Automatic Selection of Relevant Attributes for Multi-Sensor Remote Sensing Analysis: A Case Study on Sea Ice Classification
It is of considerable benefit to combine information obtained from different satellite sensors to achieve advanced and improved characterization of sea ice conditions. However, it is also true that not all the information is relevant. It may be redundant, corrupted, or unnecessary for the given task...
Published in: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/23514 https://doi.org/10.1109/JSTARS.2021.3099398 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/23514 |
---|---|
record_format |
openpolar |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/23514 2023-06-18T03:38:29+02:00 Automatic Selection of Relevant Attributes for Multi-Sensor Remote Sensing Analysis: A Case Study on Sea Ice Classification Khachatrian, Eduard Chlaily, Saloua Eltoft, Torbjørn Dierking, Wolfgang Fritz Otto Dinessen, Frode Marinoni, Andrea 2021-07-26 https://hdl.handle.net/10037/23514 https://doi.org/10.1109/JSTARS.2021.3099398 eng eng Institute of Electrical and Electronics Engineers Khachatrian, E. (2023). Multimodal Integrated Remote Sensing for Arctic Sea Ice Monitoring. (Doctoral thesis). https://hdl.handle.net/10037/29338 . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing info:eu-repo/grantAgreement/NRC/SFI/237906/Norway/Centre for Integrated Remote Sensing and Forecasting for Arctic Operations/CIRFA/ Khachatrian, Chlaily, Eltoft, Dierking, Dinessen, Marinoni. Automatic Selection of Relevant Attributes for Multi-Sensor Remote Sensing Analysis: A Case Study on Sea Ice Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2021;14:9025-9037 FRIDAID 1937726 doi:10.1109/JSTARS.2021.3099398 1939-1404 2151-1535 https://hdl.handle.net/10037/23514 openAccess Copyright 2021 The Author(s) Fjernanalyse / Remote sensing Sjøis / Sea ice Syntetisk aperturradar / Synthetic aperture radar VDP::Technology: 500 VDP::Teknologi: 500 Journal article Tidsskriftartikkel Peer reviewed publishedVersion 2021 ftunivtroemsoe https://doi.org/10.1109/JSTARS.2021.3099398 2023-06-07T23:06:22Z It is of considerable benefit to combine information obtained from different satellite sensors to achieve advanced and improved characterization of sea ice conditions. However, it is also true that not all the information is relevant. It may be redundant, corrupted, or unnecessary for the given task, hence decreasing the performance of the algorithms. Therefore, it is crucial to select an optimal set of image attributes which provides the relevant information content to enhance the efficiency and accuracy of the image interpretation and retrieval of geophysical parameters. Comprehensive studies have been focused on the analysis of relevant features for sea ice analysis obtained from different sensors, especially synthetic aperture radar. However, the outcomes of these studies are mostly data and application-dependent and can, therefore, rarely be generalized. In this article, we employ a feature selection method based on graph Laplacians, which is fully automatic and easy to implement. The proposed approach assesses relevant information on a global and local level using two metrics and selects relevant features for different regions of an image according to their physical characteristics and observation conditions. In the recent study, we investigate the effectiveness of this approach for sea ice classification, using different multi-sensor data combinations. Experiments show the advantage of applying multi-sensor data sets and demonstrate that the attributes selected by our method result in high classification accuracies. We demonstrate that our approach automatically considers varying technical, sensor-specific, environmental, and sea ice conditions by employing flexible and adaptive feature selection method as a pre-processing step. Article in Journal/Newspaper Arctic Sea ice University of Tromsø: Munin Open Research Archive IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14 9025 9037 |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
topic |
Fjernanalyse / Remote sensing Sjøis / Sea ice Syntetisk aperturradar / Synthetic aperture radar VDP::Technology: 500 VDP::Teknologi: 500 |
spellingShingle |
Fjernanalyse / Remote sensing Sjøis / Sea ice Syntetisk aperturradar / Synthetic aperture radar VDP::Technology: 500 VDP::Teknologi: 500 Khachatrian, Eduard Chlaily, Saloua Eltoft, Torbjørn Dierking, Wolfgang Fritz Otto Dinessen, Frode Marinoni, Andrea Automatic Selection of Relevant Attributes for Multi-Sensor Remote Sensing Analysis: A Case Study on Sea Ice Classification |
