This paper deals with the use of the segmentation tools and principles presented in [10] and [13] for allowing content-based functionalities. In this framework, means for supervised selection of objects in the scene are proposed. In addition, a technique for object tracking in the context of segmentation-based video coding is presented. The technique is independent of the type of segmentation approach used in the coding scheme. The algorithm relies on a double partition of the image that yields spatially homogeneous regions. This double partition permits to obtain the position and shape of the previous object in the current image while computing the projected partition. In order to demonstrate the potentialities of this algorithm, it is applied in a specific coding scheme so that content-based functionalities, such as selective coding, are allowed.

Peer Reviewed