A Pipelined Hardware Implementation of In-loop Deblocking Filter in H.264/AVC

Abstract

In this paper we present a pipelined hardware implementation of in-loop deblocking filter in H.264/AVC. A pipelined datapath has been adopted to boost the speed of the deblocking filter process. The processing order of the filter is rearranged to facilitate the deblocking of the pixels in a pipelined fashion. A suitable buffer mechanism has also been proposed that reduces the size of the on-chip SRAM and redundant external memory accesses. The hardware implementation, under TSMC 0.13 /spl mu/m standard cell library, consumes only 7.5 K gates at a clock frequency of 200 MHz. Our architecture supports real-time deblocking of high resolution (2048/spl times/1024) video applications at 30 fps over three channels.