| PhD, INRIA Sophia AntipolisKeywords: Remote Sensing, Synthetic Aperture Radar, Markov Random Fields, Hierarchical Classification, Change Detection, Data Fusion, Satellite Image Time Series.
Contact: |
 |
Abstract:
My Ph.D. research activity will address the problem of unsupervised change detection with EO data acquired by multiple and heterogeneous sensors (both multispectral and SAR) and at multiple spatial resolutions. In this framework, two methods will be developed and experimentally validated with real data, in particular with time series when available.
The first approach will consist in the extension of recent methods proposed in [Serpico12b, Voisin12]. These methods focus on multisensor and multiscale remote sensing classification using hierarchical MRFs and multivariate copulas. Here, these methods will be extented to, first, include an anisotropic Potts MRF model with an adaptive neighborhood, which will enable to take into account the local geometry of a given class. This aspect is particularly important for VHR images, for which geometrical entities such as, e.g., roads, rivers, or buildings, can be visible. The main idea is not to consider a simple 8-pixel (second order) neighborhood, but to use a dictionary of possible neighborhoods and to choose the one that leads to the highest local energy during the optimization step (within a “maximum a posteriori” Bayesian criterion). Another interesting evolution of this method is to propose a new hierarchical graph model: for this purpose, different possibilities will be investigated, in particular, involving quad-trees on regions.
The second approach will extend some of the recent methods proposed in [Serpico12b, Cianci12]. These methods separately focused on unsupervised change detection with single-polarization VHR SAR and with multisensor optical-SAR imagery, and were based on MRF models. Here, these approaches will be integrated and extended to also support input data at multiple resolutions, as well as multichannel (i.e., multipolarization and/or multifrequency) SAR images. The goal will be to develop a flexible and accurate technique that can support the identification of changes from a pair of multitemporal observations taken from multiple sensors and at multiple resolutions. For this purpose, a multiresolution MRF model, will be extended to the case of multitemporal and multisensor data and integrated within the aforementioned recent methods.
[Voisin12] A. Voisin, V. Krylov, G. Moser, S. B. Serpico, and J. Zerubia, “Classification of multi-sensor remote sensing images using an adaptive hierarchical Markovian model,” European Signal Processing Conference (EUSIPCO’12), Bucharest (Romania), August 27-31, 2012.
[Serpico12a] S. B. Serpico, S. Dellepiane, G. Boni, G. Moser, E. Angiati, and R. Rudari, “Information Extraction from Remote Sensing Images for Flood Monitoring and Damage Evaluation,” Proceedings of the IEEE, 2012, in print.
[Serpico12b] S. B. Serpico, L. Bruzzone, G. Corsini, W. J. Emery, P. Gamba, A. Garzelli, G. Mercier, J. Zerubia, N. Acito, B. Aiazzi, F. Bovolo, F. Dell’Acqua, M. De Martino, M. Diani, V. Krylov, G. Lisini, C. Marin, G. Moser, A. Voisin, C. Zoppetti, “Development and validation of multitemporal image analysis methodologies for multirisk monitoring of critical structures and infrastructures,” IEEE Geoscience and Remote Sensing Symposium, Munich, Germany, 2012.
[Cianci12] Luca Cianci, Gabriele Moser, and Sebastiano B. Serpico, “Change detection from very high-resolution multisensor remote sensing images by a Markovian approach,” in Proc. of GOLD conference, Roma, Italy, 2012.
Short Bio:
I am a PhD. candidate in computational and Applied Mathematics in cotutelle between the university of Nice Sophia-Antipolis (The French National Institute for Research in Information and Communication Sciences and Technologies(INRIA), France) and university of Genoa (Naval, Electrical, Electronic and Telecommunication Engineering department(DITEN), Italy).
