Segmentation of moving objects from cluttered background scenes using a running average model

This paper describes a system for the detection of people moving in a video scene. The system is ultimately intended to allow tracking of the major parts of the human body. Objects are detected utilizing a background subtraction method which is based on the movements of objects within the scene. The background removal algorithm is designed in a way that allows the background to be constantly up-dated automatically, allowing it to be used over a long period of time. Several methods for improving the outcome from the background removal algorithm are used which include addressing problems caused by variable shading. Mathematical morphology techniques are subsequently employed in order to improve the segmentation achieved in each frame.