Markov random field model and fuzzy formalism-based data modeling for the sea-floor classification

In this paper, we propose an original and statistical method for he sea-floor segmentation and its classification into five kinds of regions: sand, pebbles, rocks, ridges and dunes. The proposed method is based on the identification of the cast shadow shapes for each sea-bottom type and consists in four stages of processing. Firstly, the input image is segmented into two kinds of regions: shadow and sea-bottom reverberation. Secondly, the image of the contours of the detected cast shadows is partitioned into sub-windows from which a relevant geometrical feature vector is extracted. A pre-classification by a fuzzy classifier is thus required to initialize the third stage of processing. Finally, a Markov Random Field model is employed to specify homogeneity properties of the desired segmentation map. A Bayesian estimate of this map is computed using a deterministic relaxation algorithm. Reported experiments demonstrate that the proposed approach yields promising results to the problem of sea-floor classification.

[1]  W. K. Stewart,et al.  A neural network approach to classification of sidescan sonar imagery from a midocean ridge area , 1994 .

[2]  Christophe Collet,et al.  Unsupervised Hierarchical Markovian Segmentation Of Sonar Images , 1997 .

[3]  Christophe Collet,et al.  Some improvements of a rotation invariant autoregressive method. Application to the neural classification of noisy sonar images , 1998, 9th European Signal Processing Conference (EUSIPCO 1998).

[4]  J. Goodman.  Some fundamental properties of speckle , 1976 .

[5]  L. Zadeh.  Fuzzy sets as a basis for a theory of possibility , 1999 .

[6]  D.T. Cobra,et al.  Classification of side-scan sonar images through parametric modeling , 1994, Proceedings of OCEANS'94.

[7]  Patrick Pérez,et al.  Statistical model and genetic optimization: application to pattern detection in sonar images , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[8]  Andrew B. Martinez,et al.  Seafloor characterization using texture , 1993, Proceedings of Southeastcon '93.

[9]  Christophe Collet,et al.  Estimation of noise parameters on sonar images , 1996, Optics & Photonics.

[10]  B. Zerr,et al.  Sea-floor classification by neural hybrid system , 1994, Proceedings of OCEANS'94.

[11]  B. Calder,et al.  Seabed classification through multifractal analysis of sidescan sonar imagery , 1996 .

[12]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .

[13]  C. Walker,et al.  Sidescan Sonar Image Interpretation With Neural Networks , 1991, OCEANS 91 Proceedings.

[14]  D. Vray,et al.  Bottom classification using information in the spectral domain and time-frequency domain , 1994, Proceedings of OCEANS'94.