Face recognition technology based on CNN, XGBoost, model fusion and its application for safety management in power system

Abstract

The safety maintenance of operating site is important for safety management in power system. With the development of artificial intelligence (AI) and popularization of monitoring camera, face recognition technology is widely utilized in operating site of power system. To improve the capability for safety management of operating site in power system, a face recognition model based on convolutional neural network (CNN), eXtreme gradient boosting (XGBoost) and model fusion is built. Firstly, pre-processed images are input into CNN to obtain the recognition probabilities of various face and the extracted face features. Secondly, the extracted features of CNN are input into XGBoost to obtain the recognition probabilities of various face recognized by XGBoost. Finally, above two groups of probabilities are weighted by model fusion technology to obtain the final recognition probabilities of various face, and the final face recognition results are output. Simulation results show that CNN has better capability of feature extraction, and the proposed face recognition model has the highest recognition accuracy among those advanced face recognition models. In addition, this paper describes the application based on the proposed face recognition model in non-working personnel recognition, trajectory tracking of operators, etc, so as to greatly improve the safety management of operating site in power system, which not only ensures safety, but also reduces unnecessary management expenses.