未标定单幅结构场景图像的三维重构

3D Reconstruction of Structured Scene from One Uncalibrated Image

提出了一种单视三维重构方法 ,该方法是利用用户提供图像点及其对应的三维点之间几何信息。由于结构场景是由大量平面构成的 ,存在大量的平行性、正交性约束 ,因此该方法主要应用于结构场景的三维重构。首先 ,相机定标和计算每个平面的度量信息 ,即先基于 3组互相垂直方向的影灭点 ,对方形像素相机标定 ,再利用影灭线和圆环点像 ,对每个平面度量校正 ;然后考虑每个校正平面的尺度因子和非正交平面间的相对面向 ,从而将所有校正后的平面缝合起来。采用真实图像进行实验 ,实验结果表明 。

In this paper, a method for performing single view 3D reconstruction is present, in which the user provides image points and geometric information about the corresponding 3D points. The main application is to structured scene, mostly planar structures where there are plentiful constraints to be had from parallelism and orthogonality. There are two components to the reconstruction process. First, the camera calibration and metric structure of each plane is computed, that is to calibrate a square pixel camera from three vanishing points of orthogonal directions and metric rectify each plane by computing the imaged circular points and the vanishing line. The second stage involves stitching the individually rectified planes together, accounting for the arbitrary scale factors in the rectification of each plane and the relative orientation of planes not known to be orthogonal. Real image have been used to test the proposed method, and good results have been obtained and have demonstrated the proposed method is easy to use.