3D from Line Segments in Two Poorly-Textured, Uncalibrated Images

This paper addresses the problem of camera selfcalibration, bundle adjustment and 3D reconstruction from line segments in two images of poorly-textured indoor scenes. First, we generate line segment correspondences, using an extended version of our previously proposed matching scheme. The first main contribution is a new method to identify polyhedral junctions resulting from the intersections of the line segments. At the same time, the images are segmented into planar polygons. This is done using an algorithm based on a Binary Space Partitioning (BSP) tree. The junctions are matched end points of the detected line segments and hence can be used to obtain the epipolar geometry. The essential matrix is considered for metric camera calibration. For better stability, the second main contribution consists in a bundle adjustment on the line segments and the camera parameters that reduces the number of unknowns by a maximum flow algorithm. Finally, a piecewise-planar 3D reconstruction is c...

• Type: Conference
• Year: 2006
• Where: 3DPVT
• Authors: Herbert Bay, Andreas Ess, Alexander Neubeck, Luc J. Van Gool
• Keywords: 3DPVT 2006, Applied Computing, Bundle Adjustment, Line Segment Correspondences, Line Segments