High-resolution remote sensing image change detection based on feature subspace decoupling and iterative residual refinement

LI Hanzhi; LI Haiwei; GUO Qi; ZHAO Yi; SONG Liyao; LI Siyuan; LIU Sihan; XIE Yuhao

doi:10.37188/CJLCD.2026-0003

您当前的位置：

首页 >

文章列表页 >

High-resolution remote sensing image change detection based on feature subspace decoupling and iterative residual refinement

Image Processing | 更新时间：2026-09-20

- High-resolution remote sensing image change detection based on feature subspace decoupling and iterative residual refinement
- Chinese Journal of Liquid Crystals and Displays Vol. 41, Issue 3, Pages: 402-414(2026)
- 作者机构：
  
  1.中国科学院西安光学精密机械研究所，陕西西安 710119
  2.中国科学院大学，北京 101408
  3.西安工业大学计算机科学与工程学院，陕西西安 710021
  4.生态环境部卫星环境应用中心，北京 100006
- 作者简介：
- 基金信息：
  
  National Key Research and Development Program of China(2022YFF1300201);General Special Scientific Research Program Project of the Shaanxi Provincial Department of Education(24JK0481);Natural Science Foundation of Shaanxi Province(2025JC-YBQN-366;2025JC-YBMS-256)
- DOI：10.37188/CJLCD.2026-0003
  CLC： TP391.4;TP751.1
- CSTR：32172.14.CJLCD.2026-0003
- Received：07 January 2026，
  
  Revised：2026-02-01，
  
  Published：05 March 2026
- 稿件说明：
移动端阅览
LI Hanzhi, LI Haiwei, GUO Qi, et al. High-resolution remote sensing image change detection based on feature subspace decoupling and iterative residual refinement[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(3): 402-414.
DOI：

LI Hanzhi, LI Haiwei, GUO Qi, et al. High-resolution remote sensing image change detection based on feature subspace decoupling and iterative residual refinement[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(3): 402-414. DOI： 10.37188/CJLCD.2026-0003. CSTR： 32172.14.CJLCD.2026-0003.

摘要

随着高分辨率遥感对地观测技术的发展，影像中丰富的地物纹理细节在提升信息量的同时，也引入了由光照、阴影及季节性物候差异导致的复杂背景噪声。针对高分辨率遥感变化检测中复杂背景噪声引发的伪变化误检，以及传统上采样导致的微小目标细节丢失问题，提出一种基于特征解耦与迭代精炼的网络（DIR-Net）。首先，利用预训练的FastSAM作为视觉先验编码器，提取多尺度鲁棒特征。接着，设计特征子空间解耦模块，通过正交投影和交叉重校准策略，显式地将双时相特征分解为共享语义子空间和差异特征子空间，从源头抑制环境噪声。最后，提出迭代残差精炼模块，引入坐标注意力机制，将解码过程建模为由粗到精的残差回归问题，在保持分辨率的特征空间中逐步恢复微小目标的边缘细节。在LEVIR-CD、WHU-CD和SYSU-CD三个公开数据集上的实验结果表明，DIR-Net的F1分数分别达到了91.33%、93.31%和86.29%。相比于主流的ChangeFormer和BIT算法，F1分数平均提升了约5.0%，显著降低了伪变化误报率，同时保持了极高的召回率。该方法有效解决了特征耦合与细节丢失的难题，在复杂场景下具有更强的鲁棒性和更高的边界定位精度。

Abstract

With the development of high-resolution remote sensing earth observation technology， the rich texture details in images enhance information content but also introduce complex background noise caused by lighting， shadows， and seasonal phenological differences. To address the issues of pseudo-change misdetection caused by complex background noise and the loss of small target details caused by traditional upsampling in high-resolution remote sensing change detection， a network based on feature decoupling and iterative refinement（DIR-Net） is proposed. First， the pre-trained FastSAM is utilized as a visual prior encoder to extract multi-scale robust features. Next， a Feature Subspace Decoupling Module is designed to explicitly decompose bi-temporal features into a shared semantic subspace and a differential feature subspace through orthogonal projection and cross-recalibration strategies， suppressing environmental noise from the source. Finally， an Iterative Residual Refinement Module is proposed. By introducing a coordinate attention mechanism， the decoding process is modeled as a coarse-to-fine residual regression problem， gradually recovering the edge details of small targets in the resolution-maintained feature space. Experimental results on three public datasets， LEVIR-CD， WHU-CD， and SYSU-CD， demonstrate that the F1 scores of DIR-Net reached 91.33%， 93.31%， and 86.29%， respectively. Compared with mainstream ChangeFormer and BIT algorithms， the F1 score improved by an average of approximately 5.0%. The proposed method significantly reduces the false alarm rate of pseudo-changes while maintaining a very high recall rate. This method effectively resolves the challenges of feature coupling and detail loss， demonstrating stronger robustness and higher boundary localization accuracy in complex scenes.

