Flat roof classification and leaks detections by Deep Learning
DOI:
https://doi.org/10.14311/CEJ.2023.04.0042Keywords:
Thermography, remote sensing, CNN, U-NET, flat roof leak detectionAbstract
This paper presents an efficient and accurate method for detecting flat roof leaks using a combination of unmanned aerial vehicles (UAVs) and deep learning. The proposed method utilizes a DJI M300 drone equipped with RGB and thermal cameras to capture high-resolution images of the roof. These images are then processed to create orthomosaics and digital elevation models (DEMs). A deep learning model based on the U-NET architecture is then used to segment the roof into different classes, such as PVC foil, windows, and sidewalks. Finally, the damaged insulation is identified by analyzing the temperature distribution within the PVC foil segments. The proposed method has several advantages over traditional inspection methods. It is much faster and more efficient. A UAV can collect images of a large roof in a matter of minutes, while traditional methods can take several days or weeks. The orthomosaics and temperature maps generated by the UAV are much more detailed than the images that can be collected by a human inspector. Third, the UAV-based system is safer. The UAV can collect images of the roof without the need for a human inspector to climb onto the roof, which can be dangerous. The results of this study show that the proposed method is an effective and accurate way to detect flat roof leaks. The deep learning model was able to achieve an overall accuracy of 95% in segmenting the roof into different classes. The method was also able to identify damaged insulation with a high degree of accuracy.
Downloads
References
Antón García, D. y Amaro Mellado, J.L., 2021: Engineering graphics for thermal assessment: 3D thermal data visualisation based on infrared thermography, GIS and 3D point cloud processing software. Symmetry, 13 (2(335)) https://doi.org/10.3390/sym13020335
Jairo Acuña Paz y Miño, Nicolas Duport, Benoit Beckers, 2021:Pixel-by-pixel rectification of urban perspective thermography, Remote Sensing of Environment, Volume 266, 112689, https://doi.org/10.1016/j.rse.2021.112689
Adamopoulos E, Volinia M, Girotto M, Rinaudo F., 2020: Three-Dimensional Thermal Mapping from IRT Images for Rapid Architectural Heritage NDT, Buildings, 10(10):187. https://doi.org/10.3390/buildings10100187
Dlesk, A., Vach, K., and Holubec, P., 2018: USAGE OF PHOTOGRAMMETRIC PROCESSING OF THERMAL IMAGES FOR CIVIL ENGINEERS, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-5, 99–103, https://doi.org/10.5194/isprs-archives-XLII-5-99-2018
Daffara C, Muradore R, Piccinelli N, Gaburro N, de Rubeis T, Ambrosini D., 2020: A Cost-Effective System for Aerial 3D Thermography of Buildings. Journal of Imaging. 6(8):76. https://doi.org/10.3390/jimaging6080076
Yishuo Huang, Paul Shih, Keng-Tsang Hsu, Chih-Hung Chiang, 2020: To identify the defects illustrated on building facades by employing infrared thermography under shadow,
Huang, Y., Shih, P., Hsu, K. T., & Chiang, C. (2020, April 1). To identify the defects illustrated on building facades by employing infrared thermography under shadow. NDT & E International. https://doi.org/10.1016/j.ndteint.2020.102240
Tarek Rakha, Yasser El Masri, Kaiwen Chen, Eleanna Panagoulia, Pieter De Wilde, 2021: Building envelope anomaly characterization and simulation using drone time-lapse thermography, Energy and Buildings, 111754, ISSN 0378-7788, https://doi.org/10.1016/j.enbuild.2021.111754
Yuan, W., & Hua, W. (2022). A Case Study of Vignetting Nonuniformity in UAV-Based Uncooled Thermal Cameras. Drones, 6(12), 394.
Norhan Bayomi, Shreshth Nagpal, Tarek Rakha, John E. Fernandez , 2021: Building envelope modeling calibration using aerial thermography, Energy and Buildings, Volume 233, 110648, ISSN 0378-7788, https://doi.org/10.1016/j.enbuild.2020.110648.
