MFCalib: Single-shot and Automatic Extrinsic Calibration for LiDAR and Camera in Targetless Environments Based on Multi-Feature Edge

TL;DR

MFCalib introduces an automatic, single-shot extrinsic calibration method for LiDAR and camera systems in targetless environments, leveraging multi-feature edge extraction to improve accuracy and robustness.

Contribution

It presents a novel edge-based calibration approach that operates automatically with one data capture, addressing depth edge uncertainty with a physical beam model.

Findings

Outperforms state-of-the-art targetless calibration methods.

Achieves calibration accuracy comparable or superior to multi-scene methods.

Operates effectively in complex, varied environments with a single data collection.

Abstract

This paper presents MFCalib, an innovative extrinsic calibration technique for LiDAR and RGB camera that operates automatically in targetless environments with a single data capture. At the heart of this method is using a rich set of edge information, significantly enhancing calibration accuracy and robustness. Specifically, we extract both depth-continuous and depth-discontinuous edges, along with intensity-discontinuous edges on planes. This comprehensive edge extraction strategy ensures our ability to achieve accurate calibration with just one round of data collection, even in complex and varied settings. Addressing the uncertainty of depth-discontinuous edges, we delve into the physical measurement principles of LiDAR and develop a beam model, effectively mitigating the issue of edge inflation caused by the LiDAR beam. Extensive experiment results demonstrate that MFCalib outperforms the state-of-the-art targetless calibration methods across various scenes, achieving and often surpassing the precision of multi-scene calibrations in a single-shot collection. To support community development, we make our code available open-source on GitHub.