GPU-Based MPEG-2 to Secure Scalable Video Transcoding

GPU-Based MPEG-2 to Secure Scalable Video Transcoding

Yueyun Shang, Dengpan Ye, Zhuo Wei, Yajuan Xie
Copyright: © 2014 |Pages: 18
DOI: 10.4018/ijdcf.2014040104
(Individual Articles)
No Current Special Offers


Most of the high definition video content are still produced in a single-layer MPEG-2 format. Multiple-layers Scalable Video Coding (SVC) offers a minor penalty in rate-distortion efficiency when compared to single-layer coding MPEG-2. A scaled version of the original SVC bitstream can easily be extracted by dropping layers from the bitstream. This paper proposes a parallel transcoder from MPEG-2 to SVC video with Graphics Processing Unit (GPU), named PTSVC. The objective of the transcoder is to migrate MPEG-2 format video to SVC format video such that clients with different network bandwidth and terminal devices can seamlessly access video content. Meanwhile, the transcoded SVC videos are encrypted such that only authorized users can access corresponding SVC layers. Using various scalabilities SVC test sequences, experimental results on TM5 and JSVM indicate that PTSVC is a higher efficient transcoding system compared with previous systems and only causes little quality loss.
Article Preview


MPEG-2 (ITU-T, 2009) format is used for the standard of High-definition TV compression. High-definition refers to video having resolution substantially higher than traditional television systems (standard-definition TV). H.264/SVC (Scalable Video Coding) (H. Schwarz et al., 2007) supports the same video quality with more effective compression. It can be suitable for different network conditions and various terminal devices by adapting quality, spatial or temporal enhancement layers.

The drawback of MPEG-2 is that it is usually accepted by powerful and high-resolution devices, and only translated under high speed network bandwidth. One approach to making use of the existing MPEG-2 video for different users with various devices and networks is transcode it to an SVC bitstream.

In order to make existing MPEG-2 High-definition data to be widely served to various authorized clients, e.g., previewing or VOD (Video on Demand), the transcoding from MPEG-2 bitstreams to secure H.264/SVC bitstreams can satisfy the application requirements. For example, the TeleOph system in (Y. D. Wu, Z. Wei, H. X. Yao, Z. G. Zhao, N. L. Heng, R. H. Deng & S. S. Yu, (2010)) captures MPEG-2 video from HD cameras of clinics and send video to hospitals, then hospital ophthalmologists can provide consultation for patients. However, since TeleOph system must work at high-speed network condition, it cannot supply widely services for remote patients. The basic transcoding technique is the cascaded transcoding. Since the cascaded transcoding consists a full decoder and a full encoder, it is low efficient. Hence, researchers have been working on transcoding techniques and have proposed several transcoding schemes, e.g., homogeneous and heterogeneous transcoding systems. The former is done in the same or similar coding standards, e.g., (J. Nakajima, et al., 2001; A. Vetro et al., 2002; R. G. Cantos & J. D. Cock, 2011). The latter is used to perform format conversion between different compression standards (e.g., W-C. Siu et al., 2007; Y-K. Lee et al., 2006; Y. Su et al., 2005). Although there are lots of heterogeneous transcoding schemes, they must be high computation cost or unfeasible if we directly apply those transcoding schemes for HD data (i.e., MPEG-2) to H.264/SVC bitstreams. The reasons are: i) HD data contains the huge digital information, traditional transcoding systems generally produce high computation complexity because they seldom consider parallel processing; ii) Because desired H.264/SVC bitstreams contain not only base layer but also several enhancement layers, transcoding systems have to encode all of them; iii) Normally, HD data can be only accessed by authorized users, i.e., previewing of base layer, hence transcoded H.264/SVC bitstreams should be protected. In this article, since MPEG-2 and H.264/SVC are generally based on block or macroblock of images as coding units, transcoding of macroblocks can be simultaneously operated, we propose a GPU-based transcoding scheme for MPEG-2 to secure H.264/SVC, named PTSVC. PTSVC consists of parallel Intra transcoding (PIntra) and parallel Inter transcoding (PInter) techniques. Moreover, due to the scalable requirements of H.264/SVC bitstreams, H.264/SVC bitstreams may contain quality and spatial scalabilities, PTSVC further exploits parallel characteristics of GPU architecture to encode quality and spatial enhancement layers for H.264/SVC bitstreams. At last, PTSVC encrypts the transcoded H.264/SVC bitstreams by integrating access control into transcoding processes. Our experimental results on HD test sequences indicate that PTSVC is efficient and causes less bitrate loss.

The reminder of this paper is organized as follows. Section “RELATED WORKS” is about access control jobs and Section “OVERVIEW OF H.264/SVC STANDARD” gives a brief introduction of H.264/SVC standard. GPU-based transcoding and access control techniques are explained in Section “GPU-BASED TRANSCODING”. Section “EXPERIMENTS AND SECURITY EVALUATION” shows the experimental results and security evaluation, respectively. Last, we draws conclusion and future works.

Complete Article List

Search this Journal:
Volume 15: 1 Issue (2023)
Volume 14: 3 Issues (2022)
Volume 13: 6 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing