Abstract
Change detection (CD) has sparked a lot of scientific interest in recent decades as one of the core concerns in Earth observation. The enhancement of the CD source data with the availability of multitemporal images with varying resolutions provides ample change indicators due to the rapid improvement of satellite sensors. However, precisely detecting real changed locations continues to be a complicated task. CD from remote sensing images (RSI) becomes challenging when the labeled data for supervised learning is unavailable. This article proposes a novel CD framework using a self-supervised learning (SSL) approach to overcome these limitations. First, the superpixel segmentation method of simple linear iterative clustering (SLIC) using a structural similarity index is incorporated to produce a difference image (DI). The change features are extracted to represent the difference information using spatial features between the corresponding superpixels. Second, a parallel clustering algorithm called fuzzy C-means (FCM) separates the DI into three clusters of changed, unchanged, and intermediate classes. The image patches of changed, unchanged and intermediate classes are constructed as training and testing samples. A lightweight deep convolutional neural network (LWDCNN) is trained with the training samples to detect the semantic difference and classify the testing samples into the changed or unchanged class. Finally, merging intermediate and change class labels generates a robust and high-contrast CD map. Numerical experiments were performed on two small regions like the Alappuzha, Kerala, India, and Paris building dataset to demonstrate the usefulness of the proposed approach, achieving an overall accuracy of 98.28% and 96.43% for determining changes effectively.
Similar content being viewed by others
References
Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S (2012) Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282
Attioui S, Najah S (2021). Unsupervised change detection method in SAR images based on deep belief network using an improved fuzzy C-means clustering algorithm. IET Image Process
Baudhuin H, Lambot A, Schaus P (2020) Change detection in satellite imagery using deep learning
Bezdek JC, Ehrlich R, Full W (1984) Fcm: the fuzzy c-means clustering algorithm. Comput Geosci 10(2–3):191–203
Chen Y, Bruzzone L (2022) A self-supervised approach to pixel level change detection in bi-temporal RS images. IEEE Trans Geosci Remote Sens 60:1–11
Chen Y, Bruzzone L (2022) Self-supervised change detection in multiview remote sensing images. IEEE Trans Geosci Remote Sens 60:1–12. https://doi.org/10.1109/TGRS.2021.3089453
Dai Y, Zheng T, Xue C, Zhou L (2023) MViT-PCD: a lightweight ViT-based network for Martian surface topographic change detection. IEEE Geosci Remote Sens Lett 20:1–5
Dong H, Ma W, Wu Y, Zhang J, Jiao L (2020) Self-supervised representation learning for remote sensing image change detection based on temporal prediction. Remote Sens 12(11):1868
Du H, Zhuang Y, Dong S, Li C, Chen H, Zhao B, Chen L (2021). Bilateral semantic fusion siamese network for change detection from multitemporal optical remote sensing imagery. IEEE Geosci Remote Sens Lett
Fang, H., Du, P., Wang, X., Lin, C., Tang, P. (2021). Unsupervised change detection based on weighted change vector analysis and improved Markov random field for high spatial resolution imagery. IEEE Geosci Remote Sens Lett
Fang W, Xi C (2022) Land-cover change detection for SAR images based on biobjective fuzzy local information clustering method with decomposition. IEEE Geosci Remote Sens Lett 19:1–5
Gao F, Dong J, Li B, Xu Q (2016) Automatic change detection in synthetic aperture radar images based on PCANet. IEEE Geosci Remote Sens Lett 13(12):1792–1796
Gao T, Li H, Gong M, Zhang M, Qiao W (2023) Superpixel-based multiobjective change detection based on self-adaptive neighborhood based binary differential evolution. Expert Syst Appl 212:118811
Geng J, Ma X, Zhou X, Wang H (2019) Saliency-guided deep neural net works for SAR image change detection. IEEE Trans Geosci Remote Sens 57(10):7365–7377
Giang LT, Son LH, Giang NL, Tuan TM, Luong NV, Sinh MD, Gerogiannis VC (2023) A new co-learning method in spatial complex fuzzy inference systems for change detection from satellite images. Neural Comput Appl 35(6):4519–4548
Gong M, Zhan T, Zhang P, Miao Q (2017) Superpixel-based difference representation learning for change detection in multispectral remote sensing images. IEEE Trans Geosci Remote Sens 55(5):2658–2673
Guo Q, Zhang J, Zhong C, Zhang Y (2021). Unsupervised multiple change detection for multispectral images based on AMMF and spatiospectral channel augmentation. IEEE Geosci Remote Sens Lett
