CRLF: Automatic Calibration and Refinement based on Line Feature for LiDAR and Camera in Road Scenes

TL;DR

This paper introduces an automatic, robust method for calibrating LiDAR and camera sensors in road scenes using line features, eliminating the need for calibration targets or initial calibration, suitable for large-scale deployment.

Contribution

The paper proposes a novel automatic calibration and refinement method based on line features, formulated as a P3L problem, applicable without calibration targets or initial calibration.

Findings

Robustness demonstrated on KITTI and in-house datasets

Achieves accurate calibration without calibration targets

Fully automatic and user-friendly process

Abstract

For autonomous vehicles, an accurate calibration for LiDAR and camera is a prerequisite for multi-sensor perception systems. However, existing calibration techniques require either a complicated setting with various calibration targets, or an initial calibration provided beforehand, which greatly impedes their applicability in large-scale autonomous vehicle deployment. To tackle these issues, we propose a novel method to calibrate the extrinsic parameter for LiDAR and camera in road scenes. Our method introduces line features from static straight-line-shaped objects such as road lanes and poles in both image and point cloud and formulates the initial calibration of extrinsic parameters as a perspective-3-lines (P3L) problem. Subsequently, a cost function defined under the semantic constraints of the line features is designed to perform refinement on the solved coarse calibration. The whole procedure is fully automatic and user-friendly without the need to adjust environment settings or provide an initial calibration. We conduct extensive experiments on KITTI and our in-house dataset, quantitative and qualitative results demonstrate the robustness and accuracy of our method.