MODEL-BASED TRACKING OF MOVING OBJECT

This paper describes a real-time tracking system which detects an obje ct entering the field of view of a camera and executes tracking of the detected object by controlling a servo device in such a way that a ta rget always lies at the center of an image frame. In order to detect a nd track a moving object, we basically apply model matching strategy. We allow the model of a target to vary dynamically during the tracking process so that it can assimilate variations of shape and intensities of a target. We also utilize a Kalman filter to encode a tracking his tory into state parameters of the filter. The estimated state paramete rs will then be used to reduce search areas for model matching and to control a servo device. Experimental results show that model adaptatio n allows robust tracking of a target object in dynamic environments. T hese experiments also confirm that the predicted values of a Kalman fi lter are very accurate in controlling a servo device and finding out t he search areas for model matching. This paper concludes with theoreti cal bounds within which a tracking system can follow the movement of a target object. (C) 1997 Pattern Recognition Society.