The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
초고해상도 기술은 고해상도 디스플레이와 저해상도 이미지 사이의 격차를 메우는 솔루션 중 하나이다. 손실된 정보를 보간하는 알고리즘은 다양하며, 그 중 하나가 CNN(Convolutional Neural Network)을 사용하는 것입니다. 본 논문에서는 동영상을 실시간으로 처리할 수 있는 새로운 CNN 기반 초해상도 시스템의 FPGA 구현 및 성능 평가를 보여줍니다. 입력 이미지에 확대 대신 수평 및 수직 뒤집기를 적용합니다. 이 뒤집기 방법은 정보 손실을 방지하고 네트워크가 패치 크기를 최대한 활용할 수 있도록 합니다. 또한 FPGA 자원 활용도를 줄이기 위해 네트워크에 잔여수 시스템(RNS)을 채택했습니다. LUT를 통한 효율적인 곱셈 및 덧셈은 고정 소수점 연산을 사용한 구현에 비해 동일한 FPGA에서 구현할 수 있는 네트워크 규모를 약 54% 증가시켰습니다. 제안된 시스템은 960ms 미만의 지연 시간으로 540fps에서 1920×1080부터 60×1까지의 초해상도를 수행할 수 있습니다. FPGA의 리소스 제한에도 불구하고 시스템은 가장자리가 부드러운 선명한 초해상도 이미지를 생성할 수 있습니다. 평가 결과, 피크 신호 대 잡음비(PSNR), 구조적 유사성(SSIM) 지수 측면에서도 다른 방식을 적용한 시스템에 비해 우수한 품질을 나타냈다.
Taito MANABE
Nagasaki University
Yuichiro SHIBATA
Nagasaki University
Kiyoshi OGURI
Nagasaki University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Taito MANABE, Yuichiro SHIBATA, Kiyoshi OGURI, "FPGA Implementation of a Real-Time Super-Resolution System Using Flips and an RNS-Based CNN" in IEICE TRANSACTIONS on Fundamentals,
vol. E101-A, no. 12, pp. 2280-2289, December 2018, doi: 10.1587/transfun.E101.A.2280.
Abstract: The super-resolution technology is one of the solutions to fill the gap between high-resolution displays and lower-resolution images. There are various algorithms to interpolate the lost information, one of which is using a convolutional neural network (CNN). This paper shows an FPGA implementation and a performance evaluation of a novel CNN-based super-resolution system, which can process moving images in real time. We apply horizontal and vertical flips to input images instead of enlargement. This flip method prevents information loss and enables the network to make the best use of its patch size. In addition, we adopted the residue number system (RNS) in the network to reduce FPGA resource utilization. Efficient multiplication and addition with LUTs increased a network scale that can be implemented on the same FPGA by approximately 54% compared to an implementation with fixed-point operations. The proposed system can perform super-resolution from 960×540 to 1920×1080 at 60fps with a latency of less than 1ms. Despite resource restriction of the FPGA, the system can generate 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) and the structural similarity (SSIM) index, compared to systems with other methods.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E101.A.2280/_p
부
@ARTICLE{e101-a_12_2280,
author={Taito MANABE, Yuichiro SHIBATA, Kiyoshi OGURI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={FPGA Implementation of a Real-Time Super-Resolution System Using Flips and an RNS-Based CNN},
year={2018},
volume={E101-A},
number={12},
pages={2280-2289},
abstract={The super-resolution technology is one of the solutions to fill the gap between high-resolution displays and lower-resolution images. There are various algorithms to interpolate the lost information, one of which is using a convolutional neural network (CNN). This paper shows an FPGA implementation and a performance evaluation of a novel CNN-based super-resolution system, which can process moving images in real time. We apply horizontal and vertical flips to input images instead of enlargement. This flip method prevents information loss and enables the network to make the best use of its patch size. In addition, we adopted the residue number system (RNS) in the network to reduce FPGA resource utilization. Efficient multiplication and addition with LUTs increased a network scale that can be implemented on the same FPGA by approximately 54% compared to an implementation with fixed-point operations. The proposed system can perform super-resolution from 960×540 to 1920×1080 at 60fps with a latency of less than 1ms. Despite resource restriction of the FPGA, the system can generate 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) and the structural similarity (SSIM) index, compared to systems with other methods.},
keywords={},
doi={10.1587/transfun.E101.A.2280},
ISSN={1745-1337},
month={December},}
부
TY - JOUR
TI - FPGA Implementation of a Real-Time Super-Resolution System Using Flips and an RNS-Based CNN
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2280
EP - 2289
AU - Taito MANABE
AU - Yuichiro SHIBATA
AU - Kiyoshi OGURI
PY - 2018
DO - 10.1587/transfun.E101.A.2280
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E101-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2018
AB - The super-resolution technology is one of the solutions to fill the gap between high-resolution displays and lower-resolution images. There are various algorithms to interpolate the lost information, one of which is using a convolutional neural network (CNN). This paper shows an FPGA implementation and a performance evaluation of a novel CNN-based super-resolution system, which can process moving images in real time. We apply horizontal and vertical flips to input images instead of enlargement. This flip method prevents information loss and enables the network to make the best use of its patch size. In addition, we adopted the residue number system (RNS) in the network to reduce FPGA resource utilization. Efficient multiplication and addition with LUTs increased a network scale that can be implemented on the same FPGA by approximately 54% compared to an implementation with fixed-point operations. The proposed system can perform super-resolution from 960×540 to 1920×1080 at 60fps with a latency of less than 1ms. Despite resource restriction of the FPGA, the system can generate 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) and the structural similarity (SSIM) index, compared to systems with other methods.
ER -