University of Minnesota Driven to Discover
U of MNUniversity of Minnesota
Center for Transportation Studies

Keeping an (electronic) eye on bus stops

A new research report by University of Minnesota professor Nikolaos Papanikolopoulos describes an experimental system that employs sophisticated computer algorithms to carry out the tedious task of monitoring security cameras. The research was originally covered in the April 2004 Research E-News and the Spring 2004 ITS Institute Sensor newsletter.

Along with increasing mobility, ensuring the security of transportation systems has become a key application of intelligent transportation systems technologies. Papanikolopoulos’ system focuses on a specific type of suspicious activity—persons loitering around bus stops for extended periods without boarding a bus—which is frequently associated with drug dealing. The project was carried out in collaboration with Metro Transit, the Twin Cities’ public transportation agency.

Unlike a human worker, the computer never gets tired of looking at video from security cameras, and can potentially monitor numerous cameras simultaneously. If suspicious activity is detected, the system can alert a human operator, who then checks the video and determines whether further investigation is warranted. Although the system is able to distinguish between several individuals in a scene, it does not employ any face-recognition or other identification technology.

The research report, titled Recognition of Human Activity in Metro Transit Spaces, is available online.