Solar Panel Mapping via Oriented Object Detection
This work addresses the tedious and non-scalable task of manually mapping solar panels for analysts in the solar energy industry, representing an incremental improvement in domain-specific automation.
The paper tackles the problem of mapping solar panels in power plants by proposing an end-to-end deep learning framework using rotated object detection, achieving a mAP score of 83.3% on a diverse dataset from the United States.
Maintaining the integrity of solar power plants is a vital component in dealing with the current climate crisis. This process begins with analysts creating a detailed map of a plant with the coordinates of every solar panel, making it possible to quickly locate and mitigate potential faulty solar panels. However, this task is extremely tedious and is not scalable for the ever increasing capacity of solar power across the globe. Therefore, we propose an end-to-end deep learning framework for detecting individual solar panels using a rotated object detection architecture. We evaluate our approach on a diverse dataset of solar power plants collected from across the United States and report a mAP score of 83.3%.