Skip to main content

Advertisement

SpringerLink
Log in

Object-based hyperspectral image classification using a new latent block model based on hidden Markov random fields

  • Industrial and Commercial Application
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

Efficient high-dimensional analyses of hyperspectral datasets and their utilization within classification algorithms is a popular topic in the field of data analytics. A powerful tool for summarizing a large array of datasets is the latent block model (LBM), which finds homogeneous blocks within the data using the finite mixture model (FMM). In this study, for the first time, LBM was modified by replacing the hidden Markov random field (HMRF) instead of using FMM to consider the spatial relationship between pixels and, thus, to develop a new object-based classification algorithm. The proposed clustering algorithm was named LBMHMRF and was used along with the support vector machine (SVM) algorithm to classify land cover/land use (LCLU) categories using two hyperspectral datasets. Unlike LBM, HMRF, and MultiHMRF, the LBMHMRF algorithm allows for the use of more spectral information without estimating a large number of parameters and produces a model with high computation costs saving feature. Additionally, the segmentation results are produced in a shorter period of time compared to the above-mentioned algorithms. It was observed that the proposed object-based classification algorithm (i.e., LBMHMRF + SVM) had the highest potential in terms of visual and statistical accuracies as well as computation time compared to the pixel-based SVM, object-based HMRF + SVM, and MultiHMRF + SVM. The average overall classification accuracies considering the different datasets and cases investigated in this study were 93.1%, 94.6%, 95.7%, and 96.4% for SVM, HMRF + SVM, MultiHMRF + SVM, and LBMHMRF + SVM, respectively.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Adam E, Mutanga O, Rugege D (2010) Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review. Wetl Ecol Manag 18(3):281–296

    Article  Google Scholar 

  2. Amani M, Salehi B, Mahdavi S, Brisco B (2018) Spectral analysis of wetlands using multi-source optical satellite imagery. ISPRS J Photogramm Remote Sens 144:119–136

    Article  Google Scholar 

  3. Amani M, Salehi B, Mahdavi S, Brisco B, Shehata M (2018) A Multiple Classifier System to improve mapping complex land covers: a case study of wetland classification using SAR data in Newfoundland, Canada. Int J Remote Sens 39(21):7370–7383

    Article  Google Scholar 

  4. Amani M, Salehi B, Mahdavi S, Granger JE, Brisco B, Hanson A (2017) Wetland classification using multi-source and multi-temporal optical remote sensing data in Newfoundland and Labrador, Canada. Can J Remote Sens 43(4):360–373

    Article  Google Scholar 

  5. Bazi Y, Melgani F (2006) Toward an optimal SVM classification system for hyperspectral remote sensing images. IEEE Trans Geosci Remote Sens 44(11):3374–3385

    Article  Google Scholar 

  6. Benediktsson JA, Ghamisi P (2015) Spectral-spatial classification of hyperspectral remote sensing images. Artech House

    Google Scholar 

  7. Besag J (1986) On the statistical analysis of dirty pictures. J R Stat Soc Ser B (Methodol) 48(3):259–279

    MathSciNet  MATH  Google Scholar 

  8. Blaschke T, Hay GJ, Kelly M, Lang S, Hofmann P, Addink E, Feitosa RQ, van der Meer F, van der Werff H, van Coillie F, Tiede D (2014) Geographic object-based image analysis–towards a new paradigm. ISPRS J Photogramm Remote Sens 87:180–191

    Article  Google Scholar 

  9. Brault V, Keribin C, Mariadassou M (2017) Consistency and asymptotic normality of latent blocks model estimators. arXiv preprint arXiv:1704.06629

  10. Foody G (2004) Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy. Photogramm Eng Remote Sens 70:627–633

    Article  Google Scholar 

  11. Gewali UB, Monteiro ST, Saber E (2018) Machine learning based hyperspectral image analysis: a survey. arXiv preprint arXiv:1802.08701

  12. Gewali UB, Monteiro ST (2018) A tutorial on modelling and inference in undirected graphical models for hyperspectral image analysis. Int J Remote Sens 39(20):1–40

    Article  Google Scholar 

  13. Ghamisi P, Benediktsson JA, Ulfarsson MO (2014) Spectral–spatial classification of hyperspectral images based on hidden Markov random fields. IEEE Trans Geosci Remote Sens 52(5):2565–2574

    Article  Google Scholar 

  14. Ghamisi P, Plaza J, Chen Y, Li J, Plaza AJ (2017) Advanced spectral classifiers for hyperspectral images: a review. IEEE Geosci Remote Sens Mag 5(1):8–32

    Article  Google Scholar 

  15. Golipour M, Ghassemian H, Mirzapour F (2015) Integrating hierarchical segmentation maps with MRF prior for classification of hyperspectral images in a Bayesian framework. IEEE Trans Geosci Remote Sens 54(2):805–816

    Article  Google Scholar 

  16. Govaert G, Nadif M (2003) Clustering with block mixture models. Pattern Recognit 36(2):463–473

    Article  Google Scholar 

  17. Govaert G, Nadif M (2008) Block clustering with Bernoulli mixture models: comparison of different approaches. Comput Stat Data Anal 52(6):3233–3245

    Article  MathSciNet  Google Scholar 

  18. Govaert G, Nadif M (2018) Mutual information, phi-squared and model-based co-clustering for contingency tables. Adv Data Anal Classif 12(3):455–488

