VIDEO SEGMENTATION BASED ON MULTIPLE FEATURES FOR INTERACTIVE MULTIMEDIA APPLICATIONS

In this paper, we present a scheme for interactive video segmentation. A key feature of the system is the distinction between two levels of segmentation, namely, regions and object segmentation. Regions are hom ogeneous areas of the images, which are extracted automatically by the computer. Semantically meaningful objects are obtained through user i nteraction by grouping of regions according to the specific applicatio n. This splitting relieves the computer of ill-posed semantic problems , and allows a higher level of flexibility of the method, The extracti on of regions is based on the multidimensional analysis of several ima ge features by a spatially constrained fuzzy C-means algorithm. The lo cal level of reliability of the different features is taken into accou nt in order to adaptively weight the contribution of each feature to t he segmentation process. Results on the extraction of regions as well as on the tracking of spatiotemporal objects are presented.