Abstract
Real-time and rapid detection of building changes can play an important role in natural resource management. In practical change detection, many existing change detection methods need to be further improved, for example, in terms of reducing the computational cost of modeling and improving model accuracy. In this article, we propose a lightweight Siamese multiscale fusion network for building change detection. The encoder uses coordinate attention mechanism enhancement feature extraction, while the decoder uses multi-scale fusion to reconstruct the change region. In the network structure, 3 × 1, 1 × 3 and 1 × 1 convolution is widely used to replace 3 × 3 to reduce network model parameters. Finally, we use a hybrid loss function to alleviate the sample imbalance problem and a deep supervision strategy to fully utilize network hidden layer information. In comparison to other models, the model proposed in this paper achieves the best scores of 90.25%, 82.23% and 90.39%, 82.47% for its recall and IOU metrics on the LEVIR-CD and WHU-CD datasets, respectively. Experimental results show that the network model in this paper performs well in change detection.
Similar content being viewed by others
Data availability
No datasets were generated or analysed during the current study.
References
Alcantarilla PF (2018) Street-view Change Detection with Deconvolutional Networks. Auton Robot 42(7):1301–1322
Bruzzone L, Prieto DF (2020) Automatic analysis of the difference image for unsupervised change detection. IEEE Trans Geosci Remote Sens 38(3):1171–1182
Cao G, Li YP, Liu YZ, Shang YF (2014) Automatic change detection in high-resolution remote-sensing images by means of level set evolution and support vector machine classification. Int J Remote Sens 35(16):6255–6270
Chen H, Shi ZW (2020) A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection. Remote Sensing 12(10):1662
Chen J, Yuan ZY, Peng J, Chen L, Huang HZ, Zhu JW, Liu Y, Li HF (2021) DASNet: Dual Attentive Fully Convolutional Siamese Networks for Change Detection in High-Resolution Satellite Images. IEEE J Sel Top Appl Earth Obs Remote Sens 14:1194–1206
Chen H, Qi ZP, Shi ZW (2022) Remote Sensing Image Change Detection With Transformers. IEEE Trans Geosci Remote Sens 60:1–14
Cheng GL, Huang YM, Li XT, Lyu SC, Xu ZY, Zhao Q Xiang SM (2023) Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review. arXiv:2305.05813
Daudt RC, Saux BL, Boulch A, Gousseau Y (2018a) Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks. IGARSS 2018 - 2018. IEEE Int Geosci Remote Sens Symp 2115–2118
Daudt RC, Saux BL, Boulch A (2018b) Fully Convolutional Siamese Networks for Change Detection. 2018 25th IEEE International Conference on Image Processing (ICIP) 4063–4067
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai XH, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv: 2010.11929
Fang S, Li KY, Shao JY, Li Z (2022) SNUNet-CD: A Densely Connected Siamese Network for Change Detection of VHR Images. IEEE Geosci Remote Sens Lett 19:1–5
Feng YC, Xu HH, Jiang JW, Hao L, Zheng JW (2022) ICIF-Net: Intra-Scale Cross-Interaction and Inter-Scale Feature Fusion Network for Bitemporal Remote Sensing Images Change Detection. IEEE Trans Geosci Remote Sens 60:1–13
Fu J, Liu J, Tian HJ, Fang ZW, Lu HQ (2019) Dual Attention Network for Scene Segmentation. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019:3141–3149
He KM, Zhang X, Ren SQ, Sun J (2016) Deep Residual Learning for Image Recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016:770–778
Ho YS, Wookey S (2020) The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabeling. IEEE Access 8:4806–4813
Hou QB, Zhou DQ, Feng JS (2021) Coordinate Attention for Efficient Mobile Network Design. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021:13708–13717
Hu J, Shen L, Albanie S, Sun G, Wu EH (2018) Squeeze-and-Excitation Networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition 2018:7132–7141
Huang ZL, Wang XG, Huang LC, Huang C, Wei YC, Shi H, Liu WY (2020b) CCNet: Criss-Cross Attention for Semantic Segmentation. IEEE Trans Pattern Anal Mach Intell 45(6):6896–6908
Huang HM, Lin LF, Tong RF, Hu HJ, Zhang QW, Iwamoto Y, Han XH, Chen YW, Wu J (2020) UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation. ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 1055–1059
Ji SP, Wei SQ, Lu M (2019) Fully Convolutional Networks for Multisource Building Extraction from an Open Aerial and Satellite Imagery Data Set. IEEE Trans Geosci Remote Sens 57(1):574–586
Jin SM, Yang LM, Danielson P, Homer CG, Fry JE, Xian GZ (2013) A comprehensive change detection method for updating the National Land Cover Database to circa 2011. Remote Sens Environ 132:159–175
Kesikoglu MH, Atasever UH, Ozkan C (2013) Unsupervised change detection in satellite images using fuzzy c-means clustering and principal component analysis. ISPRS - Int Arch Photogramm, Remote SensSpatial Inf Sci 129–132
Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. ICML deep learning workshop 2(1)
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Commun ACM 60:84–90
Lei T, Wang J, Ning HL, Wang XW, Xue DH, Wang Q, Nandi AK (2021) Difference Enhancement and Spatial-Spectral Non-Local Network for Change Detection in VHR Remote Sensing Images. IEEE Trans Geosci Remote Sens 60:1–13
Li X, Wang WH, Hu XL, Yang J (2019) Selective Kernel Networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019:510–519