    Article  MathSciNet  Google Scholar 

  19. Hasanlou M, Seydi ST (2018) Sensitivity analysis on performance of different unsupervised threshold selection methods in hyperspectral change detection. In: Proceedings of 10th IAPR workshop on pattern recognition in remote sensing (PRRS), pp 1–4

  20. Hathaway RJ (1986) Another interpretation of the EM algorithm for mixture distributions. Stat Probab Lett 4(2):53–56

    Article  MathSciNet  Google Scholar 

  21. Huang F, Yu Y, Feng T (2019) Hyperspectral remote sensing image change detection based on tensor and deep learning. J Vis Commun Image Represent 58:233–244

    Article  Google Scholar 

  22. Jensen JR (1996) Introductory digital image processing: a remote sensing perspective, 2nd edn. Prentice-Hall Inc.

    Google Scholar 

  23. Li SZ (2009) Markov random field modeling in image analysis. Springer

    MATH  Google Scholar 

  24. Liu S, Bruzzone L, Bovolo F, Du P (2016) Unsupervised multitemporal spectral unmixing for detecting multiple changes in hyperspectral images. IEEE Trans Geosci Remote Sens 54(5):2733–2748

    Article  Google Scholar 

  25. Lomet A, Govaert G, Grandvalet Y (2018) Model selection for Gaussian latent block clustering with the integrated classification likelihood. Adv Data Anal Classif 12(3):489–508

    Article  MathSciNet  Google Scholar 

  26. Mahdavi S, Salehi B, Amani M, Granger J, Brisco B, Huang W (2019) A dynamic classification scheme for mapping spectrally similar classes: application to wetland classification. Int J Appl Earth Obs Geoinf 83:101914

    Google Scholar 

  27. MartÍnez-UsÓMartinez-Uso A, Pla F, Sotoca JM, García-Sevilla P (2007) Clustering-based hyperspectral band selection using information measures. IEEE Trans Geosci Remote Sens 45(12):4158–4171

    Article  Google Scholar 

  28. Melgani F, Bruzzone L (2004) Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans Geosci Remote Sens 42(8):1778–1790

    Article  Google Scholar 

  29. Mirzapour F, Ghassemian H (2015) Improving hyperspectral image classification by combining spectral, texture, and shape features. Int J Remote Sens 36(4):1070–1096

    Article  Google Scholar 

  30. Mountrakis G, Im J, Ogole C (2011) Support vector machines in remote sensing: a review. ISPRS J Photogramm Remote Sens 66(3):247–259

    Article  Google Scholar 

  31. Nataliia K, Lavreniuk M, Skakun S, Shelestov A (2017) Deep learning classification of land cover and crop types using remote sensing data. IEEE Geosci Remote Sens Lett 14(5):778–782

    Article  Google Scholar 

  32. Neal RM, Hinton GE (1998) A view of the EM algorithm that justifies incremental, sparse, and other variants. In: Learning in graphical models. Springer, Dordrecht, pp 355–368

  33. Schölkopf B, Smola AJ, Bach F (2002) Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT Press

    Google Scholar 

  34. Shi C, Wang L (2014) Incorporating spatial information in spectral unmixing: a review. Remote Sens Environ 149:70–87

    Article  Google Scholar 

  35. Tarabalka Y, Benediktsson JA, Chanussot J, Tilton JC (2010) Multiple spectral–spatial classification approach for hyperspectral data. IEEE Trans Geosci Remote Sens 48(11):4122–4132

    Google Scholar 

  36. Vapnik VN (1999) An overview of statistical learning theory. IEEE Trans Neural Netw 10(5):988–999

    Article  Google Scholar 

  37. Wang L, Hao S, Wang Q, Wang Y (2014) Semi-supervised classification for hyperspectral imagery based on spatial–spectral label propagation. ISPRS J Photogramm Remote Sens 97:123–137

    Article  Google Scholar 

  38. Wang Q (2012) GMM-based hidden Markov random field for color image and 3D volume segmentation. arXiv preprint arXiv:1212.4527

  39. Wenzhi Z, Du Sh (2016) Spectral–spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach. IEEE Trans Geosci Remote Sens 54(8):4544–4554

    Article  Google Scholar 

  40. Zhang Y, Brady JM, Smith SM (2001) An hmrf-em algorithm for partial volume segmentation of brain mri fmrib technical report tr01yz1. Technical Report, Oxford Centre for Functional Magnetic Resonance Imaging of the Brain

Download references

Acknowledgements

Receiving support from the Center of Excellence in Analysis of Spatio-Temporal Correlated Data at Tarbiat Modares University is acknowledged. The authors would like to thank the Grupo de Inteligencia Computacional (GIC) team for providing the hyperspectral datasets through http://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes.

Author information

Authors and Affiliations

  1. Department of Statistics, Tarbiat Modares University, Tehran, Iran

    Hamideh Sadat Fatemighomi & Mousa Golalizadeh

  2. Wood Environment and Infrastructure Solutions, Ottawa, ON, Canada

    Meisam Amani

Authors
  1. Hamideh Sadat Fatemighomi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mousa Golalizadeh
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Meisam Amani
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mousa Golalizadeh.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fatemighomi, H.S., Golalizadeh, M. & Amani, M. Object-based hyperspectral image classification using a new latent block model based on hidden Markov random fields. Pattern Anal Applic 25, 467–481 (2022). https://doi.org/10.1007/s10044-021-01050-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-021-01050-3

Keywords

Search

Navigation