SolarDK: A high-resolution urban solar panel image classification and localization dataset
This addresses the lack of public benchmark datasets for solar panel detection, which is an incremental contribution to geospatial research.
The paper introduces two new benchmark datasets for classifying and localizing solar panel arrays from aerial imagery in Denmark, including a human-annotated dataset and one based on self-reported data, and provides baseline results by fine-tuning existing models and training newer architectures.
The body of research on classification of solar panel arrays from aerial imagery is increasing, yet there are still not many public benchmark datasets. This paper introduces two novel benchmark datasets for classifying and localizing solar panel arrays in Denmark: A human annotated dataset for classification and segmentation, as well as a classification dataset acquired using self-reported data from the Danish national building registry. We explore the performance of prior works on the new benchmark dataset, and present results after fine-tuning models using a similar approach as recent works. Furthermore, we train models of newer architectures and provide benchmark baselines to our datasets in several scenarios. We believe the release of these datasets may improve future research in both local and global geospatial domains for identifying and mapping of solar panel arrays from aerial imagery. The data is accessible at https://osf.io/aj539/.