Advancing Rural Building Extraction via Diverse Dataset Construction and Model Innovation with Attention and Context Learning
Source abstract
Abstract
Rural building automatic extraction technology is of great significance for rural planning and disaster assessment; however, existing methods face the dilemma of scarce sample data and large regional differences in rural buildings. To solve this problem, this study constructed an image dataset of typical Chinese rural buildings, including nine typical geographical regions, such as the Northeast and North China Plains. Additionally, an improved remote sensing image rural building extraction network called AGSC-Net was designed. Based on an encoder–decoder structure, the model integrates multiple attention gate (AG) modules and a context collaboration network (CC-Net). The AG modules realize focused expression of building-related features through feature selection. The CC-Net module models the global dependency between different building instances, providing complementary localization and scale information to the decoder. By embedding AG and CC-Net modules between the encoder and decoder, the model can capture multiscale semantic information on building features. Experiments show that, compared with other models, AGSC-Net achieved the best quantitative metrics on two rural building datasets, verifying the accuracy of the extraction results. This study provides an effective example for automatic extraction in complex rural scenes and lays the foundation for related monitoring and planning applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote-Sensing Image Classification · Remote Sensing and Land Use · Video Surveillance and Tracking Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Surveying and Geo-Informatics, Shandong Jianzhu University, Jinan 250101, China
Funding
China National Key R and D Program during the 13th Five-year Plan Period · National Natural Science Foundation of China
References (53)
Show source-provided references
1. Zhang, J., Fukuda, T., and Yabuki, N. (2021). Development of a City-Scale Approach for Façade Color Measurement with Building Functional Classification Using Deep Learning and Street View Images. ISPRS Int. J. Geo-Inf., 10.10.3390/ijgi10080551 ↗
2. Earthquake Building Damage Detection Based on Synthetic-Aperture-Radar Imagery and Machine Learning10.5194/nhess-23-789-2023 ↗
3. Le, Q.H., Shin, H., Kwon, N., Ho, J., and Ahn, Y. (2022). Deep Learning Based Urban Building Coverage Ratio Estimation Focusing on Rapid Urbanization Areas. Appl. Sci., 12.10.3390/app122211428 ↗
4. A 3D Modeling Method for Buildings Based on LiDAR Point Cloud and DLG10.1016/j.compenvurbsys.2023.101974 ↗
5. Wei, R., Fan, B., Wang, Y., and Yang, R. (2023). A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images. Sensors, 23.10.3390/s23073643 ↗
6. Wang, C., Sun, W., Wu, H., Zhao, C., Teng, G., Yang, Y., and Du, P. (2022). A Low-Altitude Remote Sensing Inspection Method on Rural Living Environments Based on a Modified YOLOv5s-ViT. Remote Sens., 14.10.3390/rs14194784 ↗
7. Hine, J., Sasidharan, M., Torbaghan, M.E., Burrow, M., and Usman, K. (2019). Evidence of the Impact of Rural Road Investment on Poverty Reduction and Economic Development, Institute of Development Studies.