Han M, Li R, Zhang C (2022) Lwcdnet: a lightweight fully convolution network for change detection in optical remote sensing imagery. IEEE Geosci Remote Sens Lett 19:1–5
Hao M, Zhou M, Jin J, Shi W (2019) An advanced superpixel-based Markov random field model for unsupervised change detection. IEEE Geosci Remote Sens Lett 17(8):1401–1405
He P, Zhao X, Shi Y, Cai L (2021) Unsupervised change detection from remotely sensed images based on multi-scale visual saliency coarse-to-fine fusion. Remote Sens 13(4):630
Hu M, Wu C, Zhang L (2022) Hypernet: Self-supervised hyperspectral spatial-spectral feature understanding network for hyperspectral change detection. IEEE Trans Geosci Remote Sens 60:1–17
Huang L, Peng Q, Yu X (2020) Change detection in multitemporal high spatial resolution remote-sensing images based on saliency detection and spatial intuitionistic fuzzy C-means clustering. J Spectrosc
Jakka TK, Reddy YM, Rao BP (2019) GWDWT-FCM: change detection in SAR images using adaptive discrete wavelet transform with fuzzy C mean clustering. J Indian Soc Remote Sens 47(3):379–390
Jian, P., Chen, K., Cheng, W. (2021). Gan-based one-class classification for remote-sensing image change detection. IEEE Geosci Remote Sens Lett
Jiang F, Gong M, Zheng H, Liu T, Zhang M, Liu J (2023) Self-supervised global-local contrastive learning for fine-grained change detection in VHR images. IEEE Trans Geosci Remote Sens 61:1–13
Leenstra, M., Marcos, D., Bovolo, F., Tuia, D. (2021). Self-supervised pre907 training enhances change detection in sentinel-2 imagery. arXiv preprint arXiv: 2101.08122
Lei T, Xue D, Lv Z, Li S, Zhang Y, Nandi AK (2018) Unsupervised change detection using fast fuzzy clustering for landslide mapping from very high-resolution images. Remote Sens 10(9):1381
Lei Y, Liu X, Shi J, Lei C, Wang J (2019) Multiscale superpixel segmentation with deep features for change detection. Ieee Access 7:36600–36616
Levien LM, Fischer C, Roffers P, Maurizi B, Suero J, Fischer C, Huang X (1999) A machine-learning approach to change detection using multi-scale imagery. In: Proceedings of ASPRS annual conference, Vol 1, p 22
Li W, Xiao X, Xiao P, Wang H, Xu F (2022) Change detection in multitemporal SAR images based on slow feature analysis combined with improving image fusion strategy. IEEE J Sel Top Appl Earth Observ Remote Sens 15:3008–3023
Li Y, Peng C, Chen Y, Jiao L, Zhou L, Shang R (2019) A deep learning method for change detection in synthetic aperture radar images. IEEE Trans Geosci Remote Sens 57(8):5751–5763
Li Z, Tang C, Liu X, Zhang W, Dou J, Wang L, Zomaya AY (2023) Lightweight remote sensing change detection with progressive feature aggregation and supervised attention. IEEE Trans Geosci Remote Sens 61:1–12
Liang S, Hua Z, Li J (2023a). Enhanced self-attention network for remote sensing building change detection. IEEE J Sel Top Appl Earth Observ Remote Sens
Liang S, Hua Z, Li J (2023) Hybrid transformer-CNN networks using superpixel segmentation for remote sensing building change detection. Int J Remote Sens 44(8):2754–2780
Lv N, Chen C, Qiu T, Sangaiah AK (2018) Deep learning and superpixel feature extraction based on contractive autoencoder for change detection in SAR images. IEEE Trans Industr Inf 14(12):5530–5538
Meng W, Wang L, Du A, Li Y (2020) Sar image change detection based on data optimization and self-supervised learning. IEEE Access 8:21729–217305
Nayak SR, Nayak J, Sinha U, Arora V, Ghosh U, Satapathy SC (2021) An automated lightweight deep neural network for diagnosis of covid-19 from chest x-ray images. Arab J Sci Eng, pp 1–18
Ohri K, Kumar M (2021) Review on self-supervised image recognition using deep neural networks. Knowl-Based Syst 224:107090
Ou X, Liu L, Tan S, Zhang G, Li W, Tu B (2022) A hyperspec962 tral image change detection framework with self-supervised contrastive learning pretrained model. IEEE J Sel Top Appl Earth Observ Remote Sens 15:7724–7740
Oza M, Bhanderi R (2004). Irs-p6 early evaluation studies (Tech. Rep.). Scientific Report SAC/RESIPA/SR
Pandeeswari B, Sutha J, Parvathy M (2021) A novel synthetic aperture radar image change detection system using radial basis function-based deep convolutional neural network. J Ambient Intell Humaniz Comput 12:897–910
Peng Y, Cui B, Yin H, Zhang Y, Du P (2022) Automatic SAR change detection based on visual saliency and multi-hierarchical fuzzy cluster ING. IEEE J Sel Top Appl Earth Observ Remote Sens 15:7755–7769
Qu J, Xu Y, Dong W, Li Y, Du Q (2021) Dual-branch difference amplification graph convolutional network for hyperspectral image change detection. IEEE Trans Geosci Remote Sens 60:1–12
Saha S, Bovolo F, Bruzzone L (2020) Change detection in image time series using unsupervised LSTM. IEEE Geosci Remote Sens Lett
