September 2018 – Remote Sensing
Project: The Smart Point Cloud
Global workflow for modelling indoor point cloud data. Our approach takes as an input a semantically rich point cloud (A) and uses knowledge-based processes (B–D) to extract a hybrid 3D mode
Abstract and figures
3D models derived from point clouds are useful in various shapes to optimize the trade-off between precision andgeometric complexity. They are defined at different granularity levels according to each indoor situation.
In this article, we present an integrated 3D semantic reconstruction framework that leverages segmented point cloud data and domainontologies.
Our approach follows a part-to-whole conception which models a point cloud in parametric elements usableper instance and aggregated to obtain a global 3D model.
We first extract analytic features, object relationships andcontextual information to permit better object characterization. Then, we propose a multi-representation modellingmechanism augmented by automatic recognition and fitting from the 3D library ModelNet10 to provide the bestcandidates for several 3D scans of furniture. Finally, we combine every element to obtain a consistent indoor hybrid 3Dmodel.
The method allows a wide range of applications from interior navigation to virtual stores.