Journal

Journal

[Bom2008a] “Fisher Distribution for Texture Modeling of Polarimetric SAR Data,”
Bombrun Lionel, Jean-Marie Beaulieu,
IEEE Geoscience and Remote Sensing Letters, vol. 5, iss. 3, p. 512–516, July 2008.
[URL]   [DOI]   [Open]   [.. More]   [Bibtex]   [Abstract]  
The multilook polarimetric synthetic aperture radar (PolSAR) covariance matrix is generally modeled by a complex Wishart distribution. For textured areas, the product model is used, and the texture component is modeled by a Gamma distribution. In many cases, the assumption of Gamma-distributed texture is not appropriate. The Fisher distribution does not have this limitation and can represent a large set of texture distributions. As an example, we examine its advantage for an urban area. From a Fisher-distributed texture component, we derive the distribution of the complex covariance matrix for multilook PolSAR data. The obtained distribution is expressed in terms of the KummerU confluent hypergeometric function of the second kind. Those distributions are related to the Mellin transform and second-kind statistics (Log-statistics). The new KummerU-based distribution should provide in many cases a better representation of textured areas than the classic K distribution. Finally, we show that the new model can discriminate regions with different texture distribution in a segmentation experiment with synthetic textured PolSAR images.
@Article{Bom2008a,
author = {Bombrun, Lionel and Beaulieu, Jean-Marie},
title = {Fisher Distribution for Texture Modeling of Polarimetric {SAR} Data},
journal = {IEEE Geoscience and Remote Sensing Letters},
volume = {5},
number = {3},
pages = {512--516},
year = {2008},
month = {July},
abstract = {The multilook polarimetric synthetic aperture radar (PolSAR) covariance matrix is generally modeled by a complex Wishart distribution. For textured areas, the product model is used, and the texture component is modeled by a Gamma distribution. In many cases, the assumption of Gamma-distributed texture is not appropriate. The Fisher distribution does not have this limitation and can represent a large set of texture distributions. As an example, we examine its advantage for an urban area. From a Fisher-distributed texture component, we derive the distribution of the complex covariance matrix for multilook PolSAR data. The obtained distribution is expressed in terms of the KummerU confluent hypergeometric function of the second kind. Those distributions are related to the Mellin transform and second-kind statistics (Log-statistics). The new KummerU-based distribution should provide in many cases a better representation of textured areas than the classic K distribution. Finally, we show that the new model can discriminate regions with different texture distribution in a segmentation experiment with synthetic textured PolSAR images.},
publisher = {IEEE},
url = {https://ieeexplore.ieee.org/abstract/document/4554026},
isbn = {1545-598X},
doi = {10.1109/LGRS.2008.923262},
mypdf = {13},
address = {},
keywords = {Classification; complex covariance matrix distribution; covariance matrices; Fisher distributed texture component; Fisher distribution; geophysical signal processing; geophysical techniques; image segmentation; image texture; KummerU; log statistics; Mellin transform; multilook PolSAR covariance matrix; polarimetric SAR data texture modeling; polarimetric synthetic aperture radar; polarimetric synthetic aperture radar (PolSAR) images; radar polarimetry; radar signal processing; remote sensing by radar; second kind KummerU confluent hypergeometric function; second kind statistics; segmentation; statistical distributions; synthetic aperture radar; synthetic textured PolSAR image segmentation; texture; texture distributions; urban area},
openpdf = {https://hal.archives-ouvertes.fr/hal-00350055/},
openid = {HAL archives-ouvertes}
}
[Bea2004a] “Segmentation of Textured Polarimetric SAR Scenes by Likelihood Approximation,”
Beaulieu Jean-Marie, Ridha Touzi,
IEEE Transactions on Geoscience and Remote Sensing, vol. 42, iss. 10, p. 2063–2072, Oct. 2004.
[PDF]   [URL]   [DOI]   [Open]   [.. More]   [Bibtex]   [Abstract]  
A hierarchical stepwise optimization process is developed for polarimetric synthetic aperture radar image segmentation. We show that image segmentation can be viewed as a likelihood approximation problem. The likelihood segment merging criteria are derived using the multivariate complex Gaussian, the Wishart distribution, and the K-distribution. In the presence of spatial texture, the Gaussian-Wishart segmentation is not appropriate. The K-distribution segmentation is more effective in textured forested areas. The validity of the product model is also assessed, and a field-adaptable segmentation strategy combining different criteria is examined.
