Fast H.264 Encoding Based on Statistical Learning

  • Chen-Kuo Chiang
  • Shang-Hong Lai
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6298)


In this paper, we propose an efficient video coding system that applies statistical learning methods to reduce the computational cost in H.264 encoder. The proposed method can be applied to many coding components in H.264, like intermode decision, multi-reference motion estimation, intra-mode prediction. First, representative features are extracted from video to build the learning models. Then, an off-line pre-classification approach is used to determine the best results from the extracted features, thus a significant amount of computation is reduced based on the classification strategy. The proposed statistical learning based approach is applied to the aforementioned three main components and a novel framework of learning based H.264 encoder is proposed to speed up the computation. Experimental results show that the motion estimation (ME) time of the proposed system is significantly speed up with twelve times faster than the H.264 encoder with a conventional fast ME algorithm, and the total encoding time of the proposed encoder is greatly reduced with about four times faster than the fast encoder EPZS in the H.264 reference code with negligible video quality degradation.


Motion estimation multiple-reference motion estimation intermode decision intra prediction H.264 statistical learning video coding 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Pan, W.-H., Chiang, C.-K., Lai, S.-H.: Fast Intermode Decision via Statistical Learning for H.264 Video Coding. In: Satoh, S., Nack, F., Etoh, M. (eds.) MMM 2008. LNCS, vol. 4903, pp. 329–337. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  2. 2.
    Chiang, C.-K., Lai, S.-H.: Fast Multi-Reference Motion Estimation Via Statistical Learning For H.264. In: IEEE International Conference on Multimedia & Expo. (ICME), New York (2009)Google Scholar
  3. 3.
    Hwang, C., Lai, S.-H.: Efficient Intra Mode Decision Via Statistical Learning. In: Ip, H.H.-S., Au, O.C., Leung, H., Sun, M.-T., Ma, W.-Y., Hu, S.-M. (eds.) PCM 2007. LNCS, vol. 4810, pp. 148–157. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  4. 4.
    Zhan, B., Hou, B., Sotudeh, R.: A Novel Fast Inter Mode Decision Algorithm Based On Statistic And Adaptive Adjustment For H.264/AVC. In: International Conference on Software, Telecommunications and Computer Networks, SoftCOM, pp. 1–5 (2007)Google Scholar
  5. 5.
    Huang, Y.-W., Hsieh, B.-Y., Wang, T.-C., Chen, S.-Y., Ma, S.-H., Shen, C.-F., Chen, L.-G.: Analysis And Reduction Of Reference Frames For Motion Estimation In MPEG-4 AVC/JVT/H.264. In: Proceeding of IEEE International Conference on Acoustics, Speech, and Signal Processing (2003)Google Scholar
  6. 6.
    Ma, W., Yang, S., Gao, L., Pei, C., Yan, S.: Fast Mode Selection Scheme For H.264/AVC Inter Prediction Based On Statistical Learning Method. In: IEEE International Conference on Multimedia and Expo., ICME (2009)Google Scholar
  7. 7.
    Wu, P., Xiao, C.-B.: An Adaptive Fast Multiple Reference Frames Selection Algorithm For H.264/AVC. In: Proceeding of IEEE International Conference on Acoustics, Speech, and Signal Processing (2008)Google Scholar
  8. 8.
    Sim, D.-G., Kim, Y.: Context-adaptive Mode Selection For Intra-block Coding In H.264/MPEG-4 Part 10. Real-Time Imaging 11, 1–6 (2005)CrossRefGoogle Scholar
  9. 9.
    Joshi, U., Jillani, R., Bhattacharya, C., Kalva, H., Ramakrishnan, K.R.: Speedup Macroblock Mode Decision In H.264/SVC Encoding Using Cost-sensitive Learning. In: Digest of Technical Papers International Conference on Consumer Electronics, ICCE (2010)Google Scholar
  10. 10.
    Cortes, C., Vapnik, V.: Support-Vector Networks. Machine Learning, 273–297 (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Chen-Kuo Chiang
    • 1
  • Shang-Hong Lai
    • 1
  1. 1.Department of Computer ScienceNational Tsing Hua UniversityHsinchuTaiwan

Personalised recommendations