关键词

Keywords

references

SINGH A . Review article digital change detection techniques using remotely-sensed data ［J］. International Journal of Remote Sensing ， 1989 ， 10 （ 6 ）： 989 - 1003 . doi: 10.1080/01431168908903939 http://dx.doi.org/10.1080/01431168908903939

LU D ， MAUSEL P ， BRONDÍZIO E ， et al . Change detection techniques ［J］. International Journal of Remote Sensing ， 2004 ， 25 （ 12 ）： 2365 - 2401 . doi: 10.1080/0143116031000139863 http://dx.doi.org/10.1080/0143116031000139863

李延伟，伍雁雄，陈太喜，等 . 超薄超短物像距高分辨率检测成像系统设计与试验［J］. 中国光学（中英文）， 2024 ， 17 （ 1 ）： 61 - 68 . doi: 10.37188/CO.2023-0099 http://dx.doi.org/10.37188/CO.2023-0099

LI Y W ， WU Y X ， CHEN T X ， et al . Design and experiment of high-resolution detection imaging system with ultra-thin and ultra-short object-image distance ［J］. Chinese Optics ， 2024 ， 17 （ 1 ）： 61 - 68 . （in Chinese） . doi: 10.37188/CO.2023-0099 http://dx.doi.org/10.37188/CO.2023-0099

毛红敏，丁致雅，杨燕燕 . 大气湍流对高分辨率遥感卫星的成像影响研究［J］. 中国光学（中英文）， 2024 ， 17 （ 1 ）： 167 - 177 . doi: 10.37188/CO.2023-0083 http://dx.doi.org/10.37188/CO.2023-0083

MAO H M ， DING Z Y ， YANG Y Y ， et al . Effect of atmospheric turbulence on imaging quality of high-resolution remote sensing satellites ［J］. Chinese Optics ， 2024 ， 17 （ 1 ）： 167 - 177 . （in Chinese） . doi: 10.37188/CO.2023-0083 http://dx.doi.org/10.37188/CO.2023-0083

熊晶，董婷，管宗胜 . 双域差异和尺度选择增强的遥感影像变化检测［J］. 液晶与显示， 2025 ， 40 （ 11 ）： 1661 - 1674 . doi: 10.37188/cjlcd.2025-0155 http://dx.doi.org/10.37188/cjlcd.2025-0155

XIONG J ， DONG T ， GUAN Z S . Dual-domain difference and scale selection enhancement for remote sensing image change detection ［J］. Chinese Journal of Liquid Crystals and Displays ， 2025 ， 40 （ 11 ）： 1661 - 1674 . （in Chinese） . doi: 10.37188/cjlcd.2025-0155 http://dx.doi.org/10.37188/cjlcd.2025-0155

VASWANI A ， SHAZEER N ， PARMAR N ， et al . Attention is all you need ［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach， CA， USA ： Curran Associates Inc. ， 2017 ： 6000 - 6010

LECUN Y ， BOTTOU L ， BENGIO Y ， et al . Gradient-based learning applied to document recognition ［J］. Proceedings of the IEEE ， 1998 ， 86 （ 11 ）： 2278 - 2324 . doi: 10.1109/5.726791 http://dx.doi.org/10.1109/5.726791

白晨帅，白晓凤，邬开俊，等 . 超融合残差行进几何感知的遥感目标检测［J］. 光学精密工程， 2025 ， 33 （ 8 ）： 1289 - 1302 . doi: 10.37188/ope.20253308.1289 http://dx.doi.org/10.37188/ope.20253308.1289

BAI C S ， BAI X F ， WU K J ， et al . Remote sensing object detection algorithm based on ultra fusion residual marching geometric perception ［J］. Optics and Precision Engineering ， 2025 ， 33 （ 8 ）： 1289 - 1302 . （in Chinese） . doi: 10.37188/ope.20253308.1289 http://dx.doi.org/10.37188/ope.20253308.1289

潘梦洋，杨航，范祥晖 . 基于CNN-Transformer结构的遥感影像变化检测［J］. 液晶与显示， 2024 ， 39 （ 10 ）： 1361 - 1379 . doi: 10.37188/CJLCD.2024-0086 http://dx.doi.org/10.37188/CJLCD.2024-0086

PAN M Y ， YANG H ， FAN X H . Remote sensing image change detection based on CNN-Transformer structure ［J］. Chinese Journal of Liquid Crystals and Displays ， 2024 ， 39 （ 10 ）： 1361 - 1379 . （in Chinese） . doi: 10.37188/CJLCD.2024-0086 http://dx.doi.org/10.37188/CJLCD.2024-0086

DAUDT R C ， LE SAUX B ， BOULCH A . Fully convolutional siamese networks for change detection ［C］// Proceedings of the 2018 25th IEEE International Conference on Image Processing . Athens， Greece ： IEEE ， 2018 ： 4063 - 4067 . doi: 10.1109/icip.2018.8451652 http://dx.doi.org/10.1109/icip.2018.8451652

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 ， 2022 ， 19 ： 8007805 . doi: 10.1109/lgrs.2021.3056416 http://dx.doi.org/10.1109/lgrs.2021.3056416

