FPGA Implementation of Fast and Efficient CODEC for H.264/AVC Real Time Video Applications

FPGA Implementation of Fast and Efficient CODEC for H.264/AVC Real Time Video Applications

Yasser Ismail (Department of Computer Engineering, University of Bahrain, Sakhair, Bahrain)
Copyright: © 2016 |Pages: 21
DOI: 10.4018/IJTD.2016010103
OnDemand PDF Download:
No Current Special Offers


Low power networks are considered nowadays as a fundamental environment for connecting and communicating various “things.” Such connected things form the hot topic Internet-of-Things (IoT) that emphasizes on better and smarter interconnected world. The two main important issues raised in the IoT are the transmitted bit-rate and the device processing capability limitations. In this paper, a smart Skipping Motion Estimation threshold (TSME) is implemented and elaborated to match the processing capabilities of the IoT devices. The proposed threshold aims to achieve a great reduction in the computations of the Motion Estimation (ME) process with acceptable bit-rate and high speed that are suitable for real time video applications. Simulation results show that there is great reductions in the computations represented by the Motion Estimation Time Saving percentage (METS%) up to 51% and 49% in case of using average and median functions, respectively. Implementation results of the proposed threshold unit on an FPGA show low cost hardware with a maximum hardware frequency of 379.140MHz.
Article Preview

1. Introduction

Over the past two decades, digital video compression techniques have played a vital role in processing visual data. This is due to the spreading of various multimedia applications in the recent time. Mobile TV, Digital Video Broadcasting (DVB), Local Area Network (LAN) video streaming, video surveillance cameras, high resolution digital cameras, hand-held multimedia phones, Personal Digital Assistant (PDA), ultra-low power video sensors, and Digital Versatile Disk (DVD) are some examples of such applications. Due to the exponential increase in the required Megapixels per second (Mpbs) of the previous multimedia applications, video data compression is considered as a hot area nowadays.

H.264/AVC (Advanced Video Coding) and H.265/HEVC or High Efficient Video Coding standards (JVT, 2003, 2012; Ohm, Sullivan, Schwarz, Thiow Keng, & Wiegand, 2012) are the most recent recommendations that are greatly remove data redundancies from the transmitted video signal. As a result, the required transmission bit-rate is greatly reduced. H.264/AVC standard is finalized by ITU and ISO in 2003 (JVT, 2003). Many compression techniques are used by the H.264/AVC standard under a constrain of keeping high coding efficiency. High coding efficiency means high visual quality as well as low transmission bit-rate. A savings of up to 50% in the transmitted bit rate can be achieved by the H.264/AVC standard compared to all of its previous standards. This allows the H.264/AVC standard to be used in many applications such as video conferencing, video-on-demand, and video streaming. Keeping this high reduction in bit-rate and still high video quality is achieved in such standard by using many time exhaustive and computational complexity tools such as multiple reference frames, half-pel and quarter-pel accurate motion estimation, and variable block sizes. Such tools may slow down the use of such H.264/AVC standard in real time video applications.

Recently, high resolution videos become high demanding in popularity (Davis & Marikkannan, 2014). However, sending such high resolution videos over the current network infrastructure is a challenge. This is because the huge bit-rate required for transmitting such huge video data. H.265/HEVC or High Efficiency Video Coding (HEVC) standard has been originally developed and finalized by ITU-T VCEG and ISO/IEC MPEG (JVT, 2012; Ohm et al., 2012). The H.265/HEVC standard achieves two main goals. First, encoding the high resolution video such as 4K and Ultra High Definition (UHD) using lower bit-rate compared to all other previous standards. Second, utilizing parallel processing operations in order to avoid the delay results from the added tools that are used to lower the bit-rate. The main raised issue in H.265/HEVC standard is that the computational complexity has been dramatically increased compared to previous standards. H.265/HEVC encoder is four-time more complex than older standards (Bossen, Bross, Suhring, & Flynn, 2012).

Complete Article List

Search this Journal:
Open Access Articles
Volume 13: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing