Data-Driven Modeling of Pedestrian Crowds: Crowd Simulation, Computer Vision, and Real-World Applications

Numerous crowd disasters occur each year at large gatherings around the world. Unfortunately, the information about the (spatio-temporal) development of these events tend to be qualitative rather than quantitative. Video recordings from the crowd disaster in Mina, Kingdom of Saudi Arabia, on the 12th of January 2006, where hundreds of pilgrims lost their lives during the annual Muslim pilgrimage to Makkah, gave the possibility to scientifically evaluate the dynamics of the crowd. Based on the insights from the analysis of the crowd disaster, new tools and measures to detect and avoid critical crowd conditions have been proposed, and some of them have been implemented in order to reduce the likelihood of similar disasters in the future. In order to enable the revision of previous works and the analysis of the crowd disaster mentioned above, algorithms used for video-tracking have been introduced. The novelty of this work concerns not only the algorithms themselves, but also the uniqueness and quantity of data on which the algorithms have been validated and calibrated.