System analyzes walking styles to spot individuals in crowds

A team at the University of Tokyo’s Center for Spatial Information Science has developed a system that evaluates walking patterns to identify individuals in crowded places such as train stations.


It could be used for security systems that can detect suspicious characters, but also to analyze walking habits in order to design shopping districts that are easier to navigate. The team plans to partner with private-sector firms and hope the technology will be ready in two or three years.

The system combines floor-level laser beams with overhead cameras to isolate and track individuals. In tests monitoring 600 sq. meters of a crowded train station, the system isolated 80% of all passersby, even at rush hours, when about 150 people were milling about simultaneously.

With this technology, the typical walking pattern of the elderly could be used to determine where in train stations to place signs with larger, easier to read lettering. Retailers could also use the system to determine if people lingering in front of their window displays are stopping to look at their products or just stopping to talk on their phones.

Via Nikkei.