Title :
Efficient Software H.264/AVC to HEVC Transcoding on Distributed Multicore Processors
Author :
Yucong Chen ; Ziyu Wen ; Jiangtao Wen ; Minhao Tang ; Pin Tao
Author_Institution :
Tsinghua Univ., Beijing, China
Abstract :
The latest High Efficiency Video Coding (HEVC) standard achieves a significant compression efficiency improvement over the H.264/Advanced Video Coding (AVC) standard, but with a much higher computational complexity. In this paper, we propose a novel framework for software-based H.264/AVC to HEVC transcoding, integrated with tools such as wavefront parallel processing that are useful for achieving higher levels of parallelism on multicore processors and distributed systems. By utilizing information extracted from the input H.264/AVC bitstream, the transcoding process can be greatly accelerated with a visual quality loss that is modest for many applications. Based on the HEVC HM 14.0 reference software and using standard HEVC test bitstreams, the proposed transcoder can achieve up to 60× speedup on a Quad Core 8-thread server over decoding-re-encoding based on FFMPEG and the HM software with a BD-rate loss of 15%-20%. By implementing a group of picture-level task distribution on a distributed system with nine processing units, the proposed software transcoder can achieve a speed for transcoding 720 p at 30 Hz in real time.
Keywords :
computational complexity; data compression; decoding; distributed processing; multiprocessing systems; transcoding; video coding; FFMPEG; H.264-advanced video coding standard; HEVC HM 14.0 reference software; HEVC transcoding; Quad Core 8-thread server; computational complexity; distributed multicore processor; high efficiency video coding; information extraction; picture-level task distribution; software-based H.264-AVC; video compression; visual quality loss; Parallel processing; Program processors; Standards; Transcoding; Video coding; H.264/AVC; H264/Advanced Video Coding (AVC); HEVC; High Efficiency Video Coding (HEVC); Wavefront Parallel Processing; mode decision; transcoding; wavefront parallel processing (WPP);
Journal_Title :
Circuits and Systems for Video Technology, IEEE Transactions on
DOI :
10.1109/TCSVT.2014.2380231