Please wait a minute...
 
Remote Sensing for Natural Resources    2025, Vol. 37 Issue (5) : 113-121     DOI: 10.6046/zrzyyg.2024261
|
Change detection network for dual-temporal optical remote sensing images integrating fast Fourier transform and efficient multi-head self-attention
WANG Xingwei1(), TANG Kangqi2(), LIU Yan3, LIU Huan4
1. China Railway Siyuan Survey and Design Group Co.，Ltd.，Wuhan 430063，China
2. College of Earth and Planetary Sciences，Chengdu University of Technology，Chengdu 610059，China
3. College of Geography and Planning，Chengdu University of Technology，Chengdu 610059，China
4. Sichuan Anxin Kechuang Technology Co.，Ltd.，Chengdu 610045，China
Download: PDF(5536 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

The deep learning-based change detection of remote sensing images has seen rapid advances in the past few years. However，it still faces challenges for change detection in complex scenes，such as incomplete recognition and high false detection rates. In response to these challenges，this paper proposed the FTUNet，a network based on SNUnet that integrates the fast Fourier transform （FFT） and efficient multi-head self-attention （EMHSA）. Specifically，the FFT module in the network enabled style unification of dual-temporal images，reducing false detection caused by “pseudo changes” due to external factors such as light variations. Additionally，the EMHSA was introduced in the feature extraction stage to fully extract the contextual information from the feature maps，thereby enhancing the segmentation integrity of target changes. Experiments on the LEVIR-CD and SYSU-CD public datasets showed that the FTUNet exhibited increases of 1.42 and 1.53 percentage points in F1 score，as well as increases of 2.31 and 2.07 percentage points in intersection over union （IoU），compared to the SNUNet.
Keywords fast Fourier transform （FFT）      remote sensing image      change detection      style unification      contextual information     
ZTFLH:  TP79  
Issue Date: 28 October 2025
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Xingwei WANG
Kangqi TANG
Yan LIU
Huan LIU
Cite this article:   
Xingwei WANG,Kangqi TANG,Yan LIU, et al. Change detection network for dual-temporal optical remote sensing images integrating fast Fourier transform and efficient multi-head self-attention[J]. Remote Sensing for Natural Resources, 2025, 37(5): 113-121.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2024261     OR     https://www.gtzyyg.com/EN/Y2025/V37/I5/113
Fig.1  Overall structure diagram of FTUNet network
Fig.2  Basic schematic diagram of FFTM
Fig.3  LRCFEM structure diagram
Fig.4  EMHSA structure diagram
网络模型 P R IoU F1
SNUNet（基准网络） 89.91 87.21 79.44 88.54
SNUNet+FFT 90.81 87.86 80.69 89.31
SNUNet+LRCFEM 90.46 89.15 81.50 89.81
FTUNet（本文网络） 90.72 89.22 81.75 89.96
Tab.1  Results of ablation experiment （%）
序号 影像A 影像B 标签 SNUNet SNUNet+FFT SNUNet+LRCFEM FTUNet
a
b
c
d
图例
Tab.2  Visualization results of ablation experiment
Fig.5  FFTM visualization results
网络模型 P R IoU F1
FC-EF 86.69 79.87 71.15 83.14
FC-Siam-conc 89.41 85.02 77.24 87.16
FC-Siam-diff 90.12 83.01 76.09 86.42
SNUNet 89.91 87.21 79.44 88.54
BIT 92.01 86.72 80.65 89.28
FTUNet（本文网络） 90.72 89.22 81.75 89.96
Tab.3  Comparison experiment results of LEVIR-CD dataset （%）
序号 影像A 影像B 标签 FE-EF FC-Siam-
conc		 FC-Siam-
diff		 BIT SNUNet FTUNet
a
b
c
d
e
图例
Tab.4  Visualization results of LEVIR-CD dataset comparison experiment
网络模型 P R IoU F1
FC-EF 78.60 69.55 58.47 73.80
FC-Siam-conc 81.11 70.76 60.75 75.59
FC-Siam-diff 90.35 49.33 46.86 63.81
SNUNet 81.90 74.37 63.87 77.95
BIT 81.71 73.49 63.11 77.38
FTUNet（本文网络） 79.95 79.01 65.94 79.48
Tab.5  Comparison experiment results of SYSU-CD dataset （%）
序号 影像A 影像B 标签 FE-EF FC-Siam-
conc		 FC-Siam-
diff		 BIT SNUNet FTUNet
a
b
c
d
e
图例
Tab.6  Visualization results of SYSU-CD dataset comparison experiment
[1] Bruzzone L, Bovolo F. A novel framework for the design of change-detection systems for very-high-resolution remote sensing images[C]// Proceedings of the IEEE.July 24, 2012, IEEE, 2013:609-630.
