A Fast Coding Unit Size Decision Algorithm for HEVC Intra Coding Based on Image Complexity

High Efficiency Video Coding (HEVC) achieves the most significant coding efficiency compared with all the existing video coding standards. However, the Intra encoding complexity is increased dramatically since the complex recursive search algorithm for the coding unit (CU) size decisions. In this paper, a fast CU size decision algorithm based on Support Vector Machines (SVM) is proposed to further alleviate the encoder computation load. Firstly, some effective image features are extracted to judge the CU complexity. Then, a three-classifier structure of CU size decisions is established based on SVM. The experimental results show that the proposed algorithm can reduce 53% intra coding time on average with 1.2% BDBR loss on average.

[1]  Guifen Tian,et al.  Content adaptive prediction unit size decision algorithm for HEVC intra coding , 2012, 2012 Picture Coding Symposium.

[2]  Gary J. Sullivan,et al.  Overview of the High Efficiency Video Coding (HEVC) Standard , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[3]  Hongwen Yang,et al.  Fast CU splitting and pruning method based on online learning for intra coding in HEVC , 2014, 2014 IEEE Visual Communications and Image Processing Conference.

[4]  David Flynn,et al.  HEVC Complexity and Implementation Analysis , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[5]  Xingang Liu,et al.  A Texture Complexity Based Fast Prediction Unit Size Selection Algorithm for HEVC Intra-coding , 2014, 2014 IEEE 17th International Conference on Computational Science and Engineering.

[6]  Kemal Ugur,et al.  Intra Coding of the HEVC Standard , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[7]  Homer H. Chen,et al.  Fast Decision of Block Size, Prediction Mode, and Intra Block for H.264 Intra Prediction , 2010, IEEE Transactions on Circuits and Systems for Video Technology.

[8]  Yongdong Zhang,et al.  High Efficiency Video Coding: High Efficiency Video Coding , 2014 .

[9]  G. Bjontegaard,et al.  Calculation of Average PSNR Differences between RD-curves , 2001 .

[10]  Jianjun Lei,et al.  Fast Coding Tree Unit depth decision for high efficiency video coding , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[11]  Zhe Li,et al.  Gradient-based fast decision for intra prediction in HEVC , 2012, 2012 Visual Communications and Image Processing.

[12]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[13]  Feng Xu,et al.  Quantization Matrix Coding for High Efficiency Video Coding , 2012, IFTC.

[14]  F. Bossen,et al.  Common test conditions and software reference configurations , 2010 .