Synthetic Dataset for Panic Detection in Human Crowded Scenes

Abstract

AI is increasingly being used in public protection by using crowd anomaly detection. This is useful for identifying panic events enabling control forces to act faster. A significant challenge in this field is the lack of data for training these algorithms. Recreating panic events with big crowds can be both expensive and hazardous. To address this issue, this paper proposes the creation of a synthetic dataset for crowd panic behaviour. The process involves defining the scenario and setting up the appropriate CCTV cameras. Many scenarios are prepared, including variations in weather conditions. Next is the scene population with pedestrians and vehicles, with different crowd sizes and vehicle trajectories. To recreate panic, the behaviour of each person is programmed. The final videos show normality situations before the panic events start. Finally, we achieved 1717 simulations.