Online Camera-to-ground Calibration for Autonomous Driving
This addresses the need for real-time, robust calibration in autonomous vehicles without requiring specific road targets, though it is incremental as it builds on existing online methods.
The paper tackles the problem of online camera-to-ground calibration for autonomous driving, which is challenged by environmental variations and reliance on specific road targets or multiple cameras, by proposing a monocular solution using wheel odometry and factor graph optimization, and demonstrates effectiveness with real-world data outperforming state-of-the-art techniques.
Online camera-to-ground calibration is to generate a non-rigid body transformation between the camera and the road surface in a real-time manner. Existing solutions utilize static calibration, suffering from environmental variations such as tire pressure changes, vehicle loading volume variations, and road surface diversity. Other online solutions exploit the usage of road elements or photometric consistency between overlapping views across images, which require continuous detection of specific targets on the road or assistance with multiple cameras to facilitate calibration. In our work, we propose an online monocular camera-to-ground calibration solution that does not utilize any specific targets while driving. We perform a coarse-to-fine approach for ground feature extraction through wheel odometry and estimate the camera-to-ground calibration parameters through a sliding-window-based factor graph optimization. Considering the non-rigid transformation of camera-to-ground while driving, we provide metrics to quantify calibration performance and stopping criteria to report/broadcast our satisfying calibration results. Extensive experiments using real-world data demonstrate that our algorithm is effective and outperforms state-of-the-art techniques.