LCE-Calib: Automatic LiDAR-Frame/Event Camera Extrinsic Calibration With A Globally Optimal Solution

TL;DR

This paper introduces an automatic, globally optimal method for calibrating extrinsics between LiDAR and camera systems, including event cameras, enhancing multi-modal perception robustness in robotics.

Contribution

It presents a novel automatic calibration approach combining feature extraction, image reconstruction from event streams, and a globally optimal optimization framework.

Findings

Outperforms state-of-the-art calibration methods

Validated on 19 datasets with high accuracy

Effective for both frame and event cameras

Abstract

The combination of LiDARs and cameras enables a mobile robot to perceive environments with multi-modal data, becoming a key factor in achieving robust perception. Traditional frame cameras are sensitive to changing illumination conditions, motivating us to introduce novel event cameras to make LiDAR-camera fusion more complete and robust. However, to jointly exploit these sensors, the challenging extrinsic calibration problem should be addressed. This paper proposes an automatic checkerboard-based approach to calibrate extrinsics between a LiDAR and a frame/event camera, where four contributions are presented. Firstly, we present an automatic feature extraction and checkerboard tracking method from LiDAR's point clouds. Secondly, we reconstruct realistic frame images from event streams, applying traditional corner detectors to event cameras. Thirdly, we propose an initialization-refinement procedure to estimate extrinsics using point-to-plane and point-to-line constraints in a coarse-to-fine manner. Fourthly, we introduce a unified and globally optimal solution to address two optimization problems in calibration. Our approach has been validated with extensive experiments on 19 simulated and real-world datasets and outperforms the state-of-the-art.