Improving rooftop detection with interactive visual learning

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

In this paper, we report progress on the use of machine learning to improve the process of rooftop detection in aerial images. We describe an existing system for building recognition, Budds, and identify its rooftop stage as a target for improvement. We then review the naive Bayesian classifier, a simple but robust approach to supervised induction, and the visual interface we developed to ease the labeling of training data. We present the results of experiments on the rooftop detection task that reveal improved recognition levels over the handcr afted Budds classifier, then examine the reliability and speed of the interactive labeling process itself. Finally, we consider related research and plans for future work.

Paper available in PostScript (gzipped) and PDF.

Ali, K.M., Langley, P., Maloof, M.A., Sage, S., & Binford, T.O. (1998). Improving rooftop detection with interactive visual learning. Proceedings of the Image Understanding Workshop, 479–492. San Francisco, CA: Morgan Kaufmann.

@inproceedings{ali.iuw.98,
  author = "Ali, K.M. and Langley, P. and Maloof, M.A. and Sage, S.
    and Binford, T.O.",
  title = "Improving rooftop detection with interactive visual learning",
  booktitle = "{Proceedings of the Image Understanding Workshop}",
  pages = "479--492",
  address = "San Francisco, CA",
  publisher = "Morgan Kaufmann",
  year = 1998
}