Crowd behaviour recognition system for evacuation support by using machine learning

Abstract

The crowd behaviour recognition system is a subsystem of a distributed cooperative adaptive evacuation guide system, and it detects and forecasts crowd flow and anomaly occurrence by using machine learning method such as deep learning with visual and depth information obtained by RGB-D camera. The distributed cooperative adaptive evacuation guide system aims to suggest evacuation routes at extensive evacuation situations by autonomously cooperation among plural sensors and evacuation guiding devices. In this paper, a recognition method of overall behaviour of the crowd is proposed. Some indices for indicating the situation are examined in order to recognize the overall behaviour of the crowd flow and the anomaly occurrence, and cooperate among the system by sharing the recognition results rapidly.