| PhD, INRIA Sophia AntipolisKeywords: Markov Random Fields, Textural features, Hierarchical classification, Synthetic aperture radar, Data fusion, Urban areas
Contact: |
 |
Abstract:
My PhD deals with the classification of very high resolution SAR images of urban areas, as a support to multi-risk monitoring of these environments (e.g. floodings, earthquakes…). The classification is obtained by combining a statistical modeling of VHR amplitude SAR data – which uses a dictionary-based mixture probability density function (PDF) estimation approach – with a Markov random field (MRF) model, thus allowing to take into account the contextual information.
The algorithm robustness has been increased thanks to the introduction of textural features extracted from the original SAR images and combined to the statistics of the SAR amplitudes by resorting to copulas.
An improvement of this classification algorithm is obtained by using hierarchical MRFs, that aim to take into account multi-scale/multi-sensor images integrated in the hierarchical tree. Such model is based on a quad-tree structure, where each tree scale corresponds to the different input image resolutions. To obtain the classification map, we integrate an exact estimator of the marginal posterior mode.
This PhD is in collaboration with the University of Genoa (Italy). It is financed by the Direction Générale de l’Armement (DGA) and INRIA.
Short Bio:
2009-2012 : PhD student in Ayin team (ex-Ariana) (INRIA Sophia Antipolis, France)
2008-2009 : Master Recherche SIAO (Signal, Image, Acoustics and Optimization) (ENSEEIHT/UPS, Toulouse, France)
2006-2009 : Engineering school ENSEEIHT (Toulouse, France) – Electronics and Signal Processing
Last publications:
2014
Journal articles
- ref_biblio
- Aurélie Voisin, Vladimir Krylov, Gabriele Moser, Sebastiano B. Serpico, Josiane Zerubia. Supervised Classification of Multi-sensor and Multi-resolution Remote Sensing Images with a Hierarchical Copula-based Approach. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52 (6), pp.3346-3358. ⟨10.1109/TGRS.2013.2272581⟩. ⟨hal-00841234⟩
- Accès au texte intégral et bibtex
-
2013
Journal articles
- ref_biblio
- Aurélie Voisin, Vladimir A. Krylov, Gabriele Moser, Sebastiano B. Serpico, Josiane Zerubia. Classification of Very High Resolution SAR Images of Urban Areas Using Copulas and Texture in a Hierarchical Markov Random Field Model. IEEE Geoscience and Remote Sensing Letters, 2013, 10 (1), pp.96-100. ⟨10.1109/LGRS.2012.2193869⟩. ⟨hal-00723280⟩
- Accès au texte intégral et bibtex
-
2012
Conference papers
- ref_biblio
- Vladimir Krylov, Gabriele Moser, Aurélie Voisin, Sebastiano B. Serpico, Josiane Zerubia. Change detection with synthetic aperture radar images by Wilcoxon statistic likelihood ratio test. IEEE International Conference on Image Processing 2012, Sep 2012, Orlando, United States. ⟨hal-00724284⟩
- Accès au texte intégral et bibtex
-
- ref_biblio
- Aurélie Voisin, Vladimir A. Krylov, Gabriele Moser, Sebastiano B. Serpico, Josiane Zerubia. Classification of multi-sensor remote sensing images using an adaptive hierarchical Markovian model. Eusipco – 20th European Signal Processing Conference, Aug 2012, Bucarest, Romania. ⟨hal-00723286⟩
- Accès au texte intégral et bibtex
-
- ref_biblio
- Sebastiano Serpico, Lorenzo Bruzzone, Giovanni Corsini, William J. Emery, Paolo Gamba, et al.. Development and validation of multitemporal image analysis methodologies for multirisk monitoring of critical structures and infrastructures. IEEE IGARSS – International Geoscience and Remote Sensing Symposium, Jul 2012, Munich, Germany. ⟨hal-00729089⟩
- Accès au texte intégral et bibtex
-
- ref_biblio
- Aurélie Voisin, Vladimir Krylov, Gabriele Moser, Sebastiano B. Serpico, Josiane Zerubia. Multiscale classification of very high resolution SAR images of urban areas by Markov random fields, copula functions, and texture extraction. GTTI – Riunione annuale dell’associazione Gruppo nazionale Telecomunicazioni e Tecnologie dell’Informazione, Jun 2012, Cagliari, Italy. ⟨hal-00727404⟩
- Accès au texte intégral et bibtex
-
- ref_biblio
- Aurélie Voisin, Vladimir A. Krylov, Gabriele Moser, Sebastiano B. Serpico, Josiane Zerubia. Multichannel hierarchical image classification using multivariate copulas. IS&T/SPIE Electronic Imaging – Computational Imaging X, Jan 2012, San Francisco, United States. ⟨10.1117/12.917298⟩. ⟨hal-00667187⟩
- Accès au texte intégral et bibtex
-
Theses
- ref_biblio
- Aurélie Voisin. Classification supervisée d’images d’observation de la Terre à haute résolution par utilisation de méthodes markoviennes. Traitement des images [eess.IV]. Université Nice Sophia Antipolis, 2012. Français. ⟨NNT : ⟩. ⟨tel-00747906⟩
- Accès au texte intégral et bibtex
-
