3D reconstruction of an unknown scene is a classical computer vision problem. Usual solutions, which use a pair of cameras in stereoscopic configuration and an algorithm relying on image disparities, don't allow to create a densely sampled 3D model. Moreover, processing this model in real-time is a complex task which often needs an implementation on dedicated hardware (FPGA or DSP), very powerful but hard to use.In this thesis, we propose a volumetric reconstruction method aiming to produce a high-resolution 3D model of the scene surrounding a mobile robot. A pair of catadioptric cameras allows panoramic acquisition of the whole scene. The reconstruction algorithm, adapted for the massively-parallel architecture of a very powerful and inexp...
The automatic reconstruction of a scene surface from images taken by a moving camera is still an act...
The automatic 3d modeling of an environment using images is still an active topic in Computer Vision...
In this work we study the gain offered by massively parallel architecture for low-level vision proce...
3D reconstruction of an unknown scene is a classical computer vision problem. Usual solutions, which...
International audienceThis paper presents a 3-second 3D reconstruction algorithm able to process a d...
The three-dimensional structure of the world makes 3D as the natural evolution of a huge panel of ap...
This thesis deals with three-dimensional reconstruction of a mobile robot's environment. Based on om...
The Structure from Motion problem is an intense research topic in computer vision and has been the s...
This thesis examines the problem of 3D Modelling of indoor environment (supposed unknown) by a mobil...
The work presented in this thesis deals with the design and the evaluation of a vision sensor made o...
With the development of technological processes, interest in mobile robotics is constantly increasin...
This thesis is a collection of techniques used for 3D reconstruction; the creation of 3D models from...
Avec l’évolution des processus technologiques, l’intérêt pour la robotique mobile n’a de cesse d’aug...
IEEE Xplore Compliant Files 979-10-92279-01-6International audienceIn this article we propose a new ...
We present a new scalable volumetric reconstruction algorithm for multi-view stereo using a graphics...
The automatic reconstruction of a scene surface from images taken by a moving camera is still an act...
The automatic 3d modeling of an environment using images is still an active topic in Computer Vision...
In this work we study the gain offered by massively parallel architecture for low-level vision proce...
3D reconstruction of an unknown scene is a classical computer vision problem. Usual solutions, which...
International audienceThis paper presents a 3-second 3D reconstruction algorithm able to process a d...
The three-dimensional structure of the world makes 3D as the natural evolution of a huge panel of ap...
This thesis deals with three-dimensional reconstruction of a mobile robot's environment. Based on om...
The Structure from Motion problem is an intense research topic in computer vision and has been the s...
This thesis examines the problem of 3D Modelling of indoor environment (supposed unknown) by a mobil...
The work presented in this thesis deals with the design and the evaluation of a vision sensor made o...
With the development of technological processes, interest in mobile robotics is constantly increasin...
This thesis is a collection of techniques used for 3D reconstruction; the creation of 3D models from...
Avec l’évolution des processus technologiques, l’intérêt pour la robotique mobile n’a de cesse d’aug...
IEEE Xplore Compliant Files 979-10-92279-01-6International audienceIn this article we propose a new ...
We present a new scalable volumetric reconstruction algorithm for multi-view stereo using a graphics...
The automatic reconstruction of a scene surface from images taken by a moving camera is still an act...
The automatic 3d modeling of an environment using images is still an active topic in Computer Vision...
In this work we study the gain offered by massively parallel architecture for low-level vision proce...