0000000000709078

AUTHOR

Guillaume Caron

showing 3 related works from this author

Mélange de Gaussiennes Photométriques pour l'Asservissement Visuel Virtuel Direct d'une Caméra Omnidirectionnelle

2021

International audience; Cet article traite du suivi de pose direct basé modèle 3D. Nous considérons la transformation d’images omnidirectionnelles en Mélange de Gaussiennes Photométriquesn (MGP) comme primitives directes. Les contributions sont d’adapter l’optimisation de pose aux caméras omnidirectionnelles et de repenser les règles d’initialisation et d’optimisation du paramètre d’extension du MGP. Plusieurs évaluations montrent que cette approche augmente la taille du domaine de convergence. L’application à des images acquises avec un robot mobile placé dans un environnement urbain, représenté par un grand nuage de points 3D coloré, montre une robustesse significative aux grands mouvemen…

[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Asservissement visuelSuivi.Vision Omnidirectionnelle[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][INFO]Computer Science [cs][INFO] Computer Science [cs]
researchProduct

Photometric Gaussian Mixtures for Direct Virtual Visual Servoing of Omnidirectional Camera

2021

International audience

[SPI.AUTO] Engineering Sciences [physics]/Automatic[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]ComputingMilieux_MISCELLANEOUS[SPI.AUTO]Engineering Sciences [physics]/Automatic
researchProduct

Reliable Planar Object Pose Estimation in Light Fields From Best Subaperture Camera Pairs

2018

International audience; A light-field camera can obtain richer information about a scene than a usual camera. This property offers a lot of potential for robot vision. In this paper, we present a method for pose estimation of a planar object with a light-field camera. The light-field camera can be regarded as a set of sub-aperture cameras. Although any combination of them can theoretically be used for the pose estimation, the accuracy depends on the combination. We show that the estimated pose error can be reduced by selecting the best pair of sub-aperture cameras. We have evaluated the accuracy of our approach with real experiments using a light-field camera in front of planar targets held…

Control and OptimizationComputer scienceProperty (programming)Biomedical EngineeringComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONSet (abstract data type)PlanarArtificial Intelligence[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]Computer visionPoseComputer Science::DatabasesGround truthbusiness.industryMechanical EngineeringAstrophysics::Instrumentation and Methods for Astrophysics[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]16. Peace & justiceObject (computer science)Computer Science ApplicationsHuman-Computer InteractionControl and Systems EngineeringComputer Science::Computer Vision and Pattern RecognitionComputer Vision and Pattern RecognitionArtificial intelligencebusiness
researchProduct