Acta Armamentarii ›› 2024, Vol. 45 ›› Issue (3): 855-863.doi: 10.12382/bgxb.2022.0639
Previous Articles Next Articles
SU Di1,2, WANG Shaobo1, ZHANG Cheng1,*(), CHEN Zhisheng1, LIU Chaoyue3
Received:
2022-07-14
Online:
2022-07-25
Contact:
ZHANG Cheng
CLC Number:
SU Di, WANG Shaobo, ZHANG Cheng, CHEN Zhisheng, LIU Chaoyue. Projectile-borne Image Deblurring Algorithm Based on Generative Adversarial Networks[J]. Acta Armamentarii, 2024, 45(3): 855-863.
Add to citation manager EndNote|Ris|BibTeX
实验平台 | 环境配置 |
---|---|
操作系统 | Ubuntu 18.04 |
内存 | DDR4 2400MHz RegECC 128GB |
CPU | Intel(R) Xeon(R) E5 |
GPU | 3×NVIDIA RTX 3090Ti |
编程语言 | Python 3.7 |
深度学习框架 | Pytorch1.10 |
Table 1 Hardware and software configuration
实验平台 | 环境配置 |
---|---|
操作系统 | Ubuntu 18.04 |
内存 | DDR4 2400MHz RegECC 128GB |
CPU | Intel(R) Xeon(R) E5 |
GPU | 3×NVIDIA RTX 3090Ti |
编程语言 | Python 3.7 |
深度学习框架 | Pytorch1.10 |
方法 | PSNR | SSIM |
---|---|---|
基线 | 32.7 | 0.76 |
基线+梯度损失 | 36.4 | 0.85 |
基线+总变差损失 | 33.6 | 0.79 |
梯度损失+总变差损失 | 37.1 | 0.89 |
Table 2 Ablation experiments
方法 | PSNR | SSIM |
---|---|---|
基线 | 32.7 | 0.76 |
基线+梯度损失 | 36.4 | 0.85 |
基线+总变差损失 | 33.6 | 0.79 |
梯度损失+总变差损失 | 37.1 | 0.89 |
参数 | 算法 | ||||
---|---|---|---|---|---|
DeepDeblur | DeblurGAN | DeblurGAN-v2 | SRN | 本文算法 | |
PSNR | 31.5 | 33 | 36.30 | 35.80 | 37.10 |
SSIM | 0.75 | 0.77 | 0.83 | 0.85 | 0.89 |
时间/s | 4.24 | 0.82 | 0.34 | 1.57 | 0.33 |
Table 3 Deblurred results on missile-borne image dataset
参数 | 算法 | ||||
---|---|---|---|---|---|
DeepDeblur | DeblurGAN | DeblurGAN-v2 | SRN | 本文算法 | |
PSNR | 31.5 | 33 | 36.30 | 35.80 | 37.10 |
SSIM | 0.75 | 0.77 | 0.83 | 0.85 | 0.89 |
时间/s | 4.24 | 0.82 | 0.34 | 1.57 | 0.33 |
参数 | 算法 | ||||
---|---|---|---|---|---|
DeepDeblur | DeblurGAN | DeblurGAN-v2 | SRN | 本文算法 | |
PSNR | 29.08 | 28.70 | 29.55 | 30.10 | 29.80 |
SSIM | 0.914 | 0.927 | 0.934 | 0.932 | 0.921 |
时间/s | 4.33 | 0.85 | 0.35 | 1.60 | 0.35 |
Table 5 Deblurred results on GoPro dataset
参数 | 算法 | ||||
---|---|---|---|---|---|
DeepDeblur | DeblurGAN | DeblurGAN-v2 | SRN | 本文算法 | |
PSNR | 29.08 | 28.70 | 29.55 | 30.10 | 29.80 |
SSIM | 0.914 | 0.927 | 0.934 | 0.932 | 0.921 |
时间/s | 4.33 | 0.85 | 0.35 | 1.60 | 0.35 |
[1] |
裴慧坤, 颜源, 林国安, 等. 基于生成对抗网络的无人机图像去模糊方法[J]. 地理空间信息, 2019, 17(12):4-9.
|
|
|
[2] |
周玉, 彭召意. 运动模糊图像的维纳滤波复原研究[J]. 计算机工程与应用, 2009, 45(19):181-183.
|
doi: 10.3778/j.issn.1002-8331.2009.19.056 |
|
[3] |
郭永彩, 高潮, 王婀娜. 基于小波变换和非负支撑域递归逆滤波算法的盲目图像复原[J]. 光学学报, 2009, 29(11): 3000-3003.
|
doi: 10.3788/AOS URL |
|
[4] |
沈瑛, 吴建华, 吴禄慎. 由约束最小二乘方法改进的图像恢复方法[J]. 数据采集与处理, 2002, 17(3):325-327.
|
|
|
[5] |
doi: 10.1016/0167-2789(92)90242-F URL |
[6] |
|
[7] |
|
[8] |
|
[9] |
|
[10] |
|
[11] |
doi: 10.1109/TIP.83 URL |
[12] |
|
[13] |
|
[14] |
|
[15] |
|
[16] |
|
[17] |
|
[18] |
|
[19] |
|
[20] |
|
[21] |
|
[22] |
洪汉玉. 成像探测系统图像复原算法研究[D]. 武汉: 华中科技大学, 2004.
|
|
|
[23] |
梁志勇, 肖衡, 杨琳. 基于DeblurGAN对运动图像的去模糊化研究[J]. 现代计算机, 2019(31):25-27.
|
|
|
[24] |
李从利, 张思雨, 韦哲, 等. 基于深度卷积生成对抗网络的航拍图像去厚云方法[J]. 兵工学报, 2019, 40(7):1434-1442.
doi: 10.3969/j.issn.1000-1093.2019.07.013 |
|
|
[25] |
|
[26] |
|
[27] |
doi: 10.1109/TIP.2012.2192126 pmid: 22481817 |
[28] |
北京理工大学. 一种基于对抗生成网络的弹载图像去模糊方法:中国,CN202111246243.X[P].2022-01-18.
|
Beijing Institute of Technology. A deblurring method for missile borne images based on generative adversarial networks:China, CN202111246243.X[P].2022-01-18. (in Chinese)
|
|
[29] |
HOREA,
|
[30] |
|
[1] | XIONG Jiamei, WANG Yongzhen, YAN Xuefeng, WEI Mingqiang. An Algorithm of Battlefield Image Desmoking Based on Semantic Guidance and Contrastive Learning [J]. Acta Armamentarii, 2024, 45(2): 671-683. |
[2] | DUAN Yichen, SHEN Xiaohong, WANG Haiyan, YAN Yongsheng. An Anti-decoy Jamming Method of Ship-radiated Noise Signals Based on Unsupervised Time-frequency Information Fusion [J]. Acta Armamentarii, 2023, 44(9): 2722-2731. |
[3] | YAN Yuwen, BI Wenhao, ZHANG An, ZHANG Baichuan. Task Allocation Method of UAV Clusters Based on Sequence Generative Adversarial Network [J]. Acta Armamentarii, 2023, 44(9): 2672-2684. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||