MTFSR: Multitemporal and Spatial Feature Reconstruction Denoising Network for Remote Sensing Change Detection

With the widespread application of convolutional neural networks (CNNs) in remote sensing (RS) technologies, change detection (CD) has attracted increasing attention in environmental monitoring research. In RS image CD tasks, researchers often face challenges such as multiscale change capture inadeq...

Full description

Saved in:
Bibliographic Details
Main Authors: YeKai Cui, Peng Duan, Jinjiang Li
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/11003578/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849426299778498560
author YeKai Cui
Peng Duan
Jinjiang Li
author_facet YeKai Cui
Peng Duan
Jinjiang Li
author_sort YeKai Cui
collection DOAJ
description With the widespread application of convolutional neural networks (CNNs) in remote sensing (RS) technologies, change detection (CD) has attracted increasing attention in environmental monitoring research. In RS image CD tasks, researchers often face challenges such as multiscale change capture inadequacy due to feature noise interference and difficulties in spatiotemporal feature alignment. To address these issues, this article proposes a multitemporal and spatial feature reconstruction denoising network for remote sensing change detection (MTFSR). MTFSR first utilizes ResNet50 to extract deep features from dual-temporal images and innovatively introduces Bézier curves to smooth the features through feature redistribution, along with brightness enhancement to effectively suppress noise interference and enhance change areas. Meanwhile, a spatial attention mechanism and discrete cosine transform (DCT) are incorporated to further improve the spatial expression and frequency domain perception of the features. Then, multiscale filtering is applied to accurately align the frequency and spatial domains, effectively solving the spatiotemporal feature inconsistency problem. On this basis, the model designs a dynamic attention unit that includes both local and global attention to generate comprehensive feature maps and calculates difference weights through linear fusion, further strengthening the feature expression ability to more accurately capture change information. Finally, the decoder generates high-precision CD results. To verify the effectiveness of MTFSR in remote sensing change detection tasks, we conducted tests on three challenging datasets (LEVIR-CD, GZ-CD, and WHU-CD). The experimental results show that MTFSR significantly outperforms traditional methods and most existing advanced techniques in change detection performance.
format Article
id doaj-art-71ad9f541fef4df2b50a5241f6d535b5
institution Kabale University
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-71ad9f541fef4df2b50a5241f6d535b52025-08-20T03:29:28ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118147661478310.1109/JSTARS.2025.357010811003578MTFSR: Multitemporal and Spatial Feature Reconstruction Denoising Network for Remote Sensing Change DetectionYeKai Cui0https://orcid.org/0009-0001-2445-4408Peng Duan1https://orcid.org/0009-0002-2333-4735Jinjiang Li2https://orcid.org/0000-0002-2080-8678School of Computer Science and Technology, Shandong Technology and Business University, Yantai, ChinaSchool of Computer Science and Technology, Shandong Technology and Business University, Yantai, ChinaSchool of Computer Science and Technology, Shandong Technology and Business University, Yantai, ChinaWith the widespread application of convolutional neural networks (CNNs) in remote sensing (RS) technologies, change detection (CD) has attracted increasing attention in environmental monitoring research. In RS image CD tasks, researchers often face challenges such as multiscale change capture inadequacy due to feature noise interference and difficulties in spatiotemporal feature alignment. To address these issues, this article proposes a multitemporal and spatial feature reconstruction denoising network for remote sensing change detection (MTFSR). MTFSR first utilizes ResNet50 to extract deep features from dual-temporal images and innovatively introduces Bézier curves to smooth the features through feature redistribution, along with brightness enhancement to effectively suppress noise interference and enhance change areas. Meanwhile, a spatial attention mechanism and discrete cosine transform (DCT) are incorporated to further improve the spatial expression and frequency domain perception of the features. Then, multiscale filtering is applied to accurately align the frequency and spatial domains, effectively solving the spatiotemporal feature inconsistency problem. On this basis, the model designs a dynamic attention unit that includes both local and global attention to generate comprehensive feature maps and calculates difference weights through linear fusion, further strengthening the feature expression ability to more accurately capture change information. Finally, the decoder generates high-precision CD results. To verify the effectiveness of MTFSR in remote sensing change detection tasks, we conducted tests on three challenging datasets (LEVIR-CD, GZ-CD, and WHU-CD). The experimental results show that MTFSR significantly outperforms traditional methods and most existing advanced techniques in change detection performance.https://ieeexplore.ieee.org/document/11003578/Attention mechanism transformerbuilding change detection (BCD)change detectionhigh-resolution remote sensing (RS) imagesimage fusion
spellingShingle YeKai Cui
Peng Duan
Jinjiang Li
MTFSR: Multitemporal and Spatial Feature Reconstruction Denoising Network for Remote Sensing Change Detection
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Attention mechanism transformer
building change detection (BCD)
change detection
high-resolution remote sensing (RS) images
image fusion
title MTFSR: Multitemporal and Spatial Feature Reconstruction Denoising Network for Remote Sensing Change Detection
title_full MTFSR: Multitemporal and Spatial Feature Reconstruction Denoising Network for Remote Sensing Change Detection
title_fullStr MTFSR: Multitemporal and Spatial Feature Reconstruction Denoising Network for Remote Sensing Change Detection
title_full_unstemmed MTFSR: Multitemporal and Spatial Feature Reconstruction Denoising Network for Remote Sensing Change Detection
title_short MTFSR: Multitemporal and Spatial Feature Reconstruction Denoising Network for Remote Sensing Change Detection
title_sort mtfsr multitemporal and spatial feature reconstruction denoising network for remote sensing change detection
topic Attention mechanism transformer
building change detection (BCD)
change detection
high-resolution remote sensing (RS) images
image fusion
url https://ieeexplore.ieee.org/document/11003578/
work_keys_str_mv AT yekaicui mtfsrmultitemporalandspatialfeaturereconstructiondenoisingnetworkforremotesensingchangedetection
AT pengduan mtfsrmultitemporalandspatialfeaturereconstructiondenoisingnetworkforremotesensingchangedetection
AT jinjiangli mtfsrmultitemporalandspatialfeaturereconstructiondenoisingnetworkforremotesensingchangedetection