[2] Zhu Q Q, Guo X, Deng W H, et al. Land-use/land-cover change detection based on a Siamese global learning framework for high spatial resolution remote sensing imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 184:63-78.
[3] Lv Z Y, Liu T F, Benediktsson J A, et al. Land cover change detection techniques:Very-high-resolution optical images:A review[J]. IEEE Geoscience and Remote Sensing Magazine, 2022, 10(1):44-63.
[4] Wen D W, Huang X, Bovolo F, et al. Change detection from very-high-spatial-resolution optical remote sensing images:Methods,applications,and future directions[J]. IEEE Geoscience and Remote Sensing Magazine, 2021, 9(4):68-101.
[5] Bhatt A, Ghosh S K, Kumar A. Spectral indices based object oriented classification for change detection using satellite data[J]. International Journal of System Assurance Engineering and Management, 2018, 9(1):33-42.
[6] Atasever U H, Kesikoglu M H, Ozkan C. A new artificial intelligence optimization method for pca based unsupervised change detection of remote sensing image data[J]. Neural Network World, 2016, 26(2):141-154.
[7] Nagne A D, Vibhute A D, Dhumal R K, et al. Urban LULC change detection and mapping spatial variations of Aurangabad City using IRS LISS-III temporal datasets and supervised classification approach[M]//Data Analytics and Learning. Singapore: Springer Singapore,2018:369-386.
[8] Zhang X F, Cheng S L, Wang L J, et al. Asymmetric cross-attention hierarchical network based on CNN and Transformer for bitemporal remote sensing images change detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61:2000415.
[9] Fang S, Li K Y, Shao J Y, et al. SNUNet-CD:A densely connected Siamese network for change detection of VHR images[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19:8007805.
[10] Daudt R C, Le Saux B, Boulch A. Fully convolutional Siamese networks for change detection[C]//2018 25th IEEE International Conference on Image Processing (ICIP). October 7-10,2018.Athens. IEEE, 2018:4063-4067.
[11] Chen H, Shi Z W. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection[J]. Remote Sensing, 2020, 12(10):1662.
[12] Zhang C X, Yue P, Tapete D, et al. A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 166:183-200.
[13] Zhou Z W, Rahman Siddiquee M M, Tajbakhsh N, et al. UNet++:A nested U-Net architecture for medical image segmentation[M]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham: Springer Internatio-nal Publishing,2018:3-11.
[14] Chen H, Qi Z P, Shi Z W. Remote sensing image change detection with Transformers[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60:5607514.
[15] Feng Y C, Jiang J W, Xu H H, et al. Change detection on remote sensing images using dual-branch multilevel intertemporal network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61:4401015.
[16] Zhang R Q, Zhang H C, Ning X G, et al. Global-aware Siamese network for change detection on remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 199:61-72.
[17] 宋嘉鑫, 李轶鲲, 杨树文, 等. 基于后验概率空间变化向量分析的NSCT高分辨率遥感影像变化检测[J]. 自然资源遥感, 2024, 36(3):128-136.doi:10.6046/zrzyyg.2023079.
[17] Song J X, Li Y K, Yang S W, et al. NSCT-based change detection for high-resolution remote sensing images under the framework of change vector analysis in posterior probability space[J]. Remote Sensing for Natural Resources, 2024, 36(3):128-136.doi:10.6046/zrzyyg.2023079.
[18] 柴佳兴, 张云生, 杨振, 等. 联合无人机影像生成DSM和DOM的多层次建筑物变化检测[J]. 自然资源遥感, 2024, 36(2):80-88.doi:10.6046/zrzyyg.2023001.
[18] Chai J X, Zhang Y S, Yang Z, et al. Multi-level building change detection based on the DSM and DOM generated from UAV images[J]. Remote Sensing for Natural Resources, 2024, 36(2):80-88.doi:10.6046/zrzyyg.2023001.
[19] 马惠, 刘波, 杜世宏. 多任务学习孪生网络的遥感影像多类变化检测[J]. 自然资源遥感, 2024, 36(1):77-85.doi:10.6046/zrzyyg.2022446.
[19] Ma H, Liu B, Du S H. Multi-class change detection using a multi-task Siamese network of remote sensing images[J]. Remote Sensing for Natural Resources, 2024, 36(1):77-85.doi:10.6046/zrzyyg.2022446.
