Feature Points Selection for Rectangle Panorama Stitching

Weiqing Yan, Shuigen Wang, Guanghui Yue, Jindong Xu, Xiangrong Tong, Laihua Wang

Abstract: Panoramic images can provide users with large view scene, which is widely used in various fields. Image stitching can combine images of adjacent views with small horizon field into a single image with large horizon. Currently stitching method can provide a rectangle panorama by cropped method to view or print. However, this method can occur shape distortion, and information loss. In this paper, we propose a novel feature points selection method to generate rectangle panorama image. First, to avoid local distortion in overlapping region, matched feature points are selected by feature cluster analysis. And then, depending on selected feature points, we establish mesh warping method to produce rectangle mesh. At last, bilinear interpolation algorithm is used to obtain the rectangle panorama image. Experimental results show that the proposed method can effectively stitch different view image to generate rectangle panorama without shape distortion.