CODING OF SUBREGIONS FOR CONTENT-BASED SCALABLE VIDEO

We propose a scheme for coding subregions in video scenes to provide c ontent-based scalable video. For each region, a special color is used to represent the nonobject area, and the resulting frames are coded us ing conventional video coding algorithms. At the decoder, the region s hape is recovered based on chroma keying, and hence, content-based man ipulations are made possible. A number of techniques that eliminate bo undary artifacts common to region-based coding are presented. In this scheme, no explicit shape coding is needed, and advantages of existing coding algorithms are retained. This scheme was submitted to ISO MPEG -4 and performed very well in the subjective tests.