ActcastAI
Tokyo Metropolitan Bureau of Transportation
Setting the timetable for the Toei Subway requires knowing accurately which station, which car, and how many people are boarding and alighting. But surveys were carried out by staff observing in person, which limited the places, times and cars that could be measured.
The challenge Idein solves
Edge AI cameras on the platform measure the number of passengers inside the car and the numbers boarding and alighting while it is stopped. Because footage is never sent to the cloud and only counts are extracted on the spot, the setup can stay in place in a public space. Site-specific conditions — such as UV-blocking window film affecting analysis accuracy — were established by installing and testing rather than assumed.
What we did
- Selected for the Tokyo Metropolitan Government’s “on-site dialogue” startup collaboration project, with a trial run in February 2024
- The “ai cast” edge AI camera installed on the platform at Jimbocho Station on the Toei Shinjuku Line
- For boarding and alighting counts, AI achieved 100% success in detecting people in both directions
- Passenger counts were measured with very high accuracy in the area in front of the doors; accuracy dropped in the window area due to UV-blocking film, with over 90% projected after improvement
- Related release: Idein advances rail DX through a collaboration project with the Tokyo Metropolitan Government, capturing and visualizing Toei Subway passenger volumes with AI cameras (Idein, PR TIMES)