Predicting split decisions of coding units in HEVC video compression using machine learning techniques

In this work, we propose to reduce the complexity of HEVC video encoding by predicting the split decisions of coding units. We use a sequencedependent approach in which a number of frames belonging to the video being encoded are used for generating a classification model. At each coding depth of the...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Hassan, Mahitab Alaaeldin (author)
مؤلفون آخرون: Shanableh, Tamer (author)
التنسيق: article
منشور في: 2018
الموضوعات:
الوصول للمادة أونلاين:http://hdl.handle.net/11073/16373
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513434917273600
author Hassan, Mahitab Alaaeldin
author2 Shanableh, Tamer
author2_role author
author_facet Hassan, Mahitab Alaaeldin
Shanableh, Tamer
author_role author
dc.creator.none.fl_str_mv Hassan, Mahitab Alaaeldin
Shanableh, Tamer
dc.date.none.fl_str_mv 2018
2019-01-03T05:36:55Z
2019-01-03T05:36:55Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Hassan, M. & Shanableh, T. (2018). Predicting split decisions of coding units in HEVC video compression using machine learning techniques. Multimedia Tools and Applications. DOI: 10.1007/s11042-018-6882-8
1573-7721
http://hdl.handle.net/11073/16373
10.1007/s11042-018-6882-8
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv Springer
dc.relation.none.fl_str_mv https://doi.org/10.1007/s11042-018-6882-8
dc.subject.none.fl_str_mv High Efficiency Video Coding (HEVC)
Pattern recognition
Video compression
dc.title.none.fl_str_mv Predicting split decisions of coding units in HEVC video compression using machine learning techniques
dc.type.none.fl_str_mv Postprint
Peer-Reviewed
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description In this work, we propose to reduce the complexity of HEVC video encoding by predicting the split decisions of coding units. We use a sequencedependent approach in which a number of frames belonging to the video being encoded are used for generating a classification model. At each coding depth of the coding units, features representing the coding unit at that particular depth are extracted from both the present and previously encoded coding units. The feature vectors are then used for generating a dimensionality reduction model and a classification model. The generated models at each coding depth are then used to predict the split decisions of subsequent coding units. Stepwise regression, random forest reduction and principal component analysis are used for dimensionality reduction; whereas, polynomial networks and random forests are utilized for classification. The proposed solution is assessed in terms of classification accuracy, BD-rate, BD-PSNR and computational time complexity. Using seventeen video sequences with four different classes of resolution, an average classification accuracy of 86.5% is reported for the proposed classification system. In comparison to regular HEVC coding, the proposed solution resulted in a BD-rate loss of 0.55 and a BD-PSNR of -0.02 dB. The average reported computational complexity reduction is found to be 39.2%.
format article
id aus_dbf1131a9867bc56ff8d870c50ede324
identifier_str_mv Hassan, M. & Shanableh, T. (2018). Predicting split decisions of coding units in HEVC video compression using machine learning techniques. Multimedia Tools and Applications. DOI: 10.1007/s11042-018-6882-8
1573-7721
10.1007/s11042-018-6882-8
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/16373
publishDate 2018
publisher.none.fl_str_mv Springer
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Predicting split decisions of coding units in HEVC video compression using machine learning techniquesHassan, Mahitab AlaaeldinShanableh, TamerHigh Efficiency Video Coding (HEVC)Pattern recognitionVideo compressionIn this work, we propose to reduce the complexity of HEVC video encoding by predicting the split decisions of coding units. We use a sequencedependent approach in which a number of frames belonging to the video being encoded are used for generating a classification model. At each coding depth of the coding units, features representing the coding unit at that particular depth are extracted from both the present and previously encoded coding units. The feature vectors are then used for generating a dimensionality reduction model and a classification model. The generated models at each coding depth are then used to predict the split decisions of subsequent coding units. Stepwise regression, random forest reduction and principal component analysis are used for dimensionality reduction; whereas, polynomial networks and random forests are utilized for classification. The proposed solution is assessed in terms of classification accuracy, BD-rate, BD-PSNR and computational time complexity. Using seventeen video sequences with four different classes of resolution, an average classification accuracy of 86.5% is reported for the proposed classification system. In comparison to regular HEVC coding, the proposed solution resulted in a BD-rate loss of 0.55 and a BD-PSNR of -0.02 dB. The average reported computational complexity reduction is found to be 39.2%.Springer2019-01-03T05:36:55Z2019-01-03T05:36:55Z2018PostprintPeer-Reviewedinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfHassan, M. & Shanableh, T. (2018). Predicting split decisions of coding units in HEVC video compression using machine learning techniques. Multimedia Tools and Applications. DOI: 10.1007/s11042-018-6882-81573-7721http://hdl.handle.net/11073/1637310.1007/s11042-018-6882-8en_UShttps://doi.org/10.1007/s11042-018-6882-8oai:repository.aus.edu:11073/163732024-08-22T12:07:55Z
spellingShingle Predicting split decisions of coding units in HEVC video compression using machine learning techniques
Hassan, Mahitab Alaaeldin
High Efficiency Video Coding (HEVC)
Pattern recognition
Video compression
status_str publishedVersion
title Predicting split decisions of coding units in HEVC video compression using machine learning techniques
title_full Predicting split decisions of coding units in HEVC video compression using machine learning techniques
title_fullStr Predicting split decisions of coding units in HEVC video compression using machine learning techniques
title_full_unstemmed Predicting split decisions of coding units in HEVC video compression using machine learning techniques
title_short Predicting split decisions of coding units in HEVC video compression using machine learning techniques
title_sort Predicting split decisions of coding units in HEVC video compression using machine learning techniques
topic High Efficiency Video Coding (HEVC)
Pattern recognition
Video compression
url http://hdl.handle.net/11073/16373