Automatic Stitching System for Images of Plane-Like Scenes

Abstract

Traditional panoramic image stitching, which refers to single-viewpoint cylindrical or spherical panorama generation, has two crucial limitations when it is used for planelike scenes. One is the severe distortion induced by warping, and the other is that the optical center of camera must be fixed. However, existing stitching methods designed for plane-like scenes also have some drawbacks, such as ghosting and limited adaptability. In this paper, an Automatic Stitching System for Images of Plane-like Scenes (AS-SIPS) is proposed to overcome the limitations and drawbacks. In ASSIPS, input images are taken with a handheld camera which is translated along the scene. Images are firstly used to estimate their camera poses and calculate the sparse structure of the scene. Then a dominant plane is found out and all the input images are warped according to the plane. Finally, warped images are aligned incrementally with similarity model and a simplified multiband blending algorithm is used in the process of image blending. Results of ASSIPS for various plane-like scenes prove that it can provide visually attractive panoramic images which look like taken with the direction perpendicular to the scene, and effectively eliminate stitching seams, blurs and ghosts.