Séminaires sur la télédétection

dans le groupe TII

Organisation : Florence Tupin

---

---

Prochain Séminaire

•   Mardi 5 juin 2012, 11h, salle C46  (Barrault) :
  

           Intervenant: Christian Heipke (université de Hannovre)
         Sujet :  

Abstract:

Image analysis can be defined as the automatic derivation of an explicit and meaningful description of the object scene depicted in the images. For this purpose, individual objects must be recognized and described. This recognition needs prior knowledge of objects in terms of models, which must be made available to the machine. Alternatively, they can also be learnt in a first step of the process itself.
    The set up of the object models is a major problem of image analysis. At present, it is still not clear, which elements of an object and scene description need to be taken into account. Recently, more and more statistical methods are used in knowledge acquisition and representation. Presently, these attempts are still provisional, however it is obvious that an efficient automatic generation of models is a decisive prerequisite for the success of image analysis altogether.
    Another possibility for introducing a priori knowledge is based on the assumption that images are normally analysed for a certain purpose, pre-defined at least in its main features. In GIS, for example, the available information is described in object catalogues, which contain relevant information for formulating the object models for image analysis. Available GIS data may also be used as part of the knowledge base.
    In this talk, I will give an overview of the research in photogrammetry and remote sensing, and in image analysis in particular, our group in Hannover has conducted over the last years. Examples will comprise work on road extraction from high-resolution images using snakes, level sets and normalised cut segmentation, multi-temporal classification of satellite images based on conditional random fields, automatic quality control of topographic data using aerial and satellite images, and the integration of vector and height data to generate a consistent 3D topographic database.

---

Précédents Séminaires

Mardi 24 avril 2012, 11h, salle C48  (Barrault) (organisation Michel Roux):
           Intervenant: Yuilya Tarabalka (INRIA, équipe Ayin)
         Sujet :   Hierarchical models and algorithms for classification of very high
                          resolution remote sensing images

Abstract:
The very high spatial, spectral and temporal resolution of the last generation of imaging sensors provides rich information for every pixel in a particular scene at different time moments, hence increasing the ability to distinguish physical structures in the scene. However, the large number of spectral channels, as well as frequent time series, present challenges for image classification. While pixelwise classification techniques process each pixel independently without considering information about spatial structures, further improvements can be achieved by the incorporation of spatial information in a classifier, especially in areas where structural information is important to distinguish between classes.

In this talk, we will present novel strategies for spectral-spatial classification of remote sensing images. We will focus on discussing new hierarchical graph-based models for classification of hyperspectral data. In particular, we will discuss new dissimilarity measures between image regions and convergence criteria. We will show that the new techniques improve classification accuracies and provide classification maps with more homogeneous regions, when compared to previously proposed methods. Finally, we will show that our designed model can be successfully adapted and applied for multitemporal image classification.

•   Lundi 6 février 2012, à 12h, salle C48 (Barrault) : séminaire groupe TII
  

           Intervenant: Hélène Sportouche
         Sujet :   Comparaison entre la loi de Fisher et la loi Gamma Généralisée
                          pour la modélisation statistique d’images radar et étude des
                          phénomènes de mimiques à partir d'une méthode basée sur les log-cumulants.

•   Vendredi 23 septembre 2011, à 10h, salle C46 (Barrault) :

           Intervenant: Lorenzo Bruzzone (Univ. of Trento, Italy)
         Sujet :   Current and Future Trends in Automatic Classification
                          of Remote Sensing Images

•   Mardi 27 septembre 2011, à 10h, salle C48 (Barrault) :

           Intervenant: Lorenzo Bruzzone (Univ. of Trento, Italy)
         Sujet :   Challenges in Change Detection on Multitemporal
                          VHR Optical and SAR Images

•   Vendredi 10 juin 2011, à 12h30, salle C46 (Barrault) :

           Intervenant: Jean-Marie Nicolas
         Sujet :   Les statistiques de Mellin appliquées à l'analyse
                          du chatoiement et des textures en imagerie cohérente

•   Vendredi 8 avril 2011, à 12h30, salle C46 (Barrault) :

           Intervenant: Andres Almanza
         Sujet :   Methodes variationnelles, harmoniques et a contrario en télédetection
          
Dans une première partie de cette présentation je vais passer en revue très brièvement l'ensemble de mon activité en télédetection. D'un point de vue méthodologique des techniques recurrentes sont l'utilisation de méthodes variationnelles, et l'analyse non-harmonique pour obtenir des solutions très pécises, ainsi que des méthodes a contrario pour l'extraction de primitives géométriques assurant un taux de fausses détection très faible.
Dans une deuxième partie je vais me concentrer sur deux applications rélativement récentes qui illustrent ces deux aspects méthodologiques:
(i) La mise en correspondence de paires stéréoscopiques à faible rapport b/h
(ii) L'elimination d'outliers dans le domaine spatial des images SMOS, qui ont la particularité d'être échantillonnées dans un domaine étoilé en Fourier et sur un réseau hexagonal.