AN ADVERSARIAL TRAINING FRAMEWORK FOR SENTINEL-2 IMAGE SUPER-RESOLUTION

被引：2

作者：

Ciotola, M. ^{[1
]}

Martinelli, A. ^{[1
]}

Mazza, A. ^{[1
]}

Scarpa, G. ^{[1
]}

机构：

[1] Univ Federico II, Dipartimento Ingn Elettr & Tecnol Informaz, Via Claudio 21, I-80125 Naples, Italy

来源：

2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022) | 2022年

关键词：

Super-Resolution; Data-Fusion; Convolutional Neural Network; Deep Learning; Sentinel-2; Generative Adversarial Network; SUPER RESOLUTION;

D O I：

10.1109/IGARSS46834.2022.9883144

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

In this work is presented a new adversarial training framework for deep learning neural networks for super-resolution of Sentinel 2 images, exploiting the data fusion techniques on 10 and 20 meters bands. The proposed scheme is fully convolutional and tries to answer the need for generalization in scale, producing realistic and detailed accurate images. Furthermore, the presence of a L-1 loss limits the instability of GAN training, limiting possible problems of spectral distortion. In our preliminary experiments, the GAN training scheme has shown comparable results in comparison with the baseline approach.

引用

页码：3782 / 3785

页数：4

共 23 条

[1] Multi-Image Super-Resolution for Remote Sensing using Deep Recurrent Networks [J].

Arefin, Md Rifat ;

Michalski, Vincent ;

St-Charles, Pierre-Luc ;

Kalaitzis, Alfredo ;

Kim, Sookyung ;

Kahou, Samira E. ;

Bengio, Yoshua .

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), 2020, :816-825

[2] A FULL-RESOLUTION TRAINING FRAMEWORK FOR SENTINEL-2 IMAGE FUSION [J].

Ciotola, M. ;

Ragosta, M. ;

Poggi, G. ;

Scarpa, G. .

2021 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM IGARSS, 2021, :1260-1263

[3] Pansharpening by Convolutional Neural Networks in the Full Resolution Framework [J].

Ciotola, Matteo ;

Vitale, Sergio ;

Mazza, Antonio ;

Poggi, Giovanni ;

Scarpa, Giuseppe .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60

[4] Generative Adversarial Networks An overview [J].

Creswell, Antonia ;

White, Tom ;

Dumoulin, Vincent ;

Arulkumaran, Kai ;

Sengupta, Biswa ;

Bharath, Anil A. .

IEEE SIGNAL PROCESSING MAGAZINE, 2018, 35 (01) :53-65

[5]

Galar M, 2019, INT ARCH PHOTOGRAMME

[6] Fast Super-Resolution of 20 m Sentinel-2 Bands Using Convolutional Neural Networks [J].

Gargiulo, Massimiliano ;

Mazza, Antonio ;

Gaetano, Raffaele ;

Ruello, Giuseppe ;

Scarpa, Giuseppe .

REMOTE SENSING, 2019, 11 (22)

[7] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[8] Image-to-Image Translation with Conditional Adversarial Networks [J].

Isola, Phillip ;

Zhu, Jun-Yan ;

Zhou, Tinghui ;

Efros, Alexei A. .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :5967-5976

[9] Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network [J].

Lanaras, Charis ;

Bioucas-Dias, Jose ;

Galliani, Silvano ;

Baltsavias, Emmanuel ;

Schindler, Konrad .

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 146 :305-319

[10] Coupled Adversarial Training for Remote Sensing Image Super-Resolution [J].

Lei, Sen ;

Shi, Zhenwei ;

Zou, Zhengxia .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (05) :3633-3643

← 1 2 3 →