Distributed Photovoltaic Panel Target Detection Algorithm Based on Improved YOLOv8n

To address the challenges of complex background interference, target occlusion, and scale variability in the detection of distributed photovoltaic (PV) panels from high-altitude views, this paper proposed an improved target detection algorithm based on YOLOv8n.First, the C2f module in the backbone network was replaced with a C2f_AT module, enabling the model to better capture both global and local features. Second, a large separable kernel attention (LSKA) module was integrated into the SPPF structure to reduce the impact of irrelevant background information. Then, an efficient multi-scale attention module was introduced into the feature fusion network to enhance the model's adaptability to targets of various scales. Finally, the network was optimized using the WIoU loss function to further improve detection accuracy. Experimental results showed that the improved algorithm achieved an mAP@0.5 of 83.6%, representing a 3.5% increase over the baseline YOLOv8n algorithm. These results demonstrate that the improved YOLOv8n algorithm can effectively enhance the detection accuracy of distributed photovoltaic panels.