Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.5.2.3

Automatic Building Extraction Using SpaceNet Building Dataset and Context-based ResU-Net  

Yoo, Suhong (School of Civil and Environmental Engineering, Yonsei University)
Kim, Cheol Hwan (School of Civil and Environmental Engineering, Yonsei University)
Kwon, Youngmok (School of Civil and Environmental Engineering, Yonsei University)
Choi, Wonjun (School of Civil and Environmental Engineering, Yonsei University)
Sohn, Hong-Gyoo (School of Civil and Environmental Engineering, Yonsei University)
Publication Information
Korean Journal of Remote Sensing / v.38, no.5_2, 2022 , pp. 685-694 More about this Journal
Abstract
Building information is essential for various urban spatial analyses. For this reason, continuous building monitoring is required, but it is a subject with many practical difficulties. To this end, research is being conducted to extract buildings from satellite images that can be continuously observed over a wide area. Recently, deep learning-based semantic segmentation techniques have been used. In this study, a part of the structure of the context-based ResU-Net was modified, and training was conducted to automatically extract a building from a 30 cm Worldview-3 RGB image using SpaceNet's building v2 free open data. As a result of the classification accuracy evaluation, the f1-score, which was higher than the classification accuracy of the 2nd SpaceNet competition winners. Therefore, if Worldview-3 satellite imagery can be continuously provided, it will be possible to use the building extraction results of this study to generate an automatic model of building around the world.
Keywords
SpaceNet; ResU-Net; Semantic segmentation; Building extraction;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Architecture & Urban Research Institute, 2021. Ministry of Land, Infrastructure and Transport Announces Nationwide Survey on the Same Number of Buildings and Total Floor Area Change Compared to the Previous Year, http://www.aurum.re.kr/Research/PostView.aspx?mm=1&ss=1&pid=21930#.YnHQ7uhByUk, Accessed on Sep. 30, 2022.
2 Barsi, A., Z. Kugler, I. Laszlo, G. Szabo, and H. Abdulmutalib. 2018. Accuracy Dimensions in Remote Sensing, International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, 42(3): 61-67. https://doi.org/10.5194/isprs-archives-XLII-3-61-2018   DOI
3 Jeong, D. and Y. Kim, 2021. Keypoint-based Deep Learning Approach for Building Footprint Extraction Using Aerial Images, Korean Journal of Remote Sensing, 37(1): 111-122. https://doi.org/10.7780/kjrs.2021.37.1.9   DOI
4 Lafarge, F., X. Descombes, J. Zerubia, and M. PierrotDeseilligny, 2008. Automatic building extraction from DEMs using an object approach and application to the 3D-city modeling, ISPRS Journal of Photogrammetry and Remote Sensing, 63(3): 365-381. https://doi.org/10.1016/j.isprsjprs.2007.09.003   DOI
5 Liu, Y., J. Zhou, W. Qi, X. Li, L. Gross, Q. Shao, Z. Zhao, L. Ni, X. Fan, and Z. Li, 2020. ARC-Net: An efficient network for building extraction from high-resolution aerial images, IEEE Access, 8: 154997-155010. https://doi.org/10.1109/ACCESS.2020.3015701   DOI
6 Wu, Y., L. Xu, Y. Chen, A. Wong, and D.A. Clausi, 2022. TAL: Topography-Aware Multi-Resolution Fusion Learning for Enhanced Building Footprint Extraction, IEEE Geoscience and Remote Sensing Letters, 19: 1-5. https://doi.org/10.1109/LGRS.2022.3149709   DOI
7 Xu, S., X. Pan, E. Li, B. Wu, S. Bu, W. Dong, S. Xiang, and X. Zhang, 2018. Automatic building rooftop extraction from aerial images via hierarchical RGB-D priors, IEEE Transactions on Geoscience and Remote Sensing, 56(12): 7369-7387. https://doi.org/10.1109/TGRS.2018.2850972   DOI
8 Yoo, S., J. Lee, J. Bae, H. Jang, and H.-G. Sohn, 2021. Automatic generation of aerial orthoimages using sentinel-2 satellite imagery with a context-based deep learning approach, Applied Sciences, 11(3):1089. https://doi.org/10.3390/app11031089   DOI
9 Guo, H., Q. Shi, B. Du, L. Zhang, D. Wang, and H. Ding, 2020. Scene-driven multitask parallel attention network for building extraction in high-resolution remote sensing images, IEEE Transactions on Geoscience and Remote Sensing, 59(5): 4287-4306. https://doi.org/10.1109/TGRS.2020.3014312   DOI
10 Jung, S., J. Park, W.H. Lee, and Y. Han, 2020. Objectbased building change detection using azimuth and elevation angles of sun and platform in the multi-sensor images, Korean Journal of Remote Sensing, 36(5-2): 989-1006. https://doi.org/10.7780/kjrs.2020.36.5.2.12   DOI
11 Korea Aerospace Research Institute, 2022. Arirang satellite AI training data, https://niasatellitedata.imweb.me/, Accessed on Sep. 30, 2022.
