Filters








105 Hits in 4.4 sec

Three-Class Markovian Segmentation of High-Resolution Sonar Images

M. Mignotte, C. Collet, P. Pérez, P. Bouthemy
1999 Computer Vision and Image Understanding  
This paper presents an original method to analyze, in an unsupervised way, images supplied by a high resolution sonar.  ...  We aim at segmenting the sonar image into three kinds of regions: echo areas (due to the re ection of the acoustic wave on the object), shadow areas (corresponding to a lack of acoustic reverberation behind  ...  This scheme is computationally simple and well suited to automatic three-class segmentation on a large variety of sonar images. This method has been validated on a number of real sonar images.  ... 
doi:10.1006/cviu.1999.0804 fatcat:nncr4cy5abfl5lvgzclctegsde

Markov Random Field and Fuzzy Logic Modeling in Sonar Imagery: Application to the Classification of Underwater Floor

M. Mignotte, C. Collet, P. Pérez, P. Bouthemy
2000 Computer Vision and Image Understanding  
This § paper proposes an original method for the classification of seafloors from high resolution sidescan sonar images.  ...  Experiments on a variety of real high-resolution sonar images are reported. c 2000 Academic Press K ey Words: high-resolution sidescan sonar; seabed classification; acoustic shadow; shape analysis; fuzzy  ...  The good performances of this unsupervised method for segmenting high-resolution sonar images into two classes has been thoroughly assessed on a variety of real images.  ... 
doi:10.1006/cviu.2000.0844 fatcat:46riooisgneatj4j6o6lzdj2na

The fusion of large scale classified side-scan sonar image mosaics

S. Reed, I.T. Ruiz, C. Capus, Y. Petillot
2006 IEEE Transactions on Image Processing  
The corrected images are segmented using pixel-based textural features and standard classifiers. In parallel, the navigation of the sonar device is processed using Kalman filtering techniques.  ...  This paper presents a unified framework for the creation of classified maps of the seafloor from sonar imagery.  ...  Office of Naval Research, and the Woods Hole Oceanographic Institution for allowing the inclusion of data from the BP'02 experiment.  ... 
doi:10.1109/tip.2006.873448 pmid:16830923 fatcat:2ijbm7ttovdwfllele7ixhcd3q

Unsupervised segmentation using a self-organizing map and a noise model estimation in sonar imagery

K.C. Yao, M. Mignotte, C. Collet, P. Galerne, G. Burel
2000 Pattern Recognition  
This work deals with unsupervised sonar image segmentation. We present a new estimation and segmentation procedure on images provided by a high-resolution sonar.  ...  The sonar image is segmented into two kinds of regions: shadow (corresponding to a lack of acoustic reverberation behind each object lying on the seabed) and reverberation (due to the re#ection of acoustic  ...  Acknowledgements The authors thank GESMA (Groupe d'Etude Sous Marine de l' Atlantique, Brest France) for having provided real sonar images and REGION BRETAGNE for partial "nancial support of this work.  ... 
doi:10.1016/s0031-3203(99)00135-1 fatcat:nfxvaxps3fegpbhc6madzube2m

Sonar image segmentation using an unsupervised hierarchical MRF model

M. Mignotte, C. Collet, P. Perez, P. Bouthemy
2000 IEEE Transactions on Image Processing  
We present an original hierarchical segmentation procedure devoted to images given by a high-resolution sonar.  ...  We suspect that the proposed model is not well-suited to the high resolution sonar images we wish to segment for object classification purposes.  ...  ACKNOWLEDGMENT The authors thank Groupe d'Étude Sous Marine de l'Atlantique (GESMA), Brest, for having provided numerous real sonar pictures.  ... 
doi:10.1109/83.847834 pmid:18262959 fatcat:kz3ma6lv2rfedc25qduu2zcnpi

An automatic approach to the detection and extraction of mine features in sidescan sonar

S. Reed, Y. Petillot, J. Bell
2003 IEEE Journal of Oceanic Engineering  
Mine detection and classification using high-resolution sidescan sonar is a critical technology for mine counter measures (MCM).  ...  Using a priori spatial information on the physical size and geometric signature of mines in sidescan sonar, a detection-orientated MRF model is developed which directly segments the image into regions  ...  Zerr at GESMA for providing many of the sidescan images for both the detection and the CSS models.  ... 
doi:10.1109/joe.2002.808199 fatcat:sto5z5ql5jebnayal7adhn4grm

Hybrid genetic optimization and statistical model based approach for the classification of shadow shapes in sonar imagery

M. Mignotte, C. Collet, P. Perez, P. Bouthemy
2000 IEEE Transactions on Pattern Analysis and Machine Intelligence  
AbstractÐWe present an original statistical classification method using a deformable template model to separate natural objects from man-made objects in an image provided by a high resolution sonar.  ...  Second, the value of this function at convergence allows one to determine whether the desired object is present or not in the sonar image.  ...  of Defense) for partial financial support of this work (student grant).  ... 
doi:10.1109/34.825752 fatcat:irttqoqipnbvridkcbo55mxmdu

