Loading...
 
[Show/Hide Left Column]

Tracker Item History Help

Close
warningNot logging
Tracker changes are not being logged: Go to Action log admin to enable

Version Date User Field ID Field Old New
7 14:32 182 Work program The stages of the thesis are the following:
• Bibliography study concerning sparse and dense features matching in computer vision
• Graph matching/tracking under geometric changes and large illumination changes using the features points proposed in Setkov13
• Cumulative methods for registration and structure detection
• Comparison of the methods, and improvements: use of temporal prediction, optimization on GPU/CPU, etc

The stages of the thesis are the following:
  • Bibliography study concerning sparse and dense features matching in computer vision
  • Graph matching/tracking under geometric changes and large illumination changes
  • Cumulative methods for registration and structure detection
  • Adaptation to the context
  • Experiments
  • Report writting

7 14:32 183 Objectives The global static system is composed of a standard projector, one or several cameras (RGB+ depth), and a desktop with high memory/computing resources. Its roles are :
• to construct the 3D model of the scene to be augmented by structured light techniques, i.e. by projecting a known pattern and computing its distortions after projection (registration)
• to project a virtual wall. It will adapt its projection photometrically and geometrically for enhanced visualization on everyday surfaces
• to detect the presence of users in the scene by background subtraction techniques
• to track the users in order to predict their trajectories
The interaction with smartphones can be made at several levels: 1) gesture recognition for selecting, displaying or drawing new items on the virtual wall; 2) exploring inside the wall, by projecting of a 3D virtual world of data; 3) picking, sharing multimedia data by transmission of data inside the virtual wall.
The thesis will focus on feature matching which is a core aspect of several image processing algorithms, the objective is to provide some clear conclusions concerning the comparison between sparse and dense matching methods. Main stages:
1) a theoretical and bibliographic study: analyzing the trends in the domain, determining comparison criteria in terms of noise sensitivity, illumination invariance, errors, complexity.
2) study on several problems among which motion analysis (egomotion), tracking and 3D reconstruction (from stereovision or structure from motion. Examples of methodologies: sparse feature matching using feature graph matching, dense (or semi-dense) matching with cumulative techniques Bouchafa 12 or tensor-based techniques Laguzet 13.
3) A study will be made to automatically switch the type of features and/or the matching method (i.e. sparse/dense feature matching) depending on the knowledge acquired from the context.
4) Experiments in interaction and SAR

7 14:32 184 Prerequisite Some knowledges about image processing and 3D geometry are required. The student has to be able to program in C/C++.
Some knowledge about image processing and 3D geometry are required. The student has to be able to program in C/C++.
7 14:32 185 Extra information Bouchafa12 Samia Bouchafa, Bertrand Zavidovique: c-Velocity: A Flow-Cumulating Uncalibrated Approach for 3D Plane Detection. International Journal of Computer Vision 97(2): 148-166 (2012)
Setkov 13 A. Setkov, M. Gouiffès and C. Jacquemin. Color Invariant Feature Matching For Image Geometric
Correction. ACM Mirage 2013

Bouchafa12 Samia Bouchafa, Bertrand Zavidovique: c-Velocity: A Flow-Cumulating Uncalibrated Approach for 3D Plane Detection. International Journal of Computer Vision 97(2): 148-166 (2012)
Setkov 13 A. Setkov, M. Gouiffès and C. Jacquemin. Color Invariant Feature Matching For Image Geometric
Correction. ACM Mirage 2013
Laguzet13 Color tracking for contextual switching: Real-time implementation on CPU F.Laguzet, A.Romero, M.Gouiffès, L.Lacassagne, D.Etiemble JRTIP2013
6 14:32 181 Context The project focuses on collaborative Spatial Augmented Reality (SAR, or projector-based AR), using two modalities: a global context-aware SAR system and several mobile devices. Through mobile pads/smartphones equipped with a pico-projector, mobile AR can include both SAR and(monitor-based AR), and becomes increasingly ubiquitous. Using the camera of a portable device can provide the user with a portable smart projector unit. Moreover, the various onboard sensors of smart mobile devices such as accelerometer, camera, compass, and multi-touch screen combined with wireless network capabilities makes such devices a perfect tool to interact with an AR system. The project aims to make SAR more reactive by offering more input channels by analyzing the scene (geometry, color) and users’ behaviors. It will make SAR more collaborative and ubiquitous, allowing multiple people to jointly interact and share different content.
The PhD work will be a part of a more global project on Spatial Augmented Reality (SAR, or projector-based AR) and on human-computer interaction using several modules: a global context-aware SAR system, gesture analysis, several mobile devices (when available). SAR consists in adapting a videoprojection to the properties of the surface, relying on smart projectors, i.e. enhanced with sensors to gain information about the environment. These systems can be static or mobile (on smartphones for example). The works lead by the team AMI aim to make the SAR system more reactive by offering more input channels through image analysis techniques (scene analysis and users’ behaviors) and more interactive. Real-time 3D reconstruction and motion analysis will allow users to be recognized by the system. Finally, SAR should become more collaborative and ubiquitous by allowing multiple people to jointly interact through gesture (selecting, displaying or drawing) or through their mobile devices.
5 14:32 179 Subject Sparse vs. dense matching for spatial augmented reality
Sparse vs. dense matching. Application to interaction and spatial augmented reality.
4 14:32 190 Year 2013 2014
4 14:32 192 Starting October 2013 October 2014
3 14 Jun 2013 12:33 michele.gouiffes 188 Co-advisors Michèle Gouiffès (LIMSI) gouiffes at limsi.fr
Samia Bouchafa
Samia Bouchafa
2 28 May 2013 12:28 stephanie.druetta 178 Thesis advisor ZTest-Encadrant GOUIFFES Michèle
1 28 May 2013 12:04 michele.gouiffes 178 Thesis advisor ZTest-Encadrant

Ecole Doctorale Informatique Paris-Sud


Directrice
Nicole Bidoit
Assistante
Stéphanie Druetta
Conseiller aux thèses
Dominique Gouyou-Beauchamps

ED 427 - Université Paris-Sud
UFR Sciences Orsay
Bat 650 - aile nord - 417
Tel : 01 69 15 63 19
Fax : 01 69 15 63 87
courriel: ed-info at lri.fr