Remote sensing image dehazing using a wavelet-based generative adversarial networks

被引:9
作者
Chen, Guangda [1 ]
Jia, Yanfei [1 ]
Yin, Yanjiang [2 ]
Fu, Shuaiwei [1 ]
Liu, Dejun [1 ]
Wang, Tenghao [1 ]
机构
[1] Beihua Univ, Coll Elect & Informat Engn, Jilin 132013, Peoples R China
[2] Beijing Zhongdian Feihua Commun Co Ltd, Beijing 100080, Peoples R China
关键词
Remote sensing; Haze removal; Deep learning; Generative adversarial networks;
D O I
10.1038/s41598-025-87240-z
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Remote sensing images often suffer from the degradation effects of atmospheric haze, which can significantly impair the quality and utility of the acquired data. A novel dehazing method leveraging generative adversarial networks is proposed to address this challenge. It integrates a generator network, designed to enhance the clarity and detail of hazy images, with a discriminator network that distinguishes between dehazed and real clear images. Initially, a dense residual block is designed to extract primary features. Subsequently, a wavelet transform block is designed to capture high and low-frequency features. Additionally, a global and local attention block is proposed to reduce the interference of redundant features and enhance the weight of important features. PixelShuffle is used as the upsampling operation, allowing for finer control of image details during the upsampling process. Finally, these designed modules are integrated to construct the generator network for image dehazing. Moreover, an improved discriminator network is proposed by adding a noise module to the conventional discriminator, enhancing the network's robustness. A novel loss function is introduced by incorporating the color loss function and SSIM loss function into traditional loss functions, aiming to improve color accuracy and visual distortion assessment. This approach attains the highest PSNR and SSIM scores when compared to current leading methods. The proposed dehazing technique for remote sensing images successfully maintains color fidelity and detail, leading to significantly clearer images.
引用
收藏
页数:13
相关论文
共 28 条
[11]   A Dehazing Method for Remote Sensing Image Under Nonuniform Hazy Weather Based on Deep Learning Network [J].
Jiang, Bo ;
Wang, Jinshuai ;
Wu, Yuwei ;
Wang, Shuaibo ;
Zhang, Jinyue ;
Chen, Xiaoxuan ;
Li, Yaowei ;
Li, Xiaoyang ;
Wang, Lin .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
[12]  
Jin J., 2019, IOP Conference Series: Earth and Environmental Science, V384, DOI [10.1088/1755-1315/384/1/012159, DOI 10.1088/1755-1315/384/1/012159]
[13]   A Remote Sensing Image Dehazing Method Based on Heterogeneous Priors [J].
Liang, Shan ;
Gao, Tao ;
Chen, Ting ;
Cheng, Peng .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 :1-13
[14]   PhDnet: A novel physic-aware dehazing network for remote sensing images [J].
Lihe, Ziyang ;
He, Jiang ;
Yuan, Qiangqiang ;
Jin, Xianyu ;
Xiao, Yi ;
Zhang, Liangpei .
INFORMATION FUSION, 2024, 106
[15]  
Lin D, 2019, arXiv
[16]   Remote sensing imagery detects hydromorphic soils hidden under agriculture system [J].
Mello, Fellipe A. O. ;
Dematte, Jose A. M. ;
Bellinaso, Henrique ;
Poppiel, Raul R. ;
Rizzo, Rodnei ;
de Mello, Danilo C. ;
Rosin, Nicolas Augusto ;
Rosas, Jorge T. F. ;
Silvero, Nelida E. Q. ;
Rodriguez-Albarracin, Heidy S. .
SCIENTIFIC REPORTS, 2023, 13 (01)
[17]   DedustGAN: Unpaired learning for image dedusting based on Retinex with GANs [J].
Meng, Xianglong ;
Huang, Jiayan ;
Li, Zuoyong ;
Wang, Chuansheng ;
Teng, Shenghua ;
Grau, Antoni .
EXPERT SYSTEMS WITH APPLICATIONS, 2024, 243
[18]   Single Remote Sensing Image Dehazing Using Robust Light-Dark Prior [J].
Ning, Jin ;
Zhou, Yanhong ;
Liao, Xiaojuan ;
Duo, Bin .
REMOTE SENSING, 2023, 15 (04)
[19]   Enhanced Pix2pix Dehazing Network [J].
Qu, Yanyun ;
Chen, Yizi ;
Huang, Jingying ;
Xie, Yuan .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :8152-8160
[20]   Remote sensing image dehazing using generative adversarial network with texture and color space enhancement [J].
Shen, Helin ;
Zhong, Tie ;
Jia, Yanfei ;
Wu, Chunming .
SCIENTIFIC REPORTS, 2024, 14 (01)