Machine learning-based H.264/AVC to HEVC transcoding via motion information reuse and coding mode similarity analysis

• Published in: IET image processing Vol. 13; no. 1; pp. 34 - 43
• Main Authors: Lin, Hongwei, He, Xiaohai, Qing, Linbo, Su, Shan, Xiong, Shuhua
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.01.2019
• Subjects: AVC standard; Bayes methods; code standards; coding complexity reduction; coding mode similarity analysis; computational complexity; feature selection; feature selection method; H.264 standard; HEVC coding unit depth; HEVC transcoders; HEVC transcoding scheme; high‐efficiency video coding; image classification; image motion analysis; learning (artificial intelligence); machine learning; motion information reuse; motion vector calculation method; optimised tree‐augmented Naive Bayesian approach; Research Article; three‐level classifier; transcoding; transcoding algorithms; trees (mathematics); updated standard; video coding; video resources; H.264 standard; video resources; image classification; feature selection method; HEVC coding unit depth; transcoding algorithms; learning (artificial intelligence); coding complexity reduction; AVC standard; feature selection; motion vector calculation method; trees (mathematics); updated standard; optimised tree-augmented Naive Bayesian approach; video coding; code standards; machine learning; image motion analysis; HEVC transcoding scheme; three-level classifier; high-efficiency video coding; HEVC transcoders; motion information reuse; Bayes methods; transcoding; coding mode similarity analysis; computational complexity
• ISSN: 1751-9659; 1751-9667
• DOI: 10.1049/iet-ipr.2018.5703

High-efficiency video coding (HEVC), which is the latest video coding standard, is expected to have a dominant position in the market in the near future. However, most video resources are now encoded using the H.264/AVC standard. Consequently, there is a growing need for fast H.264/AVC to HEVC transcoders to facilitate the migration to the updated standard. This paper proposes a fast H.264/AVC to HEVC transcoding scheme, which constructs a three-level classifier using an optimised tree-augmented Naive Bayesian approach to predict the HEVC coding unit depth. A feature selection method is then proposed to improve prediction accuracy. A motion vector (MV) calculation method is also proposed to reduce the complexity of MV prediction in HEVC by reusing MVs from H.264/AVC. Experimental results show that, compared with other state-of-the-art transcoding algorithms, the proposed algorithm considerably reduces coding complexity while causing only negligible rate-distortion degradation.