The online extrinsic parameters calibration among multiple sensors for data fusion has been a crucial task in autonomous driving. This paper proposes a new online, robust pipeline of automatic extrinsic parameters calibration between monocular RGB cameras and LiDARs for autonomous driving applications. The novelties of this work includes threefold: (1) an automatic full pipeline of the calibration is developed for the autonomous driving system; (2) an initialization stage is developed for calibration without the initial value of extrinsic parameters; (3) a combination of depth estimation and edge detection is used to improve the calibration accuracy and robustness. We implement the proposed calibration algorithm on an autonomous driving platform, a BYD Qin electric sedan. Both the simulation and experiment results verify the online and robust performance of the proposed calibration pipeline.
Online Intelligent Calibration of Cameras and LiDARs for Autonomous Driving Systems*
2019-10-01
2341821 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Unified Spatiotemporal Calibration of Monocular Cameras and Planar Lidars
Springer Verlag | 2020
|