topic_facet |
Fjernanalyse / Remote sensing Sjøis / Sea ice Syntetisk aperturradar / Synthetic aperture radar VDP::Technology: 500 VDP::Teknologi: 500 |
description |
It is of considerable benefit to combine information obtained from different satellite sensors to achieve advanced and improved characterization of sea ice conditions. However, it is also true that not all the information is relevant. It may be redundant, corrupted, or unnecessary for the given task, hence decreasing the performance of the algorithms. Therefore, it is crucial to select an optimal set of image attributes which provides the relevant information content to enhance the efficiency and accuracy of the image interpretation and retrieval of geophysical parameters. Comprehensive studies have been focused on the analysis of relevant features for sea ice analysis obtained from different sensors, especially synthetic aperture radar. However, the outcomes of these studies are mostly data and application-dependent and can, therefore, rarely be generalized. In this article, we employ a feature selection method based on graph Laplacians, which is fully automatic and easy to implement. The proposed approach assesses relevant information on a global and local level using two metrics and selects relevant features for different regions of an image according to their physical characteristics and observation conditions. In the recent study, we investigate the effectiveness of this approach for sea ice classification, using different multi-sensor data combinations. Experiments show the advantage of applying multi-sensor data sets and demonstrate that the attributes selected by our method result in high classification accuracies. We demonstrate that our approach automatically considers varying technical, sensor-specific, environmental, and sea ice conditions by employing flexible and adaptive feature selection method as a pre-processing step. |
format |
Article in Journal/Newspaper |
author |
Khachatrian, Eduard Chlaily, Saloua Eltoft, Torbjørn Dierking, Wolfgang Fritz Otto Dinessen, Frode Marinoni, Andrea |
author_facet |
Khachatrian, Eduard Chlaily, Saloua Eltoft, Torbjørn Dierking, Wolfgang Fritz Otto Dinessen, Frode Marinoni, Andrea |
author_sort |
Khachatrian, Eduard |
title |
Automatic Selection of Relevant Attributes for Multi-Sensor Remote Sensing Analysis: A Case Study on Sea Ice Classification |
title_short |
Automatic Selection of Relevant Attributes for Multi-Sensor Remote Sensing Analysis: A Case Study on Sea Ice Classification |
title_full |
Automatic Selection of Relevant Attributes for Multi-Sensor Remote Sensing Analysis: A Case Study on Sea Ice Classification |
title_fullStr |
Automatic Selection of Relevant Attributes for Multi-Sensor Remote Sensing Analysis: A Case Study on Sea Ice Classification |
title_full_unstemmed |
Automatic Selection of Relevant Attributes for Multi-Sensor Remote Sensing Analysis: A Case Study on Sea Ice Classification |
title_sort |
automatic selection of relevant attributes for multi-sensor remote sensing analysis: a case study on sea ice classification |
publisher |
Institute of Electrical and Electronics Engineers |
publishDate |
2021 |
url |
https://hdl.handle.net/10037/23514 https://doi.org/10.1109/JSTARS.2021.3099398 |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_relation |
Khachatrian, E. (2023). Multimodal Integrated Remote Sensing for Arctic Sea Ice Monitoring. (Doctoral thesis). https://hdl.handle.net/10037/29338 . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing info:eu-repo/grantAgreement/NRC/SFI/237906/Norway/Centre for Integrated Remote Sensing and Forecasting for Arctic Operations/CIRFA/ Khachatrian, Chlaily, Eltoft, Dierking, Dinessen, Marinoni. Automatic Selection of Relevant Attributes for Multi-Sensor Remote Sensing Analysis: A Case Study on Sea Ice Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2021;14:9025-9037 FRIDAID 1937726 doi:10.1109/JSTARS.2021.3099398 1939-1404 2151-1535 https://hdl.handle.net/10037/23514 |
op_rights |
openAccess Copyright 2021 The Author(s) |
op_doi |
https://doi.org/10.1109/JSTARS.2021.3099398 |
container_title |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
container_volume |
14 |
container_start_page |
9025 |
op_container_end_page |
9037 |
_version_ |
1769003479821451264 |