FPGA Implementation of a Real-Time Super-Resolution System with a CNN Based on a Residue Number System

被引:0
|
作者
Manabe, Taito [1 ]
Shibata, Yuichiro [1 ]
Oguri, Kiyoshi [1 ]
机构
[1] Nagasaki Univ, Grad Sch Engn, Nagasaki, Japan
来源
2017 INTERNATIONAL CONFERENCE ON FIELD PROGRAMMABLE TECHNOLOGY (ICFPT) | 2017年
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A super-resolution technology is used for filling the gap between high-resolution displays and lower-resolution images. One of various algorithms to interpolate the lost information is to use a convolutional neural network (CNN). This paper shows an FPGA implementation and a performance evaluation of our CNN-based super-resolution system, which can process moving images in real time. We apply horizontal and/or vertical flips to input images instead of pre-enlargement. This method prevents information loss and enables the network to make the best use of its input size. In addition, we adopted the residue number system (RNS) to reduce resource utilization. The proposed system can perform super-resolution from 960x540 to 1920x1080 at 60fps with a latency of less than 1ms. In spite of resource restriction of the FPGA, the system generates clear super-resolution images with smooth edges. The evaluation results also revealed the superior quality in terms of the peak signal-to-noise ratio (PSNR), compared to other systems using pre-enlargement.
引用
收藏
页码:299 / 300
页数:2
相关论文
共 50 条
  • [21] Pseudorandom Number Generator Based on the Residue Number System and its FPGA Implementation
    Arturo Gayoso, Carlos
    Gonzalez, C.
    Arnone, L.
    Rabini, M.
    Castineira Moreira, Jorge
    2013 7TH ARGENTINE SCHOOL OF MICRO-NANOELECTRONICS, TECHNOLOGY AND APPLICATIONS (EAMTA), 2013, : 9 - 14
  • [22] Computationally efficient image restoration and super-resolution algorithms for real-time implementation
    Sundareshan, MK
    INFRARED AND PASSIVE MILLIMETER-WAVE IMAGING SYSTEMS: DESIGN, ANALYSIS, MODELING, AND TESTING, 2002, 4719 : 306 - 317
  • [23] A lightweight distillation recurrent convolution network on FPGA for real-time video super-resolution
    Zheng, Zhaowen
    Huang, Yuqiao
    Chen, Dihu
    MULTIMEDIA SYSTEMS, 2024, 30 (06)
  • [24] A CNN-Based Real-Time Dense Stereo SLAM System on Embedded FPGA
    Huang, Qian
    Zhang, Yu
    Zheng, Jianing
    Shang, Gaoxing
    Chen, Gang
    ARTIFICIAL INTELLIGENCE, CICAI 2023, PT II, 2024, 14474 : 569 - 574
  • [25] FPGA Implementation of Modular Multiplier in Residue Number System
    Kong, Yinan
    Hossain, Md Selim
    2018 IEEE INTERNATIONAL CONFERENCE ON INTERNET OF THINGS AND INTELLIGENCE SYSTEM (IOTAIS), 2018, : 137 - 140
  • [26] A Real-Time QKD System Based on FPGA
    Zhang, Hong-Fei
    Wang, Jian
    Cui, Ke
    Luo, Chun-Li
    Lin, Sheng-Zhao
    Zhou, Lei
    Liang, Hao
    Chen, Teng-Yun
    Chen, Kai
    Pan, Jian-Wei
    JOURNAL OF LIGHTWAVE TECHNOLOGY, 2012, 30 (20) : 3226 - 3234
  • [27] A CNN-Based Super-Resolution Processor With Short-Term Caching for Real-Time UHD Upscaling
    Ahn, Hong Keun
    Lee, Sumin
    Jung, Seong-Ook
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2024, 71 (03) : 1198 - 1207
  • [28] REAL-TIME IMAGE SUPER RESOLUTION USING AN FPGA
    Bowen, Oliver
    Bouganis, Christos-Savvas
    2008 INTERNATIONAL CONFERENCE ON FIELD PROGRAMMABLE AND LOGIC APPLICATIONS, VOLS 1 AND 2, 2008, : 89 - 94
  • [29] REAL-TIME ARCHITECTURE FOR VECTOR QUANTIZATION IN RESIDUE NUMBER SYSTEM
    GOEL, BD
    JAMALI, MM
    KWATRA, SC
    1989 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-3, 1989, : 204 - 207
  • [30] Pure FPGA Implementation of an HOG Based Real-Time Pedestrian Detection System
    Luo, Jian Hua
    Lin, Chang Hong
    SENSORS, 2018, 18 (04)