Remote Sensing Image Change Detection Based on Large Kernel Re-parameter U-Net

doi:10.19678/j.issn.1000-3428.0068459

Abstract

Abstract:

A remote sensing image change detection approach based on large kernel Re-parameter U-Net (RepUNet-CD) is proposed to address the drawbacks of missing detection, false detection, and poor edge detection of existing change detection methods for processing high-precision remote sensing images. RepUNet-CD adopts U-Net as the backbone, replacing the single convolutional kernel structure in the encoder stage with a large kernel re-parameter module for feature extraction to achieve a global receptive field through an attention mechanism. Moreover, structure re-parameter technology is used to integrate small kernel structures into large kernel structures for training, which allows the network to retain the ability to capture detailed features in small receptive fields, thereby generating multiscale features and improving change detection accuracy. At the network decoder, feature maps of different phases are fused to obtain feature difference maps, and skip connections and upsampling operations are used to generate change feature maps. In addition, a feature edge enhancement module is used to enhance the network's focus on the edge information of feature maps, further improving detection accuracy and generating resulting changes. Furthermore, to solve the problem of objective imbalance between positive and negative training samples in datasets, a hybrid loss function with better robustness is adopted for network training. The proposed approach is validated on two mainstream open datasets, LEVIR-CD and WHU-CD, and it is compared with other state-of-the-art remote sensing change detection methods. Experimental results show that the proposed approach significantly improves several evaluation criteria. For the two datasets, the F1-scores increased to 91.71% and 92.60%, and the Intersections of Unions (IoUs) increased to 84.69% and 86.20%, respectively.

Key words: change detection, structure re-parameters, edge enhancement, remote sensing image, U-Net

摘要：

针对现有变化检测方法在处理高精度遥感影像时存在漏检、误检及边缘检测效果差等问题, 提出了一种基于大核重参U-Net的遥感影像变化检测方法, 简称RepU-Net-CD。该方法以U-Net为骨干网络, 在编码端用大核重参模块代替单卷积核结构进行特征提取, 实现注意力机制的全局感受野。同时, 该方法利用重参技术将小核融合进大核结构中辅助训练, 使网络保留捕获小感受野中细节特征的能力, 从而生成多尺度特征, 提高变化检测精度。在网络解码端将不同时相的特征图进行融合, 得到特征差分图, 再通过跳跃连接和上采样得到变化特征图, 最后利用特征边缘增强模块提高网络对特征图的边缘信息关注度, 进一步提高检测精度后, 生成变化结果。此外, 针对数据集客观存在的正负训练样本不平衡问题, 采用有更高鲁棒性的混合损失函数进行网络训练。本文方法在LEVIR-CD和WHU-CD两个主流的公开数据集上进行实验验证, 并与其他最新的遥感变化检测方法进行了对比。实验结果表明本文方法在许多评估指标上有显著改进, 这两个数据集上的F1值分别提高到91.71%和92.60%, 交并比(IoU)分别提高到84.69%和86.20%。

关键词: 变化检测, 结构重参化, 边缘增强, 遥感影像, U-Net

WU Chaoyu, YANG Bin. Remote Sensing Image Change Detection Based on Large Kernel Re-parameter U-Net[J]. Computer Engineering, 2025, 51(3): 261-273.

吴潮宇, 杨斌. 基于大核重参U-Net的遥感影像变化检测[J]. 计算机工程, 2025, 51(3): 261-273.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0068459

https://www.ecice06.com/EN/Y2025/V51/I3/261

Figures/Tables 15

Fig.1 Change detection framework based on U-Net

Fig.2 Large kernel re-parameter U-Net——RepU-Net-CD

Fig.3 Structure re-parameter technology

Fig.4 Structure of FEEM

Fig.5 Accuracy, precision, recall, loss, F1-score of training and accuracy of testing of model on two datasets

