Performance of Interest Point Descriptors on Hyperspectral Images

Przemysław Głomb, Michał Cholewa

Abstract

Interest point descriptors (e.g. Scale Invariant Feature Transform, SIFT or Speeded-Up Robust Features, SURF) are often used both for classic image processing tasks (e.g. mosaic generation) or higher level machine learning tasks (e.g. segmentation or classification). Hyperspectral images are recently gaining popularity as a potent data source for scene analysis, material identification, anomaly detection or process state estimation. The structure of hyperspectral images is much more complex than traditional color or monochrome images, as they comprise of a large number of bands, each corresponding to a narrow range of frequencies. Because of varying image properties across bands, the application of interest point descriptors to them is not straightforward. To the best of our knowledge, there has been, to date, no study of performance of interest point descriptors on hyperspectral images that simultaneously integrate a number of methods and use a dataset with significant geometric transformations. Here, we study four popular methods (SIFT, SURF, BRISK, ORB) applied to complex scene recorded from several viewpoints. We presents experimental results by observing how well the methods estimate the 3D cameras’ positions, which we propose as a general performance measure.

References

  1. Bay, H., Ess, A., Tuytelaars, T., and Gool, L. V. (2008). Speeded-up robust features (SURF). Computer Vision and Image Understanding, 110(3):346 - 359. Similarity Matching in Computer Vision and Multimedia.
  2. Bradski, G. (2000). The OpenCV Library. Dr. Dobb's Journal of Software Tools.
  3. Brown, M. and Susstrunk, S. (2011). Multi-spectral SIFT for scene category recognition. In 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 177-184.
  4. Dorado-Munoz, L., Velez-Reyes, M., Mukherjee, A., and Roysam, B. (2012). A vector SIFT detector for interest point detection in hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 50(11):4521-4533.
  5. Leutenegger, S., Chli, M., and Siegwart, R. Y. (2011). BRISK: Binary robust invariant scalable keypoints. In Proceedings of the International Conference on Computer Vision (ICCV).
  6. Lowe, D. (2004). Distinctive image features from scaleinvariant keypoints. International Journal of Computer Vision, 60(2):91-110.
  7. Mikolajczyk, K. and Schmid, C. (2005). A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(10):1615-1630.
  8. Moreels, P. and Perona, P. (2007). Evaluation of features detectors and descriptors based on 3d objects. International Journal of Computer Vision, 73(3):263-284.
  9. Mukherjee, A., Velez-Reyes, M., and Roysam, B. (2009). Interest points for hyperspectral image data. IEEE Transactions on Geoscience and Remote Sensing, 47(3):748-760.
  10. Ringaby, E., Ahlberg, J., Wadströmer, N., and Forssén, P.-E. (2010). Co-aligning aerial hyperspectral push-broom strips for change detection. In Proc. SPIE, volume 7835, pages 78350Y-78350Y-7.
  11. Rublee, E., Rabaud, V., Konolige, K., and Bradski, G. (2011). ORB: an efficient alternative to SIFT or SURF. In Proceedings of the International Conference on Computer Vision (ICCV).
  12. Sima, A. A. and Buckley, S. J. (2013). Optimizing SIFT for matching of short wave infrared and visible wavelength images. Remote Sensing, 5(5):2037-2056.
  13. Vakalopoulou, M. and Karantzalos, K. (2014). Automatic descriptor-based co-registration of frame hyperspectral data. Remote Sensing, 6(4):3409-3426.
  14. Wu, C. (2011). VisualSFM: A visual structure from motion system. http://ccwu.me/vsfm/.
  15. Wu, C., Agarwal, S., Curless, B., and Seitz, S. (2011). Multicore bundle adjustment. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 3057-3064.
  16. Xu, Y., Hu, K., Tian, Y., and Peng, F. (2008). Classification of hyperspectral imagery using SIFT for spectral matching. In 2008 Congress on Image and Signal Processing, CISP 7808., volume 2, pages 704-708.
Download


Paper Citation


in Harvard Style

Głomb P. and Cholewa M. (2016). Performance of Interest Point Descriptors on Hyperspectral Images . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 198-203. DOI: 10.5220/0005785001980203


in Bibtex Style

@conference{visapp16,
author={Przemysław Głomb and Michał Cholewa},
title={Performance of Interest Point Descriptors on Hyperspectral Images},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={198-203},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005785001980203},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)
TI - Performance of Interest Point Descriptors on Hyperspectral Images
SN - 978-989-758-175-5
AU - Głomb P.
AU - Cholewa M.
PY - 2016
SP - 198
EP - 203
DO - 10.5220/0005785001980203