A very deep two-stream network for crowd type recognition

Crowd type identification is a crucial task in the emergency alert. In this paper, to solve accurate identification of crowd type, the crowd type description triad C-BMO < Behavior, Mood, Organized > and a novel crowd type recognition network (CTRN): very deep two-stream network architecture are proposed, respectively. The very deep two-stream network architecture is based on the static map and motion map in the video. To early warn the emergency, the reasoning rules of the emergency alert are proposed based on joining the crowd type and the crowd characteristics. To verify the proposed method, the crowd type dataset is collected, and we experiment with the proposed plan on the crowd type dataset. The experimental results demonstrate that the proposed model is competitive compared with the state-of-the-art techniques. (C) 2019 Published by Elsevier B.V.