Enhancing a Building Change Detection Model in Remote Sensing Imagery for Encroachments and Construction on Government Lands in Egypt as a Case Study
Source abstract
Abstract
Change detection (CD) in optical remote-sensing images is a critical task for applications such as urban planning, disaster monitoring, and environmental assessment. While UNet-based architecture has demonstrated strong performance in CD tasks, it often struggles with capturing deep hierarchical features due to the limitations of plain convolutional layers. Conversely, ResNet architectures excel at learning deep features through residual connections but may lack precise localization capabilities. To address these challenges, we propose ResUNet++, a novel hybrid architecture that combines the strengths of ResNet and UNet for accurate and robust change detection. ResUNet++ integrates residual blocks into the UNet framework to enhance feature representation and mitigate gradient vanishing problems. Additionally, we introduce a Multi-Scale Feature Fusion (MSFF) module to aggregate features at different scales, improving the detection of both large and small changes. Experimental results on multiple datasets (EGY-CD, S2Looking, and LEVIR-CD) demonstrate that ResUNet++ outperforms state-of-the-art methods, achieving higher precision, recall, and F1-scores while maintaining computational efficiency.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote-Sensing Image Classification · Remote Sensing and Land Use · Remote Sensing in Agriculture
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Information and Documentation Center, Arab Academy for Science & Technology (AASTMT), Alexandria 1029, Egypt
Computer Engineering Department, Arab Academy for Science & Technology (AASTMT), Alexandria 1029, Egypt
Department of Computer Engineering, Military Technical College (MTC), Cairo 11771, Egypt
References (72)
Show source-provided references
1. Evaluation of agricultural expansion areas in the Egyptian deserts: A review using remote sensing and GIS
2. Numbere, A.O. (2022). Application of GIS and remote sensing towards forest resource management in mangrove forest of Niger Delta. Natural Resources Conservation and Advances for a Sustainable Future, Elsevier.10.1016/B978-0-12-822976-7.00024-7 ↗
3. Janga, B., Asamani, G.P., Sun, Z., and Cristea, N. (2023). A review of practical AI for remote sensing in earth sciences. Remote Sens., 15.10.3390/rs15164112 ↗
4. DLCD: Deep learning-based change detection approach to monitor deforestation10.1007/s11760-024-03140-1 ↗
5. Weise, K., Hedden-Dunkhorst, B., and Wulf, S. (2021). Using Satellite Images for Wetland Management and Planning in Africa, Federal Agency for Nature Conservation.
6. Informal laneway encroachment: Reassessing public/private interface transformation in urban villages
7. Land use/land cover change detection and urban sprawl in the peri-urban area of Greater Cairo since the Egyptian revolution of 201110.1080/1747423X.2020.1765425 ↗
8. Land grabbing in the Brazilian Amazon: Stealing public land with government approval
9. Mansour, S., Alahmadi, M., Atkinson, P.M., and Dewan, A. (2022). Forecasting of built-up land expansion in a desert urban environment. Remote Sens., 14.10.3390/rs14092037 ↗
10. Stoica, I.V., Vîrghileanu, M., Zamfir, D., and Mihai, B.A. (2020). Comparative assessment of the built-up area expansion based on CORINE land cover and Landsat datasets. Remote Sens., 12.10.3390/rs12132137 ↗
11. Indices based assessment of built-up density and urban expansion of fast-growing Surat city using multi-temporal Landsat data sets
12. Urban development analysis using built-up area maps based on multiple high-resolution satellite data
13. De Bem, P.P., and de Carvalho Junior, O.A. (2020). Change detection of deforestation in the Brazilian Amazon using Landsat data and convolutional neural networks. Remote Sens., 12.10.3390/rs12060901 ↗
14. Land use and land cover change detection using geospatial techniques in the Sikkim Himalaya, India
15. Land use and land cover change detection and prediction in Bhutan’s high altitude city of Thimphu, using cellular automata and Markov chain
16. DASNet: Dual attentive fully convolutional Siamese networks for change detection in high-resolution satellite images
17. Lunetta, R.S., Knight, J.F., and Ediriwickrema, J. (2022). Land-cover change detection using multi-temporal MODIS NDVI data. Handbook for Water Resources, Elsevier.10.1201/9781003175025-5 ↗
18. Peng, D., Bruzzone, L., Zhang, Y., and Guan, H. (October, January 26). SemiCDNet: A semisupervised convolutional neural network for change detection in high-resolution remote-sensing images. Proceedings of the IGARSS 2020—2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA.
