access icon free Synthetic aperture radar image segmentation using non-linear diffusion-based hierarchical triplet Markov fields model

© The Institution of Engineering and Technology
Received 28/10/2016, Accepted 20/08/2017, Revised 17/03/2017, Published 30/08/2017

Triplet Markov fields (TMF) model is widely used to deal with non-stationary synthetic aperture radar (SAR) images. However, its ability to capture global information remains limited due to the non-causal property. A hierarchical TMF model is proposed in this study based on the non-linear diffusion (ND) strategy, which is denoted as ND-hierarchical TMF (HTMF). ND is adopted to generate multiscale decomposition according to local image content, and that is superior to traditional wavelet decomposition in reflecting hierarchical nature of image structure and detailed features. The auxiliary field in ND-HTMF is redefined and initialised on the finest scale to characterise edge information and that enhances the prior modelling ability for non-stationary local image features. The multiscale likelihood and multiscale causal prior energy functions are then defined respectively in bottom-up and top-down procedures to capture local and global information for performing segmentation. Segmentation experiments on simulated and real SAR images demonstrate the effectiveness of ND-HTMF in both edge characterisation accuracy and robustness against speckle noise.

Inspec keywords: image segmentation; Markov processes; image denoising; synthetic aperture radar; radar imaging; speckle

Other keywords: nonstationary synthetic aperture radar image segmentation; bottom-up procedures; prior modelling ability enhancement; top-down procedures; SAR image; multiscale likelihood; edge information characterisation; local image content; multiscale causal prior energy functions; nonlinear diffusion-based hierarchical triplet Markov field model; multiscale decomposition; ND-hierarchical TMF; nonstationary local image features; ND-HTMF; speckle noise; hierarchical TMF model

Subjects: Optical, image and video signal processing; Radar equipment, systems and applications; Markov processes

References

    1. 1)
      • 13. Provost, J.N., Collet, C., Rostaing, P., et al: ‘Hierarchical Markovian segmentation of multispectral images for the reconstruction of water depth maps’, Comput. Vis. Image Understand., 2004, 93, pp. 155–174.
    2. 2)
      • 5. Deng, H.W., Clausi, D.A.: ‘Unsupervised segmentation of synthetic aperture radar sea ice imagery using a novel Markov random field model’, IEEE Trans. Geosci. Remote Sens., 2005, 43, (3), pp. 528–538.
    3. 3)
      • 16. Wang, Y.Y., Wang, Z.E.: ‘Difference curvature driven anisotropic diffusion for image denoising using Laplacian kernel’, Appl. Mech. Mater., 2013, pp. 2412–2417.
    4. 4)
      • 7. Zhang, P., Li, M., Wu, Y., et al: ‘Unsupervised multi-class segmentation of SAR images using fuzzy triplet Markov fields model’, Pattern Recognit., 2012, 45, (11), pp. 4018–4033.
    5. 5)
      • 12. Laferté, J.M., Pérez, P., Heitz, F.: ‘Discrete Markov modeling and inference on the quad-tree’, IEEE Trans. Image Process., 2000, 9, (3), pp. 390–404.
    6. 6)
      • 10. Zhang, P., Li, M., Wu, Y., et al: ‘SAR image multiclass segmentation using a multiscale TMF model in wavelet domain’, IEEE Geosci. Remote Sens. Lett., 2012, 9, (6), pp. 1099–1103.
    7. 7)
      • 4. Mignotte, M., Collet, C., Perez, P., et al: ‘Sonar image segmentation using an unsupervised hierarchical MRF model’, IEEE Trans. Image Process., 2000, 9, (7), pp. 1216–1231.
    8. 8)
      • 1. Koosha, M., Hajsadeghi, K.: ‘Fine logarithmic adaptive soft morphological algorithm for synthetic aperture radar image segmentation’, IET Image Process., 2014, 8, (2), pp. 90–102.
    9. 9)
      • 6. Benboudjema, D., Pieczynski, W.: ‘Unsupervised statistical segmentation of nonstationary images using triplet Markov fields’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (8), pp. 1367–1378.
    10. 10)
      • 14. Perona, P., Malik, J.: ‘Scale-space and edge detection using anisotropic diffusion’, IEEE Trans. Pattern Anal. Mach. Intell., 1990, 12, (7), pp. 629–639.
    11. 11)
      • 3. Katartzis, A., Vanhamel, I., Sahli, H.: ‘A hierarchical Markovian model for multiscale region-based classification of vector-valued images’, IEEE Trans. Geosci. Remote Sens., 2005, 43, (3), pp. 548–558.
    12. 12)
      • 8. Wang, F., Wu, Y., Fan, J.W., et al: ‘Synthetic aperture radar image segmentation using fuzzy label field-based triplet Markov fields model’, IET Image Process., 2014, 8, (12), pp. 856–865.
    13. 13)
      • 2. Jackson, Q., Landgrebe, D.: ‘Adaptive Bayesian contextual classification based on Markov random fields’, IEEE Trans. Geosci. Remote Sens., 2002, 40, (11), pp. 2454–2463.
    14. 14)
      • 15. Qiang, C., Montesinos, P., Quan, S.S., et al: ‘Adaptive total variation denoising based on difference curvature’, Image Vis. Comput., 2010, 28, (3), pp. 298–306.
    15. 15)
      • 11. Gan, L., Wu, Y., Liu, M., et al: ‘Triplet Markov fields with edge location for fast unsupervised multi-class segmentation of synthetic aperture radar images’, IET Image Process., 2012, 6, (7), pp. 831–838.
    16. 16)
      • 9. Wang, F., Wu, Y., Zhang, Q., et al: ‘Unsupervised SAR image segmentation using higher order neighborhood-based triplet Markov fields model’, IEEE Trans. Geosci. Remote Sens., 2014, 52, (8), pp. 5193–5205.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2016.0901
Loading

Related content

content/journals/10.1049/iet-ipr.2016.0901
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading