© The Institution of Engineering and Technology
Combining the advantage of Contourlet transform with adaptive fuzzy Markov random field (MRF) model, a novel segmentation algorithm is proposed in this study to achieve precise and continuous division for synthetic aperture radar (SAR) image. The classical MRF model is modified to obtain the edge and process adaptive label factor. The adaptive fuzzy MRF (AFMRF) model is proposed to equilibrate the smooth regions segmentation with texture regions segmentation. At the same time, Contourlet domain hidden Markov tree (HMT) model is introduced to perform multiscale directional filtering and intrascale training on the coefficients of SAR images to achieve precise texture segmentation at each scale. Finally, the AFMRF model is integrated into interscale and intrascale HMT training results and the segmented image can be obtained. To verify the validity of the proposed algorithm, several SAR images are experimented and compared with the stateoftheart algorithms. The experimental results and analysis show that the proposed algorithm can achieve better results on noise suppression, smoothness of target regions, precise and continuous segmentation of fuzzy texture.
References


1)

1. Zhang, X.R., Jiao, L.C., Liu, F., et al: ‘Spectral clustering ensemble applied to SAR image segmentation’, IEEE Trans. Geosci. Remote Sens., 2008, 46, (7), pp. 2126–2136.

2)

2. Yang, X.Z., Ye, M., Wu, K.W., et al: ‘Speckle reduction for PolSAR image based on structure preserving bilateral filtering’, J. Electron. Inf. Technol., 2015, 37, (2), pp. 268–275.

3)

3. Yang, D., Fei, R., Yao, J., et al: ‘Twostage SAR image segmentation framework with an efficient union filter and multiobjective kernel clustering’, Appl. Soft Comput., 2016, 44, (11), pp. 30–44.

4)

4. Yu, H., Jiao, L.C., Liu, F.: ‘Context based unsupervised hierarchical iterative algorithm for SAR segmentation’, Acta Autom. Sin., 2014, 40, (1), pp. 100–116.

5)

5. Pilar, J.A., Manuel, R.Z., David de la, M.M.: ‘Spatialrange meanshift filtering and segmentation applied to SAR images’, IEEE Trans. Instrum. Meas., 2011, 60, (2), pp. 584–597.

6)

6. He, C., Deng, J.B., Xu, L.Y., et al: ‘A novel oversegmentation method for polarimetric SAR images classification’. Geoscience & Remote Sensing Symp., 2012, pp. 4299–4302.

7)

7. Ciecholewski, M.: ‘River channel segmentation in polarimetric SAR images: watershed transform combined with average contrast maximisation’, Expert Syst. Appl., 2017, 82, pp. 196–215.

8)

8. Shi, J.B., Malik, J.: ‘Normalized cuts and image segmentation’, IEEE Trans. Pattern Anal. Mach. Intell., 2000, 22, (8), pp. 888–905.

9)

9. Mignotte, M.: ‘A nonstationary MRF model for image segmentation from a soft boundary map’, Pattern Anal. Appl., 2014, 17, (1), pp. 129–139.

10)

10. He, F.Y., Tian, Z., Fu, H.J., et al: ‘Efficient segmentation of SAR images using Markov random field models with edge penalties and adaptive weighting parameter’, Acta Opt. Sin., 2013, 33, (8), pp. 93–100.

11)

11. Zhang, P., Li, M., Wu, Y., et al: ‘Unsupervised multiclass segmentation of SAR images using fuzzy triplet Markov fields model’, Pattern Recognit., 2012, 45, (11), pp. 4018–4033.

12)

12. Wang, F., Wu, Y., Fan, J.W., et al: ‘Synthetic aperture radar image segmentation using fuzzy label fieldbased triplet Markov fields model’, IET Image Process., 2014, 8, (12), pp. 856–869.

13)

13. Subudhi, B.N., Ghosh, S., Cho, S., et al: ‘Integration of fuzzy Markov random field and local information for separation of moving objects and shadows’, Inf. Sci., 2016, 331, (7), pp. 15–31.

14)

14. Duan, Y.P., Liu, F., Jiao, L.C.: ‘SAR image segmentation based on convolutionalwavelet neural network and Markov random field’, Pattern Recognit., 2017, 64, (12), pp. 255–267.

15)

15. Do, M.N., Vetterli, M.: ‘The Contourlet transform: an efficient directional multiresolution image representation’, IEEE Trans. Image Process., 2005, 14, pp. 2091–2106.

16)

16. Guo, L.: ‘Research on multiscale image segmentation algorithm based on Contourlet transform’ (Harbin Engineering University, Harbin, 2010).

17)

17. Xiao, Y.H., Xi, Z.H., Dong, G.H., et al: ‘Image segmentation based on Contourlet transform’, J. Harbin Univ. Sci. Technol., 2011, 16, (5), pp. 101–105.

18)

18. Perciano, T., Tupin, F., Hirata, R.: ‘A twolevel Markov random field for road network extraction and its application with optical, SAR, and multitemporal data’, Int. J. Remote Sens., 2014, 37, (16), pp. 3584–3610.

19)

19. Li, H., Gong, M.G., Wang, Q., et al: ‘A multiobjective fuzzy clustering method for change detection in SAR images’, Appl. Soft Comput., 2016, 46, pp. 767–777.

20)

20. Xiang, D.L., Tang, T., Hu, C.B., et al: ‘A kernel clustering algorithm with fuzzy factor: application to SAR image segmentation’, IEEE Geosci. Remote Sens. Lett., 2014, 11, (7), pp. 1290–1294.

21)

21. Sun, R., Yan, X., Gao, J.: ‘Robust video fingerprinting scheme based on Contourlet hidden Markov tree model’, Optik Int. J. Light Electron Opt., 2017, 128, pp. 139–147.

22)

22. Li, J.C., Huang, B., Peng, Y.X.: ‘A modified method to configure the parameters of the bilateral filtering for synthetic aperture radar image speckle reduction’, Acta Phys. Sin., 2012, 61, (18), pp. 1895011–1895018.

23)

23. Weidner, U.: ‘Contribution to the assessment of segmentation quality for remote sensing applications’. Proc. 21st Congress for the Int. Society for Photogrammetry and Remote Sensing, 2008.
http://iet.metastore.ingenta.com/content/journals/10.1049/ietipr.2017.0290
Related content
content/journals/10.1049/ietipr.2017.0290
pub_keyword,iet_inspecKeyword,pub_concept
6
6