BANDARA W G C ， PATEL V M . A transformer-based siamese network for change detection ［C］// Proceedings of 2022 IEEE International Geoscience and Remote Sensing Symposium . Kuala Lumpur， Malaysia ： IEEE ， 2022 ： 207 - 210 . doi: 10.1109/igarss46834.2022.9883686 http://dx.doi.org/10.1109/igarss46834.2022.9883686

SHELHAMER E ， LONG J ， DARRELL T . Fully convolutional networks for semantic segmentation ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence ， 2017 ， 39 （ 4 ）： 640 - 651 . doi: 10.1109/tpami.2016.2572683 http://dx.doi.org/10.1109/tpami.2016.2572683

KIRILLOV A ， MINTUN E ， RAVI N ， et al . Segment anything ［C］// Proceedings of 2023 IEEE/CVF International Conference on Computer Vision . Paris， France ： IEEE ， 2023 ： 3992 - 4003 . doi: 10.1109/iccv51070.2023.00371 http://dx.doi.org/10.1109/iccv51070.2023.00371

ZHAO X ， DING W C ， AN Y Q ， et al . Fast segment anything ［J/OL］. arXiv ， 2023 ： 2306 . 12156 . doi: 10.48550/arXiv.2306.12156 http://dx.doi.org/10.48550/arXiv.2306.12156

VARGHESE R S M . YOLOv8： a novel object detection algorithm with enhanced performance and robustness ［C］// Proceedings of 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems . Chennai， India ： IEEE ， 2024 ： 1 - 6 . doi: 10.1109/adics58448.2024.10533619 http://dx.doi.org/10.1109/adics58448.2024.10533619

RONNEBERGER O ， FISCHER P ， BROX T . U-Net： convolutional networks for biomedical image segmentation ［C］// Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention . Munich， Germany ： Springer ， 2015 ： 234 - 241 . doi: 10.1007/978-3-319-24574-4_28 http://dx.doi.org/10.1007/978-3-319-24574-4_28

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 . doi: 10.3390/rs12101662 http://dx.doi.org/10.3390/rs12101662

JI S P ， WEI S Q ， LU M . Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2019 ， 57 （ 1 ）： 574 - 586 . doi: 10.1109/tgrs.2018.2858817 http://dx.doi.org/10.1109/tgrs.2018.2858817

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 ， 2022 ， 60 ： 5604816 . doi: 10.1109/tgrs.2021.3085870 http://dx.doi.org/10.1109/tgrs.2021.3085870

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 . doi: 10.1016/j.isprsjprs.2020.06.003 http://dx.doi.org/10.1016/j.isprsjprs.2020.06.003

LIU Y ， PANG C ， ZHAN Z Q ， et al . Building change detection for remote sensing images using a dual-task constrained deep siamese convolutional network model ［J］. IEEE Geoscience and Remote Sensing Letters ， 2021 ， 18 （ 5 ）： 811 - 815 . doi: 10.1109/lgrs.2020.2988032 http://dx.doi.org/10.1109/lgrs.2020.2988032

CHEN H ， QI Z P ， SHI Z W . Remote sensing image change detection with Transformers ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2022 ， 60 ： 5607514 . doi: 10.1109/tgrs.2021.3095166 http://dx.doi.org/10.1109/tgrs.2021.3095166

LIU T F ， GONG M G ， LU D ， et al . Building change detection for VHR remote sensing images via local-global pyramid network and cross-task transfer learning strategy ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2022 ， 60 ： 4704817 . doi: 10.1109/tgrs.2021.3130940 http://dx.doi.org/10.1109/tgrs.2021.3130940

HAN C X ， WU C ， GUO H N ， et al . Change guiding network： incorporating change prior to guide change detection in remote sensing imagery ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ， 2023 ， 16 ： 8395 - 8407 . doi: 10.1109/jstars.2023.3310208 http://dx.doi.org/10.1109/jstars.2023.3310208

Views

405

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Lightweight detection of foreign objects on road surfaces in challenging driving environments

Photovoltaic infrared defect detection algorithm based on improved RT-DETR

Retinal micro-vessel segmentation based on wavelet and coarse probability prior dual-branch network

UAV aerial images object detection algorithm based on YOLOv11n

Driving response and two-stage waveform control of quantum-dot electrowetting display devices

Related Author

GUO Qi

ZHAO Yi

SONG Liyao

LI Siyuan

LIU Sihan

XIE Yuhao

ZHANG Chuanwei

SHANG Zhaobin

Related Institution

School of Mechanical Engineering， Xi′an University of Science and Technology， Xi′an

Shaanxi College of Communications Technology， Xi′an

School of Computer Science and Technology， Xi'an University of Posts and Telecommunications

College of Electronics and Electrical Engineering， Ningxia University

Key Laboratory of Advanced Manufacturing and Automation Technology （Guilin University of Technology）， Education Department of Guangxi Zhuang Autonomous Region

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