Graduation Semester and Year

2013

Language

English

Document Type

Thesis

Degree Name

Master of Science in Electrical Engineering

Department

Electrical Engineering

First Advisor

Kamisetty R Rao

Abstract

High Efficiency Video Coding, the latest video coding standard proposed by the JVT-VC and three profiles- HEVC main, main 10 and main intraframe were adopted in January 2013, provides significant amount of compression compared to older standards, while retaining similar visual quality. This is achieved at the cost of a computationally expensive encoding method.Intra frame coding contributes to a large portion of the computational complexity. In this research, a way to speed up the intra frame prediction mode decision using Artificial Neural Networks is proposed. The search for the correct prediction mode is simplified by using neural networks to analyze and reduce the number of modes that must be searched to arrive at the mode decision.By employing this scheme, a speed up of upto 20\% has been observed without significant loss of PSNR or increase in bitrate.

Disciplines

Electrical and Computer Engineering | Engineering

Comments

Degree granted by The University of Texas at Arlington

Download

Share

COinS