation.none.fl_str_mv http://doi.org/10.1016/j.image.2015.02.008
dc.subject.none.fl_str_mv PSNR estimation
SSIM estimation
Machine learning
Regression analysis
Video codecs
Video compression
dc.title.none.fl_str_mv A regression-based framework for estimating the objective quality of HEVC coding units and video frames
dc.type.none.fl_str_mv Postprint
Peer-Reviewed
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description A no-reference objective quality estimation framework is proposed. The framework is suitable for any block-based video codec. In the proposed solution, features are extracted from coding units and summarized to form features at frame levels. Stepwise regression is used to select the important feature variables and reduce the dimensionality of feature vectors. Thereafter, a polynomial regression-based approach is used to model the nonlinear relationship between the feature vectors and the true objective quality values. Such values are estimated for coding units and video frames. The proposed framework is implemented using MPEG-2 and HEVC. The objective quality estimation results are compared against an existing state-of-the-art solution and quantified using the Pearson correlation factor and the root mean square error measure.
format article
id aus_7277530a8ca35e97e394b80f4ef689c8
identifier_str_mv Shanableh, T. (2015). A regression-based framework for estimating the objective quality of hEVC coding units and video frames. Signal Processing: Image Communication, 34, 22-31. doi:10.1016/j.image.2015.02.008
1879-2677
10.1016/j.image.2015.02.008
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/8819
publishDate 2015
publisher.none.fl_str_mv Elsevier
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling A regression-based framework for estimating the objective quality of HEVC coding units and video framesShanableh, TamerPSNR estimationSSIM estimationMachine learningRegression analysisVideo codecsVideo compressionA no-reference objective quality estimation framework is proposed. The framework is suitable for any block-based video codec. In the proposed solution, features are extracted from coding units and summarized to form features at frame levels. Stepwise regression is used to select the important feature variables and reduce the dimensionality of feature vectors. Thereafter, a polynomial regression-based approach is used to model the nonlinear relationship between the feature vectors and the true objective quality values. Such values are estimated for coding units and video frames. The proposed framework is implemented using MPEG-2 and HEVC. The objective quality estimation results are compared against an existing state-of-the-art solution and quantified using the Pearson correlation factor and the root mean square error measure.Elsevier2017-05-01T05:56:40Z2017-05-01T05:56:40Z2015-05PostprintPeer-Reviewedinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfShanableh, T. (2015). A regression-based framework for estimating the objective quality of hEVC coding units and video frames. Signal Processing: Image Communication, 34, 22-31. doi:10.1016/j.image.2015.02.0081879-2677http://hdl.handle.net/11073/881910.1016/j.image.2015.02.008en_UShttp://doi.org/10.1016/j.image.2015.02.008oai:repository.aus.edu:11073/88192024-08-22T12:07:13Z
spellingShingle A regression-based framework for estimating the objective quality of HEVC coding units and video frames
Shanableh, Tamer
PSNR estimation
SSIM estimation
Machine learning
Regression analysis
Video codecs
Video compression
status_str publishedVersion
title A regression-based framework for estimating the objective quality of HEVC coding units and video frames
title_full A regression-based framework for estimating the objective quality of HEVC coding units and video frames
title_fullStr A regression-based framework for estimating the objective quality of HEVC coding units and video frames
title_full_unstemmed A regression-based framework for estimating the objective quality of HEVC coding units and video frames
title_short A regression-based framework for estimating the objective quality of HEVC coding units and video frames
title_sort A regression-based framework for estimating the objective quality of HEVC coding units and video frames
topic PSNR estimation
SSIM estimation
Machine learning
Regression analysis
Video codecs
Video compression
url http://hdl.handle.net/11073/8819