LiDAR-camera Calibration based on the Characteristics of LiDAR Sensors

This paper proposes a novel extrinsic calibration method between LiDAR and camera sensors by using a single observation of a calibration target board. Particularly, we focus on the LiDAR sensor characteristics which are often overlooked in previous work. First, we address the noisy LiDAR measurements by projecting points to the target plane along the ray directions, not along the surface normal. Second, we attend to discrete LiDAR observations which cause edge points extracted based on range discontinuity to lie within surface boundaries, not on the actual edges. Experimental results using simulated and real data show that our proposed method significantly improves accuracy and robustness over the state-of-the-art approaches by integrating these LiDAR-specific insights.