Please use this identifier to cite or link to this item: https://doi.org/10.1109/ACCESS.2020.2968576
Title: Energy-Quality Scalable Memory-Frugal Feature Extraction for Always-On Deep Sub-mW Distributed Vision
Authors: ANASTACIA ALVAREZ
GOPALAKRISHNAN PONNUSAMY 
ALIOTO,MASSIMO BRUNO 
Keywords: Low-power
energy-quality scaling
vision
video processing
Feature extraction
Internet of things
Sensor nodes
Issue Date: 1-Jan-2020
Publisher: IEEE
Citation: ANASTACIA ALVAREZ, GOPALAKRISHNAN PONNUSAMY, ALIOTO,MASSIMO BRUNO (2020-01-01). Energy-Quality Scalable Memory-Frugal Feature Extraction for Always-On Deep Sub-mW Distributed Vision. IEEE Access 8 : 18951-18961. ScholarBank@NUS Repository. https://doi.org/10.1109/ACCESS.2020.2968576
Rights: CC0 1.0 Universal
Abstract: In this work, an energy-quality (EQ) scalable and memory-frugal architecture for video feature extraction is introduced to reduce circuit complexity, power and silicon area. Leveraging on the inherent resiliency of vision against noise and inaccuracies, the proposed approach introduces properly selected EQ tuning knobs to reduce the energy of feature extraction at graceful quality degradation. As opposed to prior art, the proposed architecture enables the adjustment of such knobs, and adapts its cycle-level timing to reduce the amount of computation per frame at lower quality targets. As further benefit, the approach adds opportunities for energy reduction via aggressive voltage scaling. The proposed architecture mitigates the traditionally dominant area/energy of the on-chip memory by reducing the number of pixels stored on chip, introducing memory access reuse and on-the-fly computation. At the same time, EQ tuning preserves the ability to conventionally operate at maximum quality, when required by the task or the visual context. A 0.55 mm2 testchip in 40nm exhibits power down to 82μW at 5fps frame rate (i.e., 33X lower than prior art), while assuring successful object detection at VGA resolution. To the best of the authors’ knowledge, this is the first feature extractor with sub-mW operation and sub-mm2 area, making the proposed approach well suited for tightly power-constrained and low-cost distributed vision systems (e.g., video sensor nodes).
Source Title: IEEE Access
URI: https://scholarbank.nus.edu.sg/handle/10635/189162
ISSN: 2169-3536
DOI: 10.1109/ACCESS.2020.2968576
Rights: CC0 1.0 Universal
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
ENERGY~1.PDF1.74 MBAdobe PDF

OPEN

Post-printView/Download

Page view(s)

17
checked on May 6, 2021

Download(s)

2
checked on May 6, 2021

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons