arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.00992cs.RO
收藏

MFCalib:基于多特征边缘的无目标环境中LiDAR与相机单次自动外参标定

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

College of Mechatronics and Control Engineering, Shenzhen University(深圳大学机电与控制工程学院);Peng Cheng Laboratory(鹏城实验室);Manifold Tech Limited(万孚科技有限公司);The University of Hong Kong(香港大学)

Tianyong Ye, Wei Xu, Chunran Zheng, Yukang Cui

AI总结:

MFCalib提出一种基于多特征边缘的无目标LiDAR-相机外参标定方法,通过提取深度连续、深度不连续及强度不连续边缘并构建LiDAR光束模型抑制边缘膨胀,实现单次采集即达到超越多场景标定的精度。

摘要:

本文提出MFCalib,一种创新的LiDAR与RGB相机外参标定技术,可在无目标环境中通过单次数据采集自动运行。该方法的核心在于利用丰富的边缘信息,显著提升标定精度与鲁棒性。具体而言,我们同时提取深度连续边缘、深度不连续边缘以及平面上的强度不连续边缘。这种全面的边缘提取策略确保我们仅需一轮数据采集即可实现精确标定,即使在复杂多变的场景中亦然。针对深度不连续边缘的不确定性,我们深入探究LiDAR的物理测量原理并构建光束模型,有效缓解由LiDAR光束引起的边缘膨胀问题。大量实验结果表明,MFCalib在多种场景下均优于当前最先进的无目标标定方法,在单次采集中即可达到甚至超越多次场景标定的精度。为支持社区发展,我们已在GitHub上开源代码。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