Abstract:
In this talk, I present a design platform along with associated design automation tools to facilitate the development of hardware accelerated biologically inspired vision systems. First, I will focus on the communication architecture required to support streaming data computations in vision applications.  Second, I present the computational primitives that mimic the operations of various stages of the visual cortex.  Third, I will present design automation tools that are key enablers towards composing communication and computation primitives into a System-on-Chip, SoC. These automation tools provide the ability to experiment with various model perturbations and parameter variations. This allows computational neuroscientists and computer vision experts to explore various models of neuromorphic vision and quickly develop working systems that process live imagery. Finally, I will present several customized accelerators that implement various stages of the visual cortex, giving support to object detection and recognition applications. Our results indicate that domain-specific accelerators offer a promising approach to bridging the efficiency gap between digital hardware vision systems and the mammalian visual cortex.

Bio:
Kevin Irick received the PhD degree in Computer Science and Engineering from The Pennsylvania State University in 2009. Currently, he is a Research Associate in the Microsystems Design Lab in the Department of Computer Science and Engineering at Penn State. Recently, Irick led a team of four graduate students and two post-doctorates in the Neovision II program, which focused on utilizing domain specific hardware accelerators to realize bio-inspired vision systems. His research interests include application-specific hardware accelerator design methodology, hardware-assisted image processing and recognition, and high-performance computing on reconfigurable architectures.

Organized by the ISTC-EC Seminar Committee
Priya Narasimhan, Carnegie Mellon (Co-Chair)
Jeff Parkhurst, Intel Labs (Co-Chair)
Ahmed Al Maashri, Penn State University
John Schulman, University of California Berkeley
Glenn Ko, University of Illinois Urbana-Champaign
Minsung Jang, Georgia Institute of Technology
Ketan Bhardwaj, Georgia Institute of Technology
Kunal Mankodiya, Carnegie Mellon University
Jennifer Gabig, Carnegie Mellon University
Katerina Fragkiadaki, University of Pennsylvania
Yuan Tian, Cornell University