Automated building damage detection on digital imagery using machine learning
/ 0
- Details
- Category: Content №6 2023
- Last Updated on 23 December 2023
- Published on 30 November -0001
- Hits: 2057
Authors:
V.Yu.Kashtan, orcid.org/0000-0002-0395-5895, Dnipro University of Technology, Dnipro, Ukraine, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
V.V.Hnatushenko*, orcid.org/0000-0003-3140-3788, Dnipro University of Technology, Dnipro, Ukraine, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
* Corresponding author e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu. 2023, (6): 134 - 140
https://doi.org/10.33271/nvngu/2023-6/134
Abstract:
Purpose. To develop an automated method based on machine learning for accurate detection of features of a damaged building on digital imagery.
Methodology. This article presents an approach that employs a combination of unsupervised machine learning techniques, specifically Principal Component Analysis (PCA), K-means clustering, and Density-Based Spatial Clustering of Applications with Noise (DBSCAN), to identify building damage resulting from military conflicts. The PCA method is utilized to identify principal vectors representing the directions of maximum variance in the data. Subsequently, the K-means method is applied to cluster the feature vector space, with the predefined number of clusters reflecting the number of principal vectors. Each cluster represents a group of similar blocks of image differences, which helps to identify significant features associated with fractures. Finally, the DBSCAN method is employed to identify areas where points with similar characteristics are located. Subsequently, a binary fracture mask is generated, with pixels exceeding the threshold being identified as fractures.
Findings. The introduced methodology attains an accuracy rate of 98.13 %, surpassing the performance of conventional methods such as DBSCAN, PCA, and K-means. Furthermore, the method exhibits a recall of 82.38 %, signifying its ability to effectively detect a substantial proportion of positive examples. Precision of 58.54 % underscores the methodology’s capability to minimize false positives. The F1 Score of 70.90 % demonstrates a well-balanced performance between precision and recall.
Originality. DBSCAN, PCA and K-means methods have been further developed in the context of automated detection of building destruction in aerospace images. This allows us to significantly increase the accuracy and efficiency of monitoring territories, including those affected by the consequences of military aggression.
Practical value. The results obtained can be used to improve automated monitoring systems for urban development and can also serve as the basis for the development of effective strategies for the restoration and reconstruction of damaged infrastructure.
Keywords: unsupervised machine learning, digital image, recognition, building damage, military conflicts
References.
1. Kashtan, V., & Hnatushenko, V. (2023). Deep Learning Technology for Automatic Burned Area Extraction Using Satellite High Spatial Resolution Images. Lecture Notes on Data Engineering and Communications Technologies, 149, 664-685. Springer, Cham. https://doi.org/10.1007/978-3-031-16203-9_37.
2. de Alencar Rodrigues, J. A. R., Lima, N. N. R., Neto, M. L. R., & Uchida, R.R. (2022). Ukraine: War, bullets, and bombs – millions of children and adolescents are in danger, Child Abuse & Neglect, 128. https://doi.org/10.1016/j.chiabu.2022.105622.
3. Kulikov, P., Aziukovskyi, O., Vahonova, O., Bondar, O., Akimova, L., & Akimov, O. (2022). Post-war Economy of Ukraine: Innovation and Investment Development Project. Economic Affairs (New Delhi), 67(5), 943-959. https://doi.org/10.46852/04242513.5.2022.30.
4. Kolesnik, V. Ye., Borysovs’ka, O. O., Pavlychenko, А. V., & Shirin, A. L. (2017). Determination of trends and regularities of occurrence of emergency situations of technogenic and natural character in Ukraine. Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, (6), 124-131.
5. Tasci, B., Madhav, R., Baygin, M., Dogan, S., Tuncer, T., & Belhaouari, S. (2023). InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing images. International Journal of Applied Earth Observation and Geoinformation, 123. https://doi.org/10.1016/j.jag.2023.103483.
6. Hordiiuk, D. M., & Hnatushenko, V. V. (2017). Neural network and local laplace filter methods applied to very high resolution remote sensing imagery in urban damage detection. 2017 IEEE International Young Scientists Forum on Applied Physics and Engineering (YSF). https://doi.org/10.1109/ysf.2017.8126648.
7. Lubin, A., & Saleem, A. (2019). Remote sensing-based mapping of the destruction to Aleppo during the Syrian Civil War between 2011 and 2017. Applied Geography, 108, 30-38. https://doi.org/10.1016/j.apgeog.2019.05.004.
8. Mozgovoy, D., Hnatushenko, V., & Vasyliev, V. (2018). Accuracy evaluation of automated object recognition using multispectral aerial images and neural network. Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018). https://doi.org/10.1117/12.2502905.
9. Zhang, X., Cui, J., Wang, W., & Lin, C. (2017). A Study for Texture Feature Extraction of High-Resolution Satellite Images Based on a Direction Measure and Gray Level Co-Occurrence Matrix Fusion Algorithm. Sensors, 17, 1474. https://doi.org/10.3390/s17071474.
10. Knoth, C., Slimani, S., Appel, M., & Pebesma, E. (2018). Combining automatic and manual image analysis in a web-mapping application for collaborative conflict damage assessment. Applied Geography, 97, 25-34. https://doi.org/10.1016/j.apgeog.2018.05.016.
