Unsupervised Change Detection Using Multi-temporal SAR Images Based on Improvement of Level Set Methods

Document Type : Original Article

Authors

Abstract

In this research, a framework is presented for the unsupervised change detection using Multitemporal SAR images based on integration of Clustering and Level Set Methods. Spatial
correlation between pixels is considered by using contextual information. Furthermore, in the
proposed method integration of Gustafson-Kessel clustering techniques (GKC) and Level Set
Methods are used for change detection. Using clustering techniques has caused production of
the initial curve for LSM with a minimum convergence time and, as a result, use of LSM Leads
to increasing the accuracy of change map using the iterative process. In order to evaluate the
performance of the proposed method, this method is compared with some other existing stateof-the-art methods. The results show that the total error rate of the proposed method has been
reduced compared to these methods. Results show the high capability of the proposed method in
the unsupervised change detection of multi-temporal satellite SAR images.

Keywords

References

  1. 1A. Singh, “Review article digital change detection
  2. techniques using remotely-sensed data, ”
  3. International journal of remote sensing, vol. 10, pp.
  4. -1003, 1989.
  5. 2F. Wu, C. Wang, H. Zhang, and B. Zhang, “Change
  6. detection and analysis with radarsat-1 SAR image,”
  7. in Geoscience and Remote Sensing Symposium,
  8. IGARSS 2007. IEEE International, pp. 2601-
  9. , 2007.
  10. F. Bovolo and L. Bruzzone, “A detail-preserving
  11. scale-driven approach to change detection in
  12. multitemporal SAR images,” Geoscience and Remote
  13. Sensing, IEEE Transactions on, vol. 43, pp. 2963-
  14. , 2005.
  15. A. Ghosh, N. S. Mishra, and S. Ghosh, “Fuzzy
  16. clustering algorithms for unsupervised change
  17. detection in remote sensing images,” Information
  18. Sciences, vol. 181, pp. 699-715, 2011.
  19. S. Ghosh, N. S. Mishra, and A. Ghosh,
  20. “Unsupervised change detection of remotely sensed
  21. images using fuzzy clustering,” in Advances in
  22. Pattern Recognition, 2009 ICAPR'09, Seventh
  23. International Conference on, pp. 385-388, 2009.
  24. T. Celik, “A Bayesian approach to unsupervised
  25. multiscale change detection in synthetic aperture
  26. radar images,” Signal processing, vol. 90, pp. 1471-
  27. , 2010.
  28. L. Bruzzone and D. F. Prieto, “Automatic analysis of
  29. the difference image for unsupervised change
  30. detection,” Geoscience and Remote Sensing, IEEE
  31. Transactions on, vol. 38, pp. 1171-1182, 2000.
  32. Y. Bazi, L. Bruzzone, and F. Melgani, “An
  33. unsupervised approach based on the generalized
  34. Gaussian model to automatic change detection in
  35. multitemporal SAR images,” Geoscience and Remote
  36. Sensing, IEEE Transactions on, vol. 43, pp. 874-887,
  37.  
  38. L. Paul and D. P. Ramamoorthy, “Synthetic aperture
  39. radar image change detection using fuzzy c-means
  40. clustering algorithm,” International Journal of
  41. Advanced Research in Computer and
  42. Communication Engineering, vol. 2, 2013.
  43. Y. Bazi, F. Melgani, and H. D. Al-Sharari,
  44. “Unsupervised change detection in multispectral
  45. remotely sensed imagery with level set methods,
  46. ”Geoscience and Remote Sensing, IEEE Transactions
  47. on, vol. 48, pp. 3178-3187, 2010.
  48. T. Celik and K.-K. Ma, “Multitemporal image change
  49. detection using undecimated discrete wavelet
  50. transform and active contours,” Geoscience and
  51. Remote Sensing, IEEE Transactions on, vol. 49, pp.
  52. -716, 2011.
  53. M. Gong, Y. Cao, and Q. Wu, “A neighborhoodbased
  54. ratio approach for change detection in SAR
  55. images,” Geoscience and Remote Sensing Letters,
  56. IEEE, vol. 9, pp. 307-311, 2012.
  57. L. J. Chipman, T. M. Orr, and L. N. Graham,
  58. “Wavelets and image fusion,” in SPIE's 1995
  59. International Symposium on Optical Science,
  60. Engineering, and Instrumentation, 1995, pp. 208-219.
  61. S. Osher and J. A. Sethian, “Fronts propagating with
  62. curvature-dependent speed: algorithms based on
  63. Hamilton-Jacobi formulations,” Journal of
  64. computational physics, vol. 79, pp. 12-49, 1988.
  65. S. Osher and R .P. Fedkiw, “Level set methods: an
  66. overview and some recent results,” Journal of
  67. Computational physics, vol. 169, pp. 463-502, 2001.
  68. T. Chan and W. Zhu, “Level set based shape prior
  69. segmentation,” in Computer Vision and Pattern
  70. Recognition, 2005. CVPR 2005. IEEE Computer
  71. Society Conference on, pp. 1164-1170, 2005.
  72. C. Li, C. Xu, C. Gui, and M. D. Fox, “Level set
  73. evolution without re-initialization: a new variational
  74. formulation,” in Computer Vision and Pattern
  75. Recognition, 2005. CVPR 2005. IEEE Computer
  76. Society Conference on, 2005, pp. 430-436.
  77. M. Ding, Z. Tian, Z. Jin, M. Xu, and C. Cao,
  78. “Registration using robust kernel principal
  79. component for object-based change detection,”
  80. Geoscience and Remote Sensing Letters, IEEE, vol.
  81. , pp. 761-765, 2010.
  82. L. Cao, K. Chua, W. Chong, H. Lee, and Q. Gu, “A
  83. comparison of PCA, KPCA and ICA for
  84. dimensionality reduction in support vector machine,”
  85. Neurocomputing, vol. 55, pp. 321-336, 2003.
  86. R. Babuška, “Fuzzy Modeling for Control Kluwer
  87. Academic Publishers,” Boston, MA, USA, 1998.
  88. D. Gustafson and W. Kessel, “Fuzzy clustering with
  89. a fuzzy covariance matrix,” in 1978 IEEE conference
  90. on decision and control including the 17th
  91. symposium on adaptive processes, pp. 761-766,
  92.  

Files

History

  • Receive Date: 19 November 2015
  • Revise Date: 22 January 2024
  • Accept Date: 19 September 2018
  • Publish Date: 20 April 2016

Share

How to cite

Statistics