Multiscale Feature Fusion Transformer With Hybrid Attention for Insulator Defect Detection

In recent years, smart grid systems have rapidly advanced through the integration of sophisticated artificial intelligence (AI) technologies, leading to significant improvements in intelligence, efficiency, and sustainability. Insulators play a crucial role in the smart grid domain, yet accurately detecting small-target defects remains a challenge for current detection technologies. This article introduces a multiscale feature fusion transformer (MSFFT) model specifically developed to address the insufficient feature extraction capabilities in recognizing small insulator defects. This model employs a unique multiscale feature fusion method combined with an enhanced transformer framework, enabling it to capture and process information across various scales. To further improve detection accuracy, the model incorporates a novel multihead mixture attention (MHMA) mechanism. This mechanism optimizes the model’s focus on critical areas by balancing attention between fine-grained details and broader contextual features. Furthermore, this study refines the Insulator Defect Detection dataset by including annotations in both you only look once (YOLO) and common objects in context (COCO) formats, covering images of normal, damaged, and flashover insulators. The MSFFT model’s performance was compared with advanced insulator detection models, with experimental results demonstrating its impressive capabilities, achieving a mean average precision ( $\text {mAP}_{50:95}$ ) of 80.9% and an average recall ( $\text {AR}_{50:95}$ ) of 87.4%. These results underscore the model’s state-of-the-art performance and exceptional precision in detecting the smallest defects in insulators.