Segmentation of a Piece-Wise Planar Scene from Perspective Images

We study and compare two novel embedding methods for segmenting feature points of piece-wise planar structures from two (uncalibrated) perspective images. We show that a set of different homographies can be embedded in different ways to a higher-dimensional real or complex space, so that each homography corresponds to either a complex bilinear form or a real quadratic form. Each embedding reveals different algebraic properties and relations of homographies. We give a closed-form segmentation solution for each case by utilizing these properties based on subspacesegmentation methods. These theoretical results show that one can intrinsically segment a piece-wise planar scene from 2-D images without explicitly performing any 3-D reconstruction. The resulting segmentation may make subsequent 3-D reconstruction much better-conditioned. We demonstrate the proposed methods with some convincing experimental results.

• Type: Conference
• Year: 2005
• Where: CVPR
• Authors: Allen Y. Yang, Shankar Rao, Andrew Wagner, Yi Ma
• Keywords: Complex Bilinear Form, Computer Vision, CVPR 2005, Piece-wise Planar Scene, Piece-wise Planar Structures, Real Quadratic Form, Subsequent 3-d Reconstruction