Crowd behavior reconstruction with deep group feature learning

Crowd behavior understanding and reconstruction hold significant applications in areas such as public health and urban management. In dense scenes, it is challenging to obtain individual trajectories, which limits the flexibility of traditional trajectory-based methods for generating crowd behavior. To address this issue, we propose a video-based framework for reconstructing crowd behavior. It obtains multimodal group feature representations of the crowd before applying a deep learning network. These features capture the collective movement patterns and we use them to enhance the robustness of reconstruction. Experimental results demonstrate that without relying on precise individual trajectories, our method can produce crowd behavior trajectories that align with the original video's dynamics, providing a more flexible way of studying crowd behavior.