Comparative analysis of Yolo based algorithms in solar panel detection using resource-constrained hardware

This study presents a comparative analysis of YOLO models for solar panel detection with the implementation on edge devices. With the rapid adoption of renewable energy, the need for monitoring and inspecting solar panel structures is also increasing. This study dives into different YOLO models for solar panel detection. It also compares the use of CLAHE and Histogram Equalization as preprocessing techniques and investigates dataset augmentation to increase its robustness. During training, YOLOv8 emerged as the strongest model with a higher F1 Score of above 96% and accuracy, also proving to have the better inference rate on both the Raspberry Pi and Google Coral Accelerator.