High Speed Architecture for MPEG-2/H.264 Video Transcoding
YongTaek Hong, Kyungho Lee, Jingsang Kim, Won-Kyung Cho · 2006
The H.264 video coding standard is regarded as a new generation video standard due to better performance compared to other video coding standards. MPEG-2 video standard has been adopted for digital broadcasting standards by which most digital video contents have been created. It will take several years to change current video market place from MPEG-2 to H.264 standard, because of the wide usage of MPEG-2 today. This creates an important need for transcoding technologies that convert the widely available MPEG-2 compressed videos to H.264 compressed videos. However, given the significant differences between the MPEG-2 and the H.264 encoding algorithms, the transcoding process of such systems is much more complex than other heterogeneous video transcoding processes. In this paper, we propose a new high speed transcoding architecture from MPEG-2 to H.264. In the proposed transcoding architecture, the most complex encoding functions are performed in the transform domain without converting to pixel domain. The experimental results show that the proposed architecture is faster than existing transcoding architectures