Papers by Jean-marie Augustin
Geosciences, 2019
Seafloor backscatter mosaics are now routinely produced from multibeam echosounder data and used ... more Seafloor backscatter mosaics are now routinely produced from multibeam echosounder data and used in a wide range of marine applications. However, large differences (>5 dB) can often be observed between the mosaics produced by different software packages processing the same dataset. Without transparency of the processing pipeline and the lack of consistency between software packages raises concerns about the validity of the final results. To recognize the source(s) of inconsistency between software, it is necessary to understand at which stage(s) of the data processing chain the differences become substantial. To this end, willing commercial and academic software developers were invited to generate intermediate processed backscatter results from a common dataset, for cross-comparison. The first phase of the study requested intermediate processed results consisting of two stages of the processing sequence: the one-value-per-beam level obtained after reading the raw data and the lev...
IEEE Transactions on Image Processing, 2000
This paper investigates variational region-level criterion for supervised and unsupervised textur... more This paper investigates variational region-level criterion for supervised and unsupervised texture-based image segmentation. The focus is given to the demonstration of the effectiveness and robustness of this region-based formulation compared to most common variational approaches. The main contributions of this global criterion are twofold. First, the proposed methods circumvent a major problem related to classical texture based segmentation approaches. Existing methods, even if they use different and various texture features, are mainly stated as the optimization of a criterion evaluating punctual pixel likelihoods or similarity measure computed within a local neighborhood. These approaches require sufficient dissimilarity between the considered texture features. An additional limitation is the choice of the neighborhood size and shape. These two parameters and especially the neighborhood size significantly influence the classification performances: the neighborhood must be large enough to capture texture structures and small enough to guarantee segmentation accuracy. These parameters are often set experimentally. These limitations are mitigated with the proposed variational methods stated at the region-level. It resorts to an energy criterion defined on image where regions are characterized by nonparametric distributions of their responses to a set of filters. In the supervised case, the segmentation algorithm consists in the minimization of a similarity measure between region-level statistics and texture prototypes and a boundary based functional that imposes smoothness and regularity on region boundaries. In the unsupervised case, the data-driven term involves the maximization of the dissimilarity between regions. The proposed similarity measure is generic and permits optimally fusing various types of texture features. It is defined as a weighted sum of Kullback-Leibler divergences between feature distributions. The optimization of the proposed variational criteria is carried out using a level-set formulation. The effectiveness and the robustness of this formulation at region-level, compared to classical active contour methods, are evaluated for various Brodatz and natural images.
Features computed as statistics (e.g., histograms) of lo- cal lter responses have been reported a... more Features computed as statistics (e.g., histograms) of lo- cal lter responses have been reported as the best descrip- tors for texture classication and segmentation. The se- lection of the lter bank remains however a crucial issue, as well as exploiting a relevant combination of these de- scriptors. Here, we propose a novel approach relying on the denition of the texture-based
Pattern Analysis and Applications, 2008
Features computed as statistics (e.g. histograms) of local filter responses have been reported as... more Features computed as statistics (e.g. histograms) of local filter responses have been reported as the most powerful descriptors for texture classification and segmentation. The selection of the filter banks remains however a crucial issue, as well as determining a relevant combination of these descriptors. To cope with selection and fusion issues, we propose a novel approach relying on the definition of the texture-based similarity measure as a weighted sum of the Kullback-Leibler measures between empirical feature statistics. Within a supervised framework, the weighting factors are estimated according to the maximization of a margin-based criterion. This weighting scheme can also be considered as a filter selection method: texture filter response distributions are ranked according to the associated weighting factors so that the problem of selecting a subset of filters reduces to picking the first features only. An application of this similarity measure to texture recognition is reported. We also investigate its use for texture segmentation within a Bayesian Markov Random Field (MRF)-based framework. Experiments carried out on Brodatz textures and sonar images show that the proposed weighting method improves the classification and the segmentation rates while relying on a parsimonious texture representation.
