FASI-Net: Frequency-Domain Information Assisted Semantic Interaction Network for Bitemporal Remote Sensing Images Change Detection

As a crucial approach for comprehending land surface changes, remote sensing images (RSIs) change detection methods based on deep learning have been extensively studied in recent years. Among these methods, the Siamese network-based method has demonstrated remarkable performance. However, existing a...

Full description

Saved in:
Bibliographic Details
Main Authors: Fenglei Chen, Haijun Liu, Zhihong Zeng, Xiaoheng Tan
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10944583/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850155073559068672
author Fenglei Chen
Haijun Liu
Zhihong Zeng
Xiaoheng Tan
author_facet Fenglei Chen
Haijun Liu
Zhihong Zeng
Xiaoheng Tan
author_sort Fenglei Chen
collection DOAJ
description As a crucial approach for comprehending land surface changes, remote sensing images (RSIs) change detection methods based on deep learning have been extensively studied in recent years. Among these methods, the Siamese network-based method has demonstrated remarkable performance. However, existing approaches are susceptible to interference from irrelevant factors such as shadows, noise, and unrelated changes in a single temporal, which limits the model's ability to accurately perceive bitemporal crucial semantic information. To address the abovementioned problems, this article proposes a frequency-domain information assisted semantic interaction network (FASI-Net) to ensure the effective extraction of crucial semantic information in the original bitemporal features. We attempt to employ frequency-domain information to explicitly interact bitemporal low-frequency semantic information during the encoding process, subsequently preserving and enhancing the high-frequency information of each temporal feature. This enables model comprehensive perception of bitemporal features, effectively distinguishing the semantic similar information from the semantic difference information, and accurately identifying changed regions versus unchanged regions. Extensive experiments on three typical RSIs change detection datasets demonstrate a significant improvement in the performance of our proposed method (with 4.53%/7.57%, 6.66%/10.69%, and 5.11%/7.24% improvements over the baseline in terms of F1/intersection over union (IoU) metrics for WHU-CD, LEVIR-CD, and SYSU-CD datasets). Moreover, our FASI-Net comprehensively achieves state-of-the-art results with F1/IoU reaching 92.86%/86.67%, 91.73%/84.71%, and 83.72%/72.00% on WHU-CD, LEVIR-CD, and SYSU-CD datasets, respectively. In addition, the proposed bitemporal low-frequency semantic interaction module can be seamlessly inserted into existing change detection models to achieve effective crucial semantic information extraction.
format Article
id doaj-art-ac48c1431e9e410593d3c477dea6efaf
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-ac48c1431e9e410593d3c477dea6efaf2025-08-20T02:25:03ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118103601037310.1109/JSTARS.2025.355553610944583FASI-Net: Frequency-Domain Information Assisted Semantic Interaction Network for Bitemporal Remote Sensing Images Change DetectionFenglei Chen0https://orcid.org/0000-0002-5540-6070Haijun Liu1https://orcid.org/0000-0001-5782-4543Zhihong Zeng2https://orcid.org/0000-0001-7852-9172Xiaoheng Tan3https://orcid.org/0000-0001-9376-4920School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing, ChinaAs a crucial approach for comprehending land surface changes, remote sensing images (RSIs) change detection methods based on deep learning have been extensively studied in recent years. Among these methods, the Siamese network-based method has demonstrated remarkable performance. However, existing approaches are susceptible to interference from irrelevant factors such as shadows, noise, and unrelated changes in a single temporal, which limits the model's ability to accurately perceive bitemporal crucial semantic information. To address the abovementioned problems, this article proposes a frequency-domain information assisted semantic interaction network (FASI-Net) to ensure the effective extraction of crucial semantic information in the original bitemporal features. We attempt to employ frequency-domain information to explicitly interact bitemporal low-frequency semantic information during the encoding process, subsequently preserving and enhancing the high-frequency information of each temporal feature. This enables model comprehensive perception of bitemporal features, effectively distinguishing the semantic similar information from the semantic difference information, and accurately identifying changed regions versus unchanged regions. Extensive experiments on three typical RSIs change detection datasets demonstrate a significant improvement in the performance of our proposed method (with 4.53%/7.57%, 6.66%/10.69%, and 5.11%/7.24% improvements over the baseline in terms of F1/intersection over union (IoU) metrics for WHU-CD, LEVIR-CD, and SYSU-CD datasets). Moreover, our FASI-Net comprehensively achieves state-of-the-art results with F1/IoU reaching 92.86%/86.67%, 91.73%/84.71%, and 83.72%/72.00% on WHU-CD, LEVIR-CD, and SYSU-CD datasets, respectively. In addition, the proposed bitemporal low-frequency semantic interaction module can be seamlessly inserted into existing change detection models to achieve effective crucial semantic information extraction.https://ieeexplore.ieee.org/document/10944583/Bitemporal crucial semantic informationchange detectionfrequency domainremote sensingwavelet transform
spellingShingle Fenglei Chen
Haijun Liu
Zhihong Zeng
Xiaoheng Tan
FASI-Net: Frequency-Domain Information Assisted Semantic Interaction Network for Bitemporal Remote Sensing Images Change Detection
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Bitemporal crucial semantic information
change detection
frequency domain
remote sensing
wavelet transform
title FASI-Net: Frequency-Domain Information Assisted Semantic Interaction Network for Bitemporal Remote Sensing Images Change Detection
title_full FASI-Net: Frequency-Domain Information Assisted Semantic Interaction Network for Bitemporal Remote Sensing Images Change Detection
title_fullStr FASI-Net: Frequency-Domain Information Assisted Semantic Interaction Network for Bitemporal Remote Sensing Images Change Detection
title_full_unstemmed FASI-Net: Frequency-Domain Information Assisted Semantic Interaction Network for Bitemporal Remote Sensing Images Change Detection
title_short FASI-Net: Frequency-Domain Information Assisted Semantic Interaction Network for Bitemporal Remote Sensing Images Change Detection
title_sort fasi net frequency domain information assisted semantic interaction network for bitemporal remote sensing images change detection
topic Bitemporal crucial semantic information
change detection
frequency domain
remote sensing
wavelet transform
url https://ieeexplore.ieee.org/document/10944583/
work_keys_str_mv AT fengleichen fasinetfrequencydomaininformationassistedsemanticinteractionnetworkforbitemporalremotesensingimageschangedetection
AT haijunliu fasinetfrequencydomaininformationassistedsemanticinteractionnetworkforbitemporalremotesensingimageschangedetection
AT zhihongzeng fasinetfrequencydomaininformationassistedsemanticinteractionnetworkforbitemporalremotesensingimageschangedetection
AT xiaohengtan fasinetfrequencydomaininformationassistedsemanticinteractionnetworkforbitemporalremotesensingimageschangedetection