19. A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images10.1016/j.isprsjprs.2020.06.003 ↗
20. Shi, W., Zhang, M., Zhang, R., Chen, S., and Zhan, Z. (2020). Change detection based on artificial intelligence: State-of-the-art and challenges. Remote Sens., 12.10.3390/rs12101688 ↗
21. Deep learning for change detection in remote sensing images: Comprehensive review and meta-analysis10.1109/ACCESS.2020.3008036 ↗
22. Remote sensing image change detection with transformers
23. Ahmad, M., Distifano, S., Mazzara, M., and Khan, A.M. (2024). Traditional to transformers: A survey on current trends and future prospects for hyperspectral image classification. arXiv, Available online: https://arxiv.org/abs/2404.14955.
24. Kaplan, S. (2024). Data-Centric Remedies for Challenges in Computer Vision Applications: Insights from Active Learning, Deep Generative Models, and Explainable AI. [Master’s Thesis, LUT University]. Available online: https://lutpub.lut.fi/handle/10024/166005.
25. Explainable artificial intelligence methods in combating pandemics: A systematic review
26. Warde-Farley, D., and Bengio, Y. (2017, January 24–26). Improving generative adversarial networks with denoising feature matching. Proceedings of the International Conference on Learning Representations, Toulon, France. Available online: https://openreview.net/pdf?id=S1X7nhsxl.
27. Kaneko, T., and Harada, T. (2020, January 13–19). Noise robust generative adversarial networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA. Available online: https://openaccess.thecvf.com/content_CVPR_2020/html/Kaneko_Noise_Robust_Generative_Adversarial_Networks_CVPR_2020_paper.html.10.1109/CVPR42600.2020.00843 ↗
28. Boosting magnetic resonance image denoising with generative adversarial networks
29. Baheti, B., Innani, S., and Gajre, S. (2020, January 14–19). Eff-UNet: A novel architecture for semantic segmentation in unstructured environments. Proceedings of the CVPRW, Seattle, WA, USA.10.1109/CVPRW50498.2020.00187 ↗
30. Focal and Efficient IoU Loss for Accurate Bounding Box Regression10.1016/j.neucom.2022.07.042 ↗
31. An ensemble architecture of deep convolutional SegNet and UNet networks for building semantic segmentation from high-resolution aerial images10.1080/10106049.2020.1856199 ↗
32. Zunair, H., and Hamza, A.B. (2021). Sharp U-Net: Depthwise convolutional network for biomedical image segmentation. Comput. Biol. Med., 137.10.1016/j.compbiomed.2021.104699 ↗
33. ED-Net: Automatic building extraction from high-resolution aerial images with boundary information10.1109/JSTARS.2021.3073994 ↗
34. Sharp dense U-Net: An enhanced dense U-Net architecture for nucleus segmentation10.1007/s13042-023-02017-y ↗
35. Wagner, F.H., Dalagnol, R., Tarabalka, Y., Segantine, T.Y.F., Thomé, R., and Hirye, M.C.M. (2020). U-Net-Id, an Instance Segmentation Model for Building Extraction from Satellite Images—Case Study in the Joanópolis City, Brazil. Remote Sens., 12.10.3390/rs12101544 ↗
36. Shafique, A., Cao, G., Khan, Z., Asad, M., and Aslam, M. (2022). Deep learning-based change detection in remote sensing images: A review. Remote Sens., 14.10.3390/rs14040871 ↗
37. Huang, W., Zhang, S., and Wang, H.H. (2021). Efficient GAN-based remote sensing image change detection under noise conditions. Image Processing and Capsule Networks, Springer.10.1007/978-3-030-51859-2_1 ↗
38. SiameseGAN: A generative model for denoising of spectral domain optical coherence tomography images10.1109/TMI.2020.3024097 ↗
39. MP-ResNet: Multi-path Residual Network for the Semantic Segmentation of High-Resolution PolSAR Images
40. Image de-noising with machine learning: A review10.1109/ACCESS.2021.3092425 ↗
41. Momeny, M., Neshat, A.A., Hussain, M.A., and Kia, S. (2021). Learning-to-augment strategy using noisy and denoised data: Improving generalizability of deep CNN for the detection of COVID-19 in X-ray images. Comput. Biol. Med., 134.10.1016/j.compbiomed.2021.104704 ↗
42. Content-Noise Complementary Learning for Medical Image Denoising10.1109/TMI.2021.3113365 ↗
43. Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning10.1109/TIP.2020.2976814 ↗
44. A CNN-Transformer Hybrid Approach for Crop Classification Using Multitemporal Multisensor Images10.1109/JSTARS.2020.2971763 ↗
45. When CNNs Meet Vision Transformer: A Joint Framework for Remote Sensing Scene Classification10.1109/LGRS.2021.3109061 ↗
46. Shao, Z., Tang, P., Wang, Z., Saleem, N., Yam, S., and Sommai, C. (2020). BRRNet: A Fully Convolutional Neural Network for Automatic Building Extraction From High-Resolution Remote Sensing Images. Remote Sens., 12.10.3390/rs12061050 ↗
47. Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
48. Seismic Impedance Inversion Using Fully Convolutional Residual Network and Transfer Learning10.1109/LGRS.2019.2963106 ↗
49. Mandal, J., and Mukhopadhyay, S. (2020). M-UNet: Modified U-Net Segmentation Framework with Satellite Imagery. Proceedings of the Global AI Congress 2019, Kolkata, India, 12–14 September 2019, Springer.