IEEE International Symposium on Intelligent Signal Processing, 2007
We propose a novel unsupervised region based criterion for multi-class texture segmentation. The ... more We propose a novel unsupervised region based criterion for multi-class texture segmentation. The proposed criterion relies on the maximization of a weighted sum of Kullback-Leibler measure between distributions of local texture features associated to the different image regions. Hence, the segmentation issue is stated as the maximization of the proposed criterion and a regularization term that imposes smoothness and regularity
Image Processing, IEEE International Conference, 2005
This paper presents a new technique for noise removal in images. It benefits both from the recent... more This paper presents a new technique for noise removal in images. It benefits both from the recent advances in waveletbased and variational denoising. Whereas wavelet-based analysis tends to strongly depend on the selected wavelet basis, we propose to combine and fuse several mono-wavelet analysis within a variational framework. The associated energy function involves M-estimator in order to guarantee the robustness to outliers and to preserve image structures (edges, ridges,...). An experimental evaluation for a Gaussian additive noise validates the proposed approach and an application to speckle removal in sonar sea-bed images highlights the interest of this approach for real images.
International Conference on Image Processing, 2004
A new method for the segmentation of textured backscattering strength (BS) sonar images is presen... more A new method for the segmentation of textured backscattering strength (BS) sonar images is presented. The method is based on the analysis of joint wavelet statistics by using the whole information brought by cooccurrence distributions. After the wavelet transform of the image, on the most informative frequency bands of the wavelet transform, we discriminate between textures by directly measuring the similarity between co-occurrence statistics. Then, we fuse the different segmentations according to the weighted voting rule. Results on real sonar images and textures from the Brodatz album illustrate the effectiveness of the scheme. Finally, performances and results are discussed.
OCEANS - Europe, 2005
We propose a general framework to evaluate similarities from cooccurrence statistics between seab... more We propose a general framework to evaluate similarities from cooccurrence statistics between seabed textures within sonar images. Our approach aim at defining a texture based similarity as a weighted sum of the distances between cooccurrence distributions for a considered set of interaction types. The weighting factor introduces the discrimination power of each distribution and also cope, with the dependence of the cooccurrence statistics on the incidence angle. Classification experiments of the proposed approach show improved classification results with the weighting scheme compared to the method where the cooccurrence parameters are randomly chosen.
Pattern Analysis and Applications, 2008
Features computed as statistics (e.g. histograms) of local filter responses have been reported as... more Features computed as statistics (e.g. histograms) of local filter responses have been reported as the most powerful descriptors for texture classification and segmentation. The selection of the filter banks remains however a crucial issue, as well as determining a relevant combination of these descriptors. To cope with selection and fusion issues, we propose a novel approach relying on the definition of the texture-based similarity measure as a weighted sum of the Kullback–Leibler measures between empirical feature statistics. Within a supervised framework, the weighting factors are estimated according to the maximization of a margin-based criterion. This weighting scheme can also be considered as a filter selection method: texture filter response distributions are ranked according to the associated weighting factors so that the problem of selecting a subset of filters reduces to picking the first features only. An application of this similarity measure to texture recognition is reported. We also investigate its use for texture segmentation within a Bayesian Markov Random Field (MRF)-based framework. Experiments carried out on Brodatz textures and sonar images show that the proposed weighting method improves the classification and the segmentation rates while relying on a parsimonious texture representation.
IEEE Journal of Oceanic Engineering, 2010
... Bathymetry Sounders Xavier Lurton and Jean-Marie Augustin ... The authors are with Institut F... more ... Bathymetry Sounders Xavier Lurton and Jean-Marie Augustin ... The authors are with Institut Français de Recherche pour l'Exploitation de la Mer (IFREMER), NSE/AS, BP 70, 29280 Plouzané, France (e-mail: [email protected]). Digital Object Identifier 10.1109/JOE.2010.2064391 ...
A previous study ([1]) has shown that backscattered signal statistics, obtained from an acoustica... more A previous study ([1]) has shown that backscattered signal statistics, obtained from an acoustical imaging system, present a strong angular dependence. This paper deals with an extension of the proposed models to describe the intensity statistics fluctuations according to sonar resolution. Thus, the proposed model takes into account a wider variety of seabeds to provide an estimate of the order parameter of the K-law. Experimental data recorded by the EM1000 multibeam echosounder in shallow water provide the way to compare the different models on four different seafloors (mud, muddy sand, fine sand, coarse sand and a zone colonized by a bivalve population).
