Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding

This paper proposes learning-based approaches for transcoding MPEG-2 video into HEVC. In the training mode of the transcoder, mappings between extracted features and split decisions are calculated. While in the transcoding mode, the split decisions of coding units of the HEVC video are predicted. Tw...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Shanableh, Tamer (author)
مؤلفون آخرون: Hassan, Mahitab Alaaeldin (author)
التنسيق: article
منشور في: 2020
الموضوعات:
الوصول للمادة أونلاين:http://hdl.handle.net/11073/16658
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513433552027648
author Shanableh, Tamer
author2 Hassan, Mahitab Alaaeldin
author2_role author
author_facet Shanableh, Tamer
Hassan, Mahitab Alaaeldin
author_role author
dc.creator.none.fl_str_mv Shanableh, Tamer
Hassan, Mahitab Alaaeldin
dc.date.none.fl_str_mv 2020-05-17T10:06:51Z
2020-05-17T10:06:51Z
2020
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv T. Shanableh and M. Hassan, "Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding," SN Applied Sciences, Springer, Accepted for publication, May, 2020
2523-3971
http://hdl.handle.net/11073/16658
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/s42452-020-2909-7
dc.subject.none.fl_str_mv Video coding
Video transcoding
HEVC
High Efficiency Video Coding (HEVC)
Machine learning
dc.title.none.fl_str_mv Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding
dc.type.none.fl_str_mv Peer-Reviewed
Preprint
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description This paper proposes learning-based approaches for transcoding MPEG-2 video into HEVC. In the training mode of the transcoder, mappings between extracted features and split decisions are calculated. While in the transcoding mode, the split decisions of coding units of the HEVC video are predicted. Two formulations are proposed for the prediction of split decisions based on multi model and multi-tier solutions. In the former solution, multi models are generated based on the total number of split flags in a coding unit. While in the latter solution, split decisions are modelled at three different coding depths. The proposed solutions are evaluated in terms of excessive bitrate, drop in PSNR, classification accuracy, model generation time and transcoding speedup. It is shown that the multi-tier solution maintains the rate-distortion behaviour of full re-encoding at the expense of lower gain in transcoding speedup. In comparison to existing work, it is shown that the proposed solutions offer a significant enhancement in terms of rate-distortion performance and classification accuracy.
format article
id aus_ef67ddf3f4c286f20e0d1887f86d3d00
identifier_str_mv T. Shanableh and M. Hassan, "Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding," SN Applied Sciences, Springer, Accepted for publication, May, 2020
2523-3971
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/16658
publishDate 2020
publisher.none.fl_str_mv Springer
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Predicting Split Decisions in MPEG-2 to HEVC Video TranscodingShanableh, TamerHassan, Mahitab AlaaeldinVideo codingVideo transcodingHEVCHigh Efficiency Video Coding (HEVC)Machine learningThis paper proposes learning-based approaches for transcoding MPEG-2 video into HEVC. In the training mode of the transcoder, mappings between extracted features and split decisions are calculated. While in the transcoding mode, the split decisions of coding units of the HEVC video are predicted. Two formulations are proposed for the prediction of split decisions based on multi model and multi-tier solutions. In the former solution, multi models are generated based on the total number of split flags in a coding unit. While in the latter solution, split decisions are modelled at three different coding depths. The proposed solutions are evaluated in terms of excessive bitrate, drop in PSNR, classification accuracy, model generation time and transcoding speedup. It is shown that the multi-tier solution maintains the rate-distortion behaviour of full re-encoding at the expense of lower gain in transcoding speedup. In comparison to existing work, it is shown that the proposed solutions offer a significant enhancement in terms of rate-distortion performance and classification accuracy.Springer2020-05-17T10:06:51Z2020-05-17T10:06:51Z2020Peer-ReviewedPreprintinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfT. Shanableh and M. Hassan, "Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding," SN Applied Sciences, Springer, Accepted for publication, May, 20202523-3971http://hdl.handle.net/11073/16658en_UShttps://doi.org/10.1007/s42452-020-2909-7oai:repository.aus.edu:11073/166582024-08-22T12:07:32Z
spellingShingle Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding
Shanableh, Tamer
Video coding
Video transcoding
HEVC
High Efficiency Video Coding (HEVC)
Machine learning
status_str publishedVersion
title Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding
title_full Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding
title_fullStr Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding
title_full_unstemmed Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding
title_short Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding
title_sort Predicting Split Decisions in MPEG-2 to HEVC Video Transcoding
topic Video coding
Video transcoding
HEVC
High Efficiency Video Coding (HEVC)
Machine learning
url http://hdl.handle.net/11073/16658