Optimal Aerial Imaging Parameters for UAV-Based Inspection and Maintenance of Photovoltaic Installations

Unmanned Aerial Vehicles (UAVs) equipped with thermal and RGB cameras and enhanced by deep learning offer a powerful solution for autonomous photovoltaic (PV) system inspection. However, defect detection performance depends on flight parameters such as altitude, camera angles, speed, and solar position. This study examines the impact of various UAV flight parameters on the accurate detection of critical PV defects including hotspots, dirt from bird droppings, dust accumulation, and cell failures. For this purpose, two datasets were developed, comprising over 38,000 thermal infrared and RGB images. Using the YOLOv11 model, 21 flight configurations varying in altitude, camera tilt and pan angles, speed, and solar position were evaluated at four different times of day to assess the combined ambient and geometric effects on detection accuracy. Results indicate that low-altitude flights enhance small-object detection, while higher altitudes improve coverage at the expense of fine-detail accuracy. Dust detection is most effective when the camera aligns with the sun, whereas steep midday tilts cause reflective false positives. Thermal defect detection performs best during morning flights with moderate tilt angles. These findings emphasize the need to balance accuracy, coverage, efficiency, and safety, offering practical guidelines for effective and scalable PV inspection and maintenance.