OCEANS Conference, 2003
Hellequin et al. (2003) showed that backscattered signal statistics, obtained from an acoustical ... more Hellequin et al. (2003) showed that backscattered signal statistics, obtained from an acoustical imaging system, present a strong angular dependence. This paper deals with an extension of the proposed models to describe the intensity statistics fluctuations according to sonar resolution. Thus, the proposed model takes into account a wider variety of seabeds to provide an estimate of the order parameter of the K-law. Experimental data recorded by the EM1000 multibeam echosounder in shallow water provide the way to compare the different models on four different seafloors (mud, muddy sand, fine sand, coarse sand and a zone colonized by a bivalve population).
2012 Oceans - Yeosu, 2012
For modern multibeam echosounders, the use of a robust and reliable quality estimator associated ... more For modern multibeam echosounders, the use of a robust and reliable quality estimator associated with each sounding is an absolute necessity. Indeed, due to the large volume of data acquired, a lot of time is lost, both during the survey and the post-processing. This is a costly problem for hydrographers. The definition of a quality estimator based on the characteristics of the beamformed signal gives an answer to this problem. It has been successfully implemented by several sonar manufacturers and its relevance in measuring the quality of each sounding has been demonstrated.
The Journal of the Acoustical Society of America, 2008
A quantitative analysis was conducted over sonar backscatter data collected on the Cook Strait re... more A quantitative analysis was conducted over sonar backscatter data collected on the Cook Strait region, central New Zealand, featuring multibeam (∼ 30 kHz) bathymetry and backscatter data, groundtruthed by an extensive geological database (photographs, seabed samples, high-resolution seismics). A first processing step removes the effects of the sounder, seafloor topography, and water column. A second step includes sonar image mosaicing, signal calibration and compensation, speckle noise filtering, image segmentation and textural analysis. Backscatter angular dependence is then extracted from the raw data accounting for the co-registered multibeam bathymetry ; it is linked to the various facies of this geologically very active region, forming a catalogue usable for future investigation. Some local features are analysed in details, referring to the geological local context. Also the backscatter data from the Haungaroa volcano were used for a proofof-concept biodiversity mapping exercise. Ecological theory was utilised to predict biodiversity from the seabed substrate heterogeneity, derived from the segmentation of the backscatter data properly pre-processed. The backscatter analysis resulted in the identification of local features with geological, sedimentological, topographic, and possibly biological significance, otherwise not recognised with conventional surveying. This emphasises the potential of backscatter data in submarine seismic hazard studies and large-scale biodiversity mapping.
IEEE Journal of Oceanic Engineering, 2000
... Bathymetry Sounders Xavier Lurton and Jean-Marie Augustin ... The authors are with Institut F... more ... Bathymetry Sounders Xavier Lurton and Jean-Marie Augustin ... The authors are with Institut Français de Recherche pour l'Exploitation de la Mer (IFREMER), NSE/AS, BP 70, 29280 Plouzané, France (e-mail: [email protected]). Digital Object Identifier 10.1109/JOE.2010.2064391 ...
