Frame level rate control based on support vector machine in HEVC

This paper proposes a frame level rate control scheme for HEVC based on support vector machine. Firstly, textual features of frames are extracted from video sequence. According to different complexities of textual features, support vector machine is chosen as a classifier for video classification. Secondly, a frame level rate control scheme is proposed to achieve higher coding efficiency based on classification results. According to the experiment results, the proposed algorithm achieves better coding performance than the original rate control scheme JCTVC-K0103 in HEVC.

[1]  Hu Yaqi,et al.  Automatic Classification System of Wushu Video Based on SVM , 2009, 2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery.

[2]  Luca Costantini,et al.  SVM for historical sport video classification , 2012, 2012 5th International Symposium on Communications, Control and Signal Processing.

[3]  Leen-Kiat Soh,et al.  Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices , 1999, IEEE Trans. Geosci. Remote. Sens..

[4]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[5]  Yannis Avrithis,et al.  Spatiotemporal saliency for video classification , 2009, Signal Process. Image Commun..

[6]  Yang Liu,et al.  Research and implementation for texture of handback skin quantitative analysis based on co-occurrence matrix , 2009, 2009 International Conference on Industrial Mechatronics and Automation.

[7]  K. R. Rao,et al.  High Efficiency Video Coding(HEVC) , 2014 .

[8]  Nello Cristianini,et al.  Large Margin DAGs for Multiclass Classification , 1999, NIPS.

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