CONTENT BASED MESH GENERATION ALGORITHM

It is critical to choose a suitable model for accurate motion estimation, efficiently encoding image signal, and high quality decoding image in model based coding. A content based adaptive mesh generation algorithm is proposed in this paper. At first, a watershed algorithm of mathematical morphology is used to segment image into many homogeneous regions so that watershed lines can better represent image structure, contours, and edges. Boundaries of these regions are approximated by polygons that can be represented with a few parameters. Each end point of polygonal sides serves as candidate node of mesh model. Because interval between candidate nodes may be too large or small, some mesh elements based on these nodes are unsuitable for later tracking and motion estimation in quality and size. Some preprocessing are adopted to delete or insert some candidate nodes. A content based Delaunay triangular mesh can be generated on these nodes with limitation in nodal interval. The results of this algorithm can more efficiently represent encoding image structure, so accurate motion estimation and efficiently encoding can better achieve in model based coding.