Special issue on architectures and algorithms of high-efficiency video coding (HEVC) standard for real‐time video applications

Abstract

An essential task in relation to multimedia research and development is the availability of a sufficiently large dataset. Many researchers tend to put (or re-direct) efforts into the creation of such corpus individually to carry out research on large-scale datasets. A promising trend of a united web-scale and distributed multimedia coding and data management is thus needed, which would benefit the entire multimedia research community. Much of the development of video communication and processing has been directed toward very high-quality and large-scale media services through high-efficiency video coding (HEVC).

Recently, HEVC has been developed as a new video coding standard, mainly focusing on the coding of ultrahigh definition (UHD) videos, noting that high-resolution and high-quality videos are getting increasingly utilized. HEVC is a draft video compression standard, a successor to H.264/MPEG-4 AVC. Market and user demands for advanced video services with high-quality standards are steadily increasing. UDH has a resolution of 4–8 K (such as 3840 × 2160 and 7680 × 4320), while HD has a resolution of 1920 × 1080. The data rate for UHD is up to 4–16 times more than for HD video. This order of increasing data rate generates additional burden for all types of networks and services. HEVC is meant to meet the new demand in UHD TV which has large resolution, high frame rates and limited bandwidth.

This Special Issue (SI) of the Springer Journal of Real Time Image Processing (JRTIP) entitled “Architectures and Algorithms of High Efficiency Video Coding (HEVC) Standard for Real-Time Video Applications” highlights the latest research results on various signal processing algorithms, architectures and technologies for real-time approaches in ultrahigh definition (UHD) video and streaming services. This SI addresses both theoretical and practical problems along the real-time theme of JRTIP. It includes fast schemes and hardware implementations, as well as software/hardware co-design based on the HEVC standard technology.

The call for papers resulted in 33 submissions. For each submission, at least two reviewers examined its quality, together with the guest editors and editors-in-chief. Finally, 27 papers were selected for this special issue. The selected papers outlined below can be divided broadly into the following themes. The first theme involves fast-mode decisions and motion estimation algorithms to support real-time HEVC encoding systems. Eight papers fall into this theme. The second theme involves fast algorithms for VLSI, GPU and multi-core hardware-based real-time HEVC encoding, and another eight papers fall into this theme. The third theme has 11 papers and consists of real-time video networking and streaming techniques based on the HEVC standard. A summary of the papers is outlined below: