Semiautomatic 3-d Model Extraction from Uncalibrated 2-d Camera Views

Scenes that contain every-day man-made objects often possess sets of parallel lines and orthogonal planes, the projective features of which possess enough structural information to constrain possible scene element geometries as well as a camera's intrinsic and extrinsic parameters. In particular, in a scene with three mutually orthogonal sets of parallel lines, detection of the corresponding three vanishing points of the imaged lines allows us to determine the camera's image-relative principal point and e ective focal length. In this paper we introduce a new technique to solve for radial and decentering lens distortion directly from the results of vanishing point estimation, thus precluding the need for special calibration templates. This is accomplished by using an iterative method to solve for the parameters that minimize vanishing point dispersion. Dispersion here is measured as covariance of vanishing point estimation error projected on the Gaussian sphere whose origin is the estimated center of projection. Having found a complete model for each camera's intrinsic parameters, corresponding points are used in the relative orientation technique to determine the camera's extrinsic parameters as well as point-wise structure. Surfaces inherit planar geometry and extent from manually identi ed coplanar lines and points. View independent textures are created for each surface by nding the 2-D homographic texture transformation which corrects for planar perspective foreshortening. We utilize the local Jacobian of this transformation in two important ways: to prevent aliasing in the plane's texture space and to merge correctly texture data arising from varying sampling resolutions in multiple views.