Enhancing Change Detection With Edge-Guided Difference Modeling in Remote Sensing Imagery

Change detection (CD) in remote sensing imagery remains challenging due to boundary ambiguity and false alarms caused by high foreground-background similarity and insufficient difference representation. To address these issues, we propose an Edge-Guided Difference Enhancement Network (EGDENet). EGDENet integrates an edge-aware Adaptive Enhancement Module (EAEM) to extract high-frequency edge cues across scales, and a Channel-Spatial Cooperative Difference Module (CSCDM) to refine change features by jointly leveraging spatial and channel-wise differences. An Up-sampling Feature Fusion (UFF) further enhances robustness to scale variations and improves region consistency. Extensive experiments on two public datasets demonstrate that EGDENet achieves superior performance with clearer boundaries compared to state-of-the-art methods. Our source code is publicly available at https://github.com/adleess/-EGDENet.

Authors

Institutions

Publication Details

Journal
IEEE Geoscience and Remote Sensing Letters
Published
2025-01-01
DOI
https://doi.org/10.1109/lgrs.2025.3604110
Citations
1
Primary Topic
Remote-Sensing Image Classification
Type
article
Field-Weighted Citation Impact
1.14

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Enhancing Change Detection With Edge-Guided Difference Modeling in Remote Sensing Imagery

D. Narasimhan, P.P. Wang, Yuan Yao, Fuchao Cheng et al.
1 citations
IEEE Geoscience and Remote Sensing Letters
Remote-Sensing Image Classification
1.14
article

Enhancing Change Detection With Edge-Guided Difference Modeling in Remote Sensing Imagery

D. Narasimhan, P.P. Wang, Yuan Yao, Fuchao Cheng, Ling Qin, Liang Liu, Jianwei Zhang, Chang Liu, Shaohua Wang, Abdelaziz Bouras
article en
1 citations

Abstract

Change detection (CD) in remote sensing imagery remains challenging due to boundary ambiguity and false alarms caused by high foreground-background similarity and insufficient difference representation. To address these issues, we propose an Edge-Guided Difference Enhancement Network (EGDENet). EGDENet integrates an edge-aware Adaptive Enhancement Module (EAEM) to extract high-frequency edge cues across scales, and a Channel-Spatial Cooperative Difference Module (CSCDM) to refine change features by jointly leveraging spatial and channel-wise differences. An Up-sampling Feature Fusion (UFF) further enhances robustness to scale variations and improves region consistency. Extensive experiments on two public datasets demonstrate that EGDENet achieves superior performance with clearer boundaries compared to state-of-the-art methods. Our source code is publicly available at https://github.com/adleess/-EGDENet.

IEEE Geoscience and Remote Sensing LettersVol. 22
Chinese Academy of Sciences (CN), Sichuan University (CN), Chengdu University of Information Technology (CN), Chengdu University (CN), Aerospace Information Research Institute (CN), State Key Laboratory of Remote Sensing Science (CN), Qatar University (QA), SASTRA University (IN)
National Natural Science Foundation of China, Natural Science Foundation of Sichuan Province
Openalex Percentile: Top 16%
Remote-Sensing Image Classification
1.14
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.