A biological retina inspired tone mapping processor for high-speed and energy-efficient image enhancement

Xiaoqiang Xiang; Lili Liu; Luying Que; Conghan Jia; Bo Yan; Yongjie Li; Jinhong Guo; Jun Zhou

doi:10.3390/s20195600

A biological retina inspired tone mapping processor for high-speed and energy-efficient image enhancement

Xiaoqiang Xiang, Lili Liu, Luying Que, Conghan Jia, Bo Yan, Yongjie Li, Jinhong Guo, Jun Zhou^*

^*Corresponding author for this work

University of Electronic Science and Technology of China

Research output: Contribution to journal › Letter › peer-review

6 Citations (Scopus)

Abstract

In this work, a biological retina inspired tone mapping processor for high-speed and energy-efficient image enhancement has been proposed. To achieve high throughput and high energy efficiency, several hardware design techniques have been proposed, 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. Implemented on a Xilinx’s Virtex7 FPGA, the proposed design achieves a high throughput of 189 frames per second for 1024 × 768 RGB images while consuming 819 mW. Compared with several state-of-the-art tone mapping processors, the proposed design shows higher throughput and energy efficiency. It is suitable for high-speed and energy-constrained image enhancement applications.

Original language	English
Article number	5600
Pages (from-to)	1-11
Number of pages	11
Journal	Sensors
Volume	20
Issue number	19
DOIs	https://doi.org/10.3390/s20195600
Publication status	Published - 1 Oct 2020
Externally published	Yes

Keywords

Energy-efficient
High throughput
Retina
Tone mapping processor

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.3390/s20195600

Cite this

@article{e7e7d241750f458788f28b7368658e07,

title = "A biological retina inspired tone mapping processor for high-speed and energy-efficient image enhancement",

abstract = "In this work, a biological retina inspired tone mapping processor for high-speed and energy-efficient image enhancement has been proposed. To achieve high throughput and high energy efficiency, several hardware design techniques have been proposed, 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. Implemented on a Xilinx{\textquoteright}s Virtex7 FPGA, the proposed design achieves a high throughput of 189 frames per second for 1024 × 768 RGB images while consuming 819 mW. Compared with several state-of-the-art tone mapping processors, the proposed design shows higher throughput and energy efficiency. It is suitable for high-speed and energy-constrained image enhancement applications.",

keywords = "Energy-efficient, High throughput, Retina, Tone mapping processor",

author = "Xiaoqiang Xiang and Lili Liu and Luying Que and Conghan Jia and Bo Yan and Yongjie Li and Jinhong Guo and Jun Zhou",

note = "Publisher Copyright: {\textcopyright} 2020 by the authors. Licensee MDPI, Basel, Switzerland.",

year = "2020",

month = oct,

day = "1",

doi = "10.3390/s20195600",

language = "English",

volume = "20",

pages = "1--11",

journal = "Sensors",

issn = "1424-8220",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "19",

}

TY - JOUR

T1 - A biological retina inspired tone mapping processor for high-speed and energy-efficient image enhancement

AU - Xiang, Xiaoqiang

AU - Liu, Lili

AU - Que, Luying

AU - Jia, Conghan

AU - Yan, Bo

AU - Li, Yongjie

AU - Guo, Jinhong

AU - Zhou, Jun

PY - 2020/10/1

Y1 - 2020/10/1

N2 - In this work, a biological retina inspired tone mapping processor for high-speed and energy-efficient image enhancement has been proposed. To achieve high throughput and high energy efficiency, several hardware design techniques have been proposed, 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. Implemented on a Xilinx’s Virtex7 FPGA, the proposed design achieves a high throughput of 189 frames per second for 1024 × 768 RGB images while consuming 819 mW. Compared with several state-of-the-art tone mapping processors, the proposed design shows higher throughput and energy efficiency. It is suitable for high-speed and energy-constrained image enhancement applications.

AB - In this work, a biological retina inspired tone mapping processor for high-speed and energy-efficient image enhancement has been proposed. To achieve high throughput and high energy efficiency, several hardware design techniques have been proposed, 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. Implemented on a Xilinx’s Virtex7 FPGA, the proposed design achieves a high throughput of 189 frames per second for 1024 × 768 RGB images while consuming 819 mW. Compared with several state-of-the-art tone mapping processors, the proposed design shows higher throughput and energy efficiency. It is suitable for high-speed and energy-constrained image enhancement applications.

KW - Energy-efficient

KW - High throughput

KW - Retina

KW - Tone mapping processor

UR - http://www.scopus.com/inward/record.url?scp=85091860418&partnerID=8YFLogxK

U2 - 10.3390/s20195600

DO - 10.3390/s20195600

M3 - Letter

C2 - 33007833

AN - SCOPUS:85091860418

SN - 1424-8220

VL - 20

SP - 1

EP - 11

JO - Sensors

JF - Sensors

IS - 19

M1 - 5600

ER -

A biological retina inspired tone mapping processor for high-speed and energy-efficient image enhancement

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this