Wearing personal safety protective equipment (PSPE) plays a key role in reducing electrical injuries to electrical workers. However, due to the lack of safety awareness, operators often do not wear PSPE when carrying out inspection or maintenance projects in substations, which is the main reason for personal injury accidents. Therefore, it is necessary to detect the wearing of PSPE in real-time through a video surveillance system. In this paper, a wear-enhanced YOLOv3 method for real-time detection of PSPE wear of substation operators is proposed. In order to improve the detection accuracy, the gamma correction is applied as the preprocessing method to highlight the details of the operators. Besides, K-means++ algorithm is introduced to get the most suitable prior bounding box size to improve the detection speed. Based on the proposed method, it can quickly and effectively detect whether the substation operators are wearing safety helmets and insulating gloves and boots correctly. Finally, extensive experiments are carried out using a dataset of real substation monitoring images to illustrate the effectiveness of the proposed method for realtime PSPE wear detection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.