Fig.6 Visualization of ablation experimental results

Fig.7 Visualization results of network performance on LEVIR-CD dataset

Fig.8 Visualization results of network performance on WHU-CD dataset

References 58

1	ZHAO J, GONG M, LIU J, et al. Deep learning to classify difference image for image change detection[C]//Proceedings of 2014 International Joint Conference on Neural Networks. Washington D. C., USA: IEEE Press, 2014: 411-417.
2	DEMIR B , BOVOLO F , BRUZZONE L . Updating land-cover maps by classification of image time series: a novel change-detection-driven transfer learning approach. IEEE Transactions on Geoscience and Remote Sensing, 2012, 51 (1): 300- 312. URL
3	LIN Y, ZHANG L, WANG N. A new time series change detection method for landsat land use and land cover change[C]//Proceedings of 201910th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp). Washington D. C., USA: IEEE Press, 2019: 1-4.
4	季顺平, 田思琦, 张驰. 利用全空洞卷积神经元网络进行城市土地覆盖分类与变化检测. 武汉大学学报(信息科学版), 2020, 45 (2): 233- 241.
	JI S P , TIAN S Q , ZHANG C . Urban land cover classfication and change detection using fully atrous convolutional neural network. Geomatics and Information Science of Wuhan University, 2020, 45 (2): 233- 241.
5	GÄRTNER P , FÖRSTER M , KURBAN A , et al. Object based change detection of Central Asian Tugai vegetation with very high spatial resolution satellite imagery. International Journal of Applied Earth Observation and Geoinformation, 2014, 31, 110- 121. doi: 10.1016/j.jag.2014.03.004
6	李成龙, 张景发. 基于主成分分析的遥感震害变化检测方法与应用. 地震, 2013, 33 (2): 103- 108.
	LI C L , ZHANG J F . Method and application of earthquake damage change detection from remote sensing images based on principal component analysis. Earthquake, 2013, 33 (2): 103- 108.
7	LU P , QIN Y , LI Z , et al. Landslide mapping from multi-sensor data through improved change detection-based Markov random field. Remote Sensing of Environment, 2019, 231, 111235. doi: 10.1016/j.rse.2019.111235
8	SINGH A . Change detection in the tropical forest environment of northeastern India using Landsat. Remote Sensing and Tropical Land Management, 1986, 44, 254- 273.
9	HOWARTH P J , WICKWARE G M . Procedures for change detection using Landsat digital data. International Journal of Remote Sensing, 1981, 2 (3): 277- 291. doi: 10.1080/01431168108948362
10	HUANG W , HUANG J , WANG L , et al. Remote sensing image change detection based on change vector analysis of PCA component. Remote Sensing for Natural Resources, 2016, 28 (1): 22- 27.
11	CHEN J , CHEN X , CUI X , et al. Change vector analysis in posterior probability space: a new method for land cover change detection. IEEE Geoscience and Remote Sensing Letters, 2010, 8 (2): 317- 321.
12	NIELSEN A A , CONRADSEN K , SIMPSON J J . Multivariate alteration detection (MAD) and MAF postprocessing in multispectral, bitemporal image data: new approaches to change detection studies. Remote Sensing of Environment, 1998, 64 (1): 1- 19. doi: 10.1016/S0034-4257(97)00162-4
13	WU C , DU B , ZHANG L . Slow feature analysis for change detection in multispectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 2013, 52 (5): 2858- 2874.
14	ZHONG P , WANG R . A multiple conditional random fields ensemble model for urban area detection in remote sensing optical images. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45 (12): 3978- 3988. doi: 10.1109/TGRS.2007.907109
15	耿忠. 面向单波段高分辨率遥感影像的人工目标变化检测技术研究. 地理信息世界, 2007, 5 (6): 36- 41.
	GENG Z . Research on artificial object changing detection techniques of single-band oriented high resolution remote sensing image. Geomatics World, 2007, 5 (6): 36- 41.
16	SHI W , ZHANG M , ZHANG R , et al. Change detection based on artificial intelligence: state-of-the-art and challenges. Remote Sensing, 2020, 12 (10): 1688. doi: 10.3390/rs12101688
17	ALCANTARILLA P F , STENT S , ROS G , et al. Street-view change detection with deconvolutional networks. Autonomous Robots, 2018, 42, 1301- 1322. URL