In this paper, we propose and compare two super-4 vised algorithms for the segmentation of textur... more In this paper, we propose and compare two super-4 vised algorithms for the segmentation of textured sonar images, 5 with respect to seafloor types. We characterize seafloors by a set of 6 empirical distributions estimated on texture responses to a set of 7 different filters. Moreover, we introduce a novel similarity measure 8 between sonar textures in this feature space. Our similarity mea-9 sure is defined as a weighted sum of Kullback-Leibler divergences 10 between texture features. The weight setting is twofold. First, 11 each filter is weighted according to its discrimination power: The 12 computation of these weights are issued from a margin maxi-13 mization criterion. Second, an additional weight, evaluated as an 14 angular distance between the incidence angles of the compared 15 texture samples, is considered to take into account sonar-image 16 acquisition process that leads to a variability of the backscattered 17 value and of the texture aspect with the incidence-angle range. 18 A Bayesian framework is used in the first algorithm where the 19 conditional likelihoods are expressed using the proposed similarity 20 measure between local pixel statistics and the seafloor prototype 21 statistics. The second method is based on a variational framework 22
OCEANS 2006 - Asia Pacific, 2006
We propose a region-based segmentation of textured sonar images within a level set framework. We ... more We propose a region-based segmentation of textured sonar images within a level set framework. We state image segmentation as the minimization of an energy involving region regularity constraints and a texture similarity measure adapted to sonar images (introduced in our previous work [Karoui, I., et al., 2005]). In this framework, sonar textures are characterized by statistics of their responses to
IEEE Transactions on Image Processing, 2010
This paper investigates variational region-level criterion for supervised and unsupervised textur... more This paper investigates variational region-level criterion for supervised and unsupervised texture-based image segmentation. The focus is given to the demonstration of the effectiveness and robustness of this region-based formulation compared to most common variational approaches. The main contributions of this global criterion are twofold. First, the proposed methods circumvent a major problem related to classical texture based segmentation approaches. Existing methods, even if they use different and various texture features, are mainly stated as the optimization of a criterion evaluating punctual pixel likelihoods or similarity measure computed within a local neighborhood. These approaches require sufficient dissimilarity between the considered texture features. An additional limitation is the choice of the neighborhood size and shape. These two parameters and especially the neighborhood size significantly influence the classification performances: the neighborhood must be large enough to capture texture structures and small enough to guarantee segmentation accuracy. These parameters are often set experimentally. These limitations are mitigated with the proposed variational methods stated at the region-level. It resorts to an energy criterion defined on image where regions are characterized by nonparametric distributions of their responses to a set of filters. In the supervised case, the segmentation algorithm consists in the minimization of a similarity measure between region-level statistics and texture prototypes and a boundary based functional that imposes smoothness and regularity on region boundaries. In the unsupervised case, the data-driven term involves the maximization of the dissimilarity between regions. The proposed similarity measure is generic and permits optimally fusing various types of texture features. It is defined as a weighted sum of Kullback-Leibler divergences between feature distributions. The optimization of the proposed variational crite- - ria is carried out using a level-set formulation. The effectiveness and the robustness of this formulation at region-level, compared to classical active contour methods, are evaluated for various Brodatz and natural images.
Marine Geophysical Research, 2014
A rotating, acoustic gas bubble detector, BOB (Bubble OBservatory) module was deployed during two... more A rotating, acoustic gas bubble detector, BOB (Bubble OBservatory) module was deployed during two surveys, conducted in 2009 and 2011 respectively, to study the temporal variations of gas emissions from the Marmara seafloor, along the North Anatolian Fault zone. The echosounder mounted on the instrument insonifies an angular sector of 7°during a given duration (of about 1 h). Then it rotates to the next, near-by angular sector and so forth. When the full angular domain is insonified, the ''pan and tilt system'' rotates back to its initial position, in order to start a new cycle (of about 1 day). The acoustic data reveal that gas emission is not a steady process, with observed temporal variations ranging between a few minutes and 24 h (from one cycle to the other). Echo-integration and inversion performed on the acoustic data as described in the companion paper of Leblond et al. (Mar Geophys Res, 2014), also indicate important variations in, respectively, the target strength and the volumetric flow rates of individual sources. However, the observed temporal variations may not be related to the properties of the gas source only, but reflect possible variations in sea-bottom currents, which could deviate the bubble train towards the neighboring sector. During the 2011 survey, a 4-component ocean bottom seismometer (OBS) was co-located at the seafloor, 59 m away from the BOB module. The acoustic data from our rotating, monitoring system support, but do not provide undisputable evidence to confirm, the hypothesis formulated by , that the short-duration, nonseismic micro-events recorded by the OBS are likely produced by gas-related processes within the near seabed sediments. Hence, the use of a multibeam echosounder, or of several split beam echosounders should be preferred to rotating systems, for future experiments.
Uploads
Papers by Jean-marie Augustin