Optimizing Multi-Class Change Segmentation in High-Resolution Satellite Imagery With a Siamese Network for Low-Resource Environments

This work focuses on multi-class change segmentation to quantify alterations between temporal images. Unlike traditional binary change detection, which requires post-processing to identify specific transformations, we introduce a Siamese architecture called SiamSegCD. This model is designed for dire...

Full description

Saved in:
Bibliographic Details
Published in:2024 IEEE India Geoscience and Remote Sensing Symposium (InGARSS) pp. 1 - 4
Main Authors: Srivastava, Noopur, Jain, Kamal
Format: Conference Proceeding
Language:English
Published: IEEE 02.12.2024
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract This work focuses on multi-class change segmentation to quantify alterations between temporal images. Unlike traditional binary change detection, which requires post-processing to identify specific transformations, we introduce a Siamese architecture called SiamSegCD. This model is designed for direct segmentation of land-use and land-cover changes, particularly suited for low-resource environments. SiamSegCD utilizes deep learning models like UNet and DeepLabv3+ with a lightweight ResNet-50 backbone and stand-alone self-attention to yield a fully self-attentional model, implemented in a Siamese twin framework. The model's performance is assessed using the HRSCD dataset, revealing better results with the DeepLabv3+ encoderdecoder compared to the UNet-based version, which demonstrated a 5.98% improvement in mean Intersection over Union (mIoU).
AbstractList This work focuses on multi-class change segmentation to quantify alterations between temporal images. Unlike traditional binary change detection, which requires post-processing to identify specific transformations, we introduce a Siamese architecture called SiamSegCD. This model is designed for direct segmentation of land-use and land-cover changes, particularly suited for low-resource environments. SiamSegCD utilizes deep learning models like UNet and DeepLabv3+ with a lightweight ResNet-50 backbone and stand-alone self-attention to yield a fully self-attentional model, implemented in a Siamese twin framework. The model's performance is assessed using the HRSCD dataset, revealing better results with the DeepLabv3+ encoderdecoder compared to the UNet-based version, which demonstrated a 5.98% improvement in mean Intersection over Union (mIoU).
Author Srivastava, Noopur
Jain, Kamal
Author_xml – sequence: 1
  givenname: Noopur
  surname: Srivastava
  fullname: Srivastava, Noopur
  organization: Indian Institute of Technology,Geomatics Group,Department of Civil Engineering,Roorkee,Uttarakhand,India,247667
– sequence: 2
  givenname: Kamal
  surname: Jain
  fullname: Jain, Kamal
  organization: Indian Institute of Technology,Geomatics Group,Department of Civil Engineering,Roorkee,Uttarakhand,India,247667
BookMark eNo1kEFPwjAYhmuiB0X-gYfG-7Bdt7U7kgWBBCVhGo-kbF_HF7eWdEUCZ3-4inp6kyd5n8NzQy6ts0DIPWcjzln-MLfT8aosM664GsUsTkbfVCUJzy_IMJe5EikTORNJdk0-l7uAHZ7QNvRp3waMilb3PS222jZAS2g6sEEHdJaipTNsttEKetfuz6jUAdoWA9B5pxvwR_qGYUs1LVF30AN9hnBw_p0a5-nCHc7fva-ATuwHemd_7P0tuTK67WH4twPy-jh5KWbRYjmdF-NFhFyqEGWVYVwblVRGG7lRkiud8XiT5qkWfKNlFbMa6spwVSuTqUwyJUxt0iqVdSorMSB3v14EgPXOY6f9cf0fR3wBPgRjVA