Li DR, Jiang WM, J, (2020) China’s high-resolution optical remote sensing satellites and their mapping applications. Geo-Spatial Inf Sci 24:85–94
Li WM, Xue LH, Wang XQ, Li G (2023) ConvTransNet: A CNN–Transformer Network for Change Detection with Multiscale Global-Local Representations. IEEE Trans Geosci Remote Sens 61:1–15
Li KY, Li Z, Fang S (2021) Siamese NestedUNet Networks for Change Detection of High Resolution Satellite Image. Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System 42–48
Liu MX, Chai ZQ, Deng HJ, Liu R (2022) A CNN-Transformer Network With Multiscale Context Aggregation for Fine-Grained Cropland Change Detection. IEEE J Sel Top Applied Earth Obs Remote Sens 15:4297–4306
Loshchilov I, Hutter F (2017) Decoupled Weight Decay Regularization. arXiv: 1711.05101
Luo H, Liu C, Wu C, Guo X (2018) Urban Change Detection Based on Dempster-Shafer Theory for Multitemporal Very High-Resolution Imagery. Remote Sensing 10(7):980
Milletarì F, Navab N, Ahmadi S-A (2016) V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. Fourth International Conference on 3D Vision (3DV) 565–571
Papadomanolaki M, Vakalopoulou M, Karantzalos K (2021) A Deep Multitask Learning Framework Coupling Semantic Segmentation and Fully Convolutional LSTM Networks for Urban Change Detection. IEEE Trans Geosci Remote Sens 59(9):7651–7668
Peng DF, Zhang YJ, Guan HY (2019) End-to-End Change Detection for High Resolution Satellite Images Using Improved UNet++. Remote Sensing 11(11):1382
Peng CC, Zeng JY, Chen KS, Li ZG, Ma HL, Zhang X, Shi PF, Wang TT, Yi L, Bi HY (2023) Global spatiotemporal trend of satellite-based soil moisture and its influencing factors in the early 21st century. Remote Sens Environ 291
Ronneberger O, Fischer P, Brox T (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. Ar-Xiv: 1505.04597
Simonyan K and Zisserman A(2014) Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv: 1409.1556
Sun X, Wang PJ, Yan ZY, Xu F, Wang RP, Diao WH, Chen J, Li JH, Feng YC, Xu T, Weinmann M, Hinz S, Wang C, Fu K (2021) FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery. arXiv preprint arXiv:2103.05569
Wang X, Girshick RB, Gupta AK, He KM (2018) Non-local Neural Networks 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition : 7794–7803
Wang QL, Wu BG, Zhu PF, Li P, Zuo WM, Hu QH (2020) ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) : 11531–11539
Woo, S, Park JC, Lee J-Y, Kweon I-S (2018) CBAM: Convolutional Block Attention Module. arXiv:1807.06521
Wu C, Du B, Cui XH, Zhang LP (2017) A post-classification change detection method based on iterative slow feature analysis and Bayesian soft fusion. Remote Sens Environ 199:241–255
Wu CY, Zhang F, Xia JS, Xu YC, Li GQ, Xie JB, Du ZH, Liu RY (2021) Building Damage Detection Using U-Net with Attention Mechanism from Pre- and Post-Disaster Remote Sensing Datasets. Remote Sensing 13:905
Wu YR, Zhang LL, Gu ZH, Lu H, Wan SH (2023a) Edge-AI-Driven Framework with Efficient Mobile Network Design for Facial Expression Recognition 22(3):1–17
Wu YR, Kong QR, Zhang LL, Castiglione Aniello, Nappi Michele, Wan SH (2023b) CDT-CAD: Context-Aware Deformable Transformers for End-to-End Chest Abnormality Detection on X-Ray Images. IEEE/ACM Transactions on Computational Biology and Bioinformatics 1–12
Wu YR, Zhang LL, Gu ZH, Lu H, Wan SH (2023) Edge-AI-driven framework with efficient mobile network design for facial expression recognition. ACM Trans Embed Comput Syst 22(3):1–17
Xu SJ, Fina S (2023) National-scale imperviousness mapping and detection of urban land changes. ISPRS J Photogramm Remote Sens 202:369–384
Xu H, Qi SH, Li X, Gao C, Wei YC, Liu C (2021) Monitoring three-decade dynamics of citrus planting in Southeastern China using dense Landsat records. Int J Appl Earth Obs Geoinformation 103:102518
Zhang YJ, Peng DF, Huang X (2018) Object-Based Change Detection for VHR Images Based on Multiscale Uncertainty Analysis. IEEE Geosci Remote Sens Lett 15(1):13–17
Zhang CX, Yue P, Tapete D, Jiang LC (2020) A Deeply Supervised Image Fusion Network for Change Detection in High Resolution Bi-Temporal Remote Sensing Images. ISPRS J Photogramm Remote Sens 166:183–200
Zhang C, Wang LJ, Cheng SL, Li YM (2022) SwinSUNet: Pure Transformer Network for Remote Sensing Image Change Detection. IEEE Trans Geosci Remote Sens 60:1–13
Zhou ZW, Siddiquee MMR, Tajbakhsh N, Liang J (2020) UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation. IEEE Trans Med Imaging 39(6):1856–1867
Funding
This research was funded by National Natural Science Foundation of China (grant NO. 42361054) Yunnan Fundamental Research Projects (grant NO.202201AT070164), Hunan Provincial Natural Science Foundation of China (grant NO. 2023JJ60561) and "Xingdian" talent support program project.
Author information
Authors and Affiliations
Contributions
W.L.: algorithm proposed and testing, manuscript writing, and research conceptualization. L.H.: funding acquisition, directing, and manuscript writing.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Communicated by H. Babaie
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Le, W., Huang, L. A lightweight building change detection network with coordinate attention and multiscale fusion. Earth Sci Inform (2024). https://doi.org/10.1007/s12145-024-01315-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12145-024-01315-5