@Article{Bea2004a,
author = {Beaulieu, Jean-Marie and Touzi, Ridha},
title = {Segmentation of Textured Polarimetric {SAR} Scenes by Likelihood Approximation},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
volume = {42},
number = {10},
pages = {2063--2072},
year = {2004},
month = {Oct.},
abstract = {A hierarchical stepwise optimization process is developed for polarimetric synthetic aperture radar image segmentation. We show that image segmentation can be viewed as a likelihood approximation problem. The likelihood segment merging criteria are derived using the multivariate complex Gaussian, the Wishart distribution, and the K-distribution. In the presence of spatial texture, the Gaussian-Wishart segmentation is not appropriate. The K-distribution segmentation is more effective in textured forested areas. The validity of the product model is also assessed, and a field-adaptable segmentation strategy combining different criteria is examined.},
publisher = {},
url = {https://ieeexplore.ieee.org/document/1344159},
isbn = {0196-2892},
doi = {10.1109/TGRS.2004.835302},
mypdf = {11},
address = {},
keywords = {},
openpdf = {https://www.academia.edu/4591322/Segmentation_of_textured_polarimetric_SAR_scenes_by_likelihood_approximation},
openid = {Academia}
}
[Bea2004b] “Utilisation of Contour Criteria in Micro-Segmentation of SAR Images,”
Beaulieu Jean-Marie,
International Journal of Remote Sensing, vol. 25, iss. 17, p. 3497–3512, Sept. 2004.
[PDF]   [URL]   [DOI]   [Open]   [.. More]   [Bibtex]   [Abstract]  
The segmentation of SAR (Synthetic Aperture Radar) images is greatly complicated by the presence of coherent speckle. To carry out this process a hierarchical segmentation algorithm based on stepwise optimization is used. It starts with each individual pixel as a segment and then sequentially merges the segment pair that minimizes the criterion. In a hypothesis testing approach, we show how the stepwise merging criterion is derived from the probability model of image regions. The Ward criterion is derived from the Gaussian additive noise model. A new criterion is derived from the multiplicative speckle noise model of SAR images. The first merging steps produce micro-regions. With standard merging criteria, the high noise level of SAR images results in the production of micro-regions that have unreliable mean and variance values and irregular shapes. If the micro-segments are not correctly delimited then the following steps will merge segments from different fields. In examining the evolution of the initial segments, we see that the merging should take into account spatial aspects. In particular, the segment contours should have good shapes. We present three measures based on contour shapes, using the perimeter, the area and the boundary length of segments. These measures are combined with the SAR criterion in order to guide correctly the segment merging process. The new criterion produces good micro-segmentation of SAR images. The criterion is also used in the following merges to produce larger segments. This is illustrated by synthetic and real image results.
@Article{Bea2004b,
author = {Beaulieu, Jean-Marie},
title = {Utilisation of Contour Criteria in Micro-Segmentation of {SAR} Images},
journal = {International Journal of Remote Sensing},
volume = {25},
number = {17},
pages = {3497--3512},
year = {2004},
month = {Sept.},
abstract = {The segmentation of SAR (Synthetic Aperture Radar) images is greatly complicated by the presence of coherent speckle. To carry out this process a hierarchical segmentation algorithm based on stepwise optimization is used. It starts with each individual pixel as a segment and then sequentially merges the segment pair that minimizes the criterion. In a hypothesis testing approach, we show how the stepwise merging criterion is derived from the probability model of image regions. The Ward criterion is derived from the Gaussian additive noise model. A new criterion is derived from the multiplicative speckle noise model of SAR images. The first merging steps produce micro-regions. With standard merging criteria, the high noise level of SAR images results in the production of micro-regions that have unreliable mean and variance values and irregular shapes. If the micro-segments are not correctly delimited then the following steps will merge segments from different fields. In examining the evolution of the initial segments, we see that the merging should take into account spatial aspects. In particular, the segment contours should have good shapes. We present three measures based on contour shapes, using the perimeter, the area and the boundary length of segments. These measures are combined with the SAR criterion in order to guide correctly the segment merging process. The new criterion produces good micro-segmentation of SAR images. The criterion is also used in the following merges to produce larger segments. This is illustrated by synthetic and real image results.},
publisher = {},
url = {http://www.tandfonline.com/doi/abs/10.1080/01431160310001647714},
isbn = {0143-1161},
doi = {10.1080/01431160310001647714},
mypdf = {11},
address = {},
keywords = {},
openpdf = {https://pdfs.semanticscholar.org/190a/fd1a2dd30e24ea998bf7c99a66505ca78929.pdf?_ga=2.93565854.2051265828.1566578008-697872498.1566578008},
openid = {Semantics}
}
[Bel1992] “Post-segmentation classification of images containing small agricultural fields,”
Belaid Ait M, G Edwards, A Jaton, KPB Thomson, Jean-Marie Beaulieu,
Geocarto International, vol. 7, iss. 3, p. 53–60, 1992.
