Porting a H264/AVC adaptive in loop deblocking filter to a TI DM6437EVM DSP

Authors:
Abdellah Skoudarli;Mokhtar Nibouche;Amina Serir
Affiliations:
Faculty of Electronic and Informatic Laboratory of Image Processing and Radiation, USTHB, Bab Ezzouar, Alger, Algeria;UWE, Bristol, UK;Faculty of Electronic and Informatic Laboratory of Image Processing and Radiation, USTHB, Bab Ezzouar, Alger, Algeria
Venue:
ICISP'12 Proceedings of the 5th international conference on Image and Signal Processing
Year:
2012

Citing 7
Cited 0

Algorithms and DSP implementation of H.264/AVC

ASP-DAC '06 Proceedings of the 2006 Asia and South Pacific Design Automation Conference
H.264/AVC In-Loop De-Blocking Filter Targeting a Dynamically Reconfigurable Instruction Cell Based Architecture

AHS '07 Proceedings of the Second NASA/ESA Conference on Adaptive Hardware and Systems
ASIP Approach for Implementation of H.264/AVC

Journal of Signal Processing Systems
Deblocking of block-transform compressed images using weighted sums of symmetrically aligned pixels

IEEE Transactions on Image Processing
Overview of the H.264/AVC video coding standard

IEEE Transactions on Circuits and Systems for Video Technology
Adaptive deblocking filter

IEEE Transactions on Circuits and Systems for Video Technology
Iterative procedures for reduction of blocking effects in transform image coding

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Complementary units in the form encoders and decoders are generally involved in video compression standards. Both the encoder and the decoder integrate an adaptive deblocking filter, which is very beneficial in preserving and enhancing the video quality. Deblocking filters are extremely popular in improving the visual quality of decoded frames in the H.264/AVC video coding standard. The prime goal of the current paper is to efficiently implement a H.264/AVC adaptive deblocking filter using the Texas Instruments DM6437EVM DSP processor. The adopted approach requires an initial identification of the portions of the algorithm wherein parallel processing can be exploited. The functions are then re-written and the instructions rearranged using the features of the targeted hardware architecture. The adaptive deblocking algorithm was optimised and ported to a DM6437EVM DSP platform. A quick comparison shows that the optimised code is a 32 % better, in terms of speed, than the non-optimised code.