50. Automatic Semantic Segmentation with DeepLab Dilated Learning Network for Change Detection in Remote Sensing Images10.1007/s11063-019-10174-x ↗
51. Inferring 3D change detection from bitemporal optical images10.1016/j.isprsjprs.2022.12.009 ↗
52. Dang, B., and Li, Y. (2021). MSResNet: Multiscale Residual Network via Self-Supervised Learning for Water-Body Detection in Remote Sensing Imagery. Remote Sens., 13.10.3390/rs13163122 ↗
53. SCAttNet: Semantic segmentation network with spatial and channel attention mechanism for high-resolution remote sensing images10.1109/LGRS.2020.2988294 ↗
54. MDS-Net: An Image-Text Enhanced Multimodal Dual-Branch Siamese Network for Remote Sensing Change Detection10.1109/JSTARS.2025.3567508 ↗
55. Chang, Y., and Luo, B. (2019). Bidirectional Convolutional LSTM Neural Network for Remote Sensing Image Super-Resolution. Remote Sens., 11.10.3390/rs11202333 ↗
56. ST-3DGMR: Spatio-temporal 3D grouped multiscale ResNet network for region-based urban traffic flow prediction10.1016/j.ins.2022.12.066 ↗
57. UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery10.1016/j.isprsjprs.2022.06.008 ↗
58. Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., and Tang, X. (2017, January 21–26). Residual attention network for image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.683 ↗
59. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Springer.10.1007/978-3-319-24574-4_28 ↗
60. Caye Daudt, R., Le Saux, B., and Boulch, A. (2018). Fully Convolutional Siamese Networks for Change Detection. arXiv.10.1109/ICIP.2018.8451652 ↗
61. Peng, D., Zhang, Y., and Guan, H. (2019). End-to-end change detection for high resolution satellite images using improved UNet++. Remote Sens., 11.10.3390/rs11111382 ↗
62. Fan, X., Cao, P., Shi, P., Wang, J., Xin, Y., and Huang, W. (2021, January 22–24). A Nested U-Net with Attention Mechanism for Road Crack Image Segmentation. Proceedings of the 2021 IEEE 6th International Conference on Signal and Image Processing (ICSIP), Nanjing, China.10.1109/ICSIP52628.2021.9688782 ↗
63. SwinSUNet: Pure Transformer Network for Remote Sensing Image Change Detection10.1109/TGRS.2022.3221492 ↗
64. Giannopoulos, M., Tsagkatakis, G., and Tsakalides, P. (2022). 4D U-Nets for Multi-Temporal Remote Sensing Data Classification. Remote Sens., 14.10.3390/rs14030634 ↗
65. Evaluation of Unet and Unet++ Architectures in High Resolution Image Change Detection Applications10.5194/isprs-archives-XLIII-B3-2020-1507-2020 ↗
66. Jiang, J., Liu, L., Cui, Y., and Zhao, Y. (2023). A Nested UNet Based on Multi-Scale Feature Extraction for Mixed Gaussian-Impulse Removal. Appl. Sci., 13.10.3390/app13179520 ↗
67. Chen, H., and Shi, Z. (2020). A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection. Remote Sens., 12.10.3390/rs12101662 ↗
68. Shen, L., Lu, Y., Chen, H., Wei, H., Xie, D., Yue, J., Chen, R., Lv, S., and Jiang, B. (2021). S2Looking: A Satellite Side-Looking Dataset for Building Change Detection. Remote Sens., 13.10.3390/rs13245094 ↗
69. AFDE-Net: Building Change Detection Using Attention-Based Feature Differential Enhancement for Satellite Imagery10.1109/LGRS.2023.3283505 ↗
70. Pang, L., Sun, J., Chi, Y., Yang, Y., Zhang, F., and Zhang, L. (2022). CD-TransUNet: A Hybrid Transformer Network for the Change Detection of Urban Buildings Using L-Band SAR Images. Sustainability, 14.10.3390/su14169847 ↗
71. Zhang, W., Wang, S., Tong, J., Liao, F., Zhang, Y., and Shen, X. (2023). DDCNN: A Promising Tool for Simulation-To-Reality UAV Fault Diagnosis. Neural Process. Lett.10.1109/CIS-RAM61939.2024.10673092 ↗
72. Yin, H., Ma, C., Weng, L., Xia, M., and Lin, H. (2023). Bitemporal Remote Sensing Image Change Detection Network Based on Siamese-Attention Feedback Architecture. Remote Sens., 15.10.3390/rs15174186 ↗