8. Cogato, A., Cei, L., Marinello, F., and Pezzuolo, A. (2023). The Role of Buildings in Rural Areas: Trends, Challenges, and Innovations for Sustainable Development. Agronomy, 13.10.3390/agronomy13081961 ↗
9. Multi-Objective Optimization for Energy Consumption, Daylighting and Thermal Comfort Performance of Rural Tourism Buildings in North China10.1016/j.buildenv.2020.106841 ↗
10. Fire Protection in Agricultural Facilities: A Review of Research, Resources and Practices10.1177/1042391503033368 ↗
11. Jia, Y., Zhang, X., Xiang, R., and Ge, Y. (2023). Super-Resolution Rural Road Extraction from Sentinel-2 Imagery Using a Spatial Relationship-Informed Network. Remote Sens., 15.10.3390/rs15174193 ↗
12. Building Extraction Using Object-Based Classification and Shadow Information in Very High Resolution Multispectral Images, a Case Study: Tetuan, Morocco
13. A Novel Change Detection Method Using Remotely Sensed Image Time Series Value and Shape Based Dynamic Time Warping10.1080/10106049.2021.2022013 ↗
14. PCLUDA: A Pseudo-Label Consistency Learning- Based Unsupervised Domain Adaptation Method for Cross-Domain Optical Remote Sensing Image Retrieval10.1109/TGRS.2022.3233133 ↗
15. A Self-Supervised-Driven Open-Set Unsupervised Domain Adaptation Method for Optical Remote Sensing Image Scene Classification and Retrieval
16. Muhammed, E., El-Shazly, A., and Morsy, S. (2023). Building Rooftop Extraction Using Machine Learning Algorithms for Solar Photovoltaic Potential Estimation. Sustainability, 15.10.3390/su151411004 ↗
17. A Coastal Wetlands Mapping Approach of Yellow River Delta with a Hierarchical Classification and Optimal Feature Selection Framework10.1016/j.catena.2022.106897 ↗
18. Extraction of Buildings in Urban Area for Surface Area Assessment from Satellite Imagery Based on Morphological Building Index Using SVM Classifier10.1007/s12524-020-01161-0 ↗
19. BuildMapper: A Fully Learnable Framework for Vectorized Building Contour Extraction10.1016/j.isprsjprs.2023.01.015 ↗
20. Xia, L., Mi, S., Zhang, J., Luo, J., Shen, Z., and Cheng, Y. (2023). Dual-Stream Feature Extraction Network Based on CNN and Transformer for Building Extraction. Remote Sens., 15.10.3390/rs15102689 ↗
21. Yu, M., Chen, X., Zhang, W., and Liu, Y. (2022). AGs-UNet: Building Extraction Model for High Resolution Remote Sensing Images Based on Attention Gates U Network. Sensors, 22.10.3390/s22082932 ↗
22. Enhancing Building Extraction from Remote Sensing Images through UNet and Transfer Learning
23. Context–Content Collaborative Network for Building Extraction from High-Resolution Imagery10.1016/j.knosys.2023.110283 ↗
24. Wang, Y., Li, S., Teng, F., Lin, Y., Wang, M., and Cai, H. (2022). Improved Mask R-CNN for Rural Building Roof Type Recognition from UAV High-Resolution Images: A Case Study in Hunan Province, China. Remote Sens., 14.10.3390/rs14020265 ↗
25. Zhou, J., Liu, Y., Nie, G., Cheng, H., Yang, X., Chen, X., and Gross, L. (2022). Building Extraction and Floor Area Estimation at the Village Level in Rural China Via a Comprehensive Method Integrating UAV Photogrammetry and the Novel EDSANet. Remote Sens., 14.10.3390/rs14205175 ↗
26. Attention-Gate-Based Encoder–Decoder Network for Automatical Building Extraction10.1109/JSTARS.2021.3058097 ↗
27. A Dual Spatial-Graph Refinement Network for Building Extraction from Aerial Images10.1109/TGRS.2023.3320146 ↗
28. The Regional Disparity of Per-Capita CO2 Emissions in China’s Building Sector: An Analysis of Macroeconomic Drivers and Policy Implications10.1016/j.enbuild.2021.111011 ↗
29. Adaptive Reuse of Local Buildings in Sapa, Vietnam for Cultural Tourism Development towards Sustainability10.1088/1755-1315/878/1/012032 ↗
