PSNR, Coding Efficiency and Bit Rates
Clearly, video standards have evolved over the years to accommodate the changing nature of both video and the users who wish to see it. As standards have evolved over time, coding efficiency has improved, and this enables enhanced peak signal to noise ratio (PSNR) for a given bit rate or a reduction in bit rate for a given PSNR, as depicted in figure 2.
View full size
Figure 2: Comparison of PSNR for H.261 to H.264 codecs at various bit rates
Initially a broadcast or cable-TV domain, video is now moving over the Internet in increasing volume, in a wide range of formats, designed for an equally wide array of devices. The challenge, of course, is making content available and playable across all devices and platforms. One partial solution comes from the evolution of operating systems across the market, which can handle this plethora of capability. They do this, however, through high power and low density.
To successfully enable the processing of high-resolution video, designers must include power efficiency as a key design element. Video is one of the most power-intensive of all applications because it must render output that meets quality of service requirements and satisfies the viewer’s expectations. If peak power performance is to be achieved, low-power technologies should be employed. Video applications can meet programmability and low-power requirements through the use of multicore media processors designed to operate in a highly efficient pipeline fashion.
Conclusion
In this part one, the most common video standards have been briefly described. The existence of so many widely used standards is a testament to the dynamic nature of the video coding technology. As the standards evolve in lockstep with the changing demands of the market, so too must the technology evolve. In part two, we’ll address the flexible, multicore, media processor-based approach taken by silicon manufacturers.
About the authors:
Bahman Barazesh is a senior technical manager at LSI Corporation. Bahman came to LSI through the company’s acquisition of Agere Systems in April 2007. Prior to working at Agere, Bahman was an R&D manager at Apple Computer and a project lead at TRT, a leading manufacturer in Voice, Video, and Data Connectivity products.
George J. Kustka is a senior video architect at LSI Corporation. He has been an active pioneer of signal processing for data communications and video compression since he joined Bell Laboratories in 1972. His contributions have included hardware and DSP software for voice-band analog modems, modems for digital access, and broad-band cable transmission. He played an active role in development of HDTV technology and has developed numerous video and audio codecs over the years. He has received 16 patents in data transmission and codec technologies.
Mark Simkins is director of Broadband Strategy for the Network and Storage Products Division of LSI Corporation. Simkins has worked in the communications industry for nearly 20 years in various applications, systems architect and strategic marketing roles. He has been lead system architect on a variety of devices for ISDN, DSL, ATM, multi-service and Carrier Ethernet applications. He has actively participated in various international standards bodies and spoken at numerous conferences. Most recently he has been responsible for the definition of next-generation wireless and wireline access solutions, focusing on traffic management and aggregation devices.