18	PENG D , ZHANG Y , GUAN H . End-to-end change detection for high resolution satellite images using improved UNet++. Remote Sensing, 2019, 11 (11): 1382. URL
19	ZHANG X , YUE Y , GAO W , et al. DifUnet++: a satellite images change detection network based on UNet++ and differential pyramid. IEEE Geoscience and Remote Sensing Letters, 2021, 19, 8006605.
20	DAUDT R C, LE SAUX B, BOULCH A. Fully convolutional Siamese networks for change detection[C]// Proceedings of 201825th IEEE International Conference on Image Processing. Washington D. C., USA: IEEE Press, 2018: 4063-4067.
21	MOU L , BRUZZONE L , ZHU X X . Learning spectral-spatial-temporal features via a recurrent convolutional neural network for change detection in multispectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 2018, 57 (2): 924- 935. URL
22	HAN C , Wu C , GUO H , et al. HANet: a hierarchical attention network for change detection with bitemporal very-high-resolution remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16, 3867- 3878.
23	GUO E, FU X, ZHU J, et al. Learning to measure change: fully convolutional Siamese metric networks for scene change detection[EB/OL]. (2018-10-22)[2023-09-06]. https://arxiv.org/abs/1810.09111.
24	ZHANG C , YUE P , TAPETE D , et al. A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 166, 183- 200.
25	FANG S , LI K , SHAO J , et al. SNUNet-CD: a densely connected Siamese network for change detection of VHR images. IEEE Geoscience and Remote Sensing Letters, 2021, 19, 8007805. URL
26	CHEN H , SHI Z . A spatial-temporal attention-based method and a new dataset for remote sensing image change detection. Remote Sensing, 2020, 12 (10): 1662.
27	GUO Q , ZHANG J , ZHU S , et al. Deep multiscale Siamese network with parallel convolutional structure and self-attention for change detection. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60, 5406512.
28	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[EB/OL]. (2023-08-02)[2023-09-06]. https://arxiv.org/abs/1706.03762.
29	DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: Transformers for image recognition at scale[EB/OL]. (2021-06-03)[2023-09-06]. https://arxiv.org/abs/2010.11929.
30	CAO H, WANG Y, CHEN J, et al. Swin-Unet: Unet-like pure transformer for medical image segmentation[EB/OL]. (2021-05-12)[2023-09-06]. https://arxiv.org/abs/2105.05537.
31	CHEN H , QI Z , SHI Z . Remote sensing image change detection with transformers. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60, 5607514.
32	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. Washington D. C., USA: IEEE Press, 2022: 207-210.
33	RONNEBERGER O, FISCHER P, BROX T. U-net: cconvolutional networks for biomedical image segmentation[C]//Proceedings of Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2015: 234-241.
34	LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2015: 3431-3440.
35	ZHOU Z, RAHMAN SIDDIQUEE M M, TAJBAKHSH N, et al. UNet++: a nested U-Net architecture for medical image segmentation[C]//Proceedings of Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Berlin, Germany: Springer, 2018: 3-11.
36	ZHOU Z , SIDDIQUEE M M R , TAJBAKHSH N , et al. UNet++: redesigning skip connections to exploit multiscale features in image segmentation. IEEE Transactions on Medical Imaging, 2019, 39 (6): 1856- 1867. URL
37	JATURAPITPORNCHAI R , MATSUOKA M , KANEMOTO N , et al. Newly built construction detection in SAR images using deep learning. Remote Sensing, 2019, 11 (12): 1444. URL
38	PAPADOMANOLAKI M, VERMA S, VAKALOPOULOU M, et al. Detecting urban changes with recurrent neural networks from multitemporal Sentinel-2 data[C]//Proceedings of 2019 IEEE International Geoscience and Remote Sensing Symposium. Washington D. C., USA: IEEE Press, 2019: 214-217.
