Signal, Image and Video Processing

, Volume 10, Issue 1, pp 75–84 | Cite as

Block-based semantic classification of high-resolution multispectral aerial images

  • Aleksej AvramovićEmail author
  • Vladimir Risojević
Original Paper


In this paper, we compare different approaches for classification of aerial images based on descriptors computed using visible spectral bands as well as additional information obtained from the near infrared band. We also propose different methods for incorporating dimensionality reduction into descriptor extraction process for both global and local texture descriptors aiming at obtaining low-dimensional descriptors from multispectral images. Furthermore, we examine classification accuracy in cases when small training sets are used. For evaluation purposes, we use an in-house high-resolution aerial image dataset, with images containing visual and near-infrared spectral bands, as well as UC Merced land-use dataset. We achieve the classification rates of over 90 % on in-house dataset. For UC Merced, we obtain classification accuracy of 91 % which is an improvement of about 3 % compared to the state-of-the-art color SIFT descriptors.


Gist descriptor SIFT descriptor Multispectral remote sensing image classification Land use/land cover 



This work was supported in part by the Ministry of Science and Technology of the Republic of Srpska under Contract 06/0-020/961-220/11.


  1. 1.
    Campbell, J.B.: Introduction to Remote Sensing. Guilford Press, NY (2006)Google Scholar
  2. 2.
    Cheriyadat, A.M.: Unsupervised feature learning for aerial scene classification. IEEE Trans. Geosci. Remote Sens. 52(1), 439–451 (2014)CrossRefGoogle Scholar
  3. 3.
    Ma, W.Y., Manjunath, B.S.: A texture thesaurus for browsing large aerial photographs. J. Am. Soc. Inf. Sci. 49(7), 633–648 (1998)CrossRefGoogle Scholar
  4. 4.
    Newsam, S.D., Kamath, C.: Retrieval using texture features in high-resolution multispectral satellite imagery. In: Data Mining and Knowledge Discovery: Theory, Tools, and Technology VI, SPIE Proceedings, vol. 5433, pp. 21–32. SPIE (2004)Google Scholar
  5. 5.
    Ozdemir, B., Aksoy, S.: Image classification using subgraph histogram representation. In: Proceedings of 20th ICPR, pp. 1112–1115. Istanbul, Turkey (2010)Google Scholar
  6. 6.
    Risojević, V., Babić, Z.: Fusion of global and local descriptors for remote sensing image classification. IEEE Geosci. Remote Sens. Lett. 10(4), 836–840 (2013)CrossRefGoogle Scholar
  7. 7.
    dos Santos, J.A., Penatti, O.A.B., da Silva Torres, R., Gosselin, P.H., Philipp-Foliguet, S., Falcao, A.X.: Improving texture description in remote sensing image multi-scale classification tasks by using visual words. In: ICPR, pp. 3090–3093. IEEE (2012)Google Scholar
  8. 8.
    Yang, Y., Newsam, S.: Spatial pyramid co-occurrence for image classification. In: Proceedings of ICCV, pp. 1465–1472 (2011)Google Scholar
  9. 9.
    Bayram, U., Can, G., Duzgun, S., Yalabik, N.: Evaluation of textural features for multispectral images. In: Proceedings of SPIE 8180, Image and Signal Processing for Remote Sensing, pp. 81800I–81800I–14 (2011)Google Scholar
  10. 10.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. Comput. Vis. 42(3), 145–175 (2001)zbMATHCrossRefGoogle Scholar
  11. 11.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRefGoogle Scholar
  12. 12.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, vol. 2, pp. 2169–2178 (2006)Google Scholar
  13. 13.
    Filiberto, P., Gema, G., Pedro, G.S., Majid, M., Xianghua, X.: Multi-spectral texture characterisation for remote sensing image segmentation. In: Proceedings of the 4th Iberian Pattern Recognition and Image Analysis Conference, pp. 257–264. Springer, Lecture Notes in Computer Science (2009)Google Scholar
  14. 14.
    Gleason, S., Ferrell, R., Cheriyadat, A., Vatsavai, R., De, S.: Semantic information extraction from multispectral geospatial imagery via a flexible framework. In: Proceedings of IGARSS, pp. 166–169 (2010)Google Scholar
  15. 15.
    Irtaza, A., Jaffar, M.: Categorical image retrieval through genetically optimized support vector machines (gosvm) and hybrid texture features. In: Signal, Image and Video Processing pp. 1–17 (2014)Google Scholar
  16. 16.
    Rajeesh, J., Moni, R., Kumar, S.: Performance analysis of wave atom transform in texture classification. In: Signal, Image and Video Processing, pp. 1–8 (2012)Google Scholar
  17. 17.
    Brown, M., Süsstrunk, S.: Multi-spectral SIFT for scene category recognition. In: Proceedings of CVPR, pp. 177–184 (2011)Google Scholar
  18. 18.
    Salamati, N., Larlus, D., Csurka, G.: Combining visible and near-infrared cues for image categorisation. In: Proceedings of BMVC, pp. 49.1-49.11 (2011)Google Scholar
  19. 19.
    van de Sande, K., Gevers, T., Snoek, C.: Evaluating color descriptors for object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1582–1596 (2010) Google Scholar
  20. 20.
    Avramović, A., Risojević, V.: Descriptor dimensionality reduction for aerial image classification. In: Proceedings of 18th IWSSIP, pp. 105–108. Sarajevo, Bosnia and Herzegovina (2011)Google Scholar
  21. 21.
    Vedaldi, A., Fulkerson, B.: VLFeat: an open and portable library of computer vision algorithms. (2008)
  22. 22.
    Chang, C.C., Lin, C.J.: Libsvm: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1–27:27 (2011). Software available at

Copyright information

© Springer-Verlag London 2014

Authors and Affiliations

  1. 1.School of Electrical EngineeringUniversity of BelgradeBelgradeSerbia
  2. 2.Faculty of Electrical EngineeringUniversity of Banja LukaBanja LukaBosnia and Herzegovina

Personalised recommendations