Recognition of Human Activity in Metro Transit Spaces

Project summary:

Monitoring large public spaces with sensors is a challenging task with a variety of important applications. A camera system monitoring public spaces (such as airports, bridges, work zones, truck weigh stations, tunnels, buses, planes, or trains) can be developed to detect all humans occupying those spaces and collect information about their activities. The type of system developed in this research is not limited to human detection, but rather can be extended to the detection of incidents that involve vehicles. Furthermore, certain types of incidents can be detected and alerts can be issued to human operators. The specific implementation developed in this project comprises a vision-based system to monitor for suspicious human activities at a bus stop. The system currently examines behavior for drug dealing activities, characterized by individuals loitering around the bus stop for a very long time without using the bus. To accomplish this goal, the system measures how long individuals loiter around the bus stop. To facilitate this, the system must track individuals from the video feed, identify them, and keep a record of how long they spend at the bus stop. The system is broken into three distinct portions: background subtraction, object tracking, and human recognition. The background subtraction and object tracking modules use off-the-shelf algorithms and are shown to work well following people as they walk around a bus stop. The human recognition module segments the image of an individual into three portions corresponding to the head, torso, and legs. Using the median color of each of these regions, two people can be quickly compared to see if they are the same person.