Dual Polarimetric SAR Covariance Matrix Estimation Using Deep Learning
A polarimetric Synthetic Aperture Radar (PoISAR) image is able to capture target backscattering properties in different polarimetric states, making it a rich source of information for target characterization. However, as with any SAR image, PolSAR images are affected by speckle. Therefore, to extract useful information about targets, the polarimetric covariance matrix has to be first estimated by reducing speckle. In this paper, we use a deep neural network to estimate the dual PolSAR covariance matrix. This application was compared against the state of the art PolSAR despeckling methods. Even if the method is agnostic on the structure of the covariance matrix, the deep learning based PolSAR covariance matrix estimation performed better than the state of the art PolSAR despeckling methods. These results showcase the potential of supervised deep learning for the improvement of PolSAR despeckling pipelines.
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article in monograph or in proceedings biblioteca |
| Language: | English |
| Subjects: | Fully convolutional networks, PoISAR, Sentinel-1, Speckle, deep learning, |
| Online Access: | https://research.wur.nl/en/publications/dual-polarimetric-sar-covariance-matrix-estimation-using-deep-lea |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
dig-wur-nl-wurpubs-579348 |
|---|---|
| record_format |
koha |
| spelling |
dig-wur-nl-wurpubs-5793482025-01-15 Mullissa, Adugna G. Marcos, Diego Herold, Martin Reiche, Johannes Article in monograph or in proceedings Dual Polarimetric SAR Covariance Matrix Estimation Using Deep Learning 2020 A polarimetric Synthetic Aperture Radar (PoISAR) image is able to capture target backscattering properties in different polarimetric states, making it a rich source of information for target characterization. However, as with any SAR image, PolSAR images are affected by speckle. Therefore, to extract useful information about targets, the polarimetric covariance matrix has to be first estimated by reducing speckle. In this paper, we use a deep neural network to estimate the dual PolSAR covariance matrix. This application was compared against the state of the art PolSAR despeckling methods. Even if the method is agnostic on the structure of the covariance matrix, the deep learning based PolSAR covariance matrix estimation performed better than the state of the art PolSAR despeckling methods. These results showcase the potential of supervised deep learning for the improvement of PolSAR despeckling pipelines. en application/pdf https://research.wur.nl/en/publications/dual-polarimetric-sar-covariance-matrix-estimation-using-deep-lea 10.1109/IGARSS39084.2020.9324333 https://edepot.wur.nl/542090 Fully convolutional networks PoISAR Sentinel-1 Speckle deep learning Wageningen University & Research |
| institution |
WUR NL |
| collection |
DSpace |
| country |
Países bajos |
| countrycode |
NL |
| component |
Bibliográfico |
| access |
En linea |
| databasecode |
dig-wur-nl |
| tag |
biblioteca |
| region |
Europa del Oeste |
| libraryname |
WUR Library Netherlands |
| language |
English |
| topic |
Fully convolutional networks PoISAR Sentinel-1 Speckle deep learning Fully convolutional networks PoISAR Sentinel-1 Speckle deep learning |
| spellingShingle |
Fully convolutional networks PoISAR Sentinel-1 Speckle deep learning Fully convolutional networks PoISAR Sentinel-1 Speckle deep learning Mullissa, Adugna G. Marcos, Diego Herold, Martin Reiche, Johannes Dual Polarimetric SAR Covariance Matrix Estimation Using Deep Learning |
| description |
A polarimetric Synthetic Aperture Radar (PoISAR) image is able to capture target backscattering properties in different polarimetric states, making it a rich source of information for target characterization. However, as with any SAR image, PolSAR images are affected by speckle. Therefore, to extract useful information about targets, the polarimetric covariance matrix has to be first estimated by reducing speckle. In this paper, we use a deep neural network to estimate the dual PolSAR covariance matrix. This application was compared against the state of the art PolSAR despeckling methods. Even if the method is agnostic on the structure of the covariance matrix, the deep learning based PolSAR covariance matrix estimation performed better than the state of the art PolSAR despeckling methods. These results showcase the potential of supervised deep learning for the improvement of PolSAR despeckling pipelines. |
| format |
Article in monograph or in proceedings |
| topic_facet |
Fully convolutional networks PoISAR Sentinel-1 Speckle deep learning |
| author |
Mullissa, Adugna G. Marcos, Diego Herold, Martin Reiche, Johannes |
| author_facet |
Mullissa, Adugna G. Marcos, Diego Herold, Martin Reiche, Johannes |
| author_sort |
Mullissa, Adugna G. |
| title |
Dual Polarimetric SAR Covariance Matrix Estimation Using Deep Learning |
| title_short |
Dual Polarimetric SAR Covariance Matrix Estimation Using Deep Learning |
| title_full |
Dual Polarimetric SAR Covariance Matrix Estimation Using Deep Learning |
| title_fullStr |
Dual Polarimetric SAR Covariance Matrix Estimation Using Deep Learning |
| title_full_unstemmed |
Dual Polarimetric SAR Covariance Matrix Estimation Using Deep Learning |
| title_sort |
dual polarimetric sar covariance matrix estimation using deep learning |
| url |
https://research.wur.nl/en/publications/dual-polarimetric-sar-covariance-matrix-estimation-using-deep-lea |
| work_keys_str_mv |
AT mullissaadugnag dualpolarimetricsarcovariancematrixestimationusingdeeplearning AT marcosdiego dualpolarimetricsarcovariancematrixestimationusingdeeplearning AT heroldmartin dualpolarimetricsarcovariancematrixestimationusingdeeplearning AT reichejohannes dualpolarimetricsarcovariancematrixestimationusingdeeplearning |
| _version_ |
1822267952981868544 |