Method for detecting motion vectors for use in a segmentation-based coding system

A method, for use in a segmentation-based coding system, for detecting motion vectors between a current frame and a previous frame of a digital video signal, wherein the current frame includes a plurality of segmented regions and the previous frame includes a multiplicity of candidate regions, which comprises the steps of:

• (a) generating segmentation data for each of the segmented regions, the segmentation data including contour information representing the shape and location for each segmented region and texture information representing a mean gray level of all pixels contained in each segmented region;
• (b) generating candidate segmentation data for each of the candidate regions, the candidate segmentation data including contour information representing the shape and location for each candidate region and texture information representing a mean gray level of all pixels contained in each candidate region;
• (c) producing a minimum-sized predetermined geometric pattern for enveloping a segmented region to thereby generate size information thereof;
• (d) producing a minimum-sized predetermined geometric pattern for enveloping each of the candidate regions to thereby generate size information thereof;
• (e) calculating an error value between the segmented region and each of the candidate regions based on the segmentation data and the size information for the segmented region and each of the candidate regions, thereby providing a set of error values for the segmented region;
• (f) selecting a candidate region yielding a smallest error value in the set of error values as a search region having a closest similarity to the segmented region;
• (g) detecting one or more motion vectors between the segmented region and the search region;
• and
• (h) repeating said steps (c) to (g) for all the segmented regions.