In the field of the multimedia applications, future standards asMPEG4 or MPEG7 allow new image content representation that goes farfrom the basic comres- sion. This way, the objects of interest becomeentities that the user can manipulate. Nevertheless, the norm doesnot specify how objects have to be segmented, even if in some casesthis a complex task. In the fra- mework of the European projectM4M(MPEG fo(u)r Mobiles, Medea project A116), we have in charge theDevelopment of a demonstrator able to segment and Track a speaker invideophone and videoconference Applications.
展开▼