MPEG Video Encoding — Parallelization and Optimal Performance

Metadata

Publisher: SMPTE — White Plains, NY, USA
Doc Type: Journal Article
Content Type: Original Research
Volume: 105, No. 6, pp. 345–350
Abstract: This paper discusses some of the design concerns in parallelizing MPEG for video. A detailed overview of the MPEG algorithm is given (as it pertains to parallelization). Parallelization of macroblocks and groups of pictures (GOPs) are explored in detail. Work is currently under way on implementation of macroblock and GOP parallelization, being performed on both a multiprocessor Sun Sparc and an Intel 32 1860 multiprocessing computer. The results of these studies will be presented at a later time.
Publication Date: 1996-06-01
DOI: 10.5594/J09569
ISSN: Print: 0036-1682
Link: https://doi.org/10.5594/J09569
Author(s): Brian QuandtHeuris/Pulitzer, St. Louis, MO 63103, e-mail: quandt@heuris.com .
bio
Brian Quandt has been working in and around the world of MPEG for several years now. As president of HEURIS/Pulitzer, a joint venture between HEURIS Logic and Pulitzer Broadcasting, he has been responsible for designing and implementing the MPEG encoding system used for their video compression services. He is a contributing member of many of the ISO groups responsible for the MPEG specification, including ISO-IEC/JTC1/SC29/WG11 and WG1 as well as X3L3 2.1, 2.2, and 2.3. In particular, Quandt wrote significant portions of Part 5 of the MPEG-1 specification regarding the software implementation of system encoding. Quandt is a member of many other telecommunications, multimedia, and computer organizations including the ACM, IMA, and SMPTE. Often sought as an expert on the MPEG algorithm, he has written a chapter for a major college textbook on multimedia and presented this paper, on the parallelization of the MPEG algorithm, at the 136th SMPTE Technical Conference and World Media Expo in 1994. In addition, Mr. Quandt gave a brief paper on MPEG and served on a panel at COMDEX-Fall 1994.
Chaman L. SabharwalUniversity of Missouri-Rolla, St. Louis, MO 63121, e-mail: chaman@umr.edu .
bio
Chaman Sabharwal received his B.A. (with honors) and M.S. degrees in mathematics from the Punjab University in Chandigarh, India. He earned his M.S. and Ph.D. in applied mathematics from the University of Illinois, Urbana-Champaign. Currently professor of computer science at the University of Missouri-Rolla, Sabharwal previously served as professor of mathematics and director of undergraduate computer science at St. Louis University. He has also been lead engineer and senior specialist at McDonnell Douglas Corp. Sabharwal has published in the areas of software engineering, feature recognition, robotics, and geometric modeling in various journals, including the SIAM Journal on applied mathematics, computer-aided geometric design, and pattern recognition. Among his research interests are the areas of computer graphics, computer vision, geometric modeling, machine learning, parallel processing, pattern recognition, and robotics. He is a member of ACM and IEEE.
Copyright: © 1996 Society of Motion Picture and Television Engineers, Inc.

Bibliographic Reference(s)

1. ISO/IEC IS 11172 (MPEG-1 standard), available from ANSI, 11 W. 42nd St., New York, NY 10036. EXTERNAL
2. ISO/IEC IS 13818 parts 1–3 (MPEG-2 standard), available from ANSI, 11 W. 42nd St., New York, NY 10036. EXTERNAL
3. Chen W. H. Smith C. H. Fralick S. C. . “A Fast Computational Algorithm for Discrete Cosine Transform.” IEEE Trans. on Communications , COM-25 : 1004 – 1009 , Sept. 1977 . EXTERNAL
4. Schalkoff R. J. , Digital Image Processing and Computer Vision , New York : John Wiley and Sons , 1989 . EXTERNAL
5. Meng T. H-Y Hung A.C. , “Parallel Array Architectures for Motion Estimation,” International Conf. on Application Specific Array Processors, IEEE 1991 . pp. 214 – 235 . EXTERNAL

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/10.5594-J09569.json

Reference Tree

Explore all references and references to this document, as a navigable tree.

Open Reference Tree

Reference this Doc

Plain text (ISO 690 compliant)

Preview:

Brian Quandt and Chaman L. Sabharwal; MPEG Video Encoding — Parallelization and Optimal Performance, SMPTE Journal ( Volume: 105, Issue: 6, June 1996); SMPTE, 1996. Available at https://doi.org/10.5594/J09569

Snippet:

Brian Quandt and Chaman L. Sabharwal; MPEG Video Encoding — Parallelization and Optimal Performance, SMPTE Journal ( Volume: 105, Issue: 6, June 1996); SMPTE, 1996. Available at https://doi.org/10.5594/J09569

HTML (ISO 690 compliant)

Preview:

Snippet:

<span class="citation">Brian Quandt and Chaman L. Sabharwal; <cite>MPEG Video Encoding — Parallelization and Optimal Performance</cite>, SMPTE Journal ( Volume: 105, Issue: 6, June 1996); SMPTE, 1996. Available at <a href="https://doi.org/10.5594/J09569" target="_blank" rel="noopener">https://doi.org/10.5594/J09569</a></span>

SMPTE's HTML Pub

Preview:

Brian Quandt and Chaman L. Sabharwal; MPEG Video Encoding — Parallelization and Optimal Performance, SMPTE Journal ( Volume: 105, Issue: 6, June 1996); SMPTE, 1996
doi: 10.5594/J09569
url: https://doi.org/10.5594/J09569

Snippet:

<li>
Brian Quandt and Chaman L. Sabharwal; <cite id="bib-10-5594-j09569">MPEG Video Encoding — Parallelization and Optimal Performance</cite>, SMPTE Journal ( Volume: 105, Issue: 6, June 1996); SMPTE, 1996
<span class="doi">10.5594/J09569</span>
</li>