Last publications:
2019
Conference papers
- ref_biblio
- Alessandro Montaldo, Luca Fronda, Ihsen Hedhli, Gabriele Moser, Sebastiano B. Serpico, et al.. Causal Markov mesh hierarchical modeling for the contextual classification of multiresolution satellite images. ICIP 2019 – IEEE International Conference on Image Processing, Sep 2019, Taipei, Taiwan. ⟨hal-02157081⟩
- Accès au texte intégral et bibtex
-
- ref_biblio
- Alessandro Montaldo, Luca Fronda, Ihsen Hedhli, Gabriele Moser, Josiane Zerubia, et al.. Joint classification of multiresolution and multisensor data using a multiscale Markov mesh model. IGARSS 2019 – IEEE International Geoscience and Remote Sensing Symposium, Jul 2019, Yokohama, Japan. ⟨hal-02157082⟩
- Accès au texte intégral et bibtex
-
2018
Journal articles
- ref_biblio
- Ihsen Hedhli, Gabriele Moser, Josiane Zerubia. Nouvelle Méthode en Cascade pour la Classification Hiérarchique Multi-Temporelle ou Multi-Capteur d’Images Satellitaires Haute Résolution. Revue Française de Photogrammétrie et de Télédétection, 2018, 216, pp.3-17. ⟨hal-01632923⟩
- Accès au texte intégral et bibtex
-
Book sections
- ref_biblio
- Jon Atli Benediktsson, Gabriele Cavallaro, Falco Nicola, Ihsen Hedhli, Vladimir Krylov, et al.. Remote sensing data fusion: Markov models and mathematical morphology for multisensor, multiresolution, and multiscale image classification. Mathematical Models for Remote Sensing Image Processing: Models and methods for the analysis of 2D satellite and aerial images, Springer, pp.277-323, 2018, ⟨10.1007/978-3-319-66330-2_7⟩. ⟨hal-01632949⟩
- Accès au bibtex
-
2017
Journal articles
- ref_biblio
- Ihsen Hedhli, Gabriele Moser, Sebastiano Serpico, Josiane Zerubia. Classification of Multisensor and Multiresolution Remote Sensing Images through Hierarchical Markov Random Fields. IEEE Geoscience and Remote Sensing Letters, 2017, 14 (2), pp.2448-2452. ⟨10.1109/LGRS.2017.2768398⟩. ⟨hal-01632907⟩
- Accès au texte intégral et bibtex
-
Conference papers
- ref_biblio
- Ihsen Hedhli, Gabriele Moser, Sebastiano B Serpico, Josiane Zerubia. Multi-resolution Classification of Urban Areas Using Hierarchical Symmetric Markov Mesh Models. IEEE GRS/ISPRS Joint Urban Remote Sensing Event (JURSE), Mar 2017, Dubai, United Arab Emirates. ⟨hal-01415568⟩
- Accès au texte intégral et bibtex
-
2016
Journal articles
- ref_biblio
- Ihsen Hedhli, Gabriele Moser, Josiane Zerubia, Sebastiano B. Serpico. A New Cascade Model for the Hierarchical Joint Classification of Multitemporal and Multiresolution Remote Sensing Data . IEEE Transactions on Geoscience and Remote Sensing, 2016, 54 (11), pp.6333 – 6348. ⟨hal-01308039⟩
- Accès au texte intégral et bibtex
-
Conference papers
- ref_biblio
- Ihsen Hedhli, Gabriele Moser, Sebastiano B. Serpico, Josiane Zerubia. Contextual Multi-Scale Image Classification on Quadtree. IEEE International Conference on Image Processing (ICIP), Sep 2016, Phoenix, United States. ⟨hal-01316611⟩
- Accès au texte intégral et bibtex
-
Theses
- ref_biblio
- Ihsen Hedhli. Hierarchical joint classification models for multi-resolution, multi-temporal and multi-sensor remote sensing images. Application to natural disasters. Other. Université Nice Sophia Antipolis; Università degli studi (Gênes, Italie), 2016. English. ⟨NNT : 2016NICE4006⟩. ⟨tel-01333880⟩
- Accès au texte intégral et bibtex
-
2015
Conference papers
- ref_biblio
- Ihsen Hedhli, Gabriele Moser, Sebastiano B. Serpico, Josiane Zerubia. New hierarchical joint classification method of SAR-optical multiresolution remote sensing data. IEEE European Signal Processing Conference, Aug 2015, Nice, France. ⟨hal-01161824⟩
- Accès au texte intégral et bibtex
-
- ref_biblio
- Ihsen Hedhli, Gabriele Moser, Sebastiano B. Serpico, Josiane Zerubia. New cascade model for hierarchical joint classification of multisensor and multiresolution remote sensing data. IEEE International Geoscience and Remote Sensing Symposium, Jul 2015, Milan, Italy. ⟨hal-01161817⟩
- Accès au texte intégral et bibtex
-
2014
Conference papers
- ref_biblio
- Ihsen Hedhli, Gabriele Moser, Josiane Zerubia, Sebastiano B. Serpico. New cascade model for hierarchical joint classification of multitemporal, multiresolution and multisensor remote sensing data. IEEE ICIP – International Conference on Image Processing, Oct 2014, Paris, France. ⟨hal-01071034⟩
- Accès au texte intégral et bibtex
-
- ref_biblio
- Ihsen Hedhli, Gabriele Moser, Josiane Zerubia, Sebastiano B. Serpico. Fusion of multitemporal and multiresolution remote sensing data and application to natural disasters. IEEE IGARSS – International Geoscience and Remote Sensing Symposium, Jul 2014, Québec, Canada. ⟨hal-01022380⟩
- Accès au texte intégral et bibtex
-
