FPGA-accelerator system for computing biologically inspired feature extraction models

Michael DeBole, Yang Xiao, Chi Li Yu, Ahmed Al Maashri, Matthew Cotter, Chaitali Chakrabarti, Vijaykrishnan Narayanan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Neuromorphic algorithms for computer-based vision may be the next step towards improving the way computers gather and interpret visual information. However, these algorithms typically have high computational demands making them difficult to deploy in embedded environments where power consumption is equally as important as performance. In this paper, we present an embedded implementation of a ventral visual pathway model, HMAX. We describe an embedded FPGA system that implements the model, as well as accelerator engines necessary to ensure adequate performance. The final system is shown to operate within a power budget of 3W while achieving up to 16.5X speedup over a pure embedded processor implementation.

Original languageEnglish
Title of host publicationConference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011
Pages751-755
Number of pages5
DOIs
Publication statusPublished - 2011
Event45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011 - Pacific Grove, CA, United States
Duration: Nov 6 2011Nov 9 2011

Other

Other45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011
CountryUnited States
CityPacific Grove, CA
Period11/6/1111/9/11

Fingerprint

Particle accelerators
Field programmable gate arrays (FPGA)
Feature extraction
Electric power utilization
Engines

Keywords

  • Embedded Hardware
  • FPGA
  • Neuromorphic vision algorithms
  • Signal Processing Hardware

ASJC Scopus subject areas

  • Signal Processing
  • Computer Networks and Communications

Cite this

DeBole, M., Xiao, Y., Yu, C. L., Al Maashri, A., Cotter, M., Chakrabarti, C., & Narayanan, V. (2011). FPGA-accelerator system for computing biologically inspired feature extraction models. In Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011 (pp. 751-755). [6190106] https://doi.org/10.1109/ACSSC.2011.6190106

FPGA-accelerator system for computing biologically inspired feature extraction models. / DeBole, Michael; Xiao, Yang; Yu, Chi Li; Al Maashri, Ahmed; Cotter, Matthew; Chakrabarti, Chaitali; Narayanan, Vijaykrishnan.

Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011. 2011. p. 751-755 6190106.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

DeBole, M, Xiao, Y, Yu, CL, Al Maashri, A, Cotter, M, Chakrabarti, C & Narayanan, V 2011, FPGA-accelerator system for computing biologically inspired feature extraction models. in Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011., 6190106, pp. 751-755, 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011, Pacific Grove, CA, United States, 11/6/11. https://doi.org/10.1109/ACSSC.2011.6190106
DeBole M, Xiao Y, Yu CL, Al Maashri A, Cotter M, Chakrabarti C et al. FPGA-accelerator system for computing biologically inspired feature extraction models. In Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011. 2011. p. 751-755. 6190106 https://doi.org/10.1109/ACSSC.2011.6190106
DeBole, Michael ; Xiao, Yang ; Yu, Chi Li ; Al Maashri, Ahmed ; Cotter, Matthew ; Chakrabarti, Chaitali ; Narayanan, Vijaykrishnan. / FPGA-accelerator system for computing biologically inspired feature extraction models. Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011. 2011. pp. 751-755
@inproceedings{399d571a431147edaacc300ede9471c3,
title = "FPGA-accelerator system for computing biologically inspired feature extraction models",
abstract = "Neuromorphic algorithms for computer-based vision may be the next step towards improving the way computers gather and interpret visual information. However, these algorithms typically have high computational demands making them difficult to deploy in embedded environments where power consumption is equally as important as performance. In this paper, we present an embedded implementation of a ventral visual pathway model, HMAX. We describe an embedded FPGA system that implements the model, as well as accelerator engines necessary to ensure adequate performance. The final system is shown to operate within a power budget of 3W while achieving up to 16.5X speedup over a pure embedded processor implementation.",
keywords = "Embedded Hardware, FPGA, Neuromorphic vision algorithms, Signal Processing Hardware",
author = "Michael DeBole and Yang Xiao and Yu, {Chi Li} and {Al Maashri}, Ahmed and Matthew Cotter and Chaitali Chakrabarti and Vijaykrishnan Narayanan",
year = "2011",
doi = "10.1109/ACSSC.2011.6190106",
language = "English",
isbn = "9781467303231",
pages = "751--755",
booktitle = "Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011",

}

TY - GEN

T1 - FPGA-accelerator system for computing biologically inspired feature extraction models

AU - DeBole, Michael

AU - Xiao, Yang

AU - Yu, Chi Li

AU - Al Maashri, Ahmed

AU - Cotter, Matthew

AU - Chakrabarti, Chaitali

AU - Narayanan, Vijaykrishnan

PY - 2011

Y1 - 2011

N2 - Neuromorphic algorithms for computer-based vision may be the next step towards improving the way computers gather and interpret visual information. However, these algorithms typically have high computational demands making them difficult to deploy in embedded environments where power consumption is equally as important as performance. In this paper, we present an embedded implementation of a ventral visual pathway model, HMAX. We describe an embedded FPGA system that implements the model, as well as accelerator engines necessary to ensure adequate performance. The final system is shown to operate within a power budget of 3W while achieving up to 16.5X speedup over a pure embedded processor implementation.

AB - Neuromorphic algorithms for computer-based vision may be the next step towards improving the way computers gather and interpret visual information. However, these algorithms typically have high computational demands making them difficult to deploy in embedded environments where power consumption is equally as important as performance. In this paper, we present an embedded implementation of a ventral visual pathway model, HMAX. We describe an embedded FPGA system that implements the model, as well as accelerator engines necessary to ensure adequate performance. The final system is shown to operate within a power budget of 3W while achieving up to 16.5X speedup over a pure embedded processor implementation.

KW - Embedded Hardware

KW - FPGA

KW - Neuromorphic vision algorithms

KW - Signal Processing Hardware

UR - http://www.scopus.com/inward/record.url?scp=84861309075&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861309075&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2011.6190106

DO - 10.1109/ACSSC.2011.6190106

M3 - Conference contribution

AN - SCOPUS:84861309075

SN - 9781467303231

SP - 751

EP - 755

BT - Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011

ER -