抄録
Computer vision applications are rapidly gaining popularity in embedded systems, which typically involve a difficult trade-off between vision performance and energy consumption under a constraint of real-time processing throughput. Recently, hardware (FPGA and ASIC-based) implementations have emerged that significantly improve the energy efficiency of vision computation. These implementations, however, often involve intensive memory traffic that retains a significant portion of energy consumption at the system level. To address this issue, we present a lossy embedded compression framework to exploit the trade-off between vision performance and memory traffic for input images. Differential pulse-code modulation-based gradient-oriented quantization is developed as the lossy compression algorithm. We also present its hardware design that supports up to 12-scale 1080p@60fps real-time processing. For histogram of oriented gradient-based deformable part models on VOC2007, the proposed framework achieved a 49.6%-60.5% memory traffic reduction at a detection rate degradation of 0.05%-0.34%. For AlexNet on ImageNet, memory traffic reduction achieved up to 60.8% with less than 0.61% classification rate degradation.
| 元の言語 | English |
|---|---|
| ホスト出版物のタイトル | 2018 IEEE International Symposium on Circuits and Systems, ISCAS 2018 - Proceedings |
| 出版者 | Institute of Electrical and Electronics Engineers Inc. |
| 巻 | 2018-May |
| ISBN（電子版） | 9781538648810 |
| DOI | |
| 出版物ステータス | Published - 2018 4 26 |
| イベント | 2018 IEEE International Symposium on Circuits and Systems, ISCAS 2018 - Florence, Italy 継続期間: 2018 5 27 → 2018 5 30 |
Other
| Other | 2018 IEEE International Symposium on Circuits and Systems, ISCAS 2018 |
|---|---|
| 国 | Italy |
| 市 | Florence |
| 期間 | 18/5/27 → 18/5/30 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
これを引用
Embedded Frame Compression for Energy-Efficient Computer Vision Systems. / Guo, Li; Zhou, Dajiang; Zhou, Jinjia; Kimura, Shinji.
2018 IEEE International Symposium on Circuits and Systems, ISCAS 2018 - Proceedings. 巻 2018-May Institute of Electrical and Electronics Engineers Inc., 2018. 8351483.研究成果: Conference contribution
}
TY - GEN
T1 - Embedded Frame Compression for Energy-Efficient Computer Vision Systems
AU - Guo, Li
AU - Zhou, Dajiang
AU - Zhou, Jinjia
AU - Kimura, Shinji
PY - 2018/4/26
Y1 - 2018/4/26
N2 - Computer vision applications are rapidly gaining popularity in embedded systems, which typically involve a difficult trade-off between vision performance and energy consumption under a constraint of real-time processing throughput. Recently, hardware (FPGA and ASIC-based) implementations have emerged that significantly improve the energy efficiency of vision computation. These implementations, however, often involve intensive memory traffic that retains a significant portion of energy consumption at the system level. To address this issue, we present a lossy embedded compression framework to exploit the trade-off between vision performance and memory traffic for input images. Differential pulse-code modulation-based gradient-oriented quantization is developed as the lossy compression algorithm. We also present its hardware design that supports up to 12-scale 1080p@60fps real-time processing. For histogram of oriented gradient-based deformable part models on VOC2007, the proposed framework achieved a 49.6%-60.5% memory traffic reduction at a detection rate degradation of 0.05%-0.34%. For AlexNet on ImageNet, memory traffic reduction achieved up to 60.8% with less than 0.61% classification rate degradation.
AB - Computer vision applications are rapidly gaining popularity in embedded systems, which typically involve a difficult trade-off between vision performance and energy consumption under a constraint of real-time processing throughput. Recently, hardware (FPGA and ASIC-based) implementations have emerged that significantly improve the energy efficiency of vision computation. These implementations, however, often involve intensive memory traffic that retains a significant portion of energy consumption at the system level. To address this issue, we present a lossy embedded compression framework to exploit the trade-off between vision performance and memory traffic for input images. Differential pulse-code modulation-based gradient-oriented quantization is developed as the lossy compression algorithm. We also present its hardware design that supports up to 12-scale 1080p@60fps real-time processing. For histogram of oriented gradient-based deformable part models on VOC2007, the proposed framework achieved a 49.6%-60.5% memory traffic reduction at a detection rate degradation of 0.05%-0.34%. For AlexNet on ImageNet, memory traffic reduction achieved up to 60.8% with less than 0.61% classification rate degradation.
KW - computer vision
KW - embedded compression
KW - energy-efficient
KW - vision-oriented
UR - http://www.scopus.com/inward/record.url?scp=85051277735&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85051277735&partnerID=8YFLogxK
U2 - 10.1109/ISCAS.2018.8351483
DO - 10.1109/ISCAS.2018.8351483
M3 - Conference contribution
AN - SCOPUS:85051277735
VL - 2018-May
BT - 2018 IEEE International Symposium on Circuits and Systems, ISCAS 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
ER -