Home > Research > Publications & Outputs > Self-Calibrated Convolutional Neural Network fo...

Research

Associated organisational units

Links

Text available via DOI:

View graph of relations

Self-Calibrated Convolutional Neural Network for SAR Image Despeckling.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Self-Calibrated Convolutional Neural Network for SAR Image Despeckling. / Yuan, Ye; Jiang, Yan; Wu, Yanxia et al.
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE, 2021. p. 399-402.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Yuan, Y, Jiang, Y, Wu, Y & Jiang, R 2021, Self-Calibrated Convolutional Neural Network for SAR Image Despeckling. in 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE, pp. 399-402. https://doi.org/10.1109/IGARSS47720.2021.9554769

APA

Yuan, Y., Jiang, Y., Wu, Y., & Jiang, R. (2021). Self-Calibrated Convolutional Neural Network for SAR Image Despeckling. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS (pp. 399-402). IEEE. https://doi.org/10.1109/IGARSS47720.2021.9554769

Vancouver

Yuan Y, Jiang Y, Wu Y, Jiang R. Self-Calibrated Convolutional Neural Network for SAR Image Despeckling. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE. 2021. p. 399-402 Epub 2021 Jul 11. doi: 10.1109/IGARSS47720.2021.9554769

Author

Yuan, Ye ; Jiang, Yan ; Wu, Yanxia et al. / Self-Calibrated Convolutional Neural Network for SAR Image Despeckling. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE, 2021. pp. 399-402

Bibtex

@inproceedings{e8eee304cf17491f8d1a3c7240e31fe0,
title = "Self-Calibrated Convolutional Neural Network for SAR Image Despeckling.",
abstract = "Synthetic aperture radar (SAR) images are contaminated by speckle noise, which has largely limited its practical applications. Recently, convolutional neural networks (CNNs) have indicated good potential for various image processing tasks. In this paper, we propose a self-calibrated convolutional neural network for SAR image despeckling, called SAR-SCCNN. To enlarge the receptive field of the network, downsampling and dilated convolutions are employed in each self-calibrated block. Also, the contextual information from spaces with different scales is extracted and concentrated to obtain accurate despeckled images. Experiments on synthetic speckled and real SAR data are conducted to perform the subjective visual assessment of image quality and objective evaluation. Results show that our proposed method can effectively suppress speckle noise and preserve detailed features.",
author = "Ye Yuan and Yan Jiang and Yanxia Wu and Richard Jiang",
year = "2021",
month = oct,
day = "12",
doi = "10.1109/IGARSS47720.2021.9554769",
language = "English",
isbn = "9781665447621",
pages = "399--402",
booktitle = "2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Self-Calibrated Convolutional Neural Network for SAR Image Despeckling.

AU - Yuan, Ye

AU - Jiang, Yan

AU - Wu, Yanxia

AU - Jiang, Richard

PY - 2021/10/12

Y1 - 2021/10/12

N2 - Synthetic aperture radar (SAR) images are contaminated by speckle noise, which has largely limited its practical applications. Recently, convolutional neural networks (CNNs) have indicated good potential for various image processing tasks. In this paper, we propose a self-calibrated convolutional neural network for SAR image despeckling, called SAR-SCCNN. To enlarge the receptive field of the network, downsampling and dilated convolutions are employed in each self-calibrated block. Also, the contextual information from spaces with different scales is extracted and concentrated to obtain accurate despeckled images. Experiments on synthetic speckled and real SAR data are conducted to perform the subjective visual assessment of image quality and objective evaluation. Results show that our proposed method can effectively suppress speckle noise and preserve detailed features.

AB - Synthetic aperture radar (SAR) images are contaminated by speckle noise, which has largely limited its practical applications. Recently, convolutional neural networks (CNNs) have indicated good potential for various image processing tasks. In this paper, we propose a self-calibrated convolutional neural network for SAR image despeckling, called SAR-SCCNN. To enlarge the receptive field of the network, downsampling and dilated convolutions are employed in each self-calibrated block. Also, the contextual information from spaces with different scales is extracted and concentrated to obtain accurate despeckled images. Experiments on synthetic speckled and real SAR data are conducted to perform the subjective visual assessment of image quality and objective evaluation. Results show that our proposed method can effectively suppress speckle noise and preserve detailed features.

U2 - 10.1109/IGARSS47720.2021.9554769

DO - 10.1109/IGARSS47720.2021.9554769

M3 - Conference contribution/Paper

SN - 9781665447621

SP - 399

EP - 402

BT - 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS

PB - IEEE

ER -