Abstract | ||
---|---|---|
This paper proposes an energy-efficient VGA full-frame feature extraction processor design. It is based on the SURF algorithm and makes various algorithmic modifications to improve efficiency and reduce hardware overhead while maintaining extraction performance. Low clock frequency and deep parallelism derived from a one-sample-per-cycle matched-throughput architecture provide significantly larger room for voltage scaling and enables full-frame extraction. The proposed design consumes 4.7mW at 400mV and achieves 72% higher energy efficiency than prior work. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICASSP.2013.6638152 | 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Keywords | Field | DocType |
Feature extraction, Energy-optimal design, SURF | Efficient energy use,Computer science,Voltage,Feature extraction,Processor design,Computer hardware,Scaling,Video Graphics Array,Clock rate,Embedded system | Conference |
ISSN | Citations | PageRank |
1520-6149 | 0 | 0.34 |
References | Authors | |
7 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dongsuk Jeon | 1 | 183 | 21.01 |
Yejoong Kim | 2 | 276 | 31.29 |
Inhee Lee | 3 | 275 | 33.89 |
Zhengya Zhang | 4 | 502 | 48.41 |
David Blaauw | 5 | 8916 | 823.47 |
Dennis Sylvester | 6 | 5295 | 535.53 |