A vision-based multi-camera fusion and CAD projection framework for risk-point identification in metro stations
Yichao Pu, Qianqi Fan, Shengyu Zhang, Qi Zhang, Jianyong Zuo · 2026
Read A vision-based multi-camera fusion and CAD projection framework for risk-point identification in metro stations by Yichao Pu, Qianqi Fan, Shengyu Zhang, Qi Zhang, Jianyong Zuo (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13338194.txt.
Description
Five engineers built a camera system that spots risky crowding in metro stations, in a 2026 paper. Packed stations face sudden surges and blockages, and older crowd tools miss spots, react slowly, or fail when people hide each other from view. The team wanted station-wide, real-time risk sensing that operators can act on.
Their system merges feeds from many cameras into one shared map of the station. Station floor plans drawn in CAD software anchor the map, so risk points land in real places. A risk score blends crowd density with walking speed, catching stalls that density alone would miss. A baseline comparison separates daily crowding from fresh trouble. Trials at two Shanghai transfer hubs caught over ninety percent of risk points at real-time speed. The authors see pilot use in daily safety management.
Catalog record
| CREATOR | Yichao Pu, Qianqi Fan, Shengyu Zhang, Qi Zhang, Jianyong Zuo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 100 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |