A Design of Fast High-Efficiency Video Coding Scheme Based on Markov Chain Monte Carlo Model and Bayesian Classifier
A Design of Fast High-Efficiency Video Coding Scheme Based on Markov Chain Monte Carlo Model and Bayesian Classifier
复制标题
DOI：
10.1109/tie.2018.2815941
复制
发表时间：
2018-11
影响因子：
7.7
通讯作者：
Kalyan Goswami;Byung-Gyu Kim
中科院分区：
文献类型：
--
作者：
Kalyan Goswami;Byung-Gyu Kim
新一代高效视频编码（HEVC）标准最近已由视频编码联合合作小组开发，以提供图片质量的显著改善，尤其是对于高分辨率视频。然而，HEVC中最重要的挑战之一是高度的计算复杂度。该问题以一种新颖的方式解决，将跳过检测和编码单元终止视为两类决策问题。贝叶斯分类器用于这两种方法。贝叶斯分类器的先验和类别条件概率值在编码视频帧时是未知的。因此，使用马尔可夫链蒙特卡罗模型。实验结果表明，该方法提供了显着的时间减少编码与合理的低损失的视频质量。
The new-generation high-efficiency video coding (HEVC) standard has recently been developed by the Joint Collaborative Team on Video Coding to provide significant improvement in picture quality, especially for high-resolution videos. However, one of the most important challenges in HEVC is a high degree of computational complexity. This problem is addressed in a novel way considering skip detection and coding unit termination as two-class decision making problems. A Bayesian classifier is used for both of these approaches. Prior and class conditional probability values for a Bayesian classifier are not known at the time of encoding a video frame. Therefore, the Markov chain Monte Carlo model is used. Experimental results show that the proposed method provides significant time reduction for encoding with reasonably low loss in video quality.