RECONSTRUCTION OF 3D POINT

Abstract

Retrieving 3D information from 2D images taken from different viewpoints has always been an area of great interest for the computer vision community. In this dissertation, I present a robust 3D reconstruction algorithm using Direct Linear Transformation (DLT) Method and using Triangulation Method. To extract precise 3D information from imagery, a calibration procedure must be performed. In DLT Method, two images are taken from two cameras but the available information of the cameras is not taken into account. A few control points on each image are taken and then calibration is done for both the cameras. Then the 3D points, present in both the images, are reconstructed using this calibration results. Then the calibration error from calibration results and reconstruction error from the original and reconstructed points is computed. Finally, the accuracy of DLT Method is discussed. Using Triangulation Method, a 3D point is reconstructed, if the position of this 3D point is taken in t...