[URL]   [DOI]   [.. More]   [Bibtex]   [Abstract]  
This paper presents results from applying a hierarchical segmentation algorithm to two agricultural data sets characterised by small fields. Several new techniques were developed over the course of this project. These include a new supervised classification technique for identifying segments and the inclusion of other information derived from the segmentation process. In addition, a technique for including cartographic information to help structure the segmentation is also described. The results indicate that significant improvement in classification accuracy can be achieved. A number of problems which arise when working with segmentation data are also reported and discussed. These problems appear to be different enough from those encountered in pixel classifications to be worth describing in greater detail. The paper concludes with the lines of research being pursued to circumvent these problems and to further increase the fidelity of the segmentation results.
@Article{Bel1992,
author = {Belaid, M Ait and Edwards, G and Jaton, A and Thomson, K P B and Beaulieu, Jean-Marie},
title = {Post-segmentation classification of images containing small agricultural fields},
journal = {Geocarto International},
volume = {7},
number = {3},
pages = {53--60},
year = {1992},
month = {},
abstract = {This paper presents results from applying a hierarchical segmentation algorithm to two agricultural data sets characterised by small fields. Several new techniques were developed over the course of this project. These include a new supervised classification technique for identifying segments and the inclusion of other information derived from the segmentation process. In addition, a technique for including cartographic information to help structure the segmentation is also described. The results indicate that significant improvement in classification accuracy can be achieved.
A number of problems which arise when working with segmentation data are also reported and discussed. These problems appear to be different enough from those encountered in pixel classifications to be worth describing in greater detail. The paper concludes with the lines of research being pursued to circumvent these problems and to further increase the fidelity of the segmentation results.},
publisher = {Taylor \& Francis},
url = {https://www.tandfonline.com/doi/abs/10.1080/10106049209354380},
isbn = {},
doi = {10.1080/10106049209354380},
mypdf = {13},
address = {},
keywords = {},
openpdf = {},
openid = {Belaid 1992}
}
[Bea1989a] “Hierarchy in Picture Segmentation: a Stepwise Optimization Approach,”
Beaulieu Jean-Marie, Moris Goldberg,
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, iss. 2, p. 150–163, 1989.
[PDF]   [URL]   [DOI]   [.. More]   [Bibtex]   [Abstract]  
A segmentation algorithm based on sequential optimization which produces a hierarchical decomposition of the picture is presented. The decomposition is data driven with no restriction on segment shapes. It can be viewed as a tree, where the nodes correspond to picture segments and where links between nodes indicate set inclusions. Picture segmentation is first regarded as a problem of piecewise picture approximation, which consists of finding the partition with the minimum approximation error. Then, picture segmentation is presented as an hypothesis-testing process which merges only segments that belong to the same region. A hierarchical decomposition constraint is used in both cases, which results in the same stepwise optimization algorithm. At each iteration, the two most similar segments are merged by optimizing a stepwise criterion. The algorithm is used to segment a remote-sensing picture, and illustrate the hierarchical structure of the picture
@Article{Bea1989a,
author = {Beaulieu, Jean-Marie and Goldberg, Moris},
title = {Hierarchy in Picture Segmentation: a Stepwise Optimization Approach},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume = {11},
number = {2},
pages = {150--163},
year = {1989},
month = {},
abstract = {A segmentation algorithm based on sequential optimization which produces a hierarchical decomposition of the picture is presented. The decomposition is data driven with no restriction on segment shapes. It can be viewed as a tree, where the nodes correspond to picture segments and where links between nodes indicate set inclusions. Picture segmentation is first regarded as a problem of piecewise picture approximation, which consists of finding the partition with the minimum approximation error. Then, picture segmentation is presented as an hypothesis-testing process which merges only segments that belong to the same region. A hierarchical decomposition constraint is used in both cases, which results in the same stepwise optimization algorithm. At each iteration, the two most similar segments are merged by optimizing a stepwise criterion. The algorithm is used to segment a remote-sensing picture, and illustrate the hierarchical structure of the picture},
publisher = {},
url = {https://ieeexplore.ieee.org/document/16711},
isbn = {0162-8828},
doi = {10.1109/34.16711},
mypdf = {12},
address = {},
keywords = {computerised picture processing; data structure; hierarchical decomposition; iterative methods; optimisation; picture segmentation; sequential optimization; stepwise optimization; tree; trees (mathematics); nw-05},
openpdf = {},
openid = {}
}
[Coh1980] “The Modeling and Generation of Visual Textures,”
Cohen Paul, Jean-Marie Beaulieu,
Canadian Electrical Engineering Journal, vol. 5, iss. 3, p. 5–8, 1980.
