Low Cost Implementation of Motion Estimation System Based on Diagonal Match Criterion

Conference Paper · June 2008
DOI: 10.1109/CISP.2008.569 · Source: IEEE Xplore
Conference: Image and Signal Processing, 2008. CISP '08. Congress on, Volume: 2

    Abstract

    To reduce the excessive amount of computation of traditional motion estimation (ME) algorithm, the diagonal match criterion (DMC) was proposed. DMC brings 75% reduction of computation Complexity and just 2.08% reduction of performance (PSNR) compare with traditional ME algorithm. What’s more important is that beside low, the performance reduction is very stable. And this makes DMC a valuable criterion. However, at the implementing side, DMC brings much irregularity of data flow. So the Lean snake registers array (LSRA) was proposed to conquer the irregularity. With this problem solved, the implementation makes a good use of the advancement of the algorithm, leading to high speed with very low cost of PEs and bandwidth. The implementation was designed when DMC was used in full-search strategy. The implementation supports real-time processing of 720×576 video with 25 fps at 80 MHz for a search range of [-7, +7] and macro block size of 8.