Tampere University of Technology

TUTCRIS Research Portal

Blind Prediction of Original Image Quality for Sentinel Sar Data

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

Blind Prediction of Original Image Quality for Sentinel Sar Data. / Rubel, Oleksii; Rubel, Andrii; Lukin, Vladimir; Carli, Marco; Egiazarian, Karen.

2019 8th European Workshop on Visual Information Processing (EUVIP). IEEE, 2019. p. 105-110 (European Workshop on Visual Information Processing).

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Rubel, O, Rubel, A, Lukin, V, Carli, M & Egiazarian, K 2019, Blind Prediction of Original Image Quality for Sentinel Sar Data. in 2019 8th European Workshop on Visual Information Processing (EUVIP). European Workshop on Visual Information Processing, IEEE, pp. 105-110, European Workshop on Visual Information Processing, 1/01/00. https://doi.org/10.1109/EUVIP47703.2019.8946231

APA

Rubel, O., Rubel, A., Lukin, V., Carli, M., & Egiazarian, K. (2019). Blind Prediction of Original Image Quality for Sentinel Sar Data. In 2019 8th European Workshop on Visual Information Processing (EUVIP) (pp. 105-110). (European Workshop on Visual Information Processing). IEEE. https://doi.org/10.1109/EUVIP47703.2019.8946231

Vancouver

Rubel O, Rubel A, Lukin V, Carli M, Egiazarian K. Blind Prediction of Original Image Quality for Sentinel Sar Data. In 2019 8th European Workshop on Visual Information Processing (EUVIP). IEEE. 2019. p. 105-110. (European Workshop on Visual Information Processing). https://doi.org/10.1109/EUVIP47703.2019.8946231

Author

Rubel, Oleksii ; Rubel, Andrii ; Lukin, Vladimir ; Carli, Marco ; Egiazarian, Karen. / Blind Prediction of Original Image Quality for Sentinel Sar Data. 2019 8th European Workshop on Visual Information Processing (EUVIP). IEEE, 2019. pp. 105-110 (European Workshop on Visual Information Processing).

Bibtex - Download

@inproceedings{7fc503cdc3084952bd3a60741ab21160,
title = "Blind Prediction of Original Image Quality for Sentinel Sar Data",
abstract = "Synthetic aperture radar (SAR) images are often subject to visual inspection and analysis. Many factors impact on visual quality of SAR images, such as properties of speckle, dynamic range of data, etc. Thus, the corresponding metrics have to be applied and it is worth predicting their values before one starts analyzing images. Using a set of input parameters (both statistical and spectral) and a trained neural network (NN), we show that full-reference visual quality metrics can be predicted for images acquired by modern SAR Sentinel-1. A prediction accuracy is studied and verified on real-life examples. The source codes and datasets will be made publicly available at https://github.com/asrubel/EUVIP2019.",
keywords = "Image quality, prediction algorithms, synthetic aperture radar, multi-layer neural network, speckle",
author = "Oleksii Rubel and Andrii Rubel and Vladimir Lukin and Marco Carli and Karen Egiazarian",
note = "EXT={"}Lukin, Vladimir{"} EXT={"}Carli, Marco{"}",
year = "2019",
month = "10",
day = "1",
doi = "10.1109/EUVIP47703.2019.8946231",
language = "English",
isbn = "978-1-7281-4497-9",
series = "European Workshop on Visual Information Processing",
publisher = "IEEE",
pages = "105--110",
booktitle = "2019 8th European Workshop on Visual Information Processing (EUVIP)",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - Blind Prediction of Original Image Quality for Sentinel Sar Data

AU - Rubel, Oleksii

AU - Rubel, Andrii

AU - Lukin, Vladimir

AU - Carli, Marco

AU - Egiazarian, Karen

N1 - EXT="Lukin, Vladimir" EXT="Carli, Marco"

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Synthetic aperture radar (SAR) images are often subject to visual inspection and analysis. Many factors impact on visual quality of SAR images, such as properties of speckle, dynamic range of data, etc. Thus, the corresponding metrics have to be applied and it is worth predicting their values before one starts analyzing images. Using a set of input parameters (both statistical and spectral) and a trained neural network (NN), we show that full-reference visual quality metrics can be predicted for images acquired by modern SAR Sentinel-1. A prediction accuracy is studied and verified on real-life examples. The source codes and datasets will be made publicly available at https://github.com/asrubel/EUVIP2019.

AB - Synthetic aperture radar (SAR) images are often subject to visual inspection and analysis. Many factors impact on visual quality of SAR images, such as properties of speckle, dynamic range of data, etc. Thus, the corresponding metrics have to be applied and it is worth predicting their values before one starts analyzing images. Using a set of input parameters (both statistical and spectral) and a trained neural network (NN), we show that full-reference visual quality metrics can be predicted for images acquired by modern SAR Sentinel-1. A prediction accuracy is studied and verified on real-life examples. The source codes and datasets will be made publicly available at https://github.com/asrubel/EUVIP2019.

KW - Image quality

KW - prediction algorithms

KW - synthetic aperture radar

KW - multi-layer neural network

KW - speckle

U2 - 10.1109/EUVIP47703.2019.8946231

DO - 10.1109/EUVIP47703.2019.8946231

M3 - Conference contribution

SN - 978-1-7281-4497-9

T3 - European Workshop on Visual Information Processing

SP - 105

EP - 110

BT - 2019 8th European Workshop on Visual Information Processing (EUVIP)

PB - IEEE

ER -