Adaptive Techniques for Energy-Efficient Video Processing
CPCC Talk
Featuring:
Vasily Moshnyaga
Abstract:
The recent explosive growth of portable applications, such as video phones, PDA, digital video cameras, etc., has elevated needs for low-energy video processing hardware and software. This talk will introduce new algorithmic and architectural techniques which can significantly shrink the energy consumption of video coding and decoding tasks. Unlike traditional methods, the techniques exploit picture correlation and input statistics to dynamically adjust the number of operations, memory accesses, operational bit-width and supply voltage to varying picture content. Applications to motion estimation, discrete cosine transform and memory access optimization will be presented. Practical issues and open problems will be outlined.
Biography:
Vasily Moshnyaga received Computer Engineering Degree with Honors from
Dr. Moshnyaga is a member of organizing committees of the Asia-Pacific Design Automation Conference, Asia Pacific Conference on Chip Design Languages, and a technical program committee member of several conferences including IEEE International Symposium on Circuits and Systems, ACM/IEE International Symposium on Low-Power Electronics and Design, IEEE System on Chip Conference, etc. He is an Associate Editor of the IEICE Transactions on Fundamentals of Electronics, Communication and Computer Sciences. Dr. Moshnyaga is a senior member of IEEE, Computer System Society and Circuits and System Society, a member of Information Processing Society of Japan, and Engineering Sciences Society of Japan.
Share
Upcoming Events
-
MSE 298 Seminar: Improving Coherence In Superconducting Qubits For Quantum Computing
-
EECS Seminar: Evaluating Generative AI in Healthcare
-
MAE 298 Seminar: Data Science Tools for Studying Laser-Induced Ignition in a Rocket Combustor
-
CBE 298 Seminar: Synergistic Effects in Oxygen Evolution catalysis – in-situ X-ray based approaches
-
CEE Seminar: Machine Learning and Neural Networks for Porous Media and Materials - From Fluid Flow, Transport and Deformation to Learning the Governing Equations for Datasets