Hardware acceleration for neuromorphic vision algorithms

Ahmed Al Maashri, Matthew Cotter, Nandhini Chandramoorthy, Michael DeBole, Chi Li Yu, Vijaykrishnan Narayanan, Chaitali Chakrabarti

Research output: Contribution to journalArticle

4 Citations (Scopus)

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× (2.6×) more power efficient when compared to CPU (GPU) implementation.

Original languageEnglish (US)
Pages (from-to)163-175
Number of pages13
JournalJournal of Signal Processing Systems
Volume70
Issue number2
DOIs
StatePublished - Feb 1 2013

Fingerprint

Hardware Acceleration
Particle accelerators
Visual Cortex
Accelerator
Hardware
Object recognition
Program processors
Field programmable gate arrays (FPGA)
Object Recognition
Vision System
Field Programmable Gate Array
Processing
Robustness
Model
Vision
Primates
Graphics processing unit

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Signal Processing
  • Information Systems
  • Modeling and Simulation
  • Hardware and Architecture

Cite this

Al Maashri, A., Cotter, M., Chandramoorthy, N., DeBole, M., Yu, C. L., Narayanan, V., & Chakrabarti, C. (2013). Hardware acceleration for neuromorphic vision algorithms. Journal of Signal Processing Systems, 70(2), 163-175. https://doi.org/10.1007/s11265-012-0699-x
Al Maashri, Ahmed ; Cotter, Matthew ; Chandramoorthy, Nandhini ; DeBole, Michael ; Yu, Chi Li ; Narayanan, Vijaykrishnan ; Chakrabarti, Chaitali. / Hardware acceleration for neuromorphic vision algorithms. In: Journal of Signal Processing Systems. 2013 ; Vol. 70, No. 2. pp. 163-175.
@article{f85ed29eb05440738e6e11cd5870101a,
title = "Hardware acceleration for neuromorphic vision algorithms",
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× (2.6×) more power efficient when compared to CPU (GPU) implementation.",
author = "{Al Maashri}, Ahmed and Matthew Cotter and Nandhini Chandramoorthy and Michael DeBole and Yu, {Chi Li} and Vijaykrishnan Narayanan and Chaitali Chakrabarti",
year = "2013",
month = "2",
day = "1",
doi = "10.1007/s11265-012-0699-x",
language = "English (US)",
volume = "70",
pages = "163--175",
journal = "Journal of Signal Processing Systems",
issn = "1939-8018",
publisher = "Springer New York",
number = "2",

}

Al Maashri, A, Cotter, M, Chandramoorthy, N, DeBole, M, Yu, CL, Narayanan, V & Chakrabarti, C 2013, 'Hardware acceleration for neuromorphic vision algorithms', Journal of Signal Processing Systems, vol. 70, no. 2, pp. 163-175. https://doi.org/10.1007/s11265-012-0699-x

Hardware acceleration for neuromorphic vision algorithms. / Al Maashri, Ahmed; Cotter, Matthew; Chandramoorthy, Nandhini; DeBole, Michael; Yu, Chi Li; Narayanan, Vijaykrishnan; Chakrabarti, Chaitali.

In: Journal of Signal Processing Systems, Vol. 70, No. 2, 01.02.2013, p. 163-175.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Hardware acceleration for neuromorphic vision algorithms

AU - Al Maashri, Ahmed

AU - Cotter, Matthew

AU - Chandramoorthy, Nandhini

AU - DeBole, Michael

AU - Yu, Chi Li

AU - Narayanan, Vijaykrishnan

AU - Chakrabarti, Chaitali

PY - 2013/2/1

Y1 - 2013/2/1

N2 - 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× (2.6×) more power efficient when compared to CPU (GPU) implementation.

AB - 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× (2.6×) more power efficient when compared to CPU (GPU) implementation.

UR - http://www.scopus.com/inward/record.url?scp=84892810283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892810283&partnerID=8YFLogxK

U2 - 10.1007/s11265-012-0699-x

DO - 10.1007/s11265-012-0699-x

M3 - Article

VL - 70

SP - 163

EP - 175

JO - Journal of Signal Processing Systems

JF - Journal of Signal Processing Systems

SN - 1939-8018

IS - 2

ER -