Solar Panel Segmentation :Self-Supervised Learning Solutions for Imperfect Datasets (2402.12843v3)
Abstract: The increasing adoption of solar energy necessitates advanced methodologies for monitoring and maintenance to ensure optimal performance of solar panel installations. A critical component in this context is the accurate segmentation of solar panels from aerial or satellite imagery, which is essential for identifying operational issues and assessing efficiency. This paper addresses the significant challenges in panel segmentation, particularly the scarcity of annotated data and the labour-intensive nature of manual annotation for supervised learning. We explore and apply Self-Supervised Learning (SSL) to solve these challenges. We demonstrate that SSL significantly enhances model generalization under various conditions and reduces dependency on manually annotated data, paving the way for robust and adaptable solar panel segmentation solutions.
- Research on self-supervised building information extraction with high-resolution remote sensing images for photovoltaic potential evaluation. Remote Sensing, 14(21), 2022. ISSN 2072-4292. doi: 10.3390/rs14215350. URL https://www.mdpi.com/2072-4292/14/21/5350.
- A simple framework for contrastive learning of visual representations. In Hal Daumé III and Aarti Singh (eds.), Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pp. 1597–1607. PMLR, 13–18 Jul 2020. URL https://proceedings.mlr.press/v119/chen20j.html.
- Scarcity of labels in non-stationary data streams: A survey. ACM Comput. Surv., 55(2), jan 2022. ISSN 0360-0300. doi: 10.1145/3494832. URL https://doi.org/10.1145/3494832.
- Deep residual learning for image recognition, 2015.
- Using self-supervised learning can improve model robustness and uncertainty. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett (eds.), Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019. URL https://proceedings.neurips.cc/paper_files/paper/2019/file/a2b15837edac15df90721968986f7f8e-Paper.pdf.
- Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery. Earth System Science Data, 13(11):5389–5401, 2021. doi: 10.5194/essd-13-5389-2021. URL https://essd.copernicus.org/articles/13/5389/2021/.
- Adam: A method for stochastic optimization, 2017.
- Feature pyramid networks for object detection, 2017.
- Focal loss for dense object detection, 2018.
- The challenge of reproducing remote sensing data from satellites and unmanned aerial vehicles (uavs) in the context of management zones and precision agriculture. Precision Agriculture, 22:834–851, 2021.
- U-net: Convolutional networks for biomedical image segmentation, 2015.
- Segformer: Simple and efficient design for semantic segmentation with transformers, 2021.
- Pyramid scene parsing network, 2017.
- Zhi-Hua Zhou. A brief introduction to weakly supervised learning. National Science Review, 5(1):44–53, 08 2017. ISSN 2095-5138. doi: 10.1093/nsr/nwx106. URL https://doi.org/10.1093/nsr/nwx106.
- The automatic segmentation of residential solar panels based on satellite images: A cross learning driven u-net method. Appl. Soft Comput., 92:106283, 2020. URL https://api.semanticscholar.org/CorpusID:216382564.