System-On-Chip for Biologically Inspired Vision Applications

Neuromorphic vision algorithms are biologically-inspired computational models of the primate visual pathway. They promise robustness, high accuracy, and high energy efficiency in advanced image processing applications. Despite these potential benefits, the realization of neuromorphic algorithms typically exhibit low performance even when executed on multi-core CPU and GPU platforms. This is due to the disparity in the computational modalities prominent in these algorithms and those modalities most exploited in contemporary computer architectures. In essence, acceleration of neuromorphic algorithms requires adherence to specific computational and communicational requirements. This paper discusses these requirements and proposes a framework for mapping neuromorphic vision applications on a System-on-Chip, SoC. A neuromorphic object detection and recognition on a multi-FPGA platform is presented with performance and power efficiency comparisons to CMP and GPU implementations.

[1]  E. Newman,et al.  Integration of visual and infrared information in bimodal neurons in the rattlesnake optic tectum. , 1981, Science.

[2]  N. Drasdo.  Eye, brain, and vision David H. Hubel Scientific American Library Book — distributed by W. H. Freeman, New York, £15.95 , 1990 .

[3]  Nikos K Logothetis,et al.  The color-opponent and broad-band channels of the primate visual system , 1990, Trends in Neurosciences.

[4]  William J. Dally,et al.  A bandwidth-efficient architecture for media processing , 1998, Proceedings. 31st Annual ACM/IEEE International Symposium on Microarchitecture.

[5]  Joseph P. Racamato,et al.  Solid-State Color Night Vision: Fusion of Low-Light Visible and Thermal Infrared Imagery , 1998 .

[6]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

[7]  W. Dally,et al.  Route packets, not wires: on-chip interconnection networks , 2001, Proceedings of the 38th Design Automation Conference (IEEE Cat. No.01CH37232).

[8]  Edward A. Lee,et al.  Dataflow process networks , 2001 .

[9]  Axel Jantsch,et al.  A network on chip architecture and design methodology , 2002, Proceedings IEEE Computer Society Annual Symposium on VLSI. New Paradigms for VLSI Systems Design. ISVLSI 2002.

[10]  Lizy Kurian John,et al.  Bottlenecks in Multimedia Processing with SIMD Style Extensions and Architectural Enhancements , 2003, IEEE Trans. Computers.

[11]  S. Grossberg,et al.  Pattern formation, contrast control, and oscillations in the short term memory of shunting on-center off-surround networks , 1975, Biological Cybernetics.

[12]  Gert Cauwenberghs,et al.  Saliency-driven image acuity modulation on a reconfigurable silicon array of spiking neurons , 2004, NIPS 2004.

[13]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[14]  B. Nauta,et al.  Analog circuits in ultra-deep-submicron CMOS , 2005, IEEE Journal of Solid-State Circuits.

[15]  Thomas Serre,et al.  A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex , 2005 .

[16]  David G. Lowe,et al.  University of British Columbia. , 1945, Canadian Medical Association journal.

[17]  William J. Dally,et al.  A Programmable 512 GOPS Stream Processor for Signal, Image, and Video Processing , 2007, IEEE Journal of Solid-State Circuits.

[18]  Thomas Serre,et al.  Robust Object Recognition with Cortex-Like Mechanisms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  John K. Tsotsos,et al.  An Information Theoretic Model of Saliency and Visual Search , 2008, WAPCV.

[20]  Jason Cong,et al.  AutoPilot: A Platform-Based ESL Synthesis System , 2008 .

[21]  Johannes Schemmel,et al.  Wafer-scale integration of analog neural networks , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[22]  Hoi-Jun Yoo,et al.  A 201.4 GOPS 496 mW Real-Time Multi-Object Recognition Processor With Bio-Inspired Neural Perception Engine , 2009, IEEE Journal of Solid-State Circuits.

[23]  Weijia Shang,et al.  ShapeUp: A High-Level Design Approach to Simplify Module Interconnection on FPGAs , 2010, 2010 18th IEEE Annual International Symposium on Field-Programmable Custom Computing Machines.

[24]  Nikil D. Dutt,et al.  Towards reverse engineering the brain: Modeling abstractions and simulation frameworks , 2010, 2010 18th IEEE/IFIP International Conference on VLSI and System-on-Chip.

[25]  Jason Cong,et al.  High-Level Synthesis for FPGAs: From Prototyping to Deployment , 2011, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[26]  Narayanan Vijaykrishnan,et al.  A framework for accelerating neuromorphic-vision algorithms on FPGAs , 2011, 2011 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[27]  Narayanan Vijaykrishnan,et al.  A reconfigurable platform for the design and verification of domain-specific accelerators , 2012, 17th Asia and South Pacific Design Automation Conference.