Sparse Representation based Classification for mine hunting using Synthetic Aperture Sonar

Raquel Fandos, Leyna Sadamori, Abdelhak M. Zoubir
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Due to the greater variability of sonar images, for mine hunting applications it is more convenient to transform the image samples into a different feature domain.  ...  The class of the training samples with greater weight is likely to be the candidate sample class.  ...  We have employed a Markovian segmentation algorithm [8] to segment the images. Three regions have been considered: highlight, shadow and background (see Fig. 1 for an illustration).  ... 
doi:10.1109/icassp.2012.6288644 dblp:conf/icassp/FandosSZ12 fatcat:bkup37ky5rd73djl5s7l44vwka

Model-based approach to the detection and classification of mines in sidescan sonar

Scott Reed, Yvan Petillot, Judith Bell
2004 Applied Optics  
This paper presents a model-based approach to mine detection and classification by use of sidescan sonar.  ...  Similarities between the sidescan sonar and synthetic aperture radar ͑SAR͒ imaging processes ensure that the approach outlined here could be made applied to SAR image analysis.  ...  The DRDC-Atlantic data were collected with a Klein 5500 multibeam 550-kHz high-resolution sidescan sonar.  ... 
doi:10.1364/ao.43.000237 pmid:14735943 fatcat:kbxigjbtvnd7bm43laxgrup5je

Image Processing Techniques For the Detection and Classification of Man Made Objects in Side-Scan Sonar Images [chapter]

Esther Dura
2011 Sonar Systems  
Segmentation Segmentation is the process of classifying pixels as belonging to a certain class. In side-scan sonar mages the classes of interest normally are: highlight and shadow.  ...  Fusion of adaptive algorithms for the classification of sea mines using high resolution side scan sonar in very shallow water, OCEANS, 2001.  ... 
doi:10.5772/21920 fatcat:fylrskfcpvhozl7qapckr6fgh4

High Quality Segmentation Of Synthetic Aperture Sonar Images Using The Min-Cut/Max-Flow Algorithm

Raquel Fandos, Leyna Sadamori, Abdelhak M. Zoubir
2011 Zenodo  
Publication in the conference proceedings of EUSIPCO, Barcelona, Spain, 2011  ...  INTRODUCTION The high resolution achieved by Synthetic Aperture Sonar (SAS) images encourages the development of Automatic Detection and Automatic Classification (ADAC) systems for mine hunting applications  ...  CONCLUSION Assuming a Markovian image model, a computationally efficient implementation of a graph cut algorithm has been employed to segment a SAS image database.  ... 
doi:10.5281/zenodo.42736 fatcat:ocfqe3wtnncf7aw6nkm4d6h6si

Unsupervised multiscale oil slick segmentation from SAR images using a vector HMC model

Stéphane Derrode, Grégoire Mercier
2007 Pattern Recognition  
Results of segmentation are shown in two types of scenarios. The first one concerns an oil spill in the Mediterranean sea detected by the ERS SAR sensor at a resolution of 25 m.  ...  of the original image is developed.  ...  The image in Fig. 8(b) presents the result of segmentation with three classes.  ... 
doi:10.1016/j.patcog.2006.04.032 fatcat:a7wlqqo44re5hnq527mrf3uwwa

A Conditional Random Field Approach to Unsupervised Texture Image Segmentation

Chang-Tsun Li
2010 EURASIP Journal on Advances in Signal Processing  
This approach involves local and long-range information in the CRF neighbourhood to determine the classes of image blocks.  ...  Like most Markov random field (MRF) approaches, the proposed method treats the image as an array of random variables and attempts to assign an optimal class label to each.  ...  Figures 4, 5 , and 6 illustrate the segmentation results of three textured images, Image I, II, and III, at different resolution levels.  ... 
doi:10.1155/2010/167942 fatcat:zyzbcz2jynfidlwebgde456pfi

Nonparametric multiscale energy-based model and its application in some imagery problems

M. Mignotte
2004 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper investigates the use of a nonparametric regularization energy term for devising a example-based rendering and segmentation technique.  ...  In this context, the formulation of our example-based regularization term also allows to directly infer an intuitive dissimilarity measure between two contour shapes.  ...  SEGMENTATION MODEL The goal of the segmentation is to assign, to each pixel of a noisy image y, a label indicating to which class the pixel belongs.  ... 
doi:10.1109/tpami.2004.1262180 pmid:15376894 fatcat:g3mhe6sw6vcana566hhs5bdnna

Unsupervised Local Spatial Mixture Segmentation of Underwater Objects in Sonar Images

Avi Abu, Roee Diamant
2021 Zenodo  
Segmentation of sonar images is a challenging task.  ...  In this paper, we propose our local spatial mixture (LSM) method for image segmentation of side-scan deployed sonar systems of any type.  ...  Sonar systems, like the synthetic aperture sonar (SAS), multibeam sonar and sidescan sonar, can produce high-resolution images of the seafloor, even in murky water.  ... 
doi:10.5281/zenodo.4982696 fatcat:zoft43drxzfcja6nqroro5na2e
« Previous Showing results 1 — 15 out of 105 results