A 995Mpixels/s 0.2nJ/pixel fractional motion estimation architecture in HEVC for Ultra-HD

Gang He, Dajiang Zhou, Zhixiang Chen, Tianruo Zhang, Satoshi Goto

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    11 Citations (Scopus)

    Abstract

    This paper presents a fractional motion estimation (FME) design in high efficiency video coding (HEVC) for ultrahigh definition video (Ultra-HD). To reduce complexity and achieve high throughput, the design is co-optimized in algorithm and hardware architecture. Bilinear quarter pixel approximation, together with a 5T12S search pattern is proposed to reduce the complexity of the interpolation and search process. Furthermore, we introduce an exhaustive size-hadamard transform (ES-HAD), to improve coding quality, and determine the best transform size rather than using complex transform coding. Besides, a data reuse method of ES-HAD is applied to reduce the hardware overhead. This design is implemented in 65nm CMOS chip and verified by FPGA based evaluation system. It achieves 995Mpixels/s for 7680×4320 30fps encoding, at least 4.7 times faster than previous designs. Its power dissipation is 198.6mW at 188MHz, with 0.2nJ/pixel power efficiency. Despite high complexity in HEVC, the chip achieves 56% improvement on power efficiency than previous works in H.264.

    Original languageEnglish
    Title of host publicationProceedings of the 2013 IEEE Asian Solid-State Circuits Conference, A-SSCC 2013
    Pages301-304
    Number of pages4
    DOIs
    Publication statusPublished - 2013
    Event2013 9th IEEE Asian Solid-State Circuits Conference, A-SSCC 2013 - Singapore
    Duration: 2013 Nov 112013 Nov 13

    Other

    Other2013 9th IEEE Asian Solid-State Circuits Conference, A-SSCC 2013
    CitySingapore
    Period13/11/1113/11/13

    Keywords

    • FME
    • Hardware architecture
    • HEVC
    • Ultra-HD

    ASJC Scopus subject areas

    • Hardware and Architecture

    Fingerprint Dive into the research topics of 'A 995Mpixels/s 0.2nJ/pixel fractional motion estimation architecture in HEVC for Ultra-HD'. Together they form a unique fingerprint.

  • Cite this

    He, G., Zhou, D., Chen, Z., Zhang, T., & Goto, S. (2013). A 995Mpixels/s 0.2nJ/pixel fractional motion estimation architecture in HEVC for Ultra-HD. In Proceedings of the 2013 IEEE Asian Solid-State Circuits Conference, A-SSCC 2013 (pp. 301-304). [6691042] https://doi.org/10.1109/ASSCC.2013.6691042