Publication detail

Software and Hardware HEVC Encoding

KUFA, J. KRATOCHVÍL, T.

Original Title

Software and Hardware HEVC Encoding

English Title

Software and Hardware HEVC Encoding

Type

conference paper

Language

en

Original Abstract

In comparison with older standards, High Efficiency Video Coding (HEVC) significantly improves coding efficiency. At the same time, it increases computational complexity of coding and therefore encoding takes a longer time. In this paper, the usage of different implementations of HEVC is proposed where some of them can take advantage of a multicore Central Processing Unit (CPU). The others are accelerated by using a Video Engine (VE) in the Graphics Processing Unit (GPU). In the paper, different predefined quality presets are also used which set the balance between the video quality and encoding speed. Another aspect was to compare power consumption and utilization of components in a Personal Computer (PC) depending on different HEVC implementations. Research has been carried out for both resolutions, Full HD and Ultra HD. Our experimental results show that hardware-accelerated encoding can encode video that consumes less CPU time, with only small impact on video quality.

English abstract

In comparison with older standards, High Efficiency Video Coding (HEVC) significantly improves coding efficiency. At the same time, it increases computational complexity of coding and therefore encoding takes a longer time. In this paper, the usage of different implementations of HEVC is proposed where some of them can take advantage of a multicore Central Processing Unit (CPU). The others are accelerated by using a Video Engine (VE) in the Graphics Processing Unit (GPU). In the paper, different predefined quality presets are also used which set the balance between the video quality and encoding speed. Another aspect was to compare power consumption and utilization of components in a Personal Computer (PC) depending on different HEVC implementations. Research has been carried out for both resolutions, Full HD and Ultra HD. Our experimental results show that hardware-accelerated encoding can encode video that consumes less CPU time, with only small impact on video quality.

Keywords

HEVC; x265; HM; Turing encoder; NVENC

Released

22.05.2017

Publisher

Poznań University of Technology

Location

Poznaň

ISBN

978-1-5090-6343-7

Book

2017 International Conference on Systems, Signals and Image Processing (IWSSIP)

Pages from

1

Pages to

5

Pages count

5

URL

BibTex


@inproceedings{BUT136240,
  author="Jan {Kufa} and Tomáš {Kratochvíl}",
  title="Software and Hardware HEVC Encoding",
  annote="In comparison with older standards, High Efficiency Video Coding (HEVC) significantly improves coding efficiency. At the same time, it increases computational complexity of coding and therefore encoding takes a longer time. In this paper, the usage of different implementations of HEVC is proposed where some of them can take advantage of a multicore Central Processing Unit (CPU). The others are accelerated by using a Video Engine (VE) in the Graphics Processing Unit (GPU). In the paper, different predefined quality presets are also used which set the balance between the video quality and encoding speed. Another aspect was to compare power consumption and utilization of components in a Personal Computer (PC) depending on different HEVC implementations. Research has been carried out for both resolutions, Full HD and Ultra HD. Our experimental results show that hardware-accelerated encoding can encode video that consumes less CPU time, with only small impact on video quality.",
  address="Poznań University of Technology",
  booktitle="2017 International Conference on Systems, Signals and Image Processing (IWSSIP)",
  chapter="136240",
  doi="10.1109/IWSSIP.2017.7965585",
  howpublished="electronic, physical medium",
  institution="Poznań University of Technology",
  year="2017",
  month="may",
  pages="1--5",
  publisher="Poznań University of Technology",
  type="conference paper"
}