Reconstruction of 3-D affine and euclidean mesh models from video

3-D mesh modeling offers several advantages over 2-D mesh modeling for object-based video manipulation including digital postprocessing and editing. This paper proposes a new method for automatic reconstruction of 3-D affine and Euclidean mesh representations of objects from video sequences. Our approach is to first design a 2-D mesh by selecting node points from a set of salient (corner) points followed by constrained Delaunay triangulation. Next, an improved 2-D mesh tracking scheme is proposed that estimates motion vectors at the node points by global motion estimation followed by a local refinement scheme. A 3-D mesh is then reconstructed by estimating the depth at these node points in an affine space using computer vision techniques. A Euclidean reconstruction is also computed by imposing additional constraints. Experimental results are provided to demonstrate the accuracy of the reconstructions.