Parallelization and performance evaluation of open-source HEVC codecs

Autor: Pedro Cuenca, David García-Lucas, Gabriel Cebrián-Márquez
Rok vydání: 2016
Předmět:
Zdroj: The Journal of Supercomputing. 73:495-513
ISSN: 1573-0484
0920-8542
DOI: 10.1007/s11227-016-1895-4
Popis: High Efficiency Video Coding (HEVC) was developed by the Joint Collaborative Team on Video Coding (JCT-VC) to replace the current H.264/Advanced Video Coding (AVC) standard, which has dominated digital video services in all segments of the domestic and professional markets for over 10 years. In terms of rate-distortion, HEVC roughly doubles the compression performance of H.264/AVC, but at a cost of extremely high computational complexities during encoding. Parallelizing HEVC encoding is an efficient way of fulfilling this computational requirement. Since its standardization, several open-source HEVC video codecs have been developed with parallel encoding capabilities. This paper presents a rate-distortion/complexity analysis of the open-source HEVC codecs using objective measures of assessment to analyze their real parallelization capabilities. Experimental results show that DivX265 and x265 obtain the best parallel performance on average for the high-quality encoding scenario. In the case of the high-speed encoding scenario, x265 obtains the best parallel performance. In both scenarios, the coding efficiency of the encoders remains virtually unaffected regardless of the amount of parallelism.
Databáze: OpenAIRE