Adaptive planar and rotational image stitching for mobile devices
Christopher Herbon, Klaus D. Tönnies, Bernd Stock · 2014
A novel stitching method is presented that is capable of automatically determining the panorama type, planar or rotational, form a set of input images. The proposed method distinguishes between two kinds of panoramas, which we achieve through homography parametrization for the estimation of a global camera motion. The presented algorithm is part of a complete image stitching pipeline, where the determined panorama type is utilized for adaptive bundle adjustment with a matching number of degrees of freedom (DOFs). For planar scenes bundle adjustment for the homography's full eight DOFs are used, while three DOFs have proven to be sufficient for rotational panoramas.