39	LI H , ZHU F , ZHENG X , et al. MSCDUNet: a deep learning framework for built-up area change detection integrating multispectral, SAR, and VHR data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15, 5163- 5176.
40	JIANG K, LIU J, LIU F, et al. Dual UNet: a novel Siamese network for change detection with cascade differential fusion[C]//Proceedings of 2022 IEEE International Geoscience and Remote Sensing Symposium. Washington D. C., USA: IEEE Press, 2022: 1428-1431.
41	周豫阳, 王明常, 王凤艳, 等. 改进U-Net的高分辨率遥感影像建筑区变化检测方法. 世界地质, 2023, 42 (1): 159- 167.
	ZHOU Y Y , WANG M C , WANG F Y , et al. Detection method of high-resolution remote sensing building area change based on improved U-Net. Global Geology, 2023, 42 (1): 159- 167.
42	梁燕, 易春霞, 王光宇. 基于编解码网络UNet3+的遥感影像建筑变化检测. 计算机学报, 2023, 46 (8): 1720- 1733.
	LIANG Y , YI C X , WANG G Y . Detection of building change in remote sensing image based on encoder-decoder network UNet3+. Chinese Journal of Computers, 2023, 46 (8): 1720- 1733.
43	LEI T , ZHANG Y , LÜ Z , et al. Landslide inventory mapping from bitemporal images using deep convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 2019, 16 (6): 982- 986.
44	CHEN J , YUAN Z , PENG J , et al. DASNet: dual attentive fully convolutional Siamese networks for change detection in high-resolution satellite images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 14, 1194- 1206. URL
45	LIU R , CHENG Z , ZHANG L , et al. Remote sensing image change detection based on information transmission and attention mechanism. IEEE Access, 2019, 7, 156349- 156359. URL
46	DING X, ZHANG X, HAN J, et al. Scaling up your kernels to 31×31: revisiting large kernel design in CNNs[EB/OL]. (2022-03-13)[2023-09-06]. https://arxiv.org/abs/2203.06717.
47	LIU Z, LIN Y, CAO Y, et al. Swin Transformer: hierarchical vision transformer using shifted windows[C] //Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2021: 10012-10022.
48	DING X, GUO Y, DING G, et al. ACNet: strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2019: 1911-1920.
49	DING X, ZHANG X, MA N, et al. RepVGG: making VGG-style convnets great again[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2021: 13733-13742.
50	DING X, ZHANG X, HAN J, et al. Diverse branch block: building a convolution as an inception-like unit[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2021: 10886-10895.
51	DING X, HAO T, TAN J, et al. ResRep: lossless CNN pruning via decouplingg remembering and forgetting[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2021: 4510-4520.
52	MILLETARI F, NAVAB N, AHMADI S A. V-Net: fully convolutional neural networks for volumetric medical image segmentation[EB/OL]. (2016-06-15)[2023-09-06]. https://arxiv.org/abs/1606.04797.
53	JI S , WEI S , LU M . Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set. IEEE Transactions on Geoscience and Remote Sensing, 2018, 57 (1): 574- 586. URL
54	逄涛, 张学敏, 姚亚洲, 等. 基于特征增强的光学遥感图像建筑物变化检测. 计算机工程, 2023, 49 (4): 182- 187. URL
	PANG T , ZHANG X M , YAO Y Z , et al. Optical remote sensing image building change detection based on feature enhancement. Computer Engineering, 2023, 49 (4): 182- 187. URL
55	BAI B , FU W , LU T , et al. Edge-guided recurrent convolutional neural network for multitemporal remote sensing image building change detection. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60, 5610613.
56	MO J , SEONG S , OH J , et al. SAUNet3+ CD: a Siamese-attentive UNet3+ for change detection in remote sensing images. IEEE Access, 2022, 10, 101434- 101444.
57	LIU Y , PANG C , ZHAN Z , et al. Building change detection for remote sensing images using a dual-task constrained deep Siamese convolutional network model. IEEE Geoscience and Remote Sensing Letters, 2020, 18 (5): 811- 815.
58	HAN C, WU C, DU B. HCGMNet: a hierarchical change guiding map network for change detection[C]//Proceedings of 2023 IEEE International Geoscience and Remote Sensing Symposium, Washington D. C., USA: IEEE Press, 2023: 207-210.

