Detailed Aerial Mapping of Photovoltaic Power Plants Through Semantically Significant Keypoints

Abstract

An accurate and up-to-date model of a photovoltaic (PV) power plant is essential for its optimal operation and maintenance. However, such a model may not be easily available. This work introduces a novel approach for PV power plant mapping based on aerial overview images. It enables the automation of the mapping process while removing the reliance on third-party data. The presented mapping method takes advantage of the structural layout of the power plants to achieve detailed modeling down to the level of individual PV modules. The approach relies on visual segmentation of PV modules in overview images and the inference of structural information in each image, assigning modules to individual benches, rows, and columns. We identify visual keypoints related to the layout and use these to merge detections from multiple images while maintaining their structural integrity. The presented method was experimentally verified and evaluated on two different power plants. The final fusion of 3D positions and semantic structures results in a compact georeferenced model suitable for power plant maintenance.

Keywords

• UAV
• photogrammetry
• photovoltaic
• mapping
• structure-from-motion
• aerial systems
• PV
• Computer vision for automation

References

1. Gholami, A. (2024). Exploring drone classifications and applications: a review. International Journal of Engineering and Geosciences, 9(3), 418-442. https://doi.org/10.26833/ijeg.1428724
2. Niccolai, A., Grimaccia, F., & Leva, S. (2019). Advanced asset management tools in photovoltaic plant monitoring: UAV-based digital mapping. Energies, 12(24). https://doi.org/10.3390/en12244736
3. Michail, A., Livera, A., Tziolis, G., Carús Candás, J. L., Fernandez, A., Antuña Yudego, E., Fernández Martínez, D., Antonopoulos, A., Tripolitsiotis, A., Partsinevelos, P., Koutroulis, E., & Georghiou, G. E. (2024). A comprehensive review of unmanned aerial vehicle-based approaches to support photovoltaic plant diagnosis. Heliyon, 10(1), e23983. https://doi.org/10.1016/j.heliyon.2024.e23983
4. Niccolai, A., Gandelli, A., Grimaccia, F., Zich, R., & Leva, S. (2019). Overview on photovoltaic inspections procedure by means of unmanned aerial vehicles. 2019 IEEE Milan PowerTech, 1–6. https://doi.org/10.1109/PTC.2019.8810987
5. Yakar, M., & Dogan, Y. (2018, November). 3D Reconstruction of residential areas with SfM photogrammetry. In Conference of the Arabian Journal of Geosciences (pp. 73-75). Cham: Springer International Publishing.
6. Jiang, H., Yao, L., Lu, N., Qin, J., Liu, T., Liu, Y., & Zhou, C. (2021). Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery. Earth System Science Data, 13(11), 5389–5401. https://doi.org/10.5194/essd-13-5389-2021 Piccinini, F., Pierdicca, R., & Malinverni, E. S. (2020). A relational conceptual model in GIS for the management of photovoltaic systems. Energies, 13(11). https://doi.org/10.3390/en13112860
7. Kozák, V., Košnar, K., Chudoba, J., Kulich, M., & Přeučil, L. (2025). Visual localization via semantic structures in autonomous photovoltaic power plant inspection. arXiv preprint. https://doi.org/10.48550/arXiv.2501.14587
8. Bommes, L., Buerhop-Lutz, C., Pickel, T., Hauch, J., Brabec, C., & Marius Peters, I. (2022). Georeferencing of photovoltaic modules from aerial infrared videos using structure-from-motion. Progress in Photovoltaics: Research and Applications, 30(9), 1122–1135. https://doi.org/10.1002/pip.3564

9. He, K., Gkioxari, G., Dollár, P., & Girshick, R. B. (2017). Mask R-CNN. 2017 IEEE International Conference on Computer Vision (ICCV), 2980–2988. https://doi.org/10.1109/ICCV.2017.322
10. Hernández-López, D., de Oña, E. R., Moreno, M. A., & González-Aguilera, D. (2023). SunMap: Towards unattended maintenance of photovoltaic plants using drone photogrammetry. Drones, 7(2). https://doi.org/10.3390/drones7020129
11. Kaya, Y., Şenol, H. İ., Yiğit, A. Y., & Yakar, M. (2023). Car detection from very high-resolution UAV images using deep learning algorithms. Photogrammetric Engineering & Remote Sensing, 89(2), 117-123.
12. Mapillary. (2020). OpenSfM. https://github.com/mapillary/OpenSfM (Accessed June 15, 2025).
13. Abeho, D. R., Shoko, M., & Odera, P. A. (2024). Effects of camera calibration on the accuracy of Unmanned Aerial Vehicle sensor products. International Journal of Engineering and Geosciences, 9(3), 314-323. https://doi.org/10.26833/ijeg.1422619
14. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
15. Jocher, G., Chaurasia, A., & Qiu, J. (2023). Ultralytics YOLOv8. https://github.com/ultralytics/ultralytics
16. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderfplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
17. Seznam.cz, a.s., & TopGis, s.r.o. (2025). Mapy.cz. https://mapy.cz (Accessed June 15, 2025).
18. NASA Shuttle Radar Topography Mission (SRTM). (2013). Shuttle Radar Topography Mission (SRTM) Global. Distributed by OpenTopography. https://doi.org/10.5069/G9445JDF (Accessed June 15, 2025).
19. Niccolai, A., Grimaccia, F., Leva, S., & Eleftheriadis, P. (2021). Photovoltaic plant inspection by means of UAV: Current practices and future perspectives. In 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe) (pp. 1–6). https://doi.org/10.1109/EEEIC/ICPSEurope51164.2021.9499554
20. Álvarez Tey, G., & García-López, C. (2022). Strategy based on two stages for IR thermographic inspections of photovoltaic plants. Applied Sciences, 12(13), 6331. https://doi.org/10.3390/app12136331
21. Gallardo-Saavedra, S., Hernández-Callejo, L., & Duque-Perez, O. (2018). Image resolution influence in aerial thermographic inspections of photovoltaic plants. IEEE Transactions on Industrial Informatics, 14(12), 5678–5686. https://doi.org/10.1109/TII.2018.2865403
22. Morando, L., Recchiuto, C. T., Calla, J., Scuteri, P., & Sgorbissa, A. (2022). Thermal and visual tracking of photovoltaic plants for autonomous UAV inspection. Drones, 6(11), 347. https://doi.org/10.3390/drones6110347