Tracking areas of interest for content-based functionalities in segmentation-based video coding

This paper presents a technique for tracking areas of interest in the framework of segmentation-based video coding. The technique is independent of the type of segmentation technique used in the coding approach. Therefore, it can also be used in block-based coding schemes. The algorithm relies on a double segmentation of the image based on morphological tools. This double segmentation permits to obtain the position and shape of the previous area of interest in the current image. In order to demonstrate the potentialities of this algorithm, it is applied in a specific coding scheme so that content-based selective coding is allowed