La réalité augmentée bouleverse de nombreux secteurs industriels en offrant une nouvelle perception de l’environnement.
Par son expertise en vision par ordinateur, estimation de pose et visualisation 3D, le laboratoire Technologies Immersives & Médicales conçoit composants et plateformes pour augmenter les expériences des professionnels et renforcer leur efficacité, notamment grâce à la réalité augmentée et la réalité virtuelle, dans des domaines tels que l’industrie et la santé. L’utilisateur est au cœur de sa réflexion et de ses travaux, depuis la définition des besoins jusqu’à la confrontation à l’usage des technologies développées. Dans le domaine de la santé, le laboratoire travaille, avec ses partenaires médicaux, sur des technologies clefs telles que le traitement des images et des vidéos médicales, la connectivité ou l’interopérabilité.
08.03.2019
Camera relocalization is a common problem in several applications such as augmented reality or robot navigation. Especially, augmented reality requires fast, accurate and robust camera localization. However, it is still challenging to have a both real-time and accurate method. In this paper, we present our hybrid method combing machine learning approach and geometric approach for real-time camera…
lire la publication
21.08.2018
The main objective of this work is to facilitate the identification, sharing and reasoning about cerebral tumors observations via the formalization of their semantic meanings in order to facilitate their exploitation in both the clinical practice and research. We have focused our analysis on the VASARI terminology as a proof of concept, but we are convinced that our work can be useful in other…
lire la publication
04.10.2018
Imaging Biomarker Ontology (IBO): A Biomedical Ontology to Annotate and Share Imaging Biomarker Data
Imaging biomarkers refer to radiological measurements that characterize biological processes of imaged subjects and help clinicians particularly in the assessment of therapeutic responses and the early prediction of pathologies. Several imaging features (size of a lesion, volume of a tumor, blood perfusion in a specific anatomical region, anisotropic water diffusion in a particular tissue region,…
lire la publication
07.01.2019
Accurate Sparse Feature Regression Forest Learning for Real-Time Camera Relocalization
Camera relocalization is needed in several applications such as augmented reality or robot navigation. However, it is still challenging to have a both real-time and accurate method. In this paper, we present our hybrid method combing machine learning approach and geometric approach for real-time camera relocalization from a single RGB image. We introduce our sparse feature regression forest to…
lire la publication
