FAA-YOLO: A Method for Defects Detection of Small Infrared Targets in Photovoltaic Modules
Weihao Li, Jianqi Li, Binfang Cao, Jiang Zhu, Minghui Tian
Abstract
The regular inspection of photovoltaic (PV) modules is a crucial measure to ensure the safety of solar power generation. To address the challenges posed by small, multiscale infrared defects in PV modules, this article proposes a method called filter and adaptive assisted-you only look once (FAA-YOLO) for detecting small infrared defects in PV modules. First, we design a multiscale parameter-free edge detection (MPED) module to enhance shallow features, such as texture and edges, thereby improving the network’s capability to extract features from small defect targets. Second, we introduce an improved feature fusion network named SlimNet, which mitigates the challenges of small infrared defects in PV modules and the tendency of such features to be overlooked by fusing information from different scales. Last, we propose an adaptive auxiliary detection layer (AAD-Layer). The multiscale AAD-Layer enables feature reuse and enriches defect feature representation by cascading features of different scales across layers and combining deep and shallow features. Experimental results show that the proposed FAA-YOLO model achieves a detection accuracy of 87.5%. Compared to others methods, it also strikes a good balance between accuracy and computational complexity.