We use deep learning methods for automated detection of solar panel locations and their surface area using aerial imagery. The framework, which consists of a two-branch model using an image classifier in tandem with a semantic segmentation model, is trained on our created dataset of. . Recognition of photovoltaic cells in aerial images with Convolutional Neural Networks (CNNs). Object detection with YOLOv5 models and image segmentation with Unet++, FPN, DLV3+ and PSPNet. Automating solar panel identification is a rel- evant task in the context of renewable energies, where the need to keep track of these installations has increased ex- ponentially and solar developers have little to no tools to. . This paper aims to evaluate the effectiveness of two object detection models, specifically aiming to identify the superior model for detecting photovoltaic (PV) modules based on aerial images.
[PDF Version]
