Fast Algorithm and Efficient Architecture for Integer and Fractional Motion Estimation

  • Authors:
  • Obianuju Ndili;Tokunbo Ogunfunmi

  • Affiliations:
  • Santa Clara University, Santa Clara, USA;Santa Clara University, Santa Clara, USA

  • Venue:
  • Journal of Signal Processing Systems
  • Year:
  • 2014

Quantified Score

Hi-index 0.00

Visualization

Abstract

Motion estimation in H.264/AVC, is done in two parts --- integer motion estimation, and fractional motion estimation. Hardware reuse for both parts is inefficient due to the differences between them. In this paper we address the hardware reuse problem by proposing a, fast motion estimation algorithm as well as a pipelined FPGA-based, field programmable system-on-chip (FPSoC), for integer and fractional motion estimation. Our results show that the rate-distortion loss of our algorithm is insignificant when compared to full search in H.264/AVC. Its average Y-PSNR loss is 0.065聽dB, its average percentage bit rate increase is 5聽%, and its power consumption is 76聽mW. Our FPSoC is hardware-efficient, even out-performing some state-of-the-art ASIC implementations. It can support up to high definition 1280驴脳驴720p video at 24Hz. Thus, our proposed algorithm and architecture is suitable for delivery of high quality video on low power devices and low bit rate applications which typically use H.264/AVC baseline profile@levels 1---3.1.