Friday, September 12, 2014

[beasiswa] [info] PhD studentship: Large scale semantization of 3D urban mesh models

 

The IMAGINE group at Ecole des Ponts - ParisTech, Marne-la-Vallée (France) is recruiting a PhD student  to work on a project on large scale semantization of 3D urban mesh models. The student will be co-advised by Guillaume Obozinski , Nikos Komodakis and Olivier Tournaire (see contacts lists for details).          RESEARCH TOPIC      Digital 3D models of urban landscape provide today an essential tool for city design studies. They are notably used by local administrations and authorities, by design offices, architects and urban planners, to model traffic, acoustics,  the diffusion of pollutants in a city, or to optimize solar panel location choices, etc.       Most 3D maps are however at this point essentially unstructured 3D meshes on which texture is reprojected, so that they only encode the geometry and the appearance of the scene. While some high level semantic description is encoded in some geographic information systems (GIS), it may be difficult to put it in correspondence with the map, and such information is typically lacking in many developing countries. Furthermore, detailed semantic annotation or segmentation of the map is crucially lacking to describe the different material and partition the urban scene into its different constituents.  Such semantic annotations are essential for most of the applications mentioned above.      IMAGINE is a common research project between Ecole des Ponts and the Centre Scientifique et Technique du Bâtiment (Center for Building Science) that focusses on semantized reconstruction of buildings.      A certain amount of research has been conducted in the team on the problem of inference of the semantics of 3D point clouds and 3D model of buildings, mostly with techniques based on deterministic grammars.          The objective of this PhD project is to tackle this problem on the urban scale with graphical model and inference techniques. The challenges are not only to work on a larger scale (a whole neighborhood or a whole city), but also to be able to predict a broader diversity of semantic labels.      TEAM:      IMAGINE is both a project that focusses on 3D reconstruction and semantized reconstruction of buildings and a research group with a broader expertise in computer vision, stereo vision and machine learning. It is affiliated with the Computer Science department of Université Paris-Est and with one of the most prestigious french engineering school Ecole des Ponts which is part of the ParisTech group.      http://imagine.enpc.fr/index.html      The lab is located on the campus of Cité Descartes in Champs-sur-Marne,  20 minutes by RER East of Paris. This campus is a common campus for Université Paris-Est Marne-la-Vallée, three engineering schools namely Ecole des Ponts, Ecole Nationale des Sciences Géographiques and ESIEE, an architecture school ENSA VT and the IFFSTAR research institute.          APPLICANT PROFILE:      Prospective applicants should have   - a Master degree in science in computer science, applied math or electrical engineering  with a strong emphasis in machine learning and/or computer vision and some knowledge of optimization theory.  - strong programming skills, including in C++.  - Familiarity with photogrammetry, 3D reconstruction techniques or algorithmic geometry would be a plus but is not necessary.      CONTACTS:      To apply or for more information please contact Nikos Komodakis, Olivier Tournaire or Guillaume Obozinski (see contact information below)      Nikos Komodakis   nikos.komodakis@imagine.enpc.fr  http://cvc-komodakis.centrale-ponts.fr/      Guillaume Obozinski   guillaume.obozinski@imagine.enpc.fr  http://imagine.enpc.fr/~obozinsg/      Olivier Tournaire   olivier.tournaire@cstb.fr  http://recherche.ign.fr/labos/matis/~tournaire

__._,_.___

Posted by: Tri Kurniawan Wijaya <trikurniawanwijaya@yahoo.com>
Reply via web post Reply to sender Reply to group Start a New Topic Messages in this topic (1)
INFO, TIPS BEASISWA, FAQ - ADS:
http://id-scholarships.blogspot.com/

===============================

INFO LOWONGAN DI BIDANG MIGAS:
http://www.lowongan-kerja.info/lowongan/oil-jobs/

===============================

INGIN KELUAR DARI MILIS BEASISWA?
Kirim email kosong ke beasiswa-unsubscribe@yahoogroups.com

.

__,_._,___