Skip to main content
SpringerLink
Log in

Looking Outside the Box: The Role of Context in Random Forest Based Semantic Segmentation of PolSAR Images

  • Conference paper
  • First Online:
Pattern Recognition (DAGM GCPR 2020)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12544))

Included in the following conference series:

  • 1099 Accesses

Abstract

Context - i.e. information not contained in a particular measurement but in its spatial proximity - plays a vital role in the analysis of images in general and in the semantic segmentation of Polarimetric Synthetic Aperture Radar (PolSAR) images in particular. Nevertheless, a detailed study on whether context should be incorporated implicitly (e.g. by spatial features) or explicitly (by exploiting classifiers tailored towards image analysis) and to which degree contextual information has a positive influence on the final classification result is missing in the literature. In this paper we close this gap by using projection-based Random Forests that allow to use various degrees of local context without changing the overall properties of the classifier (i.e. its capacity). Results on two PolSAR data sets - one airborne over a rural area, one space-borne over a dense urban area - show that local context indeed has substantial influence on the achieved accuracy by reducing label noise and resolving ambiguities. However, increasing access to local context beyond a certain amount has a negative effect on the obtained semantic maps.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Aghababaee, H., Sahebi, M.R.: Game theoretic classification of polarimetric SAR images. Eur. J. Remote Sens. 48(1), 33–48 (2015)

    Article  Google Scholar 

  2. Aksoy, S., Koperski, K., Tusk, C., Marchisio, G., Tilton, J.C.: Learning Bayesian classifiers for scene classification with a visual grammar. IEEE Trans. Geosci. Remote Sens. 43(3), 581–589 (2005)

    Article  Google Scholar 

  3. Anfinsen, S.N., Eltoft, T.: Application of the matrix-variate Mellin transform to analysis of polarimetric radar images. IEEE Trans. Geosci. Remote Sens. 49(6), 2281–2295 (2011)

    Article  Google Scholar 

  4. Bouchemakh, L., Smara, Y., Boutarfa, S., Hamadache, Z.: A comparative study of speckle filtering in polarimetric radar SAR images. In: 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications, pp. 1–6 (2008)

    Google Scholar 

  5. Bovolo, F., Bruzzone, L.: A context-sensitive technique based on support vector machines for image classification. In: Pal, S.K., Bandyopadhyay, S., Biswas, S. (eds.) Pattern Recogn. Mach. Intell., pp. 260–265. Springer, Heidelberg (2005). https://doi.org/10.1007/11590316_36

    Chapter  Google Scholar 

  6. Camps-Valls, G., Bruzzone, L.: Kernel-based methods for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 43(6), 1351–1362 (2005)

    Article  Google Scholar 

  7. Deng, X., López-Martínez, C., Chen, J., Han, P.: Statistical modeling of polarimetric SAR data: a survey and challenges. Remote Sens. 9(4) (2017). https://doi.org/10.3390/rs9040348

  8. Farhadiani, R., Homayouni, S., Safari, A.: Impact of polarimetric SAR speckle reduction on classification of agriculture lands. ISPRS - Int. Arch. Photogrammetry Remote Sens. Spatial Inf. Sci. XLII-4/W18, 379–385 (2019). https://doi.org/10.5194/isprs-archives-XLII-4-W18-379-2019

  9. Fauvel, M., Chanussot, J., Benediktsson, J.A., Sveinsson, J.R.: Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles. In: 2007 IEEE International Geoscience and Remote Sensing Symposium, pp. 4834–4837 (2007)

    Google Scholar 

  10. Fischer, G., Papathanassiou, K.P., Hajnsek, I.: Modeling and compensation of the penetration bias in InSAR DEMs of Ice sheets at different frequencies. IEEE J. Selected Topics Appl. Earth Observ. Remote Sens. 13, 2698–2707 (2020)

    Article  Google Scholar 

  11. Fjortoft, R., Delignon, Y., Pieczynski, W., Sigelle, M., Tupin, F.: Unsupervised classification of radar images using hidden Markov chains and hidden Markov random fields. IEEE Trans. Geosci. Remote Sens. 41(3), 675–686 (2003)

    Article  Google Scholar 

  12. Hänsch, R., Hellwich, O.: Skipping the real world: classification of PolSAR images without explicit feature extraction. ISPRS J. Photogrammetry Remote Sens. 140, 122–132 (2017). https://doi.org/10.1016/j.isprsjprs.2017.11.022

  13. Hänsch, R., Hellwich, O.: A comparative evaluation of polarimetric distance measures within the random forest framework for the classification of PolSAR images. In: IGARSS 2018–2018 IEEE International Geoscience and Remote Sensing Symposium, pp. 8440–8443. IEEE, July 2018. https://doi.org/10.1109/IGARSS.2018.8518834

  14. Hänsch, R., Wiesner, P., Wendler, S., Hellwich, O.: Colorful trees: visualizing random forests for analysis and interpretation. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 294–302. IEEE, January 2019. https://doi.org/10.1109/WACV.2019.00037