[20] Duhamel P, Vetterli M. Fast Fourier transforms:A tutorial review and a state of the art[J]. Signal Processing, 1990, 19(4):259-299.
[21] Gao Y H, Zhou M, Metaxas D N. UTNet:A hybrid transformer architecture for medical image segmentation[M]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2021.Cham: Springer International Publishing,2021:61-71.
[22] Shi Q, Liu M X, Li S C, et al. A deeply supervised attention metric-based network and an open aerial image dataset for remote sensing change detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60:5604816.
[1] ZHU Juanjuan, HUANG Liang, ZHU Shasha. SD-BASNet：a building extraction network for high-spatial-resolution remote sensing imagery[J]. Remote Sensing for Natural Resources, 2025, 37(5): 122-130.
[2] GONG Shaojun, CHEN Chao, FAN Jing. A precise coastline extraction method using surface moisture content and long-time-series remote sensing imagery[J]. Remote Sensing for Natural Resources, 2025, 37(5): 53-61.
[3] FANG Liuyang, YANG Changhao, SHU Dong, YANG Xuekun, CHEN Xingtong, JIA Zhiwen. Landslide detection in complex environments based on dual feature fusion[J]. Remote Sensing for Natural Resources, 2025, 37(5): 91-100.
[4] XU Ziyao, YANG Wu, SHI Xiaolong. Small target detection in remote sensing images based on lightweight YOLOv7-tiny[J]. Remote Sensing for Natural Resources, 2025, 37(4): 1-11.
[5] WANG Xinshuang, ZHAO Yehe, LIU Jiange, SUN Xin, ZHANG Yongzhen, MAO Dehua. Remote sensing-based assessment of wetland restoration potential in important wetland reserves along the Silk Road[J]. Remote Sensing for Natural Resources, 2025, 37(4): 204-211.
[6] LIU Haoran, YAN Tianxiao, ZHU Yueqin, WANG Yanping, CHEN Zuyi, YANG Zhaoying, ZHU Haomeng. Landslide identification based on an improved YOLOv7 model: A case study of the Baige area[J]. Remote Sensing for Natural Resources, 2025, 37(4): 48-57.
[7] ZHANG Qiao, CAO Zhicheng, SHEN Yang, WANG Zhoufeng, WANG Chengwu, XU Jiaxin. A method combining the siamese inverted residual structure with self-attention enhancement for change detection based on remote sensing images[J]. Remote Sensing for Natural Resources, 2025, 37(3): 85-94.
[8] HE Xiaojun, LUO Jie. Semantic segmentation of high-resolution remote sensing images based on context- and class-aware feature fusion[J]. Remote Sensing for Natural Resources, 2025, 37(2): 1-10.
[9] PANG Min. An intelligent platform for extracting patches from multisource domestic satellite images and its application[J]. Remote Sensing for Natural Resources, 2025, 37(2): 148-154.
[10] SHAO Pan, GUAN Zongsheng, JIA Fuwen. Unsupervised change detection using SAR images based on the broad learning system[J]. Remote Sensing for Natural Resources, 2025, 37(2): 19-29.
[11] NIE Shiyin, LIU Yansong, LI Huiling, XUE Kailun, SHEN Duheng, HE Boyu. Identification and classification of land types of alpine wetlands based on spectral coupling[J]. Remote Sensing for Natural Resources, 2025, 37(2): 204-211.
[12] DENG Jianming, YAO Hang, FU Bolin, GU Sen, TANG Jie, GAN Yuanyuan. Monitoring the spatiotemporal dynamics of mangrove forests in Beibu Gulf, Guangxi Zhuang Autonomous Region, China, using Google Earth Engine and time-series active and passive remote sensing images[J]. Remote Sensing for Natural Resources, 2025, 37(2): 235-245.
[13] CHEN Jiaxue, XIAO Dongsheng, CHEN Hongyu. A boundary guidance and cross-scale information interaction network for water body extraction from remote sensing images[J]. Remote Sensing for Natural Resources, 2025, 37(1): 15-23.
[14] XU Xinyu, LI Xiaojun, GE Junfei, LI Yikun. A multispectral image pansharpening algorithm based on nonsubsampled contourlet transform (NSCT) combined with a guided filter[J]. Remote Sensing for Natural Resources, 2025, 37(1): 24-30.
[15] WANG Tixin, YANG Jinzhong, XING Yu, WANG Kaijian. A method for automatic mapping of the remote sensing monitoring results of national nature reserves based on ArcPy and map optimization[J]. Remote Sensing for Natural Resources, 2025, 37(1): 252-259.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech