Abstract
Safety helmets and gloves are indispensable personal protective equipment in power grid operation environments. Traditional detection methods for safety helmets and gloves suffer from reduced accuracy due to factors such as dense personnel presence, varying lighting conditions, occlusions, and diverse postures. To enhance the detection performance of safety helmets and gloves in power grid operation environments, this paper proposes a novel algorithm, YOLO-DCRCF, based on YOLO11 for detecting the wearing of safety helmets and gloves in such settings. By integrating Deformable Convolutional Network version 2 (DCNv2), the algorithm enhances the network's capability to model geometric transformations. Additionally, a recalibration feature pyramid (RCF) network is innovatively designed to strengthen the interaction between shallow and deep features, enabling the network to capture multi-scale information of the target. Experimental results show that the proposed YOLO-DCRCF model achieved mAP50 scores of 92.7% on the Safety Helmet Wearing Dataset (SHWD) and 79.6% on the Safety Helmet and Gloves Wearing Dataset (SHAGWD), surpassing the baseline YOLOv11 model by 1.1% and 2.7%, respectively. These results meet the real-time safety monitoring requirements of power grid operation sites.