FPGA architecture of the LDPS Motion Estimation for H.264/AVC Video Coding

  • Authors:

  • Moez Kthiri;Hassen Loukil;Ahmed Ben Atitallah;Patrice Kadionik;Dominique Dallet;Nouri Masmoudi

  • Affiliations:

  • IMS laboratory--ENSEIRB-MATMECA, CNRS UMR 5218, University Bordeaux 1, Talence, France 33 405;National School of Engineering, University of Sfax, Sfax, Tunisia 3038;High Institute of Electronics and Communication, BP University of Sfax, Sfax, Tunisia 3018;IMS laboratory--ENSEIRB-MATMECA, CNRS UMR 5218, University Bordeaux 1, Talence, France 33 405;IMS laboratory--ENSEIRB-MATMECA, CNRS UMR 5218, University Bordeaux 1, Talence, France 33 405;National School of Engineering, University of Sfax, Sfax, Tunisia 3038

  • Venue:
  • Journal of Signal Processing Systems
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Motion estimation is a highly computational demanding operation during video compression process and significantly affects the output quality of an encoded sequence. Special hardware architectures are required to achieve real-time compression performance. Many fast search block matching motion estimation (BMME) algorithms have been developed in order to minimize search positions and speed up computation but they do not take into account how they can be effectively implemented by hardware. In this paper, we propose three new hardware architectures of fast search block matching motion estimation algorithm using Line Diamond Parallel Search (LDPS) for H.264/AVC video coding system. These architectures use pipeline and parallel processing techniques and present minimum latency, maximum throughput and full utilization of hardware resources. The VHDL code has been tested and can work at high frequency in a Xilinx Virtex-5 FPGA circuit for the three proposed architectures.