Bandwidth-Aware High-Efficiency Video Coding Design Scheme on a Multiprocessor System on Chip

IF 2.3 4区计算机科学 Q2 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

IEEE MultiMedia Pub Date : 2023-07-01 DOI:10.1109/MMUL.2023.3253521

Jui-Hung Hsieh, Zhi-Yu Zhang, Jing-Cheng Syu, Mao-Cheng Hsieh

{"title":"Bandwidth-Aware High-Efficiency Video Coding Design Scheme on a Multiprocessor System on Chip","authors":"Jui-Hung Hsieh, Zhi-Yu Zhang, Jing-Cheng Syu, Mao-Cheng Hsieh","doi":"10.1109/MMUL.2023.3253521","DOIUrl":null,"url":null,"abstract":"H.265/high-efficiency video coding (HEVC) provides a multitude of video data compression to minimize data storage and data transmission while preserving video coding quality and ameliorating coding bit rates. However, HEVC encoder chips are frequently integrated into mobile multiprocessor system-on-chip (MPSoC) systems that adopt intelligent thermal and power management techniques for heat- and power-dissipation reductions. Consequently, the accessible coding bandwidth (CB) for HEVC encoder chip use is not fixed, and the compressed video data for data transmission within MPSoCs are restricted to time-altering wireless transmission bandwidths (TBs). Therefore, the proposed bandwidth-aware H.265/HEVC controller design solves the video coding problems of limited CB and TB by jointly using a machine learning method and convex optimization. The ancillary experimental and implementation results demonstrate that the proposed CB-TB rate-coding distortion algorithm modeling and the very large-scale integration hardware architecture are applicable for CB- and TB-constrained HEVC encoder design within MPSoCs.","PeriodicalId":13240,"journal":{"name":"IEEE MultiMedia","volume":"30 1","pages":"37-47"},"PeriodicalIF":2.3000,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE MultiMedia","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/MMUL.2023.3253521","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}

引用次数: 0

Abstract

H.265/high-efficiency video coding (HEVC) provides a multitude of video data compression to minimize data storage and data transmission while preserving video coding quality and ameliorating coding bit rates. However, HEVC encoder chips are frequently integrated into mobile multiprocessor system-on-chip (MPSoC) systems that adopt intelligent thermal and power management techniques for heat- and power-dissipation reductions. Consequently, the accessible coding bandwidth (CB) for HEVC encoder chip use is not fixed, and the compressed video data for data transmission within MPSoCs are restricted to time-altering wireless transmission bandwidths (TBs). Therefore, the proposed bandwidth-aware H.265/HEVC controller design solves the video coding problems of limited CB and TB by jointly using a machine learning method and convex optimization. The ancillary experimental and implementation results demonstrate that the proposed CB-TB rate-coding distortion algorithm modeling and the very large-scale integration hardware architecture are applicable for CB- and TB-constrained HEVC encoder design within MPSoCs.

查看原文本刊更多论文

基于片上多处理器系统的带宽感知高效视频编码设计方案

H.265高效视频编码（HEVC）提供了大量视频数据压缩，以最小化数据存储和数据传输，同时保持视频编码质量并改善编码比特率。然而，HEVC编码器芯片经常集成到移动多处理器片上系统（MPSoC）系统中，该系统采用智能热管理和功率管理技术来降低散热和功耗。因此，HEVC编码器芯片使用的可访问编码带宽（CB）不是固定的，并且用于在MPSoC内进行数据传输的压缩视频数据被限制为时间改变的无线传输带宽（TB）。因此，所提出的带宽感知H.265/HEVC控制器设计通过联合使用机器学习方法和凸优化来解决有限CB和TB的视频编码问题。辅助实验和实现结果表明，所提出的CB-TB率编码失真算法建模和非常大规模的集成硬件架构适用于MPSoC中CB和TB约束的HEVC编码器设计。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE MultiMedia 工程技术-计算机：理论方法

CiteScore

6.40

自引率

3.10%

发文量

审稿时长

>12 weeks

期刊介绍： The magazine contains technical information covering a broad range of issues in multimedia systems and applications. Articles discuss research as well as advanced practice in hardware/software and are expected to span the range from theory to working systems. Especially encouraged are papers discussing experiences with new or advanced systems and subsystems. To avoid unnecessary overlap with existing publications, acceptable papers must have a significant focus on aspects unique to multimedia systems and applications. These aspects are likely to be related to the special needs of multimedia information compared to other electronic data, for example, the size requirements of digital media and the importance of time in the representation of such media. The following list is not exhaustive, but is representative of the topics that are covered: Hardware and software for media compression, coding & processing; Media representations & standards for storage, editing, interchange, transmission & presentation; Hardware platforms supporting multimedia applications; Operating systems suitable for multimedia applications; Storage devices & technologies for multimedia information; Network technologies, protocols, architectures & delivery techniques intended for multimedia; Synchronization issues; Multimedia databases; Formalisms for multimedia information systems & applications; Programming paradigms & languages for multimedia; Multimedia user interfaces; Media creation integration editing & management; Creation & modification of multimedia applications.