Hardware Acceleration for Neuromorphic Vision Algorithms

Authors:
Ahmed Al Maashri;Matthew Cotter;Nandhini Chandramoorthy;Michael Debole;Chi-Li Yu;Vijaykrishnan Narayanan;Chaitali Chakrabarti
Affiliations:
Microsystems Design Laboratory, The Pennsylvania State University, University Park, USA;Microsystems Design Laboratory, The Pennsylvania State University, University Park, USA;Microsystems Design Laboratory, The Pennsylvania State University, University Park, USA;IBM Systems and Technology Group, Poughkeepsie, USA;School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, USA;Microsystems Design Laboratory, The Pennsylvania State University, University Park, USA;School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, USA
Venue:
Journal of Signal Processing Systems
Year:
2013

Citing 6
Cited 0

Robust Object Recognition with Cortex-Like Mechanisms

IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer Vision on Mars

International Journal of Computer Vision
Object Class Recognition and Localization Using Sparse Features with Limited Receptive Fields

International Journal of Computer Vision
CogniServe: Heterogeneous Server Architecture for Large-Scale Recognition

IEEE Micro
3D recursive Gaussian IIR on GPU and FPGAs -- A case for accelerating bandwidth-bounded applications

SASP '11 Proceedings of the 2011 IEEE 9th Symposium on Application Specific Processors
Accelerating neuromorphic vision algorithms for recognition

Proceedings of the 49th Annual Design Automation Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

Neuromorphic vision algorithms are biologically inspired models that follow the processing that takes place in the primate visual cortex. Despite their efficiency and robustness, the complexity of these algorithms results in reduced performance when executed on general purpose processors. This paper proposes an application-specific system for accelerating a neuromorphic vision system for object recognition. The system is based on HMAX, a biologically-inspired model of the visual cortex. The neuromorphic accelerators are validated on a multi-FPGA system. Results show that the neuromorphic accelerators are 13.8脳 (2.6脳) more power efficient when compared to CPU (GPU) implementation.