ABSTRACT
The background modeling process is basically characterized by three fundamental tasks which are the followings: 1) model representation, that describes the kind of model used to represent the background; 2) model initialization, that regards the initialization of this model; and 3) model adaptation, that concerns the mechanism used for adapting the model to the background changes. In the last two decades, several methods have been proposed in order to address these tasks, as witnessed by several surveys [10, 18, 36, 40, 41] and by many other Chapters in this Book. Most of these methods focus on the representation and the adaption issues, whereas limited attention is given to the model initialization. In the following, we will focus our attention on existing approaches that specifically address background model initialization, referring the interested reader to the above mentioned literature for other background modeling issues.
