A Hybrid Structure/Trajectory Constraint for Visual SLAM

Angélique Loesch (1) , Steve Bourgeois (1) , Vincent Gay-Bellile (1) , Michel Dhome (2)

1 LVIC - Laboratoire Vision et Ingénierie des Contenus
2 IP - Institut Pascal

This paper presents a hybrid structure/trajectory constraint, that uses output camera poses of a model-based tracker, for object localization with SLAM algorithm. This constraint takes into account the structure information given by a CAD model while relying on the formalism of trajectory constraints. It has the advantages to be compact in memory and to accelerate the SLAM optimization process. The accuracy and robustness of the resulting localization as well as the memory and time gains are evaluated on synthetic and real data. Videos are available as supplementary material.

Keywords: 3D model; SLAM Simultaneous Localisation and Mapping; Local bundle adjustment; Object tracking

Domains: Engineering Sciences [physics]; Signal and Image processing

Angélique Loesch, Steve Bourgeois, Vincent Gay-Bellile, Michel Dhome. A Hybrid Structure/Trajectory Constraint for Visual SLAM. 2016 Fourth International Conference on 3D Vision (3DV), Oct 2016, Stanford, United States. ⟨10.1109/3DV.2016.12⟩. ⟨cea-01830449⟩