An Extrinsic Sensor Calibration Framework for Sensor-fusion based Autonomous Vehicle Perception

Mokhtar Bouain (1) , Denis Berdjag (1) , Nizar Fakhfakh , Rabie Ben Atitallah (1)

1 LAMIH - Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201

In this paper we deal with sensor alignment problems that appear when implementing sensor fusion-based autonomous vehicle perception. We focus on extrinsic calibration of vision-based and line scan LIDAR sensors. Based on state-of-art solutions, a consistent calibration toolchain is developed, with improvements (accuracy and calibration duration). Additionally, sensor alignment/calibration impact on fusion-based perception is investigated. Experimental results are provided for illustration, using real-world data.

Mots clés: Sensor Alignment; Sensor Calibration; Sensor Fusion; Intelligent Vehicles

Domaines: Robotique [cs.RO]

Mokhtar Bouain, Denis Berdjag, Nizar Fakhfakh, Rabie Ben Atitallah. An Extrinsic Sensor Calibration Framework for Sensor-fusion based Autonomous Vehicle Perception. 14th International Conference on Informatics in Control, Automation and Robotics, Jul 2017, Madrid, Spain. pp.505-512, ⟨10.5220/0006438105050512⟩. ⟨hal-03388639⟩