Robust Features for Snapshot Hyperspectral Terrain-Classification

  • Christian WinkensEmail author
  • Volkmar Kobelt
  • Dietrich Paulus
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10424)


Hyperspectral imaging increases the amount of information incorporated per pixel in comparison to normal RGB color cameras. Conventional spectral cameras as used in satellite imaging use spatial or spectral scanning during acquisition which is only suitable for static scenes. In dynamic scenarios, such as in autonomous driving applications, the acquisition of the entire hyperspectral cube at the same time is mandatory. We investigate the eligibility of novel snapshot hyperspectral cameras which capture an entire hyperspectral cube without requiring moving parts or line-scanning. Captured hyperspectral data is used for multi class terrain classification utilizing machine learning techniques. Prior to classification, the data is segmented using Superpixel segmentation which is modified to work successfully on hyperspectral data. We further investigate a simple approach to normalize the hyperspectral data in terms of illumination, which yields vast improvements in classification accuracy, preventing most errors caused by shading and other influences. Furthermore we utilize Gabor texture features which add spatial information to the feature space without increasing the data dimensionality in an excessive fashion. The multi-class classification is evaluated against a novel hyperspectral ground truth dataset specifically created for this purpose.


Hyperspectral imaging Terrain classification Spectral analysis Autonomous vehicles 


  1. 1.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)CrossRefGoogle Scholar
  2. 2.
    Bradley, D.M., Unnikrishnan, R., Bagnell, J.: Vegetation detection for driving in complex environments. In: 2007 IEEE International Conference on Robotics and Automation, pp. 503–508. IEEE (2007)Google Scholar
  3. 3.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  4. 4.
    Brown, M., Süsstrunk, S.: Multi-spectral sift for scene category recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 177–184. IEEE (2011)Google Scholar
  5. 5.
    Camps-Valls, G., Bruzzone, L.: Kernel-based methods for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 43(6), 1351–1362 (2005)CrossRefGoogle Scholar
  6. 6.
    Camps-Valls, G., Gomez-Chova, L., Muñoz-Marí, J., Vila-Francés, J., Calpe-Maravilla, J.: Composite kernels for hyperspectral image classification. IEEE Geosci. Remote Sens. Lett. 3(1), 93–97 (2006)CrossRefGoogle Scholar
  7. 7.
    Camps-Valls, G., Tuia, D., Gómez-Chova, L., Jiménez, S., Malo, J.: Remote sensing image processing. Synth. Lect. Image Video Multimedia Process. 5(1), 1–192 (2011)CrossRefzbMATHGoogle Scholar
  8. 8.
    Cavigelli, L., Bernath, D., Magno, M., Benini, L.: Computationally efficient target classification in multispectral image data with deep neural networks. In: SPIE Security+Defence. p. 99970L. International Society for Optics and Photonics (2016)Google Scholar
  9. 9.
    Chetan, J., Krishna, M., Jawahar, C.: Fast and spatially-smooth terrain classification using monocular camera. In: Pattern Recognition (ICPR), 2010 20th International Conference on. pp. 4060–4063. IEEE (2010)Google Scholar
  10. 10.
    Fauvel, M., Benediktsson, J.A., Chanussot, J., Sveinsson, J.R.: Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles. IEEE Trans. Geosci. Remote Sens. 46(11), 3804–3814 (2008)CrossRefGoogle Scholar
  11. 11.
    Finlayson, G.D., Hordley, S.D., Lu, C., Drew, M.S.: On the removal of shadows from images. IEEE Trans. Pattern Anal. Mach. Intell. 28(1), 59–68 (2006)CrossRefGoogle Scholar
  12. 12.
    Geelen, B., Tack, N., Lambrechts, A.: A compact snapshot multispectral imager with a monolithically integrated per-pixel filter mosaic. In: SPIE Moems-Mems. p. 89740L. International Society for Optics and Photonics (2014)Google Scholar
  13. 13.
    Gevers, T., Stokman, H., Weijer, J.V.d.: Colour constancy from hyper-spectral data. In: Proceedings of the British Machine Vision Conference, pp. 30.1-30.10. BMVA Press (2000)Google Scholar
  14. 14.
    Hughes, G.: On the mean accuracy of statistical pattern recognizers. IEEE Trans. Inf. Theory 14(1), 55–63 (1968)CrossRefGoogle Scholar
  15. 15.
    Javanbakhti, S., Zinger, S., de With, P.H.N.: Context-based region labeling for event detection in surveillance video. In: 2014 International Conference on Information Science, Electronics and Electrical Engineering, vol. 1, pp. 94–98, April 2014Google Scholar
  16. 16.
    Li, J., Bioucas-Dias, J.M., Plaza, A.: Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning. IEEE Trans. Geosci. Remote Sens. 48(11), 4085–4098 (2010)Google Scholar
  17. 17.
    Li, J., Bioucas-Dias, J.M., Plaza, A.: Spectral-spatial hyperspectral image segmentation using subspace multinomial logistic regression and markov random fields. IEEE Trans. Geosci. Remote Sens. 50(3), 809–823 (2012)CrossRefGoogle Scholar
  18. 18.
    Melgani, F., Bruzzone, L.: Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans. Geosci. Remote Sens. 42(8), 1778–1790 (2004)CrossRefGoogle Scholar
  19. 19.
    Naghdy, G.A., Wang, J., Ogunbona, P.O.: Texture analysis using gabor wavelets, vol. 2657, pp. 74–85 (1996)Google Scholar
  20. 20.
    Namin, S.T., Petersson, L.: Classification of materials in natural scenes using multi-spectral images. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1393–1398. IEEE (2012)Google Scholar
  21. 21.
    Plaza, A., Benediktsson, J.A., Boardman, J.W., Brazile, J., Bruzzone, L., Camps-Valls, G., Chanussot, J., Fauvel, M., Gamba, P., Gualtieri, A., et al.: Recent advances in techniques for hyperspectral image processing. Remote Sens. Environ. 113, S110–S122 (2009)CrossRefGoogle Scholar
  22. 22.
    Salamati, N., Larlus, D., Csurka, G.: Combining visible and near-infrared cues for image categorisation. In: Proceeding of the 22nd British Machine Vision Conference (BMVC 2011), No. EPFL-CONF-169247 (2011)Google Scholar
  23. 23.
    Tarabalka, Y., Fauvel, M., Chanussot, J., Benediktsson, J.A.: SVM-and MRF-based method for accurate classification of hyperspectral images. IEEE Geosci. Remote Sens. Lett. 7(4), 736–740 (2010)CrossRefGoogle Scholar
  24. 24.
    Winkens, C., Sattler, F., Paulus, D.: Hyperspectral terrain classification for ground vehicles. In: 12th International Conference on Computer Vision Theory and Applications (VISAPP) (2017)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Christian Winkens
    • 1
    Email author
  • Volkmar Kobelt
    • 1
  • Dietrich Paulus
    • 1
  1. 1.Active Vision Group, Institute for Computational VisualisticsUniversity of Koblenz-LandauKoblenzGermany

Personalised recommendations