Dlesk A, Vach K, Pavelka K. 2021: Transformations in the Photogrammetric Co-Processing of Thermal Infrared Images and RGB Images, Sensors. 2021; 21(15):5061. https://doi.org/10.3390/s21155061
Motayyeb, S., Samadzedegan, F., Javan, F. D., & Hosseinpour, H. (2023). Fusion of UAV-based infrared and visible images for thermal leakage map generation of building facades. Heliyon, 9(3)
Stokowiec, K., & Sobura, S. (2022, September). Hand-held and UAV camera comparison in building thermal inspection process. In Journal of Physics: Conference Series (Vol. 2339, No. 1, p. 012017). IOP Publishing.
Kuo, C. F. J., Chen, S. H., & Huang, C. Y. (2023). Automatic detection, classification and localization of defects in large photovoltaic plants using unmanned aerial vehicles (UAV) based infrared (IR) and RGB imaging. Energy Conversion and Management, 276, 116495.
Meng, L., Zhou, J., Liu, S., Wang, Z., Zhang, X., Ding, L., ... & Wang, S. (2022). A robust registration method for UAV thermal infrared and visible images taken by dual-cameras. ISPRS Journal of Photogrammetry and Remote Sensing, 192, 189-214.
Osco, L. P., Marcato, J., Ramos, A. P. M., De Castro Jorge, L. A., Fatholahi, S. N., De Andrade Silva, J., Matsubara, E. T., Pistori, H., Gonçalves, W. N., & Li, J. (2021, October 1). A review on deep learning in UAV remote sensing. International Journal of Applied Earth Observation and Geoinformation. https://doi.org/10.1016/j.jag.2021.102456
Naushad, R., Kaur, T., & Ghaderpour, E. (2021, December 3). Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study. Sensors. https://doi.org/10.3390/s21238083
Natesan, S., Armenakis, C., & Vepakomma, U. (2019, June 4). RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGES. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. https://doi.org/10.5194/isprs-archives-xlii-2-w13-475-2019
Yi-Jun, L., Mohammadi, M. E., & Wood, R. L. (2020, June 22). Deep Learning Classification of 2D Orthomosaic Images and 3D Point Clouds for Post-Event Structural Damage Assessment. Drones. https://doi.org/10.3390/drones4020024
How U-net works? | ArcGIS API for Python. (n.d.). https://developers.arcgis.com/python/guide/how-unet-works/
R. (n.d.). GitHub - reachsumit/deep-unet-for-satellite-image-segmentation: Satellite Imagery Feature Detection with SpaceNet dataset using deep UNet. GitHub. https://github.com/reachsumit/deep-unet-for-satellite-image-segmentation
Reder, S., Mund, J., Albert, N. G., Waßermann, L., & Miranda, L. (2021, December 24). Detection of Windthrown Tree Stems on UAV-Orthomosaics Using U-Net Convolutional Networks. Remote Sensing. https://doi.org/10.3390/rs14010075
Kislov, D. E., & Korznikov, K. A. (2020, April 3). Automatic Windthrow Detection Using Very-High-Resolution Satellite Imagery and Deep Learning. Remote Sensing. https://doi.org/10.3390/rs12071145
Satari, R., Kazimi, B., & Sester, M. (2021, June 4). Extraction of linear structures from digital terrain models using deep learning. AGILE: GIScience Series. https://doi.org/10.5194/agile-giss-2-11-2021
A Deep Learning Model for Identifying Mountain Summits in Digital Elevation Model Data. (2018, September 1). IEEE Conference Publication | IEEE Xplore. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8527481
Park, G., Lee, M., Jang, H. I., & Kim, C. (2021, May 1). Thermal anomaly detection in walls via CNN-based segmentation. Automation in Construction. https://doi.org/10.1016/j.autcon.2021.103627
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Stavební obzor - Civil Engineering Journal
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
¨
