Online Recalibration of a Camera and Lidar System

Abstract

Sensor fusion, especially in 2D cameras and 3D laser scanners, is crucial for robot and autonomous driving. Calibration is a major aspect of sensor fusion. Most of the calibration is conducted offline by using checkerboards to determine the sensor pose. However, problems arise when robots or vehicles have irregular vibrations during movement. This leads to sensors having a different position from the initial pose. Therefore, online calibration, which allows robots to be calibrated at any time during their movement, is required. This study focused on calibrating a 2D camera and 3D lidar scanner by using their resembling features. For lidar calibration, we transformed the 3D point cloud into a 2D range image and removed the edge points. For calibrating the camera, we applied an edge filter to the image. Then, the inverse distance transform was used to identify the alignment of the edges. The sensor pose relative to the camera and lidar system was determined from their corresponding images.