AN ANALISYS OF 3D SCENE RECONSTRUCTION PROCESS USING STEREO VISION

Abstract

Accurate 3D perception from image pair is a core subject in computer vision and robotics. This paper contains analysis of epipolar geometry of the stereo system and an analytical description of tools to compute a 3D point cloud from matched pixels. Stereo camera parameters from the camera calibration process and disparity map are two important parameters to obtain an accurate result for the 3D reconstruction. 3D reconstruction process generates the coordinates of world points (point cloud).