Regional Linear Warping for Image Stitching with Dominant Edge Extraction

Image stitching techniques produce an image with wide field-of-view by aligning multiple images with narrow field-of-view. While conventional algorithms successfully stitch images with small parallax, structure misalignment may occur when input images contain large parallax. This paper presents an image stitching algorithm which aligns images with large parallax by regional linear warping. To this end, input images are first approximated as multiple planar surfaces, and different linear warping is applied to each planar surface. For the approximation of input images as multiple planar surfaces, a concept of dominant edges is introduced. Dominant edges are defined as conspicuous edges of lines in input images, and extracted dominant edges identify boundaries of each planar surface. Dominant edge extraction is conducted by detecting distinct change of local characteristics around strong edge pixels. Experimental results show that the proposed algorithm successfully stitches images with large parallax without structure misalignment.