|
|
Publications about Bayesian
Result of the query in the list of publications :
2 Articles |
1 - Looking for shapes in two-dimensional, cluttered point clouds.
A. Srivastava and I. H. Jermyn. IEEE Trans. Pattern Analysis and Machine Intelligence, 31(9): pages 1616-1629, September 2009.
Keywords : Shape, Bayesian, Point cloud, Diffeomorphism, Sampling, Fisher-Rao.
Copyright : ©2008 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
@ARTICLE{SrivastavaJermyn09,
|
| author |
= |
{Srivastava, A. and Jermyn, I. H.}, |
| title |
= |
{Looking for shapes in two-dimensional, cluttered point clouds}, |
| year |
= |
{2009}, |
| month |
= |
{September}, |
| journal |
= |
{IEEE Trans. Pattern Analysis and Machine Intelligence}, |
| volume |
= |
{31}, |
| number |
= |
{9}, |
| pages |
= |
{1616-1629}, |
| url |
= |
{http://dx.doi.org/10.1109/TPAMI.2008.223}, |
| pdf |
= |
{http://www-sop.inria.fr/members/Ian.Jermyn/publications/SrivastavaJermyn09.pdf}, |
| keyword |
= |
{Shape, Bayesian, Point cloud, Diffeomorphism, Sampling, Fisher-Rao} |
| } |
Abstract :
We study the problem of identifying shape classes in point clouds. These clouds contain sampled contours and are
corrupted by clutter and observation noise. Taking an analysis-by-synthesis approach, we simulate high-probability configurations of
sampled contours using models learnt from training data to evaluate the given test data. To facilitate simulations, we develop statistical
models for sources of (nuisance) variability: (i) shape variations within classes, (ii) variability in sampling continuous curves, (iii) pose
and scale variability, (iv) observation noise, and (v) points introduced by clutter. The variability in sampling closed curves into finite
points is represented by positive diffeomorphisms of a unit circle. We derive probability models on these functions using their squareroot
forms and the Fisher-Rao metric. Using a Monte Carlo approach, we simulate configurations from a joint prior on the shape-sample
space and compare them to the data using a likelihood function. Average likelihoods of simulated configurations lead to estimates of
posterior probabilities of different classes and, hence, Bayesian classification. |
|
2 - A higher-order active contour model of a ‘gas of circles' and its application to tree crown extraction.
P. Horvath and I. H. Jermyn and Z. Kato and J. Zerubia. Pattern Recognition, 42(5): pages 699-709, May 2009.
Keywords : Shape, Higher-order, Active contour, Gas of circles, Tree Crown Extraction, Bayesian.
@ARTICLE{Horvath09,
|
| author |
= |
{Horvath, P. and Jermyn, I. H. and Kato, Z. and Zerubia, J.}, |
| title |
= |
{A higher-order active contour model of a ‘gas of circles' and its application to tree crown extraction}, |
| year |
= |
{2009}, |
| month |
= |
{May}, |
| journal |
= |
{Pattern Recognition}, |
| volume |
= |
{42}, |
| number |
= |
{5}, |
| pages |
= |
{699-709}, |
| url |
= |
{http://dx.doi.org/10.1016/j.patcog.2008.09.008}, |
| pdf |
= |
{http://www-sop.inria.fr/members/Ian.Jermyn/publications/Horvathetal09.pdf}, |
| keyword |
= |
{Shape, Higher-order, Active contour, Gas of circles, Tree Crown Extraction, Bayesian} |
| } |
Abstract :
We present a model of a ‘gas of circles’: regions in the image domain composed of a unknown
number of circles of approximately the same radius. The model has applications
to medical, biological, nanotechnological, and remote sensing imaging. The model is constructed
using higher-order active contours (HOACs) in order to include non-trivial prior
knowledge about region shape without constraining topology. The main theoretical contribution
is an analysis of the local minima of the HOAC energy that allows us to guarantee
stable circles, fix one of the model parameters, and constrain the rest. We apply the model
to tree crown extraction from aerial images of plantations. Numerical experiments both
confirm the theoretical analysis and show the empirical importance of the prior shape information. |
|
 top of the page
Technical and Research Report |
1 - Classification of very high resolution SAR images of urban areas.
A. Voisin and V. Krylov and G. Moser and S.B. Serpico and J. Zerubia. Rapport de recherche 7758, INRIA, October 2011.
Keywords : Synthetic Aperture Radar (SAR) image, Supervised classification, Bayesian, finite mixture models, hierarchical Markov random fields, wavelet.
@TECHREPORT{RR-7758,
|
| author |
= |
{Voisin, A. and Krylov, V. and Moser, G. and Serpico, S.B. and Zerubia, J.}, |
| title |
= |
{Classification of very high resolution SAR images of urban areas}, |
| year |
= |
{2011}, |
| month |
= |
{October}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Rapport de recherche}, |
| number |
= |
{7758}, |
| url |
= |
{http://hal.inria.fr/docs/00/63/10/38/PDF/RR-7758.pdf}, |
| keyword |
= |
{Synthetic Aperture Radar (SAR) image, Supervised classification, Bayesian, finite mixture models, hierarchical Markov random fields, wavelet} |
| } |
Résumé :
Dans le cadre d’une approche face aux risques environnementaux, nous proposons une nouvelle méthode de classification bayésienne supervisée. Celle-ci combine une modélisation statistique des images avec une prise en compte contextuelle via des champs de Markov hiérarchiques. Ce rapport de recherche vise à détailler plus amplement cette modélisation contextuelle, à savoir expliciter le modèle mathématique sur quad-arbre et l’obtention des observations par décomposition en ondelettes de l’image originale. Il met également en exergue certaines modifications apportées en
vue d’améliorer la classification finale. |
Abstract :
In the framework of the assessment of environmental risks, we propose herein a new supervised Bayesian classification method. It combines statistical image modeling with a contextual approach via hierarchical Markov random fields. This research report aims to further focus on this kind of contextual classification approach by detailing both the quad-tree mathematical model and the statistics of the observations, obtained by wavelet transform. We therefore introduce modifications to a classical Markovian single-scale algorithm that lead to more accurate classification results. |
|
top of the page
These pages were generated by 
|
get the bibtex