Saha S, Ebel P, Zhu XX (2022) Self-supervised multisensor change detection. IEEE Transac Geosci Remote Sens, 60
Saha S, Mou L, Zhu XX, Bovolo F, Bruzzone L (2020) Semisupervised change detection using graph convolutional network. IEEE Geosci Remote Sens Lett 18(4):607–611
Shao P, Yi Y, Liu Z, Dong T, Ren D (2022) Novel multiscale decision fusion approach to unsupervised change detection for high-resolution images. IEEE Geosci Remote Sens Lett 19:1–5
Shi, J., Zhang, Z., Tan, C., Liu, X., Lei, Y. (2021). Unsupervised multiple change detection in remote sensing images via generative representation learning network. IEEE Geosci Remote Sens Lett
Shu Y, Li W, Yang M, Cheng P, Han S (2021) Patch-based change detection method for SAR images with label updating strategy. Remote Sens 13(7):1236
Singh A (1989) Review article digital change detection techniques using remotely-sensed data. Int J Remote Sens 10(6):989–1003
Song K, Cui F, Jiang J (2021) An efficient lightweight neural network for remote sensing image change detection. Remote Sens 13(24):5152
Tewkesbury AP, Comber AJ, Tate NJ, Lamb A, Fisher PF (2015) A critical synthesis of remotely sensed optical image change detection techniques. Remote Sens Environ 160:1–14
Wang C, Du S, Sun W, Fan D (2023) Self-supervised learning for high-resolution remote sensing images change detection with variational information bottleneck. IEEE J Sel Top Appl Earth Observ Remote Sens
Wang J, Wang Y, Liu H (2022) Hybrid variability aware network (HVANet): a self-supervised deep framework for label-free SAR image change detection. Remote Sens 14(3):734
Xiao T, Wan Y, Chen J, Shi W, Qin J, Li D (2022) Multiresolution based rough fuzzy possibilistic-means clustering method for land cover change detection. IEEE J Sel Top Appl Earth Observ Remote Sens 16:570–580
Yan L, Yang J, Wang J (2023) Domain knowledge-guided self-supervised change detection for remote sensing images. IEEE J Sel Top Appl Earth Observ Remote Sens
Yeh C-H, Lin C-H, Kang L-W, Huang C-H, Lin M-H, Chang C-Y, Wang C-C (2021). Lightweight deep neural network for joint learning of underwater object detection and color conversion. IEEE Trans Neural Netw Learn Syst
Zhan T, Gong M, Jiang X, Zhao W (2021). Transfer learning-based bilinear convolutional networks for unsupervised change detection. IEEE Geosci Remote Sens Lett
Zhang H, Lin M, Yang G, Zhang L (2021). Escnet: an end-to-end superpixel-enhanced change detection network for very-high-resolution remote sensing images. IEEE Trans Neural Netw Learn Syst
Zhang K, Lv X, Chai H, Yao J (2022) Unsupervised SAR image change detection for few changed area based on histogram fitting error mini mization. IEEE Trans Geosci Remote Sens 60:1–19
Zhang P, Gong M, Zhang H, Liu J, Ban Y (2018) Unsupervised difference representation learning for detecting multiple types of changes in multitemporal remote sensing images. IEEE Trans Geosci Remote Sens 57(4):2277–2289
Zhang W, Li J, Zhang F, Sun J, Zhang K (2021). Unsupervised change detection of multispectral images based on PCA and low-rank prior. IEEE Geosci Remote Sens Lett
Zhang Y, Zhao Y, Dong Y & Du B (2023) Self-supervised pre-training via multi-modality images with transformer for change detection. IEEE Trans Geosci Remote Sens
Zhao B, Tang P, Luo X, Liu D, Wang H (2022) 3m-cdnet-v2: an efficient medium-weight neural network for remote sensing image change detection. IEEE Access 10:89581–89597
Zhao W, Chen X, Ge X & Chen J (2020). Using adversarial network for multiple change detection in bitemporal remote sensing imagery. IEEE Geosci Remote Sens Lett
Zhu L, Zhang J, Sun Y (2021) Remote sensing image change detection using superpixel cosegmentation. Information 12(2):94
Acknowledgements
The authors would like to thank the National Remote Sensing Centre, Indian Space Research Organization (ISRO), Hyderabad, Government of India, for providing the LISS-III RSI data and the authors for the building dataset of high-resolution images from Google Earth Pro.
Funding
No funding was received for conducting this study.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Nitesh Naik, Kandasamy Chandrasekaran, Venkatesan Meenakshi Sundaram and Prabhavathy Panneer. The first draft of the manuscript was written by Nitesh Naik and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Availability of data and materials
The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.
Additional information
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
Naik, N., Chandrasekaran, K., Meenakshi Sundaram, V. et al. Spatio-temporal analysis of land use/land cover change detection in small regions using self-supervised lightweight deep learning. Stoch Environ Res Risk Assess 37, 5029–5049 (2023). https://doi.org/10.1007/s00477-023-02554-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-023-02554-6