SCALABLE AND DETAIL-PRESERVING GROUND SURFACE RECONSTRUCTION FROM MOBILE LASER SYSTEMS FOR DRIVING SIMULATORS ENGINES

Daniela Craciun (1) , Jean-Emmanuel Deschaud (1) , François Goulette (1)

1 CAOR - Centre de Robotique

Driving simulation engines represent a cost effective solution for vehicle development, being employed for performing feasibility studies, tests failure and for assessing new functionalities. Nevertheless, they require geometrically accurate and realistic 3D models in order to allow driver's training. This paper presents the Automatic Ground Surface Reconstruction (AGSR) method, a framework which exploits 3D data acquired by mobile laser systems. They are particularly attractive due to their fast acquisition at terrestrial level. Nevertheless, such a mobile acquisition introduces several constraints for the existing 3D surface reconstruction algorithms. The proposed surface modeling framework produces a regular surface and recovers sharp depth features within a scalable and detail-preserving framework. Experimental results on real data acquired in urban environments allow us to conclude on the effectiveness of the proposed method.

Mots clés: surface reconstruction; LiDAR; driving simulator engines; road network; mobile laser systems

Domaines: Robotique [cs.RO]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Daniela Craciun, Jean-Emmanuel Deschaud, François Goulette. SCALABLE AND DETAIL-PRESERVING GROUND SURFACE RECONSTRUCTION FROM MOBILE LASER SYSTEMS FOR DRIVING SIMULATORS ENGINES. DSC, Sep 2014, Paris, France. ⟨hal-01097388⟩