Detection of Safety Helmet Wearing Based on Improved Faster R-CNN

In order to ensure the safety of workers and the stable operation of the power grid, the power grid companies in China have developed a very strict safety control system which contains many regulations, such as safety regulations and the two-ticket regulations. However, some workers are still lack of safety awareness in that they even do not wear safety helmets when carrying out construction or maintenance projects in substations. Safety helmet is an indispensable safety tool in electric power work, which can maintain the head safety of workers at all times and avoid fatal injuries such as electric shock and strike. Working without safety helmet is not only a violation of the safety control system, but also a manifestation of not being responsible for personal life and property. Nevertheless, the existing control means can not identify and prevent such behavior timely, efficiently and accurately. In order to better avoid this unsafe behavior, this paper proposes the Improved Faster R-CNN algorithm to inspect the wearing of safety helmet. Considering the real situation, the Retinex image enhancement is introduced to improve image quality for the outdoor complex scenes in substations. K-means++ algorithm is also adopted for better adaptation to the small size helmet. The experimental results show that compared with the Faster R-CNN algorithm, the mean average precision of the Improved Faster R-CNN is improved and the real-time automatic detection of the wearing of safety helmets is realized.