[URL]   [Bibtex]   [Abstract]  
Describes two methods of generating artificial textures, based on a second order statistical model. By choosing the correct model parameters, these methods make it possible to obtain textures with given statistical properties (granularity, homogeneity, periodicity, desired directions). Such artificial textures are a useful tool both in analyzing the stochastic structure of real images and in studying the discriminatory power of the eye.
@Article{Coh1980,
author = {Cohen, Paul and Beaulieu, Jean-Marie},
title = {The Modeling and Generation of Visual Textures},
journal = {Canadian Electrical Engineering Journal},
volume = {5},
number = {3},
pages = {5--8},
year = {1980},
month = {},
abstract = {Describes two methods of generating artificial textures, based on a second order statistical model. By choosing the correct model parameters, these methods make it possible to obtain textures with given statistical properties (granularity, homogeneity, periodicity, desired directions). Such artificial textures are a useful tool both in analyzing the stochastic structure of real images and in studying the discriminatory power of the eye.},
publisher = {},
url = {Google Scholar},
isbn = {},
doi = {},
mypdf = {},
address = {},
keywords = {},
openpdf = {},
openid = {Cohen 1980}
}

Thesis

[ElM2012] “Segmentation, Regroupement et Classification pour l’Analyse d’Image Polarimétrique Radar,”
El Mabrouk Abdelhai, Msc,
Master Thesis, Département d’Informatique et de Génie Logiciel, Université Laval, 2012.
[URL]   [Bibtex]  
@phdthesis{ElM2012,
author = {El Mabrouk, Abdelhai},
title = {Segmentation, Regroupement et Classification pour l'Analyse d'Image Polarim{\'e}trique Radar},
school = {Universit{\'e} Laval},
dept = {D{\'e}partement d'Informatique et de G{\'e}nie Logiciel},
degree = {Msc},
thesis = {Master},
address = {},
pages = {},
year = {2012},
month = {},
publisher = {Universit{\'e} Laval},
url = {Google Scholar},
isbn = {},
doi = {},
wdown = {},
mypdf = {},
openpdf = {},
openid = {ElMabrouk 2012a}
abstract = {},
keywords = {}}
[Bea1984] “Hierarchical Picture Segmentation by Step-Wise Optimization,”
Beaulieu Jean-Marie, Ph.D.,
PhD Thesis, Electrical Engineering, University of Ottawa (Canada)., 1984.
[URL]   [Bibtex]  
@phdthesis{Bea1984,
author = {Beaulieu, Jean-Marie},
title = {Hierarchical Picture Segmentation by Step-Wise Optimization},
school = {University of Ottawa (Canada).},
dept = {Electrical Engineering},
degree = {Ph.D.},
thesis = {PhD},
address = {},
pages = {},
year = {1984},
month = {},
publisher = {University of Ottawa (Canada).},
url = {Google Scholar},
isbn = {},
doi = {},
wdown = {},
mypdf = {},
openpdf = {},
openid = {Beaulieu 1984}
abstract = {},
keywords = {nw-01}}

In Book

[Min1998] “An object indexing methodology as support to object recognition,”
Mineau Guy W, Mounsif Lahboub, Jean-Marie Beaulieu,
in Advances in Artificial Intelligence, Université Laval, Springer Berlin Heidelberg, 1998, pp. 72-85.
