Machine Learning

, Volume 53, Issue 1, pp 157–191

Improved Rooftop Detection in Aerial Images with Machine Learning

  • M.A. Maloof
  • P. Langley
  • T.O. Binford
  • R. Nevatia
  • S. Sage
Article

DOI: 10.1023/A:1025623527461

Cite this article as:
Maloof, M., Langley, P., Binford, T. et al. Machine Learning (2003) 53: 157. doi:10.1023/A:1025623527461

Abstract

In this paper, we examine the use of machine learning to improve a rooftop detection process, one step in a vision system that recognizes buildings in overhead imagery. We review the problem of analyzing aerial images and describe an existing system that detects buildings in such images. We briefly review four algorithms that we selected to improve rooftop detection. The data sets were highly skewed and the cost of mistakes differed between the classes, so we used ROC analysis to evaluate the methods under varying error costs. We report three experiments designed to illuminate facets of applying machine learning to the image analysis task. One investigated learning with all available images to determine the best performing method. Another focused on within-image learning, in which we derived training and testing data from the same image. A final experiment addressed between-image learning, in which training and testing sets came from different images. Results suggest that useful generalization occurred when training and testing on data derived from images differing in location and in aspect. They demonstrate that under most conditions, naive Bayes exceeded the accuracy of other methods and a handcrafted classifier, the solution currently used in the building detection system.

supervised learning learning for computer vision evaluation of algorithms applications of learning 
Download to read the full article text

Copyright information

© Kluwer Academic Publishers 2003

Authors and Affiliations

  • M.A. Maloof
    • 1
  • P. Langley
    • 2
  • T.O. Binford
    • 3
  • R. Nevatia
    • 4
  • S. Sage
    • 2
  1. 1.Department of Computer ScienceGeorgetown UniversityWashingtonUSA
  2. 2.Institute for the Study of Learning and ExpertisePalo AltoUSA
  3. 3.Robotics Laboratory, Department of Computer ScienceStanford UniversityStanfordUSA
  4. 4.Institute for Robotics and Intelligent Systems, School of EngineeringUniversity of Southern CaliforniaLos AngelesUSA

Personalised recommendations