12 Lindenbaum, D., 2017. 2nd SpaceNet Competition Winners Code Release, https://medium.com/the-downlinq/2nd-spacenet-competition-winnerscode-release-c7473eea7c11, Accessed on Sep. 30, 2022.
13 Liu, Y., L. Gross, Z. Li, X. Li, X. Fan, and W. Qi, 2019. Automatic building extraction on high-resolution remote sensing imagery using deep convolutional encoder-decoder with spatial pyramid pooling, IEEE Access, 7: 128774-128786. https://doi.org/10.1109/ACCESS.2019.2940527   DOI
14 National Information Society Agency, 2022. Aihub, https://aihub.or.kr/, Accessed on Sep. 30, 2022.
15 Rottensteiner, F., G. Sohn, M. Gerke, and J.D. Wegner, 2014. ISPRS semantic labeling contest, ISPRS: Leopoldshohe, Germany, 1: 4.
16 SpaceNet, 2022a. SpaceNet, https://spacenet.ai/, Accessed on Sep. 30, 2022.
17 Chen, L.-C., Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation, Proc. of the European Conference on Computer Vision (ECCV), Munich, Germany, Sep. 8-14, pp. 833-851. https://doi.org/10.1007/978-3-030-01234-2_49   DOI
18 Shao, Z., P. Tang, Z. Wang, N. Saleem, S. Yam, and C. Sommai, 2020. BRRNet: A fully convolutional neural network for automatic building extraction from high-resolution remote sensing images, Remote Sensing, 12(6): 1050. https://doi.org/10.3390/rs12061050   DOI
19 SpaceNet, 2022b. SpaceNet 2: Building Detection v2, https://spacenet.ai/spacenet-buildings-dataset-v2/, Accessed on Sep. 30, 2022.
20 Temenos, A., E. Protopapadakis, A. Doulamis, and N. Temenos, 2021. Building Extraction from RGB Satellite Images using Deep Learning: A U-Net Approach, Proc. of the 14th PErvasive Technologies Related to Assistive Environments Conference, Corfu, Greece, Jun. 29-Jul. 2, pp. 391-395. https://doi.org/10.1145/3453892.3461320   DOI
21 Temenos, A., N. Temenos, A. Doulamis, and N. Doulamis, 2022. On the Exploration of Automatic Building Extraction from RGB Satellite Images Using Deep Learning Architectures Based on U-Net, Technologies, 10(1): 19. https://doi.org/10.3390/technologies10010019   DOI
22 Tiwari, P.S., H. Pande, and B.N. Nanda, 2006. Building footprint extraction from ikonos imagery based on multi-scale object oriented fuzzy classification for urban disaster management, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 34: 1-7.
23 Van Etten, A., D. Lindenbaum, and T.M. Bacastow, 2018. Spacenet: A remote sensing dataset and challenge series, arXiv preprint arXiv:1807.01232. https://doi.org/10.48550/arXiv.1807.01232   DOI
24 Wang, J., K. Sun, T. Cheng, B. Jiang, C. Deng, Y. Zhao, D. Liu, Y. Mu, M. Tan, and X. Wang, 2020. Deep high-resolution representation learning for visual recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10): 3349-3364. https://doi.org/10.1109/TPAMI.2020.2983686   DOI
25 Zhao, H., J. Shi, X. Qi, X. Wang, and J. Jia, 2017. Pyramid scene parsing network, Proc. of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, Jul. 21-26, pp. 2881-2890. https://10.1109/CVPR.2017.660   DOI
26 Zhou, Z., M.M. Rahman Siddiquee, N. Tajbakhsh, and J. Liang, 2018. 'Unet++: A nested u-net architecture for medical image segmentation, In: Danail, S. et al. (eds), Deep learning in medical image analysis and multimodal learning for clinical decision support, Springer, Cham, Switzerland, pp. 3-11.
27 Yoo, S., J. Lee, M.G. Farkoushi, E. Lee, and H.-G. Sohn, 2022. Automatic generation of land use maps using aerial orthoimages and building floor data with a Conv-Depth Block (CDB) ResU-Net architecture, International Journal of Applied Earth Observation and Geoinformation, 107: 102678. https://doi.org/10.1016/j.jag.2022.102678   DOI