[1]	ZHANG Xingpeng, HE Dong, YANG Mo, YE Hangbin. Nucleus Segmentation Based on Multiscale Attention and Data Augmentation [J]. Computer Engineering, 2025, 51(2): 387-396.
[2]	Wanqiu ZHAO, Junhu ZHANG, Haitao LI. Feature Fusion Network with Parallel Structure for Building Segmentation [J]. Computer Engineering, 2024, 50(8): 239-248.
[3]	Huanyu LU, Yonghong ZHANG, Guangyi MA, Donglin XIE, Wei TIAN. Semi-Supervised Adversarial Learning-Based Water Body Extraction from Remote Sensing Images [J]. Computer Engineering, 2024, 50(7): 251-263.
[4]	CHEN Jiayu, WANG Yuanlong, ZHANG Hu. Question Generation Model Based on Text Knowledge Enhancement [J]. Computer Engineering, 2024, 50(6): 86-93.
[5]	Baihao JIANG, Jing LIU, Dawei QIU, Liang JIANG. Review of Deep Learning Applications in Spinal Image Segmentation [J]. Computer Engineering, 2024, 50(3): 1-15.
[6]	YANG Yudi, GE Haibo, XIN Shiao, XUE Zihan, YUAN Hao. Lightweight Small-Object Detection for Remote Sensing Images Integrating Super-Resolution and Feature Enhancement [J]. Computer Engineering, 2024, 50(11): 284-296.
[7]	Bingyan ZHU, Zhihua CHEN, Bin SHENG. Remote Sensing Image Detection Based on Perceptually Enhanced Swin Transformer [J]. Computer Engineering, 2024, 50(1): 216-223.
[8]	YU Haiyang, JING Peng, ZHANG Wentao, XIE Saifei, HUA Zhihua, SONG Caoyuan. Improved U-Net Model for Road Crack Detection Based on Residual and Attention Mechanism [J]. Computer Engineering, 2023, 49(6): 265-273.
[9]	PANG Tao, ZHANG Xuemin, YAO Yazhou, GAO Mingke. Optical Remote Sensing Image Building Change Detection Based on Feature Enhancement [J]. Computer Engineering, 2023, 49(4): 182-187.
[10]	HE Yue, CHEN Guangsheng, JING Weipeng, XU Zekun. Remote Sensing Image Retrieval Based on Deep Multi-Similarity Hashing Method [J]. Computer Engineering, 2023, 49(2): 206-212.
[11]	Zerui WANG, Shi CHEN. Quality-Aware Rotating-Ship Template Matching Algorithm Based on Deep Features [J]. Computer Engineering, 2023, 49(12): 161-168.
[12]	Yanggan FU, Lanwei ZHU, Hongrong WU, Fang CHEN. Coral Reef Benthic Material Information Extraction Method Based on Improved U-Net [J]. Computer Engineering, 2023, 49(12): 231-242.
[13]	Bo KONG, Hu HAN, Jingjing CHEN, Xue BAI, Fei DENG. Aspect-Based Sentiment Analysis Through Virtual Dependency and Knowledge Enhancement [J]. Computer Engineering, 2023, 49(10): 53-63.
[14]	Zhangqingqing CHU, Zhiqiang ZHONG, Ziye YAN, Yinwei ZHAN. Brain Tumor Segmentation Algorithm Based on Feature Fusion and Attention Mechanism [J]. Computer Engineering, 2023, 49(10): 154-161.
[15]	Pengquan XU, Yuxiang LIANG, Ying LI. Medical Image Segmentation Fusing Multi-Scale Semantic and Residual Bottleneck Attention [J]. Computer Engineering, 2023, 49(10): 162-170.

Please choose a citation manager

Content to export