Detecting and Identifying Moving Objects in Real-Time

For surveillance applications or for human-computer interaction, the automated real-time tracking of moving objects in images from a stationary camera can be very useful. In this chapter we describe a novel method for object tracking which works in real-time using standard hardware. The object tracking algorithm uses an improved adaptive version of an existing robust motion detection method and a set of decision-rules is used to handle difficult situations such as tracking multiple objects at the same time, crossing paths and partial occlusion. Experiments on several real complex test sets were performed and discussed.