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/InGARSS61818.2024.10984419
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350390346
EndPage 4
ExternalDocumentID 10984419
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i178t-6cf01af84cfaf7b8718a612b595a31ba7c20dedcf18d8f6867083fdf5c57d57c3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001515777600100&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu May 29 05:57:29 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i178t-6cf01af84cfaf7b8718a612b595a31ba7c20dedcf18d8f6867083fdf5c57d57c3
PageCount 4
ParticipantIDs ieee_primary_10984419
PublicationCentury 2000
PublicationDate 2024-Dec.-2
PublicationDateYYYYMMDD 2024-12-02
PublicationDate_xml – month: 12
  year: 2024
  text: 2024-Dec.-2
  day: 02
PublicationDecade 2020
PublicationTitle 2024 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)
PublicationTitleAbbrev InGARSS
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8912983
Snippet This work focuses on multi-class change segmentation to quantify alterations between temporal images. Unlike traditional binary change detection, which...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Computational modeling
Computer architecture
Deep learning
Encoderdecoder architectures
Feature extraction
Image segmentation
Multi-class change segmentation
Remote sensing
Residual neural networks
Satellite images
Semantics
Siamese network
Stand-alone self-attention
Testing
Title Optimizing Multi-Class Change Segmentation in High-Resolution Satellite Imagery With a Siamese Network for Low-Resource Environments
URI https://ieeexplore.ieee.org/document/10984419
WOSCitedRecordID wos001515777600100&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELWgYmACRBHfuoHVJUkT2xkRaqESKhUB0a1y7DNkaIpKCoKZH47tpHwMDGyWLcuS7dOdz--9I-REBTqVzCDN7TCNwwiplHFOozj3emaCGemLTfDhUIzH6aghq3suDCJ68Bl2XNP_5euZWrhUmbXwVFj3na6SVc5ZTdZqhETt0OmgvDi7yTJmnZYDbUVxZznhV-kU7zn6G_9cc5O0vzl4MPryLltkBctt8nFtLXxavNse8NRZ6otaQs0RgAwfpg2XqISiBAfioC5BX18vyKTX36wQBlOnXfEG90X1CBKywoFlEYY1KBxsJAtXs1e6TO5D7wcfrk3u-r3b80va1FGgRchFRZkyQSiNiJWRhuf2iSSkDWzyJE1kN8wlV1GgUSsTCi0ME4zbuMxok6iE64Sr7g5plbMSdwlIHaBI88hFTTE33RxZzIwyyGQQ6m60R9puCydPtVTGZLl7-3_0H5B1d1AeHxIdklY1X-ARWVMvVfE8P_YH_AnfNKzD
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFLagIMEEiCJuPLC65LSdEaGWVpRQkSK6VT4hQ1NUUhDM_HBsJ-UYGNgiW1Yk20_v5eU7ADgVnkwY1gpxM40iP1CIsYijIOJOz4xizZzZBElTOholg5qs7rgwSikHPlMt--j-5cupmNtWmYnwhJr0nSyDFWudFVd0rVpK1Eye9YrL89sswyZtWdhWELUWS36Zp7jc0dn451s3QfObhQcHX_llCyypYht83JgYn-TvZgQ68ixytpawYgnATD1MajZRAfMCWhgHsi366oLBjDkFzlLB3sSqV7zB-7x8hAxmuYXLKphWsHBoalnYn76iRXsftn8w4prgrtMeXnRR7aSAcp_QEmGhPZ9pGgnNNOHmI4kyU9rwOIlZ6HNGROBJJYX2qaQaU0xMZaaljkVMZExEuAMaxbRQuwAy6Sma8MDWTRHRIVc4wlpohZnnyzDYA027heOnSixjvNi9_T_GT8Bad3jdH_d76dUBWLeH5tAiwSFolLO5OgKr4qXMn2fH7rA_AQt2sA4
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2024+IEEE+India+Geoscience+and+Remote+Sensing+Symposium+%28InGARSS%29&rft.atitle=Optimizing+Multi-Class+Change+Segmentation+in+High-Resolution+Satellite+Imagery+With+a+Siamese+Network+for+Low-Resource+Environments&rft.au=Srivastava%2C+Noopur&rft.au=Jain%2C+Kamal&rft.date=2024-12-02&rft.pub=IEEE&rft.spage=1&rft.epage=4&rft_id=info:doi/10.1109%2FInGARSS61818.2024.10984419&rft.externalDocID=10984419