Three-Class Markovian Segmentation of High-Resolution Sonar Images

This paper presents an original method for analyzing, in an unsupervised way, images supplied by high resolution sonar. We aim at segmenting the sonar image into three kinds of regions: echo areas (due to the reflection of the acoustic wave on the object), shadow areas (corresponding to a lack of acoustic reverberation behind an object lying on the sea-bed), and sea-bottom reverberation areas. This unsupervised method estimates the parameters of noise distributions, modeled by a Weibull probability density function (PDF), and the label field parameters, modeled by a Markov random field (MRF). For the estimation step, we adopt a maximum likelihood technique for the noise model parameters and a least-squares method to estimate the MRF prior model. Then, in order to obtain an accurate segmentation map, we have designed a two-step process that finds the shadow and the echo regions separately, using the previously estimated parameters. First, we introduce a scale-causal and spatial model called SCM (scale causal multigrid), based on a multigrid energy minimization strategy, to find the shadow class. Second, we propose a MRF monoscale model using a priori information (at different level of knowledge) based on physical properties of each region, which allows us to distinguish echo areas from sea-bottom reverberation. This technique has been successfully applied to real sonar images and is compatible with automatic processing of massive amounts of data.

[1]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Patrick Pérez,et al.  Unsupervised Segmentation Applied on Sonar Images , 1997, EMMCVPR.

[3]  S. Guillaudeux,et al.  Optimization of a sonar image processing chain: a fuzzy rules based expert system approach , 1996, OCEANS 96 MTS/IEEE Conference Proceedings. The Coastal Ocean - Prospects for the 21st Century.

[4]  Haluk Derin,et al.  Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Fields , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[6]  M. Gensane.  A statistical study of acoustic signals backscattered from the sea bottom , 1989 .

[7]  Patrick Pérez,et al.  Unsupervised Markovian segmentation of sonar images , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  P. Pérez,et al.  Multiscale minimization of global energy functions in some visual recovery problems , 1994 .

[9]  Pierre Cervenka,et al.  Sidescan sonar image processing techniques , 1993 .

[10]  Josiane Zerubia,et al.  A Hierarchical Markov Random Field Model and Multitemperature Annealing for Parallel Image Classification , 1996, CVGIP Graph. Model. Image Process..

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

[12]  Gianni Vernazza,et al.  A multilevel GMRF-based approach to image segmentation and restoration , 1993, Signal Process..

[13]  Il Y. Kim,et al.  Efficient image labeling based on markov random field and error backpropagation network , 1993, Pattern Recognit..

[14]  S. Daniel,et al.  Adaptation of a partial shape recognition approach , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[15]  Patrick Pérez,et al.  Sonar image segmentation using an unsupervised hierarchical MRF model , 2000, IEEE Trans. Image Process..

[16]  Samantha Dugelay,et al.  Deep seafloor characterization with multibeam echosounders by image segmentation using angular acoustic variations , 1996, Optics & Photonics.

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

[18]  Charles A. Bouman,et al.  A multiscale random field model for Bayesian image segmentation , 1994, IEEE Trans. Image Process..

[19]  Christophe Collet,et al.  Contrast control for sonar pictures , 1996, Optics & Photonics.

[20]  M. Jiang,et al.  Segmentation of seafloor sidescan imagery using Markov random fields and neural networks , 1993, Proceedings of OCEANS '93.

[21]  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).

[22]  Benoît Zerr,et al.  Three-dimensional reconstruction of underwater objects from a sequence of sonar images , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[23]  Christophe Collet,et al.  Hierarchical MRF modeling for sonar picture segmentation , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[24]  Isabelle Herlin,et al.  Stochastic segmentation of ultrasound images , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[25]  Marco Lops,et al.  Optimised radar detection in correlated weibull clutter , 1993 .

[26]  Wojciech Pieczynski,et al.  Unsupervised Bayesian segmentation using hidden Markovian fields , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.