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 | |
| 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 |
Fingerprint
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
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
}
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
SN - 9781450311991
SP - 579
EP - 584
BT - Proceedings of the 49th Annual Design Automation Conference, DAC '12
ER -