An Unsupervised Deep Learning Method for Subsurface Target Detection in Radar Sounder Data
Radar sounder data are widely used for investigating geological structures and processes in the subsurface of icy and arid areas. Visual interpretation is one of the main techniques used in the literature to extract information from radargrams. There exist some automatic approaches but mostly superv...
Published in: | 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS |
---|---|
Main Authors: | , , |
Format: | Conference Object |
Language: | English |
Published: |
IEEE
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/11572/322995 https://doi.org/10.1109/IGARSS47720.2021.9554785 https://ieeexplore.ieee.org/document/9554785/authors#authors |
id |
ftutrentoiris:oai:iris.unitn.it:11572/322995 |
---|---|
record_format |
openpolar |
spelling |
ftutrentoiris:oai:iris.unitn.it:11572/322995 2024-02-11T10:08:41+01:00 An Unsupervised Deep Learning Method for Subsurface Target Detection in Radar Sounder Data Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo 2021 ELETTRONICO https://hdl.handle.net/11572/322995 https://doi.org/10.1109/IGARSS47720.2021.9554785 https://ieeexplore.ieee.org/document/9554785/authors#authors eng eng IEEE country:USA place:New York, Stati Uniti info:eu-repo/semantics/altIdentifier/isbn/978-1-6654-0369-6 ispartofbook:IEEE 2021 Int. Geoscience and Remote Sensing Symposium IGARSS 2021 firstpage:2955 lastpage:2958 numberofpages:4 serie:IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM PROCEEDINGS https://hdl.handle.net/11572/322995 doi:10.1109/IGARSS47720.2021.9554785 info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85125502348 https://ieeexplore.ieee.org/document/9554785/authors#authors info:eu-repo/semantics/closedAccess deep learning statistical analysis subsurface target detection radar sounder info:eu-repo/semantics/conferenceObject 2021 ftutrentoiris https://doi.org/10.1109/IGARSS47720.2021.9554785 2024-01-16T23:13:28Z Radar sounder data are widely used for investigating geological structures and processes in the subsurface of icy and arid areas. Visual interpretation is one of the main techniques used in the literature to extract information from radargrams. There exist some automatic approaches but mostly supervised. However, no methods exploit deep learning in an unsupervised way. Here, we propose an automatic and unsupervised technique for extracting information on the subsurface geological targets. The technique is built upon three steps: i) generation of a coarse segmentation map based on the radargram statistical properties, ii) refinement of the coarse map with deep learning to detect target reflections, and iii) analysis of the deep features to identify buried targets. We tested the proposed method on MARSIS radar data acquired near the South Pole of Mars. The experimental results prove the effectiveness of the proposed method. Conference Object South pole Università degli Studi di Trento: CINECA IRIS South Pole 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS 2955 2958 |
institution |
Open Polar |
collection |
Università degli Studi di Trento: CINECA IRIS |
op_collection_id |
ftutrentoiris |
language |
English |
topic |
deep learning statistical analysis subsurface target detection radar sounder |
spellingShingle |
deep learning statistical analysis subsurface target detection radar sounder Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo An Unsupervised Deep Learning Method for Subsurface Target Detection in Radar Sounder Data |
topic_facet |
deep learning statistical analysis subsurface target detection radar sounder |
description |
Radar sounder data are widely used for investigating geological structures and processes in the subsurface of icy and arid areas. Visual interpretation is one of the main techniques used in the literature to extract information from radargrams. There exist some automatic approaches but mostly supervised. However, no methods exploit deep learning in an unsupervised way. Here, we propose an automatic and unsupervised technique for extracting information on the subsurface geological targets. The technique is built upon three steps: i) generation of a coarse segmentation map based on the radargram statistical properties, ii) refinement of the coarse map with deep learning to detect target reflections, and iii) analysis of the deep features to identify buried targets. We tested the proposed method on MARSIS radar data acquired near the South Pole of Mars. The experimental results prove the effectiveness of the proposed method. |
author2 |
Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo |
format |
Conference Object |
author |
Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo |
author_facet |
Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo |
author_sort |
Donini, Elena |
title |
An Unsupervised Deep Learning Method for Subsurface Target Detection in Radar Sounder Data |
title_short |
An Unsupervised Deep Learning Method for Subsurface Target Detection in Radar Sounder Data |
title_full |
An Unsupervised Deep Learning Method for Subsurface Target Detection in Radar Sounder Data |
title_fullStr |
An Unsupervised Deep Learning Method for Subsurface Target Detection in Radar Sounder Data |
title_full_unstemmed |
An Unsupervised Deep Learning Method for Subsurface Target Detection in Radar Sounder Data |
title_sort |
unsupervised deep learning method for subsurface target detection in radar sounder data |
publisher |
IEEE |
publishDate |
2021 |
url |
https://hdl.handle.net/11572/322995 https://doi.org/10.1109/IGARSS47720.2021.9554785 https://ieeexplore.ieee.org/document/9554785/authors#authors |
geographic |
South Pole |
geographic_facet |
South Pole |
genre |
South pole |
genre_facet |
South pole |
op_relation |
info:eu-repo/semantics/altIdentifier/isbn/978-1-6654-0369-6 ispartofbook:IEEE 2021 Int. Geoscience and Remote Sensing Symposium IGARSS 2021 firstpage:2955 lastpage:2958 numberofpages:4 serie:IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM PROCEEDINGS https://hdl.handle.net/11572/322995 doi:10.1109/IGARSS47720.2021.9554785 info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85125502348 https://ieeexplore.ieee.org/document/9554785/authors#authors |
op_rights |
info:eu-repo/semantics/closedAccess |
op_doi |
https://doi.org/10.1109/IGARSS47720.2021.9554785 |
container_title |
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS |
container_start_page |
2955 |
op_container_end_page |
2958 |
_version_ |
1790608230455443456 |