Recent advances in detection and description of buildings from multiple aerial images

  • Sanjay Noronha
  • Ram Nevatia
Session S1A: Recent Advances in Computer Vision
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1352)


A brief description of a method for detection and description of rectangular buildings from two or more registered aerial intensity images is provided. A new interactive editing module that can use partial results of the automated process to efficiently correct errors and derive complete descriptions is also described. The automated system operates by grouping features hierarchically to form roof hypotheses which are then verified by using wall and shadow evidence. Grouping and matching steps are interleaved and multiple descriptions are preserved when clear choices are not available. Some recent results are given.


Stereo Building Detection Multiple Images 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    A. Gruen and M. Baltsavias, Editors, “Automatic Extraction of Man-Made Objects from Aerial and Space Images”, Birkhauser Verlag, 1997.Google Scholar
  2. [2]
    S. Heuel, R. Nevatia, “Including Interaction in an Automated Modeling System”, Symposium on Computer Vision, Miami Beach, FL, November 1995(383–388)Google Scholar
  3. [3]
    M. Ito and A. Ishii, “Three-view stereo analysis”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 8:524–532, 1986.Google Scholar
  4. [4]
    C. Lin, and R. Nevatia, “3D Descriptions of Buildings from an Oblique View Aerial Image”, IEEE International Symposium of Computer Vision, 377–382, 1995.Google Scholar
  5. [5]
    S. Noronha and R. Nevatia, “Detection and Description of Buildings from Multiple Aerial Images”, IEEE Computer Vision and Pattern Recognition, pp. 588–594, San Juan, PR, June, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Sanjay Noronha
    • 1
  • Ram Nevatia
    • 1
  1. 1.Institute for Robotics and Intelligent SystemsUniversity of Southern CaliforniaLos Angeles

Personalised recommendations