ECE Colloquium with Ricardo L. de Queiroz
- Starts: 4:00 pm on Wednesday, November 14, 2012
Green Computing for Video Processing With Professor Ricardo L. de Queiroz Universidade de Brasilia IEEE SPS Distinguished Lecturer Refreshments will be served outside Room 339 at 3:45 p.m. Faculty Host: Janusz Konrad Abstract: Computers and information technology are proving themselves as energy-hungry partners in a society with carbon emission issues to be resolved. We will discuss means to reduce energy consumption on a consumer processor for a class of tasks such as video processing. We will approach green computing by setting task parameters in order to minimize energy consumption for a given performance. We will use training and real energy measurements and discuss options in inexact computing. Since video coding is a very computation-intensive, energy-demanding task, we applied the concept to H.264/AVC video coding, showing that one can substantially reduce energy consumption at the expense of a small rate-distortion (RD) performance penalty. In essence, we can do the same task, using exactly the same resources (modern off-the-shelf hardware and software), but with substantial energy savings. About the Speaker: Dr. Ricardo L. de Queiroz received his PhD degree from The University of Texas at Arlington in 1994. He joined the research staff at Xerox Corp. from 1994 to 2002. Since 2004, he has been with Universidade de Brasilia, where he is now a Full Professor in the Computer Science Department. Dr. de Queiroz has published over 150 articles in journals and conferences and contributed chapters to books as well. He also holds 46 issued patents. He is an elected member of the IEEE Signal Processing Society's Multimedia Signal Processing (MMSP) Technical Committee and a former member of other committees and editorial boards. He has been appointed an IEEE Signal Processing Society Distinguished Lecturer for the 2011-2012 term. He also organized many conferences and IEEE chapters. His research interests include image and video compression, multi-rate signal processing, and color imaging.
- Photonics Center, 8 Saint Mary’s St., Room 211