[URL]   [DOI]   [Bibtex]  
@incollection{Min1998,
author = {Mineau, Guy W and Lahboub, Mounsif and Beaulieu, Jean-Marie},
title = {An object indexing methodology as support to object recognition},
booktitle = {Advances in Artificial Intelligence},
editor = {},
publisher = {Springer Berlin Heidelberg},
address = {Universit{\'e} Laval},
pages = {72-85},
year = {1998},
month = {},
url = {SpringerLink},
isbn = {},
doi = {10.1007/3-540-64575-6_41},
mypdf = {},
openpdf = {},
openid = {Mineau 1998}
abstract = {This paper presents an object recognition methodology which uses a step-by-step discrimination process. This process is made possible by the use of a classification structure built over examples of the objects to recognize. Thus, our approach combines numerical vision (object recognition) with conceptual clustering, showing how the latter helps the former, giving another example of useful synergy among different AI techniques. It presents our application domain: the recognition of road signs, which must support semi-autonomous vehicles in their navigational task. The discrimination process allows appropriate actions to be taken by the recognizer with regard to the actual data it has to recognize the object from: light, angle, shading, etc., and with regard to its recognition capabilities and their associated cost. Therefore, this paper puts the emphasis on this multiple criteria adaptation capability, which is the novelty of our approach.},
keywords = {}}
[Bea1989b] “Segmentation of Range Images by Piecewise Approximation with Shape Constraints,”
Beaulieu Jean-Marie, Pierre Boulanger,
in Computer Vision and Shape Recognition, World Scientific Pub Co Inc, 1989, p. 87.
[URL]   [Bibtex]  
@incollection{Bea1989b,
author = {Beaulieu, Jean-Marie and Boulanger, Pierre},
title = {Segmentation of Range Images by Piecewise Approximation with Shape Constraints},
booktitle = {Computer Vision and Shape Recognition},
editor = {},
publisher = {World Scientific Pub Co Inc},
address = {},
pages = {87},
year = {1989},
month = {},
url = {Google Scholar},
isbn = {},
doi = {},
mypdf = {},
openpdf = {},
openid = {Beaulieu 1989}
abstract = {},
keywords = {}}
[Bea1989c] “Segmentation Hiérarchique de l’Image par Optimisation Séquentielle,”
Beaulieu Jean-Marie,
in Télédétection et Gestion des Ressources, Association Québécoise de Télédétection, Québec, 1989, pp. 245-251.
[Bibtex]  
@incollection{Bea1989c,
author = {Beaulieu, Jean-Marie},
title = {Segmentation Hi{\'e}rarchique de l'Image par Optimisation S{\'e}quentielle},
booktitle = {T{\'e}l{\'e}d{\'e}tection et Gestion des Ressources},
editor = {},
publisher = {Association Qu{\'e}b{\'e}coise de T{\'e}l{\'e}d{\'e}tection, Qu{\'e}bec},
address = {},
pages = {245-251},
year = {1989},
month = {},
url = {},
isbn = {},
doi = {},
mypdf = {},
openpdf = {},
openid = {Beaulieu 1989}
abstract = {},
keywords = {}}
[Bea1985] “Selection of Segment Similarity Measures for Hierarchical Picture Segmentation,”
Beaulieu Jean-Marie, M Goldberg,
in Computer-Generated Images, Springer, 1985, pp. 87-97.
[URL]   [Bibtex]  
@incollection{Bea1985,
author = {Beaulieu, Jean-Marie and Goldberg, M},
title = {Selection of Segment Similarity Measures for Hierarchical Picture Segmentation},
booktitle = {Computer-Generated Images},
editor = {},
publisher = {Springer},
address = {},
pages = {87-97},
year = {1985},
month = {},
url = {https://link.springer.com/chapter/10.1007/978-4-431-68033-8_8},
isbn = {},
doi = {},
mypdf = {},
openpdf = {},
openid = {Beaulieu 1985}
abstract = {The problem of defining appropriate segment similarity measures for picture segmentation is exmained. In agglomerative hierqarchical segmentation, two segments are coamapared and merged if found similar. The propesed Hierarchical Step-Wise Optimization (HSWO) algorithm finds and then merges the two most similar segements, on a step-by-step basis. By considering picture segmentation as a piece-wise picture approximation problem, the similarity measure (or the step-wise criterion) is related to the overall approximation error. The measure then corresponds to the increase of the approximation error resulting from merging two segments. Similarity measures derived from constant approximations (zeroth order polynomials) and planar approximations (first order polynomials). An adaptive measurebased upon local variance is also used. The advantages of combining similarity measures (or cirteria) are also stressed. Different picture areas can require different measures which must therefore be combined in order to obtain good overall results. Moreover, in hierarchical segmentation, simple measures can be used for the first merging steps, while, at a higher level of the segment hierarchy, more complex measures can be employed.},
keywords = {Hierarchical segmentation; Similarity measures; Clustering}}