Understanding rooftop PV panel semantic segmentation of satellite and aerial images for better using machine learning

The photovoltaic (PV) industry boom and increased PV applications call for better planning based on accurate and updated data on the installed capacity. Compared with the manual statistical approach, which is often timeconsuming and labor-intensive, using satellite/aerial images to estimate the existing PV installed capacity offers a new method with cost-effective and data-consistent features. Previous studies investigated the feasibility of segmenting PV panels from images involving machine learning technologies. However, due to the particular characteristics of PV panel semantic-segmentation, the machine learning tools need to be designed and applied with careful considerations of the issue formulation, data quality, and model explainability. This paper investigated the characteristics of PV panel semantic-segmentation from the perspective of computer vision. The results reveal that the PV panel image data has several specific characteristics: highly class-imbalance and non-concentrated distribution; homogeneous texture and heterogenous color features; and the notable resolution threshold for effective semantic-segmentation. Moreover, this paper provided recommendations for data obtaining and model design, aiming at each observed character from the viewpoints of recent solutions in computer vision, which can be helpful for future improvement of the PV panel semantic-segmentation.

Automated summary

Photovoltaic panel image data has specific characteristics such as highly class-imbalanced and non-concentrated distribution, homogeneous texture and heterogeneous color features, and a notable resolution threshold for effective semantic segmentation. Recommendations for data obtaining and model design are provided for future improvement in PV panel semantic segmentation.