Accelerating neuromorphic vision algorithms for recognition

Ahmed Al Maashri; Michael DeBole; Matthew Cotter; Nandhini Chandramoorthy; Yang Xiao; Vijaykrishnan Narayanan; Chaitali Chakrabarti

doi:10.1145/2228360.2228465

Accelerating neuromorphic vision algorithms for recognition

Ahmed Al Maashri^*, Michael DeBole, Matthew Cotter, Nandhini Chandramoorthy, Yang Xiao, Vijaykrishnan Narayanan, Chaitali Chakrabarti

^*Corresponding author for this work

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

39 Citations (Scopus)

Abstract

Video analytics introduce new levels of intelligence to automated scene understanding. Neuromorphic algorithms, such as HMAX, are proposed as robust and accurate algorithms that mimic the processing in the visual cortex of the brain. HMAX, for instance, is a versatile algorithm that can be repurposed to target several visual recognition applications. This paper presents the design and evaluation of hardware accelerators for extracting visual features for universal recognition. The recognition applications include object recognition, face identification, facial expression recognition, and action recognition. These accelerators were validated on a multi-FPGA platform and significant performance enhancement and power efficiencies were demonstrated when compared to CMP and GPU platforms. Results demonstrate as much as 7.6X speedup and 12.8X more power-efficient performance when compared to those platforms.

Original language	English
Title of host publication	Proceedings of the 49th Annual Design Automation Conference, DAC '12
Pages	579-584
Number of pages	6
DOIs	https://doi.org/10.1145/2228360.2228465
Publication status	Published - 2012
Event	49th Annual Design Automation Conference, DAC '12 - San Francisco, CA, United States Duration: Jun 3 2012 → Jun 7 2012

Other

Other	49th Annual Design Automation Conference, DAC '12
Country	United States
City	San Francisco, CA
Period	6/3/12 → 6/7/12

Keywords

domain-specific acceleration
heterogeneous system
power efficiency
recognition

ASJC Scopus subject areas

Computer Science Applications
Control and Systems Engineering
Electrical and Electronic Engineering
Modelling and Simulation

Access to Document

10.1145/2228360.2228465

Fingerprint Dive into the research topics of 'Accelerating neuromorphic vision algorithms for recognition'. Together they form a unique fingerprint.

Cite this

Accelerating neuromorphic vision algorithms for recognition. / Al Maashri, Ahmed; DeBole, Michael; Cotter, Matthew; Chandramoorthy, Nandhini; Xiao, Yang; Narayanan, Vijaykrishnan; Chakrabarti, Chaitali.

Proceedings of the 49th Annual Design Automation Conference, DAC '12. 2012. p. 579-584.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Al Maashri, A, DeBole, M, Cotter, M, Chandramoorthy, N, Xiao, Y, Narayanan, V & Chakrabarti, C 2012, Accelerating neuromorphic vision algorithms for recognition. in Proceedings of the 49th Annual Design Automation Conference, DAC '12. pp. 579-584, 49th Annual Design Automation Conference, DAC '12, San Francisco, CA, United States, 6/3/12. https://doi.org/10.1145/2228360.2228465

@inproceedings{9976334f656b4b018a31a3b7bcbb026e,

title = "Accelerating neuromorphic vision algorithms for recognition",

abstract = "Video analytics introduce new levels of intelligence to automated scene understanding. Neuromorphic algorithms, such as HMAX, are proposed as robust and accurate algorithms that mimic the processing in the visual cortex of the brain. HMAX, for instance, is a versatile algorithm that can be repurposed to target several visual recognition applications. This paper presents the design and evaluation of hardware accelerators for extracting visual features for universal recognition. The recognition applications include object recognition, face identification, facial expression recognition, and action recognition. These accelerators were validated on a multi-FPGA platform and significant performance enhancement and power efficiencies were demonstrated when compared to CMP and GPU platforms. Results demonstrate as much as 7.6X speedup and 12.8X more power-efficient performance when compared to those platforms.",

keywords = "domain-specific acceleration, heterogeneous system, power efficiency, recognition",

author = "{Al Maashri}, Ahmed and Michael DeBole and Matthew Cotter and Nandhini Chandramoorthy and Yang Xiao and Vijaykrishnan Narayanan and Chaitali Chakrabarti",

year = "2012",

doi = "10.1145/2228360.2228465",

language = "English",

isbn = "9781450311991",

pages = "579--584",

booktitle = "Proceedings of the 49th Annual Design Automation Conference, DAC '12",

note = "49th Annual Design Automation Conference, DAC '12 ; Conference date: 03-06-2012 Through 07-06-2012",

}

TY - GEN

T1 - Accelerating neuromorphic vision algorithms for recognition

AU - Al Maashri, Ahmed

AU - DeBole, Michael

AU - Cotter, Matthew

AU - Chandramoorthy, Nandhini

AU - Xiao, Yang

AU - Narayanan, Vijaykrishnan

AU - Chakrabarti, Chaitali

PY - 2012

Y1 - 2012

N2 - Video analytics introduce new levels of intelligence to automated scene understanding. Neuromorphic algorithms, such as HMAX, are proposed as robust and accurate algorithms that mimic the processing in the visual cortex of the brain. HMAX, for instance, is a versatile algorithm that can be repurposed to target several visual recognition applications. This paper presents the design and evaluation of hardware accelerators for extracting visual features for universal recognition. The recognition applications include object recognition, face identification, facial expression recognition, and action recognition. These accelerators were validated on a multi-FPGA platform and significant performance enhancement and power efficiencies were demonstrated when compared to CMP and GPU platforms. Results demonstrate as much as 7.6X speedup and 12.8X more power-efficient performance when compared to those platforms.

AB - Video analytics introduce new levels of intelligence to automated scene understanding. Neuromorphic algorithms, such as HMAX, are proposed as robust and accurate algorithms that mimic the processing in the visual cortex of the brain. HMAX, for instance, is a versatile algorithm that can be repurposed to target several visual recognition applications. This paper presents the design and evaluation of hardware accelerators for extracting visual features for universal recognition. The recognition applications include object recognition, face identification, facial expression recognition, and action recognition. These accelerators were validated on a multi-FPGA platform and significant performance enhancement and power efficiencies were demonstrated when compared to CMP and GPU platforms. Results demonstrate as much as 7.6X speedup and 12.8X more power-efficient performance when compared to those platforms.

KW - domain-specific acceleration

KW - heterogeneous system

KW - power efficiency

KW - recognition

UR - http://www.scopus.com/inward/record.url?scp=84863551827&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863551827&partnerID=8YFLogxK

U2 - 10.1145/2228360.2228465

DO - 10.1145/2228360.2228465

M3 - Conference contribution

AN - SCOPUS:84863551827

SN - 9781450311991

SP - 579

EP - 584

BT - Proceedings of the 49th Annual Design Automation Conference, DAC '12

T2 - 49th Annual Design Automation Conference, DAC '12

Y2 - 3 June 2012 through 7 June 2012

ER -

Accelerating neuromorphic vision algorithms for recognition

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this