Recognition of Human Activity in Metro Transit Spaces

In this report, we introduce a vision-based system to monitor for suspicious human activities at a bus stop. The system currently examines behavior for drug dealing activities which is characterized by individuals loitering around the bus stop for a very long time with no intention of using the bus. To accomplish this goal, the system must measure 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. EXECUTIVE SUMMARY In this report, we introduce a vision-based system to monitor for suspicious human activities at a bus stop. The system currently examines behavior for drug dealing activities which is characterized by individuals loitering around the bus stop for a very long time with no intention of using the bus. To accomplish this goal, the system must measure 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. We show that the system can successfully track individuals in sparsely-populated outdoor scenes with limited occlusion in near real time. We also show that individuals can be correctly distinguished from each other with an accuracy of about 80 percent. INTRODUCTION Overview The purpose of this work is to …