A Comprehensive Approach for Camera/LIDAR Frame Alignment

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

This paper deals with the initial phase of any multi-sensor acquisition, the sensor alignment process. We focus on extrinsic calibration of vision-based and line scan LIDAR sensors for automotive application. We investigate two research approaches for the calibration process: analytical and numeric solutions. Additionally, we present a complete implementable tool-chain, to extract the co-features for both types of sensors: line detections for cameras and segmentation process for LIDAR sensors. Moreover, we investigate the impact of the calibration accuracy on sensor fusion performance. Results of experiments using real-world data are presented.

Mots clés: Sensor alignment; Sensor calibration; Sensor fusion; Intelligent vehicles

Domaines: Informatique [cs]; Automatique / Robotique

Mokhtar Bouain, Denis Berdjag, Nizar Fakhfakh, Rabie Ben Atitallah. A Comprehensive Approach for Camera/LIDAR Frame Alignment. Informatics in Control, Automation and Robotics, 495, Springer International Publishing, pp.761-785, 2020, Lecture Notes in Electrical Engineering, ⟨10.1007/978-3-030-11292-9_38⟩. ⟨hal-03378974⟩