  15. Hoeser, T., Kuenzer, C.: Object detection and image segmentation with deep learning on earth observation data: a review-part I: evolution and recent trends. Remote Sens. 12, 1667 (2020)

    Google Scholar 

  16. Jong-Sen Lee, Grunes, M.R., Pottier, E., Ferro-Famil, L.: Unsupervised terrain classification preserving polarimetric scattering characteristics. IEEE Trans. Geosci. Remote Sens. 42(4), 722–731 (2004)

    Google Scholar 

  17. Ley, A., D’Hondt, O., Valade, S., Hänsch, R., Hellwich, O.: Exploiting GAN-based SAR to optical image transcoding for improved classification via deep learning. In: EUSAR 2018; 12th European Conference on Synthetic Aperture Radar, pp. 396–401. VDE, June 2018

    Google Scholar 

  18. Liu, X., Jiao, L., Tang, X., Sun, Q., Zhang, D.: Polarimetric convolutional network for polSAR image classification. IEEE Trans. Geosci. Remote Sens. 57(5), 3040–3054 (2019)

    Article  Google Scholar 

  19. Mohammadimanesh, F., Salehi, B., Mahdianpari, M., Gill, E., Molinier, M.: A new fully convolutional neural network for semantic segmentation of polarimetric SAR imagery in complex land cover ecosystem. ISPRS J. Photogramm. Remote. Sens. 151, 223–236 (2019)

    Article  Google Scholar 

  20. Mullissa, A., Persello, C., Stein, A.: Polsarnet: a deep fully convolutional network for polarimetric sar image classification. IEEE J. Selected Topics Appl. Earth Observ. Remote Sens. 12(12), 5300–5309 (2019)

    Google Scholar 

  21. Paradiso, M.A., Blau, S., Huang, X., MacEvoy, S.P., Rossi, A.F., Shalev, G.: Lightness, filling-in, and the fundamental role of context in visual perception. In: Visual Perception, Progress in Brain Research, vol. 155, pp. 109–123. Elsevier (2006)

    Google Scholar 

  22. Pesaresi, M., Benediktsson, J.A.: A new approach for the morphological segmentation of high-resolution satellite imagery. IEEE Trans. Geosci. Remote Sens. 39(2), 309–320 (2001)

    Article  Google Scholar 

  23. Tang, H.H., et al.: A multiscale latent Dirichlet allocation model for object-oriented clustering of VHR panchromatic satellite images. IEEE Trans. Geosci. Remote Sens. 51(3), 1680–1692 (2013)

    Article  Google Scholar 

  24. Tilton, J.C., Swain, P.H.: Incorporating spatial context into statistical classification of multidimensional image data. LARS (Purdue University. Laboratory for Applications of Remote Sensing), vol. 072981 (1981)

    Google Scholar 

  25. Tison, C., Nicolas, J., Tupin, F., Maitre, H.: A new statistical model for Markovian classification of urban areas in high-resolution SAR images. IEEE Trans. Geosci. Remote Sens. 42(10), 2046–2057 (2004)

    Article  Google Scholar 

  26. Uhlmann, S., Kiranyaz, S.: Integrating color features in polarimetric SAR image classification. IEEE Trans. Geosci. Remote Sens. 52(4), 2197–2216 (2014)

    Article  Google Scholar 

  27. Vogel, J., Schiele, B.: Semantic modeling of natural scenes for content-based image retrieval. Int. J. Comput. Vis. 72, 133–157 (2007). https://doi.org/10.1007/s11263-006-8614-1

    Article  Google Scholar 

  28. Watanabe, T., Suzuki, H.: An experimental evaluation of classifiers using spatial context for multispectral images. Syst. Comput. Japan 19(4), 33–47 (1988)

    Article  Google Scholar 

  29. Wu, Y., Ji, K., Yu, W., Su, Y.: Region-based classification of polarimetric SAR images using wishart MRF. IEEE Geosci. Remote Sens. Lett. 5(4), 668–672 (2008)

    Article  Google Scholar 

  30. Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions (2015)

    Google Scholar 

  31. Zhu, X.X., et al.: Deep learning meets SAR (2020)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. SAR Technology, German Aerospace Center (DLR), Cologne, Germany

    Ronny Hänsch

Authors
  1. Ronny Hänsch
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ronny Hänsch .

Editor information

Editors and Affiliations

  1. University of Tübingen, Tübingen, Germany

    Zeynep Akata

  2. University of Tübingen, Tübingen, Germany

    Andreas Geiger

  3. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Hänsch, R. (2021). Looking Outside the Box: The Role of Context in Random Forest Based Semantic Segmentation of PolSAR Images. In: Akata, Z., Geiger, A., Sattler, T. (eds) Pattern Recognition. DAGM GCPR 2020. Lecture Notes in Computer Science(), vol 12544. Springer, Cham. https://doi.org/10.1007/978-3-030-71278-5_19

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-71278-5_19

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-71277-8

  • Online ISBN: 978-3-030-71278-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation