Abstract
This paper describes a tracking system for multiple moving objects undergoing a planar motion in a scene observed by a still camera. The objects are tracked through a sequence of frames. The direction and velocity of each object are calculated between each pair of frames and are used to predict the position of the object in the next frame. The calibration procedure and the problems due to the presence of noise and shadows in the images are also addressed and the adopted strategies are detailed. Our system has successfully been tested on a fish tracking application and is currently used to study the behavior of the fish in response to changes in environmental conditions.