A High throughput and energy-efficient retina-inspired tone mapping processor

Lili Liu; Xiaoqiang Xiang; Yuxiang Xie; Yongjie Li; Bo Yan; Jun Zhou

doi:10.1109/FCCM.2019.00062

A High throughput and energy-efficient retina-inspired tone mapping processor

Lili Liu
, Xiaoqiang Xiang
, Yuxiang Xie
, Yongjie Li
, Bo Yan
, Jun Zhou^*

^*此作品的通讯作者

University of Electronic Science and Technology of China

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

3 引用（Scopus）

摘要

This paper presents a high throughput and energy-efficient retina inspired tone mapping processor. Several hardware design techniques have been proposed to achieve high throughput and high energy efficiency, including data partition based parallel processing with S-shape sliding, adjacent frame feature sharing, multi-layer convolution pipelining and convolution filter compression with zero skipping convolution. The proposed processor has been implemented on a Xilinx's Virtex7 FPGA for demonstration. It is able to achieve a throughput of 189 frames per second for 1024∗768 RGB images with 819 mW. Compared with several state-of-The-Art tone mapping processors, the proposed processor achieves higher throughput and energy efficiency. It is suitable for high-speed and energy-constrained video enhancement applications such as autonomous vehicle and drone monitoring.

源语言	英语
主期刊名	Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019
出版商	Institute of Electrical and Electronics Engineers Inc.
页	321
页数	1
ISBN（电子版）	9781728111315
DOI	https://doi.org/10.1109/FCCM.2019.00062
出版状态	已出版 - 4月 2019
已对外发布	是
活动	27th Annual IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019 - San Diego, 美国期限: 28 4月 2019 → 1 5月 2019

出版系列

姓名	Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019

会议

会议	27th Annual IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019
国家/地区	美国
市	San Diego
时期	28/04/19 → 1/05/19

联合国可持续发展目标

此成果有助于实现下列可持续发展目标：

可持续发展目标 7 经济适用的清洁能源

访问文件

10.1109/FCCM.2019.00062

其它文件与链接

链接到 Scopus 的出版物

引用此

Liu, L., Xiang, X., Xie, Y., Li, Y., Yan, B., & Zhou, J. (2019). A High throughput and energy-efficient retina-inspired tone mapping processor. 在 Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019 (页码 321). 文章 8735569 (Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FCCM.2019.00062

Liu, Lili ; Xiang, Xiaoqiang ; Xie, Yuxiang 等. / A High throughput and energy-efficient retina-inspired tone mapping processor. Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 页码 321 (Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019).

@inproceedings{19242c71085c4e55976c5e1abf8c793b,

title = "A High throughput and energy-efficient retina-inspired tone mapping processor",

abstract = "This paper presents a high throughput and energy-efficient retina inspired tone mapping processor. Several hardware design techniques have been proposed to achieve high throughput and high energy efficiency, including data partition based parallel processing with S-shape sliding, adjacent frame feature sharing, multi-layer convolution pipelining and convolution filter compression with zero skipping convolution. The proposed processor has been implemented on a Xilinx's Virtex7 FPGA for demonstration. It is able to achieve a throughput of 189 frames per second for 1024∗768 RGB images with 819 mW. Compared with several state-of-The-Art tone mapping processors, the proposed processor achieves higher throughput and energy efficiency. It is suitable for high-speed and energy-constrained video enhancement applications such as autonomous vehicle and drone monitoring.",

keywords = "Energy Efficient, Retina Inspired, Tone Mapping Processor",

author = "Lili Liu and Xiaoqiang Xiang and Yuxiang Xie and Yongjie Li and Bo Yan and Jun Zhou",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 27th Annual IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019 ; Conference date: 28-04-2019 Through 01-05-2019",

year = "2019",

month = apr,

doi = "10.1109/FCCM.2019.00062",

language = "English",

series = "Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "321",

booktitle = "Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019",

address = "United States",

}

Liu, L, Xiang, X, Xie, Y, Li, Y, Yan, B & Zhou, J 2019, A High throughput and energy-efficient retina-inspired tone mapping processor. 在 Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019., 8735569, Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019, Institute of Electrical and Electronics Engineers Inc., 页码 321, 27th Annual IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019, San Diego, 美国, 28/04/19. https://doi.org/10.1109/FCCM.2019.00062

A High throughput and energy-efficient retina-inspired tone mapping processor. / Liu, Lili; Xiang, Xiaoqiang; Xie, Yuxiang 等.
Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 页码 321 8735569 (Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - A High throughput and energy-efficient retina-inspired tone mapping processor

AU - Liu, Lili

AU - Xiang, Xiaoqiang

AU - Xie, Yuxiang

AU - Li, Yongjie

AU - Yan, Bo

AU - Zhou, Jun

PY - 2019/4

Y1 - 2019/4

N2 - This paper presents a high throughput and energy-efficient retina inspired tone mapping processor. Several hardware design techniques have been proposed to achieve high throughput and high energy efficiency, including data partition based parallel processing with S-shape sliding, adjacent frame feature sharing, multi-layer convolution pipelining and convolution filter compression with zero skipping convolution. The proposed processor has been implemented on a Xilinx's Virtex7 FPGA for demonstration. It is able to achieve a throughput of 189 frames per second for 1024∗768 RGB images with 819 mW. Compared with several state-of-The-Art tone mapping processors, the proposed processor achieves higher throughput and energy efficiency. It is suitable for high-speed and energy-constrained video enhancement applications such as autonomous vehicle and drone monitoring.

AB - This paper presents a high throughput and energy-efficient retina inspired tone mapping processor. Several hardware design techniques have been proposed to achieve high throughput and high energy efficiency, including data partition based parallel processing with S-shape sliding, adjacent frame feature sharing, multi-layer convolution pipelining and convolution filter compression with zero skipping convolution. The proposed processor has been implemented on a Xilinx's Virtex7 FPGA for demonstration. It is able to achieve a throughput of 189 frames per second for 1024∗768 RGB images with 819 mW. Compared with several state-of-The-Art tone mapping processors, the proposed processor achieves higher throughput and energy efficiency. It is suitable for high-speed and energy-constrained video enhancement applications such as autonomous vehicle and drone monitoring.

KW - Energy Efficient

KW - Retina Inspired

KW - Tone Mapping Processor

UR - https://www.scopus.com/pages/publications/85068351221

U2 - 10.1109/FCCM.2019.00062

DO - 10.1109/FCCM.2019.00062

M3 - Conference contribution

AN - SCOPUS:85068351221

T3 - Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019

SP - 321

BT - Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 27th Annual IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019

Y2 - 28 April 2019 through 1 May 2019

ER -

Liu L, Xiang X, Xie Y, Li Y, Yan B, Zhou J. A High throughput and energy-efficient retina-inspired tone mapping processor. 在 Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 页码 321. 8735569. (Proceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019). doi: 10.1109/FCCM.2019.00062

A High throughput and energy-efficient retina-inspired tone mapping processor

摘要

出版系列

会议

联合国可持续发展目标

访问文件

其它文件与链接

指纹

引用此