People Tracking System Using DeepSORT

The rapid development of image detection algorithm has led to its widespread application in security, such as facial recognition and crowd surveillance. However, real-time tracking is very challenging, especially in crowded places where the person might be in part or entirely occluded for some period. Hence, this paper objective is to create a people tracking system in crowd surveillance, using Deep SORT framework. Unlike object detection frameworks like CNN, this system does not just detect a person in real-time but on top of that, uses the information it has learned to track the trajectory of the person until they exit the frame of the camera. The system will use You Only Look Once (YOLO) for the person detection, and then use Deep SORT to process the detected person frame by frame to predict its movement path. The system was able to successfully detect and track the person movement path with average 2.59 frames per second (FPS).