Segmentation of complex objects’ sonar images using parameter-fixed MRF model

Abstract

The effective method of the recognition of underwater complex objects in sonar image is to segment sonar image into target, shadow and sea-bottom reverberation regions and then extract the edge of the object. Because of the time-varying and space-varying characters of underwater acoustics environment, the sonar images have poor quality and serious speckle noise, so traditional image segmentation is unable to achieve precise segmentation. In the paper, the image segmentation process based on MRF (Markov random field) model is studied, and a practical method of estimating model parameters is proposed. Through analyzing the impact of chosen model parameters, a sonar imagery segmentation algorithm based on fixed parameters’ MRF model is proposed. Both of the segmentation effect and the low computing load are gained. By applying the algorithm to the synthesized texture image and actual side-scan sonar image, the algorithm can be achieved with precise segmentation result.

Keywords

parameter-fixed MRF model / sonar image / image segmentation

References

[1] Murino V., Trucco A. Three-dimensional image generation and processing in underwater acoustic vision [J]. Proceedings of the IEEE, 2000, 88(12): 1903-1948

[2] Sang E. F., Liu Z. F. Underwater acoustic image segmentation based on deformable template [J]. ACTA ACUSICA, 2005, 30(4): 146-171

[3] Guo H. T., Tian T., Zhang C. T. The sonar image segmentation for multi-regions based on fuzzy clustering [J]. Ocean Technology, 2004, 23(3): 39-40

[4] CEXUS J C, BOUDRAA A O. Multi-channel model for sonar image segmentation [A]. Seventh International Symposium on Signal Processing and Its Applications[C]. Paris, France, 2003.

[5] Winkler G. Image analysis, random fields and dynamic monte carlo methods [M]. 1999, Berlin: Springer-Verlag

[6] Li S. Z. Markov random field modeling in computer vision [M]. 1995, Berlin: Springer-Verlag

[7] YANG Y, CAO Y F, SUN H. Segmentation of SAR imagery using the Gaussian Markov random field model [A]. 7th International Conference on Signal Processing[C]. Istanbul, Turkey, 2004.

[8] WERSENSEEL R A, KARL W C. MRF-based algorithm for segmentation of SAR images [A]. Proceeding of Int Conf on Image Processing[C]. Chicago, 1998.

[9] Mignotte M., Colle C., et al. Sonar image segmentation using an unsupervised hierarchical MRF model [J]. IEEE Transaction on Image Processing, 2000, 9(7): 1216-1231

[10] HU R, FAHMY M M. Texture segmentation based on a hierarchical markov random field model [A]. IEEE International Sympoisum on Circuits and Systems[C]. Singapore, 1991.