11. Quinn, J. A., Nyhan, M. M., Navarro, C., Coluccia, D., Bromley, L., & Luengo-Oroz, M. (2018). Humanitarian applications of machine learning with remote-sensing data: Review and case study in refugee settlement mapping. Philosophical Transactions of the Royal Society of London. https://doi.org/10.1098/rsta.2017.0363.
12. Nex, F., Duarte, D., Tonolo, F., & Kerle, N. (2019). Building damage detection with deep learning: Assessment of a state-of-the-art CNN in operational conditions. Remote Sensing, 11, 2765. https://doi.org/10.3390/rs11232765.
13. D’Apice, C., Kogut, P. I., Kupenko, O., & Manzo, R. (2023). On Variational Problem with Nonstandard Growth Functional and Its Applications to Image Processing. Journal of Mathematical Imaging and Vision, 65(3), 472-491. https://doi.org/10.1007/s10851-022-01131-w.
14. Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (pp. 3431-3440). Boston, MA, USA. https://doi.org/10.1109/CVPR.2015.7298965.
15. Liu, L., Ouyang, W., Wang, X., Fieguth, W. P., Chen, J., Liu, X., & Pietikinen, M. (2020). Deep learning for generic object detection. A survey. International Journal of Computer Vision, 128, 261-318. https://doi.org/10.48550/arXiv.1809.02165.
16. Huang, J., Zhang, X., Xin, Q., Sun, Y., & Zhang, P. (2019). Automatic building extraction from high-resolution aerial images and LiDAR data using gated residual refinement network. ISPRS Journal of Photogrammetry and Remote Sensing, 151, 91-105. https://doi.org/10.1016/j.isprsjprs.2019.02.019.
17. Mueller, H., Groeger, A., Hersh, J., Matranga, A., & Serrat, J. (2021). Monitoring war destruction from space using machine learning. Proceedings of the National Academy of Sciences, 118(23). https://doi.org/10.1073/pnas.2025400118.
18. Hnatushenko, V., Hnatushenko, Vik. V., Kavats, A. A., & Shevchenko, V. Ju. (2015). Pansharpening technology of high resolution multispectral and panchromatic satellite images. Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, (4), 91-98.
19. Garcia-Alvarez, D., Bregon, A., Pulido, B., & Alonso-Gonzalez, C. J. (2023). Integrating PCA and structural model decomposition to improve fault monitoring and diagnosis with varying operation points. Engineering Applications of Artificial Intelligence, 122. https://doi.org/10.1016/j.engappai.2023.106145.
20. Pranata, K. S., Gunawan, A. A. S., & Gaol, F. L. (2023). Development clustering system IDX company with k-means algorithm and DBSCAN based on fundamental indicator and ESG. Procedia Computer Science, 216, 319-327. https://doi.org/10.1016/j.procs.2022.12.142.
21. Perafan-Lopez, J. C., & Sierra-Pérez, J. (2021). An unsupervised pattern recognition methodology based on factor analysis and a genetic-DBSCAN algorithm to infer operational conditions from strain measurements in structural applications. Chinese Journal of Aeronautics, 34, 165-181. https://doi.org/10.1016/j.cja.2020.09.035.
22. Xu, J., Zhang, Yu., & Miao, D. (2020). Three-way confusion matrix for classification: A measure driven view. Information Sciences, 507, 772-794. https://doi.org/10.1016/j.ins.2019.06.064.
Newer news items:
- Peculiarities of truck transportation in wartime conditions - 23/12/2023 01:30
- Information support for management of energy-saving economic development of enterprises - 23/12/2023 01:29
- Investment principles in value-target processes of electricity consumption at iron ore enterprises - 23/12/2023 01:29
- Development of digital infrastructure and blockchain in Ukraine - 23/12/2023 01:29
- Dual form of education within the framework of contemporary educational trends in Ukraine - 23/12/2023 01:29
- Structuring “education – migration – labour market” chain - 23/12/2023 01:29
- Legal provision of social protection of employees in the conditions of martial law - 23/12/2023 01:29
Older news items:
- Methodology of creation and development of information systems for technological safety of mining facilities - 23/12/2023 01:29
- Legal support of labor protection standards under martial law - 23/12/2023 01:29
- Activities efficiency assessment of the governing body’s task force under environmental emergency - 23/12/2023 01:29
- Assessment of coal mining impact on the geoecological transformation of the Emerald network ecosystem - 23/12/2023 01:29
- Smart grid projects in the pan-European energy system - 23/12/2023 01:29
- Accounting for a positive, negative and zero sequences power in a three-phase unbalanced electrical system - 23/12/2023 01:29
- Study of leakage current in underground mine power network: a case study in mining in Vietnam - 23/12/2023 01:29
- A methodological approach to assessing the durability of welded structures of screens using SolidWorks Simulation software - 23/12/2023 01:29
- Mathematical models for determining and analyzing thermal regimes in mining industry mechanism structures - 23/12/2023 01:29
- Efficiency and seismic safety of constructing underground structures in complex rock masses - 23/12/2023 01:29
Archive