Multiple stereo vision for 3D object reconstruction

Abstract

A vision system for 3D information extraction and surface reconstruction of objects in a robot workspace is described. The system consists of <e1 xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</e1> cameras arranged in an <e1 xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</e1> /2 periodic stereo pair structure. The surface reconstruction is performed in two stages. The 3D data from different perspectives are inferred independently using a periodic stereo structure, and then the extracted information from neighboring camera pairs is used to reconstruct the surface of the object