This PhD thesis, conducted in cooperation with ONERA, focuses on active 3D object recognition by an autonomous visual agent. Whereas in passive recognition, acquisition modalities of observations are fixed and may generate ambiguities, active recognition exploits the possibility of controling these modalities online in a sequential inference process in order to remove these ambiguities. The aim of this work is to design, in a statistical learning framework, planning strategies in the acquisition of information while achieving a realistic implementation of active recognition. The first part of the work is dedicated to learning to plan. Two realistic constraints are taken into account : on the one hand, planning with imperfect object modeling...
International audienceA lot of vision applications, for instance in robotics, require id...
The thesis Autonomous 3D Modeling of Unknown Objects for Active Scene Exploration presents an approa...
During the last few years, there has been a growing interest in object recognition schemes directly ...
Cette thèse, réalisée en coopération avec l’ONERA, concerne la reconnaissance active d’objets 3D par...
Cette thèse, réalisée en coopération avec l ONERA, concerne la reconnaissance active d objets 3D par...
This document concerns service robotics for human assistance. A companion robot will have to manipul...
In this work, we examine the literature of active object recognition in the past and present. We not...
This thesis deals with the 3D structure estimation and exploration of static scenes using active vis...
In recognizing 3D objects that are symmetric or similar, ambiguity may occur if the image is taken f...
Perception is the way by which we know the outside world. Thanks to our perceptions we are able to i...
This report deals with the scientific problem of objects visual recognition within an observed scene...
L’analyse d’une scène visuelle devient un passage obligé pour la réalisation d’un grand nombre de sy...
This thesis addresses the problem of how to improve the acquisition of 3D range data with a mobile r...
3D object detection is vital for autonomous driving. However, to train a 3D detector often requires ...
Pour un agent, apprendre une représentation visuelle de façon autonome en environnement ouvert est u...
International audienceA lot of vision applications, for instance in robotics, require id...
The thesis Autonomous 3D Modeling of Unknown Objects for Active Scene Exploration presents an approa...
During the last few years, there has been a growing interest in object recognition schemes directly ...
Cette thèse, réalisée en coopération avec l’ONERA, concerne la reconnaissance active d’objets 3D par...
Cette thèse, réalisée en coopération avec l ONERA, concerne la reconnaissance active d objets 3D par...
This document concerns service robotics for human assistance. A companion robot will have to manipul...
In this work, we examine the literature of active object recognition in the past and present. We not...
This thesis deals with the 3D structure estimation and exploration of static scenes using active vis...
In recognizing 3D objects that are symmetric or similar, ambiguity may occur if the image is taken f...
Perception is the way by which we know the outside world. Thanks to our perceptions we are able to i...
This report deals with the scientific problem of objects visual recognition within an observed scene...
L’analyse d’une scène visuelle devient un passage obligé pour la réalisation d’un grand nombre de sy...
This thesis addresses the problem of how to improve the acquisition of 3D range data with a mobile r...
3D object detection is vital for autonomous driving. However, to train a 3D detector often requires ...
Pour un agent, apprendre une représentation visuelle de façon autonome en environnement ouvert est u...
International audienceA lot of vision applications, for instance in robotics, require id...
The thesis Autonomous 3D Modeling of Unknown Objects for Active Scene Exploration presents an approa...
During the last few years, there has been a growing interest in object recognition schemes directly ...