A Speckle Filter for Sentinel-1 SAR Ground Range Detected Data Based on Residual Convolutional Neural Networks
In recent years, machine learning algorithms have become widespread in all the fields of remote sensing and earth observation. This has allowed the rapid development of new procedures to solve problems affecting these sectors. In this context, this work aims at presenting a novel method for filtering speckle noise from Sentinel-1 ground range detected data by applying deep learning (DL) algorithms, based on convolutional neural networks. This article provides an easy yet very effective approach to extract the large amount of training data needed for DL approaches in this challenging case. The experimental results on simulated speckled images and an actual synthetic aperture radar dataset show a clear improvement with respect to the state of the art in terms of peak signal-to-noise ratio, structural similarity index, equivalent number of looks, proving the effectiveness of the proposed architecture..
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:15 |
|---|---|
| Enthalten in: |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing - 15(2022), Seite 5086-5101 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Alessandro Sebastianelli [VerfasserIn] |
|---|
| Links: |
doi.org [kostenfrei] |
|---|
| Themen: |
Artificial intelligence (AI) |
|---|
| doi: |
10.1109/JSTARS.2022.3184355 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
DOAJ039795985 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | DOAJ039795985 | ||
| 003 | DE-627 | ||
| 005 | 20230503111142.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230227s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/JSTARS.2022.3184355 |2 doi | |
| 035 | |a (DE-627)DOAJ039795985 | ||
| 035 | |a (DE-599)DOAJ845d246c5d45470b9f77000ddc07eb91 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 050 | 0 | |a TC1501-1800 | |
| 050 | 0 | |a QC801-809 | |
| 100 | 0 | |a Alessandro Sebastianelli |e verfasserin |4 aut | |
| 245 | 1 | 2 | |a A Speckle Filter for Sentinel-1 SAR Ground Range Detected Data Based on Residual Convolutional Neural Networks |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a In recent years, machine learning algorithms have become widespread in all the fields of remote sensing and earth observation. This has allowed the rapid development of new procedures to solve problems affecting these sectors. In this context, this work aims at presenting a novel method for filtering speckle noise from Sentinel-1 ground range detected data by applying deep learning (DL) algorithms, based on convolutional neural networks. This article provides an easy yet very effective approach to extract the large amount of training data needed for DL approaches in this challenging case. The experimental results on simulated speckled images and an actual synthetic aperture radar dataset show a clear improvement with respect to the state of the art in terms of peak signal-to-noise ratio, structural similarity index, equivalent number of looks, proving the effectiveness of the proposed architecture. | ||
| 650 | 4 | |a Artificial intelligence (AI) | |
| 650 | 4 | |a convolutional neural networks (CNNs) | |
| 650 | 4 | |a deep learning (DL) | |
| 650 | 4 | |a ground range detected (GRD) data | |
| 650 | 4 | |a noise filtering | |
| 650 | 4 | |a Sentinel-1 | |
| 653 | 0 | |a Ocean engineering | |
| 653 | 0 | |a Geophysics. Cosmic physics | |
| 700 | 0 | |a Maria Pia Del Rosso |e verfasserin |4 aut | |
| 700 | 0 | |a Silvia L. Ullo |e verfasserin |4 aut | |
| 700 | 0 | |a Paolo Gamba |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i In |t IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |d IEEE, 2020 |g 15(2022), Seite 5086-5101 |w (DE-627)DOAJ078635624 |x 21511535 |7 nnns |
| 773 | 1 | 8 | |g volume:15 |g year:2022 |g pages:5086-5101 |
| 856 | 4 | 0 | |u https://doi.org/10.1109/JSTARS.2022.3184355 |z kostenfrei |
| 856 | 4 | 0 | |u https://doaj.org/article/845d246c5d45470b9f77000ddc07eb91 |z kostenfrei |
| 856 | 4 | 0 | |u https://ieeexplore.ieee.org/document/9800702/ |z kostenfrei |
| 856 | 4 | 2 | |u https://doaj.org/toc/2151-1535 |y Journal toc |z kostenfrei |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_DOAJ | ||
| 912 | |a SSG-OLC-PHA | ||
| 951 | |a AR | ||
| 952 | |d 15 |j 2022 |h 5086-5101 | ||