Description
Date depot: 1 janvier 1900
Titre: Satellite Image Sequences Analysis using 3D Clustering
Directrice de thèse:
Maria TROCAN (LISITE)
Directeur de thèse:
Jérémie SUBLIME (LISITE)
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Non defini
Resumé:
With the booming number of available satellite images and data, the automatic interpretation of remotely sensed images has become an increasingly active domain [1]. With sensors now capable of getting images at very high resolution (VHR), it is more and more difficult to design algorithms and methods able to efficiently process such data in a reasonable amount of time. Such process usually contains two steps: (1) a segmentation step that consists in grouping together connected groups of pixels with the goal of finding homogeneous segments; (2) a spatial-temporal clustering step, wherein the segmented objects are analyzed in order to create groups of 3D similar elements.
With the recent progress in satellite imaging, there are several possible levels of interest in a very high resolution satellite image [2]: firstly, we can usually distinguish three main types of objects, namely water bodies, vegetation areas and urban areas. At a second level we can separate different types of urban blocs, different types of vegetation areas, and start to distinguish elements such as roads.
Following the evolution of such objects in time is an emerging problem with a wide range of applications, such as predicting the evolution of urban areas, monitoring the evolution of crops culture. Furthermore, more global issues can be analyzed, such as assessing deforestation phenomenon through time or predicting the long-term effects of natural disasters (for example, hurricanes, flash flood or droughts).
Doctorant.e: Kalinicheva Ekaterina