Advertisement

A method for the 3D reconstruction of indoor scenes from monocular images

  • Paolo Olivieri
  • Maurizio Gatti
  • Marco Straforini
  • Vincent Torre
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)

Abstract

The recovery of the 3D structure of indoor scenes from a single image is an important goal of machine vision Therefore, a simple and reliable solution to this problem will have a great influence on many tasks in robotics, such as the autonomous navigation of a mobile vehicle in indoor environments.

This communication describes the recovery, in a reliable and robust way, of the 3D structure of a corridor and of obstacles from a sequence of images obtained by a T.V. camera moving through the corridor. The obtained 3D information can be used to extract the free space in the viewed scene in order to plan the trajectory of a mobile vehicle. This application is being worked on at the moment and the results will be illustrated in a future communication.

Keywords

Simple Polygon Perspective Projection Autonomous Navigation Mobile Vehicle Polygonal Approximation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. [B2]
    Barrow, H.G, Tenenbaum, J.M.: Interpreting line-drawings as three-dimensional surfaces. Artif. Intell. 17 (1981) 75–116Google Scholar
  2. [C1]
    Coelho C., Straforini M., Campani M.: A fast and precise method to extract vanishing points, SPIE's International Symposia on Applications in Optical Science and Engineering, Boston 1990.Google Scholar
  3. [H1]
    Haralick, R.M.: Using perspective transformation in scene analysis. Comput. Graphics Image Process 13 (1980) 191–221Google Scholar
  4. [S1]
    Straforini, M., Coelho, C., Campani, M., Torre V.: The recovery and understanding of a line drawing from indoor scenes. PAMI in the press (1991)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Paolo Olivieri
    • 1
  • Maurizio Gatti
    • 1
  • Marco Straforini
    • 2
  • Vincent Torre
    • 2
  1. 1.Dipartimento di Informatica e Scienza dell'InformazioneUniversità di GenovaItaly
  2. 2.Dipartimento di FisicaUniversità di GenovaItaly

Personalised recommendations