作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2020, Vol. 46 ›› Issue (11): 42-47. doi: 10.19678/j.issn.1000-3428.0056282

• 人工智能与模式识别 • 上一篇    下一篇

基于深度学习的HEVC SCC帧内编码快速算法

黄胜1,2, 张倩云1,2, 李萌芳1,2, 郑秀凤1,2   

  1. 1. 重庆邮电大学 通信与信息工程学院, 重庆 400065;
    2. 光通信与网络重点实验室, 重庆 400065
  • 收稿日期:2019-10-14 修回日期:2019-11-20 发布日期:2019-11-22
  • 作者简介:黄胜(1974-),男,教授,主研方向为视频编码、视频传输、人工智能;张倩云、李萌芳、郑秀凤,硕士研究生。
  • 基金资助:
    国家自然科学基金(61571072)。

Fast Algorithm for HEVC SCC Intra-frame Coding Based on Deep Learning

HUANG Sheng1,2, ZHANG Qianyun1,2, LI Mengfang1,2, ZHENG Xiufeng1,2   

  1. 1. School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
    2. Key Laboratory of Optical Communication and Network, Chongqing 400065, China
  • Received:2019-10-14 Revised:2019-11-20 Published:2019-11-22

摘要: 为降低屏幕内容编码的计算复杂度,提出一种基于深度学习的屏幕内容编码帧内CTU深度范围预测快速算法。将编码足够数量的屏幕内容视频帧序列作为训练数据,通过大量的训练数据统计CTU深度范围的分布,根据分布占比设置CTU类别标签。设计并训练卷积神经网络(CNN)架构以预测CTU深度范围,考虑CTU分割特性,设计的CNN架构运用三层不同大小的卷积核提取与CTU深度相关的特征,为CNN模型提供训练参数。在编码时调用训练后的CNN模型预测CTU深度范围,以减少不必要的深度遍历。实验结果表明,与SCM-8.0相比,该算法平均节省48.34%的编码时间,码率上升2.59%,有效降低了编码的计算复杂度。

关键词: 屏幕内容编码, 帧内快速算法, 深度学习, 编码单元, CTU深度范围预测

Abstract: In order to reduce the computational complexity of Screen Content Coding(SCC),this paper proposes a fast algorithm for SCC intra-frame CTU depth range prediction based on deep learning.A sufficient number of screen content video frame sequences are encoded as training data,and the distribution of CTU depth range is counted through a large amount of training data.The CTU category label is set according to the distribution ratio.Convolutional Neural Networks(CNN) architecture is designed and trained to predict the CTU depth range.Considering the CTU segmentation characteristics,the designed CNN architecture uses three different layers of convolution kernels to extract CTU depth-related features and provide training parameters for the CNN model.The trained CNN model is called at the time of encoding to predict the CTU depth range and reduce unnecessary depth traversal.Experimental results show that compared with SCM-8.0,the proposed algorithm saves an average of 48.34% coding time and increases the code rate by 2.59%,which effectively reduces the computational complexity of coding.

Key words: Screen Content Coding(SCC), intra-frame fast algorithm, deep learning, Coding Unit(CU), CTU depth range prediction

中图分类号: