Over-crowdedness Alert! Forecasting the Future Crowd Distribution
This addresses forecasting crowd dynamics for applications in public safety and urban planning, but it is incremental as it builds on existing vision-based crowd analysis methods.
The paper tackles the problem of predicting future crowd distribution from sequential video frames without identity annotations, proposing a global-residual two-stream recurrent network that uses simulated data for pretraining and demonstrates applications like forecasting crowd count and high-density regions.
In recent years, vision-based crowd analysis has been studied extensively due to its practical applications in real world. In this paper, we formulate a novel crowd analysis problem, in which we aim to predict the crowd distribution in the near future given sequential frames of a crowd video without any identity annotations. Studying this research problem will benefit applications concerned with forecasting crowd dynamics. To solve this problem, we propose a global-residual two-stream recurrent network, which leverages the consecutive crowd video frames as inputs and their corresponding density maps as auxiliary information to predict the future crowd distribution. Moreover, to strengthen the capability of our network, we synthesize scene-specific crowd density maps using simulated data for pretraining. Finally, we demonstrate that our framework is able to predict the crowd distribution for different crowd scenarios and we delve into applications including predicting future crowd count, forecasting high-density region, etc.