Low-complexity heterogeneous architecture for H.264/HEVC video transcoding |
| |
Authors: | Antonio Jesús Díaz-Honrubia Gabriel Cebrián-Márquez José Luis Martínez Pedro Cuenca José Miguel Puerta José Antonio Gámez |
| |
Affiliation: | 1.Albacete Research Institute of Informatics (I3A),University of Castilla-La Mancha,Albacete,Spain |
| |
Abstract: | High efficiency video coding (HEVC) was developed by the Joint Collaborative Team on video coding to replace the current H.264/AVC standard, which has been widely adopted over the last few years. Therefore, there is a lot of legacy content encoded with H.264/AVC, and an efficient conversion to HEVC is needed. This paper presents a hybrid transcoding algorithm which makes use of soft computing techniques as well as parallel processing. On the one hand, a fast quadtree level decision algorithm tries to exploit the information gathered at the H.264/AVC decoder to make faster decisions on coding unit splitting in HEVC using a Naïve–Bayes probabilistic classifier that is determined by a supervised data mining process. On the other hand, a parallel HEVC-encoding algorithm makes use of a heterogeneous platform composed of a multi-core central processing unit plus a graphics processing unit (GPU). In this way, from a coarse point of view, groups of frames or rows of a frame (both options are possible) are divided into threads to be executed on each core (each of which executes one of the aforementioned classifiers) and, from a finer point of view, all these threads work in a collaborative way on a single GPU to perform the motion estimation process on the co-processor. Experimental results show that the proposed transcoder can achieve a good tradeoff between coding efficiency and complexity compared with the anchor transcoder. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|