Performance optimisation of real-time video processing on multicore architecture

Sankaraiah, Sreeramula (2014) Performance optimisation of real-time video processing on multicore architecture. PhD thesis, Multimedia University.

Full text not available from this repository.
Official URL: http://library.mmu.edu.my/diglib/onlinedb/dig_lib....

Abstract

Emergence of multi-core processors has paved the way for the use of computers for a wide variety of applications in computer vision and multimedia fields. Real-time implementation of computationally intensive applications such as Full High Definition (FHD) video processing, 3D object meshing and texture mapping have been made possible due to the advent of multicore processors. In order to fully exploit the capability of available multicore processors, it has become necessary to develop parallel processing algorithms. The aim of the thesis is to propose new techniques for optimising the performance of real-time 2D and 3D video processing applications on multicore architecture using parallelization concepts. Data level parallelization method based on Group of Pictures (GOP) using a dynamic memory scheduling algorithm is proposed to improve the performance of FHD video encoding and decoding processes. This method requires less memory resource (less cache misses) and also makes use of advanced data structures such as non-temporal and MALLOC functions for minimizing latency and memory stalls.

Item Type: Thesis (PhD)
Additional Information: Call. No: QA76.642 S64 2014
Uncontrolled Keywords: Parallel programming (Computer science), Parallelization
Subjects: Q Science > QA Mathematics > QA75.5-76.95 Electronic computers. Computer science
Q Science > QA Mathematics > QA75.5-76.95 Electronic computers. Computer science > QA76.75-76.765 Computer software
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 13 Jul 2015 03:25
Last Modified: 13 Jul 2015 03:25
URI: http://shdl.mmu.edu.my/id/eprint/6235

Actions (login required)

View Item View Item