OBJECT-ORIENTED IMAGE-ANALYSIS FOR VERY-LOW-BITRATE VIDEO-CODING SYSTEMS USING THE CNN UNIVERSAL MACHINE

The CNN universal machine (CNNUM) is applied to object-oriented video compression and proves its universality for future applications in the held of very-low-bitrate coding. This proposal joins recent work of V enetianer and Roska in unfolding the enormous computational abilities of the CNNUM for a wide class of video compression techniques. Here a novel image analysis technique is considered and realized in the form of analogic CNN algorithms. The specific features of the scheme, among them the extensive use of dynamic (finite running time) CNN cloning t emplates, are outlined and discussed through different computer simula tions. When implemented on the CNNUM, its performances outdo those of equivalent digital systems and qualify the CNNUM as a serious competit or for future video coding hardware. (C) 1997 by John Wiley & Sons, Lt d.