This paper proposes a novel method for 2D-to-3D video conversion, based on boundary information to automatically\ngenerate the depth map. First, we use the Gaussian model to detect foreground objects and then separate the\nforeground and background. Second, we employ the superpixel algorithm to find the edge information. According to\nthe superpixels, we will assign corresponding hierarchical depth value to initial depth map. From the result of depth\nvalue assignment, we detect the edges by Sobel edge detection with two thresholds to strengthen edge information.\nTo identify the boundary pixels, we use a thinning algorithm to modify edge detection. Following these results, we\nassign the depth value of foreground to refine it. We use four kinds of scanning path for the entire image to create a\nmore accurate depth map. After that, we have the final depth map. Finally, we utilize depth image-based rendering\n(DIBR) to synthesize left and right view images. After combining the depth map and the original 2D video, a vivid 3D\nvideo is produced.
Loading....