Learning to detect rooftops in aerial images

Marcus A. Maloof, Pat Langley, Stephanie Sage, and Thomas O. Binford

In this paper, we examine the use of machine learning to improve the robustness of systems for image analysis on the task of roof detection. We review the problem of analyzing aerial photographs, and describe an existing vision system that attempts to automate the identification of buildings in aerial images. After this, we briefly review several well-known learning algorithms that represent a wide variety of inductive biases. We report three experiments designed to illuminate facets of applying machine learning methods to the image analysis task; one experiment focuses on within-image learning, another deals with the cost of different errors, and a third addresses between-image learning. Experimental results demonstrate that machine-learned classifiers meet or exceed the accuracy of handcrafted solutions and that useful generalization occurs when training and testing on data derived from different images.

Paper available in PostScript (gzipped) and PDF.

  author = "Maloof, M.A. and Langley, P. and Sage, S. and Binford, T.O.",
  title = "Learning to detect rooftops in aerial images",
  booktitle = "{Proceedings of the Image Understanding Workshop}",
  pages = "835--845",
  address = "San Francisco, CA",
  publisher = "Morgan Kaufmann",
  year = 1997