Supervised Change Detection Using Prechange Optical-SAR and Postchange SAR Data
Change detection using satellite/aerial images is used to quantify the impacts of many natural and man-made disasters. At the occurrence of such events, both prechange optical and synthetic aperture radar (SAR) images can be obtained by going back in time. However, the availability of the postchange...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9901395/ |
_version_ | 1811258125478526976 |
---|---|
author | Sudipan Saha Muhammad Shahzad Patrick Ebel Xiao Xiang Zhu |
author_facet | Sudipan Saha Muhammad Shahzad Patrick Ebel Xiao Xiang Zhu |
author_sort | Sudipan Saha |
collection | DOAJ |
description | Change detection using satellite/aerial images is used to quantify the impacts of many natural and man-made disasters. At the occurrence of such events, both prechange optical and synthetic aperture radar (SAR) images can be obtained by going back in time. However, the availability of the postchange optical image is often hindered by the presence of artifacts like clouds. To circumnavigate this, we propose a novel change detection data setting that uses both optical and SAR images prechange, yet only SAR imagery postchange. For this challenging scenario, we propose a Siamese network that processes the prechange and postchange SAR inputs using a shared set of weights, while the prechange optical input is processed using a network that do not share the weights with the SAR inputs. The encoded weights from the three networks are fused and finally decoded using a common decoder to obtain the change map. Our model effectively fuses multisensor information and can obtain satisfactory result despite the absence of the postchange optical image. Experimental results on a multisensor urban dataset demonstrate the effectiveness of the proposed approach. |
first_indexed | 2024-04-12T18:08:21Z |
format | Article |
id | doaj.art-9c915d18070845fdbd540825750bdde2 |
institution | Directory Open Access Journal |
issn | 2151-1535 |
language | English |
last_indexed | 2024-04-12T18:08:21Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj.art-9c915d18070845fdbd540825750bdde22022-12-22T03:21:54ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01158170817810.1109/JSTARS.2022.32068989901395Supervised Change Detection Using Prechange Optical-SAR and Postchange SAR DataSudipan Saha0https://orcid.org/0000-0002-9440-0720Muhammad Shahzad1https://orcid.org/0000-0002-8278-9118Patrick Ebel2Xiao Xiang Zhu3https://orcid.org/0000-0001-5530-3613Department of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Ottobrunn, GermanyDepartment of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Munich, GermanyDepartment of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Ottobrunn, GermanyDepartment of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Ottobrunn, GermanyChange detection using satellite/aerial images is used to quantify the impacts of many natural and man-made disasters. At the occurrence of such events, both prechange optical and synthetic aperture radar (SAR) images can be obtained by going back in time. However, the availability of the postchange optical image is often hindered by the presence of artifacts like clouds. To circumnavigate this, we propose a novel change detection data setting that uses both optical and SAR images prechange, yet only SAR imagery postchange. For this challenging scenario, we propose a Siamese network that processes the prechange and postchange SAR inputs using a shared set of weights, while the prechange optical input is processed using a network that do not share the weights with the SAR inputs. The encoded weights from the three networks are fused and finally decoded using a common decoder to obtain the change map. Our model effectively fuses multisensor information and can obtain satisfactory result despite the absence of the postchange optical image. Experimental results on a multisensor urban dataset demonstrate the effectiveness of the proposed approach.https://ieeexplore.ieee.org/document/9901395/Change detection (CD)fusionmultisensor analysisoptical imagesSiamese networksynthetic aperture radar (SAR) |
spellingShingle | Sudipan Saha Muhammad Shahzad Patrick Ebel Xiao Xiang Zhu Supervised Change Detection Using Prechange Optical-SAR and Postchange SAR Data IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Change detection (CD) fusion multisensor analysis optical images Siamese network synthetic aperture radar (SAR) |
title | Supervised Change Detection Using Prechange Optical-SAR and Postchange SAR Data |
title_full | Supervised Change Detection Using Prechange Optical-SAR and Postchange SAR Data |
title_fullStr | Supervised Change Detection Using Prechange Optical-SAR and Postchange SAR Data |
title_full_unstemmed | Supervised Change Detection Using Prechange Optical-SAR and Postchange SAR Data |
title_short | Supervised Change Detection Using Prechange Optical-SAR and Postchange SAR Data |
title_sort | supervised change detection using prechange optical sar and postchange sar data |
topic | Change detection (CD) fusion multisensor analysis optical images Siamese network synthetic aperture radar (SAR) |
url | https://ieeexplore.ieee.org/document/9901395/ |
work_keys_str_mv | AT sudipansaha supervisedchangedetectionusingprechangeopticalsarandpostchangesardata AT muhammadshahzad supervisedchangedetectionusingprechangeopticalsarandpostchangesardata AT patrickebel supervisedchangedetectionusingprechangeopticalsarandpostchangesardata AT xiaoxiangzhu supervisedchangedetectionusingprechangeopticalsarandpostchangesardata |