Advertisement

GPU Acceleration for Directional Variance Based Intra-prediction in HEVC

  • Derek Nola
  • Elena G. Paraschiv
  • Damián Ruiz-Coll
  • María PantojaEmail author
  • Gerardo Fernández-Escribano
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 979)

Abstract

HEVC (High Efficiency Video Encoding) greatly improves the efficiency of intra-prediction in video compression. However, such gains are achieved with an encoder of significantly increased computational complexity. In this paper we present a Graphic Processing Unit (GPU) implementation of our modified intra-prediction algorithm: Mean Directional Variance in Sliding Window (MDV-SW). MDV-SW detects the texture orientation of a block of input pixels, and allows easy parallelization of intra-prediction; by doubling the detectable number of texture orientations and eliminating the data dependency generated by using pixels from the original image as reference samples instead of the reconstructed pixels. Once this dependency was removed we were able to calculate all intra-prediction blocks in a frame in parallel by hardware accelerators, specifically the GPU. Results show that the GPU implementation speeds up the execution by 10x compared to sequential implementation.

Keywords

HEVC Intra-prediction Parallel programming GPU CUDA 

References

  1. 1.
    Rec. ITU-T H.265 and ISO/IEC 23008-2, High Efficiency Video Coding, techreport, E 41298, December 2016Google Scholar
  2. 2.
    Rec. ITU-T H.264 and ISO/IEC 14496-10 (MPEG-4 AVC), Advanced video coding for generic audiovisual services, techreport, E 41560, April 2017Google Scholar
  3. 3.
    Ruiz, D., Fernández-Escribano, G., Martínez, J.L., Cuenca, P.: Fast intra mode decision algorithm based on texture orientation detection in HEVC. Signal Process. Image Commun. 44, 12–28 (2016)CrossRefGoogle Scholar
  4. 4.
    Paraschiv, E.G., Ruiz, D., Pantoja, M., Fernández-Escribano, G.: Texture orientation detection over parallel architectures: a qualitative overview. In: Proceedings of the 17th International Conference on Computational and Mathematical Methods in Science and Engineering, CMMSE 2017, vol. VI, pp. 2147–2158, July 2017Google Scholar
  5. 5.
    Kao, H.C., Wang, I.C., Lee, C.R., Lo, C.W., Kang, H.P.: Accelerating HEVC motion estimation using GPU. In: 2016 IEEE Second International Conference on Multimedia Big Data (BigMM 2016), pp. 255–258, April 2016.  https://doi.org/10.1109/BigMM.2016.13
  6. 6.
    Wang, B., et al.: Efficient HEVC decoder for heterogeneous CPU with GPU systems. In: 2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP 2016), pp. 1–6, September 2016.  https://doi.org/10.1109/MMSP.2016.7813353
  7. 7.
    Takano, F., Igarashi, H., Moriyoshi, T.: 4K-UHD real-time HEVC encoder with GPU accelerated motion estimation. In: 2017 IEEE International Conference on Image Processing (ICIP 2017), pp. 2731–2735, September 2017Google Scholar
  8. 8.
    Luo, F., Wang, S., Ma, S., Zhang, N., Zhou, Y., Gao, W.: Fast intra coding unit size decision for HEVC with GPU based keypoint detection. In: 2017 IEEE International Symposium on Circuits and Systems (ISCAS 2017), pp. 1–4, May 2017.  https://doi.org/10.1109/ISCAS.2017.8050260
  9. 9.
    Sullivan, G.J., Ohm, J., Han, W.-J., Wiegand, T.: Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circ. Syst. Video Technol. 22(12), 1649–1668 (2012)CrossRefGoogle Scholar
  10. 10.
    Lainema, J., Bossen, F., Han, W.-J., Min, J., Ugur, K.: Intra coding of the HEVC standard. IEEE Trans. Circ. Syst. Video Technol. 22(12), 1792–1801 (2012)CrossRefGoogle Scholar
  11. 11.
    OpenMP Specification for Parallel Programming. http://www.OpenMP.org/
  12. 12.
    OpenACC Specification for Parallel Programming. http://www.nvidia.com/OpenACC/
  13. 13.
    Compute Unified Device Architecture (CUDA). http://www.nvidia.com/CUDA/
  14. 14.
    Joint Collaborative Team on Video Coding Reference Software, ver. HM 16.8. https://hevc.hhi.fraunhofer.de/

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Derek Nola
    • 1
  • Elena G. Paraschiv
    • 2
  • Damián Ruiz-Coll
    • 3
  • María Pantoja
    • 1
    Email author
  • Gerardo Fernández-Escribano
    • 2
  1. 1.Cal Poly San Luis Obispo College of EngineeringSan Luis ObispoUSA
  2. 2.Instituto de Investigación en InformáticaUniversidad de Castilla-La ManchaAlbaceteSpain
  3. 3.Universidad Rey Juan CarlosFuenlabradaSpain

Personalised recommendations