Multisource-Knowledge-Based Approach for Crowd Evacuation Navigation

Abstract

In crowd evacuation research, the knowledge contained in crowd evacuation is very complex and is multisource. Crowd evacuation scenarios restrict pedestrians’ movement decision-making, and the movement states of the crowd imply the movement characteristics. However, the existing studies on crowd evacuation navigation approach cannot make full use of the complex and multisource crowd evacuation knowledge, which reduces the effect of the evacuation navigation. To solve this problem, a new crowd evacuation navigation approach based on multisource knowledge is proposed. First, we collect relevant data on crowd evacuation using an image sensor network and establish a crowd evacuation knowledge graph to organize and store this data. Second, the explicit knowledge of scene structure and crowd movements is represented based on the crowd evacuation knowledge graph. Then, a deep-learning-based tacit knowledge model (DLTKM) is designed to extract the tacit knowledge of different groups and scene entities. Finally, a new crowd evacuation navigation approach based on wireless sensor network and related knowledge representations is designed to plan evacuation paths for evacuees. The experiment results show that this approach can plan reasonable evacuation paths for pedestrians, and improve the efficiency of crowd evacuations.