ESTIMATING PLANAR STRUCTURE IN SINGLE IMAGES BY LEARNING FROM EXAMPLES

Osian Haines, Andrew Calway

Abstract

Outdoor urban scenes typically contain many planar surfaces, which are useful for tasks such as scene reconstruction, object recognition, and navigation, especially when only a single image is available. In such situations the lack of 3D information makes finding planes difficult; but motivated by how humans use their prior knowledge to interpret new scenes with ease, we develop a method which learns from a set of training examples, in order to identify planar image regions and estimate their orientation. Because it does not rely explicitly on rectangular structures or the assumption of a ‘Manhattan world’, our method can generalise to a variety of outdoor environments. From only one image, our method reliably distinguishes planes from non-planes, and estimates their orientation accurately; this is fast and efficient, with application to a real-time system in mind.

References

  1. Bartoli, A. (2007). A random sampling strategy for piecewise planar scene segmentation. Computer Vision and Image Understanding, 105(1).
  2. Birchfield, S. and Rangarajan, S. (2005). Spatiograms versus histograms for region-based tracking. In Computer Vision and Pattern Recognitionn, volume 2.
  3. Choi, S. (2008). Algorithms for orthogonal nonnegative matrix factorization. In International Joint Conference on Neural Networks. IEEE.
  4. Deerwester, S., Dumais, S., Furnas, G., Landauer, T., and Harshman, R. (1990). Indexing by latent semantic analysis. Journal of the American society for Information Science, 41(6).
  5. Fergus, R., Perona, P., and Zisserman, A. (2005). A sparse object category model for efficient learning and exhaustive recognition. In Computer Vision and Pattern Recognition, volume 1.
  6. Gee, A., Chekhlov, D., Calway, C., and Mayol-Cuevas, W. (2008). Discovering higher level structure in visual slam. Transactions on Robotics, 24.
  7. Haines, O. and Calway, A. (2011). Estimating planar structure in single images by learning from examples. Technical Report CSTR-11-005, University of Bristol.
  8. Hoiem, D., Efros, A., and Hebert, M. (2007). Recovering surface layout from an image. International Journal of Computer Vision, 75(1).
  9. Kos?ecká, J. and Zhang, W. (2005). Extraction, matching, and pose recovery based on dominant rectangular structures. Computer Vision and Image Understanding, 100(3).
  10. Lowe, D. (2004). Distinctive image features from scaleinvariant keypoints. International Journal of Computer Vision.
  11. Martínez-Carranza, J. and Calway, A. (2010). Unifying planar and point mapping in monocular slam. In British Machine Vision Conference.
  12. Michels, J., Saxena, A., and Ng, A. (2005). High speed obstacle avoidance using monocular vision and reinforcement learning. In International Conference on Machine learning.
  13. Mic?us?ík, B., Wildenauer, H., and Kos?ecká, J. (2008). Detection and matching of rectilinear structures. In Computer Vision and Pattern Recognition.
  14. O Conaire, C., O'Connor, N. E., and Smeaton, A. F. (2007). An improved spatiogram similarity measure for robust object localisation. In International Conference on Acoustics, Speech and Signal Processing, volume 1.
  15. Rosten, E. and Drummond, T. (2006). Machine learning for high-speed corner detection. Lecture Notes in Computer Science, 3951.
  16. Saxena, A., Sun, M., and Ng, A. (2008). Make3d: learning 3d scene structure from a single still image. Transactions on Pattern Analysis and Machine Intelligence.
Download


Paper Citation


in Harvard Style

Haines O. and Calway A. (2012). ESTIMATING PLANAR STRUCTURE IN SINGLE IMAGES BY LEARNING FROM EXAMPLES . In Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM, ISBN 978-989-8425-99-7, pages 289-294. DOI: 10.5220/0003708902890294


in Bibtex Style

@conference{icpram12,
author={Osian Haines and Andrew Calway},
title={ESTIMATING PLANAR STRUCTURE IN SINGLE IMAGES BY LEARNING FROM EXAMPLES},
booktitle={Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,},
year={2012},
pages={289-294},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003708902890294},
isbn={978-989-8425-99-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,
TI - ESTIMATING PLANAR STRUCTURE IN SINGLE IMAGES BY LEARNING FROM EXAMPLES
SN - 978-989-8425-99-7
AU - Haines O.
AU - Calway A.
PY - 2012
SP - 289
EP - 294
DO - 10.5220/0003708902890294