Mitsubishi Electric: The World’s First Real-Time Crowd Simulator

Mitsubishi Electric Corporation announced that it has jointly developed what is believed to be the world’s first system that analyzes data from surveillance cameras for high-accuracy real-time estimation and prediction of crowd congestion on pathways to and from event sites, working in collaboration with the Research Center for Advanced Science and Technology of Tokyo University (RCAST). As a solution for effectively managing crowd congestion based on highly accurate prediction, it is hoped that the technology will contribute to increased visitor safety and security at events.

Traditional and new systems algorithms are fundamentally different. Traditional system relies only on previously collected data of human flow density. It is uploaded from the database to the motion simulator, which is making a real time map of density of human flows.

Mitsubishi Electric represents alternative approach. To simulate the dynamics of pedestrian traffic the system analyzes data of video cameras located in strategic positions – for example, entrances to the mass event area. The system evaluates the speed and direction of people movement in real time and on this basis, data card simulates density of pedestrian flow, which is precision prediction instead of statement of the current status.

Full content of this issue you can read here

The full version of the article can be read in our printed issue, also you can subscribe to the web-version of the magazine