Galibr: Targetless LiDAR-Camera Extrinsic Calibration Method via Ground Plane Initialization
This addresses the need for convenient, maintenance-friendly calibration in autonomous driving and SLAM applications, though it appears to be an incremental improvement on existing targetless calibration methods.
The paper tackles the problem of extrinsic calibration between LiDAR and camera sensors for autonomous systems by introducing Galibr, a fully automatic targetless calibration tool that uses ground planes and edge information. The method achieved significant calibration performance improvements in unstructured natural environments, as demonstrated on the KITTI and KAIST quadruped datasets.
With the rapid development of autonomous driving and SLAM technology, the performance of autonomous systems using multimodal sensors highly relies on accurate extrinsic calibration. Addressing the need for a convenient, maintenance-friendly calibration process in any natural environment, this paper introduces Galibr, a fully automatic targetless LiDAR-camera extrinsic calibration tool designed for ground vehicle platforms in any natural setting. The method utilizes the ground planes and edge information from both LiDAR and camera inputs, streamlining the calibration process. It encompasses two main steps: an initial pose estimation algorithm based on ground planes (GP-init), and a refinement phase through edge extraction and matching. Our approach significantly enhances calibration performance, primarily attributed to our novel initial pose estimation method, as demonstrated in unstructured natural environments, including on the KITTI dataset and the KAIST quadruped dataset.