Thesis-2006-Agha.pdf (5.88 MB)
Software and hardware techniques for accelerating MPEG2 motion estimation
thesis
posted on 2018-07-17, 07:51 authored by Shahrukh AghaThe aim of this thesis is to accelerate the process of motion estimation (ME)
for the implementation of real time, portable video encoding. To this end a
number of different techniques have been considered and these have been
investigated in detail. Data Level Parallelism (DLP) is exploited first, through
the use of vector instruction extensions using configurable/re-configurable
processors to form a fast System-On-Chip (SoC) video encoder capable of
embedding both full search and fast ME methods.
Further parallelism is then exploited in the form of Thread Level
Parallelism (TLP), introduced into the ME process through the use of multiple
processors incorporated onto a single Soc. A theoretical explanation of the
results, obtained with these methodologies, is then developed for algorithmic
optimisations.
This is followed with the investigation of an efficient, orthogonal
technique based on the use of a reduced number of bits (RBSAD) for the
purposes of image comparison. This technique, which provides savings of
both power and time, is investigated along with a number of criteria for its
improvement to full resolution. Finally a VLSI layout of a low-power ME
engine, capable of using this technique, is presented.
The combination of DLP, TLP and RBSAD is found to reduce the clock
frequency requirement by around an order of magnitude.
History
School
- Mechanical, Electrical and Manufacturing Engineering
Publisher
© Shahrukh AghaPublisher statement
This work is made available according to the conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licence. Full details of this licence are available at: https://creativecommons.org/licenses/by-nc-nd/4.0/Publication date
2006Notes
A Doctoral Thesis. Submitted in partial fulfilment of the requirements for the award of Doctor of Philosophy at Loughborough University.Language
- en