Feature extraction and dynamic identification of drivers' emotions

摘要

Human emotions are the revulsive of intentions. It's an important premise to identify drivers' emotions dynamically and correctly for the realization of drivers' intentions identification, active vehicle security warning and mind control driving. It is also an essential requirement for the microscopic research of traffic flow theory. Taking the car-following condition as an example, multi-source and dynamic data of human-vehicle-environment under drivers' different emotional states was obtained through emotions induced experiments, actual driving experiments and virtual driving experiments in this paper. The main influencing factors of typical driving emotions were extracted with factor analysis method and emotion identification model was established based on the fuzzy comprehensive evaluation and PAD emotional model. The emotions of joy, anger, sadness and fear can be identified online. The rationality and validity of the emotions feature extraction and identification model were verified through the experiments of actual driving, virtual driving and interactive simulation. The theoretical foundation for the study of emotion guidance mechanism of drivers' intentions can be provided. (C) 2019 Elsevier Ltd. All rights reserved.