30. Zhang, T., Chen, X., Zhang, F., Yang, Z., Wang, Y., Li, Y., and Wei, L. (2022). A Case Study of Refined Building Climate Zoning under Complicated Terrain Conditions in China. Int. J. Environ. Res. Public Health, 19.10.3390/ijerph19148530 ↗
31. Research on the Relationship between the Formation of Local Construction Culture and Geographical Environment Based on Adaptability Analysis10.1016/j.jksus.2022.102387 ↗
32. LCS: A Collaborative Optimization Framework of Vector Extraction and Semantic Segmentation for Building Extraction
33. DA-ActNN-YOLOV5: Hybrid YOLO v5 Model with Data Augmentation and Activation of Compression Mechanism for Potato Disease Identification10.1155/2022/6114061 ↗
34. Fully Convolutional Networks for Multisource Building Extraction from an Open Aerial and Satellite Imagery Data Set10.1109/TGRS.2018.2858817 ↗
35. Building Extraction from Very High-Resolution Remote Sensing Images Using Refine-UNet10.1109/LGRS.2023.3243609 ↗
36. Yu, M., Zhang, W., Chen, X., Liu, Y., and Niu, J. (2022). An End-to-End Atrous Spatial Pyramid Pooling and Skip-Connections Generative Adversarial Segmentation Network for Building Extraction from High-Resolution Aerial Images. Appl. Sci., 12.10.3390/app12105151 ↗
37. Liu, W., Liu, H., Liu, C., Kong, J., and Zhang, C. (2023). AGDF-Net: Attention-Gated and Direction-Field-Optimized Building Instance Extraction Network. Sensors, 23.10.3390/s23146349 ↗
38. Li, P., Sun, Z., Duan, G., Wang, D., Meng, Q., and Sun, Y. (2023). DMU-Net: A Dual-Stream Multi-Scale U-Net Network Using Multi-Dimensional Spatial Information for Urban Building Extraction. Sensors, 23.10.3390/s23041991 ↗
39. Decoupling Semantic and Edge Representations for Building Footprint Extraction from Remote Sensing Images10.1109/TGRS.2023.3287298 ↗
40. Urban Building Extraction from High-Resolution Remote Sensing Imagery Based on Multi-Scale Recurrent Conditional Generative Adversarial Network10.1080/15481603.2022.2076382 ↗
41. BOMSC-Net: Boundary Optimization and Multi-Scale Context Awareness Based Building Extraction from High-Resolution Remote Sensing Imagery
42. Qiu, Y., Wu, F., Yin, J., Liu, C., Gong, X., and Wang, A. (2022). MSL-Net: An Efficient Network for Building Extraction from Aerial Imagery. Remote Sens., 14.10.3390/rs14163914 ↗
43. Asymmetric Cascade Fusion Network for Building Extraction10.1109/TGRS.2023.3306018 ↗
44. Enhanced Self-Attention Network for Remote Sensing Building Change Detection10.1109/JSTARS.2023.3278726 ↗
45. A dataset of building sampling and labeling of UAV images in rural China
46. Cai, W., Jin, K., Hou, J., Guo, C., Wu, L., and Yang, W. (2023). VDD: Varied Drone Dataset for Semantic Segmentation. arXiv.
47. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation10.1109/TPAMI.2016.2644615 ↗
48. An Ensemble Architecture of Deep Convolutional Segnet and UNet Networks for Building Semantic Segmentation from High-Resolution Aerial Images10.1080/10106049.2020.1856199 ↗
49. Multiscale Building Extraction with Refined Attention Pyramid Networks10.1109/LGRS.2021.3075436 ↗
50. CSA-UNet: Channel-Spatial Attention-Based Encoder–Decoder Network for Rural Blue-Roofed Building Extraction From UAV Imagery10.1109/LGRS.2022.3197319 ↗
51. Automatic Building Extraction on High-Resolution Remote Sensing Imagery Using Deep Convolutional Encoder-Decoder with Spatial Pyramid Pooling10.1109/ACCESS.2019.2940527 ↗
52. Dave, M., Garg, R., Dua, M., and Hussien, J. (2020, January 1–3). Automatic Building Extraction from High-Resolution Satellite Images Using Deep Learning Techniques. Proceedings of the International Conference on Paradigms of Computing, Communication and Data Sciences, Kurukshetra, India. Algorithms for Intelligent Systems.
53. Predicting the Slump of Industrially Produced Concrete Using Machine Learning: A Multiclass Classification Approach10.1016/j.jobe.2022.104997 ↗