{"title":"Software and hardware HEVC encoding","authors":"Jan Kufa, T. Kratochvil","doi":"10.1109/IWSSIP.2017.7965585","DOIUrl":null,"url":null,"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.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"65 3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IWSSIP.2017.7965585","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
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.