A Minimal Set of Parameters Based Depth-Dependent Distortion Model and Its Calibration Method for Stereo Vision Systems

📄 arXiv: 2404.19242v2 📥 PDF

作者: Xin Ma, Puchen Zhu, Xiao Li, Xiaoyin Zheng, Jianshu Zhou, Xuchen Wang, Kwok Wai Samuel Au

分类: cs.CV, eess.IV, stat.ME

发布日期: 2024-04-30 (更新: 2024-05-01)

备注: This paper has been accepted for publication in IEEE Transactions on Instrumentation and Measurement


💡 一句话要点

提出基于最小参数集的深度依赖畸变模型以提升立体视觉系统精度

🎯 匹配领域: 支柱四:生成式动作 (Generative Motion)

关键词: 立体视觉 畸变模型 深度估计 相机标定 三维重建 机器人视觉 自动驾驶

📋 核心要点

  1. 现有立体视觉系统在近距离摄影中受深度位置影响,导致测量精度不足,传统标定方法复杂。
  2. 提出了一种基于最小参数集的深度依赖畸变模型(MDM),简化了标定过程并提高了精度。
  3. 实验结果显示,MDM的标定精度比现有模型显著提升,且迭代重建方法的精度提高了9.08%。

📝 摘要(中文)

深度位置对镜头畸变有显著影响,尤其在近距离摄影中,这限制了现有立体视觉系统的测量精度。传统的深度依赖畸变模型及其标定方法复杂。本文提出了一种基于最小参数集的深度依赖畸变模型(MDM),考虑了镜头的径向和偏心畸变,以提高立体视觉系统的精度并简化标定过程。此外,提出了一种灵活的MDM标定方法,使用常见的平面图案,要求相机在不同方向观察平面图案。实验验证表明,MDM的标定精度比Li的畸变模型和传统的Brown畸变模型分别提高了56.55%和74.15%。

🔬 方法详解

问题定义:本文旨在解决现有立体视觉系统在近距离摄影中因深度位置变化导致的镜头畸变问题。传统的深度依赖畸变模型及其标定方法复杂,影响了测量精度。

核心思路:提出了一种基于最小参数集的深度依赖畸变模型(MDM),该模型考虑了镜头的径向和偏心畸变,旨在提高立体视觉系统的精度并简化标定过程。

技术框架:整体架构包括MDM模型的建立和基于平面图案的灵活标定方法。标定过程中,相机需在不同方向观察平面图案,以获取必要的畸变参数。

关键创新:MDM模型的最大创新在于其使用最小参数集来描述深度依赖的畸变,显著简化了传统方法的复杂性,并提高了标定精度。

关键设计:在MDM中,关键参数包括径向畸变和偏心畸变的描述,标定过程中采用了灵活的观察角度设计,避免了传统方法中相机需垂直于平面图案的限制。实验中还提出了一种迭代重建方法,以提高深度信息的估计精度。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果表明,MDM的标定精度比Li的畸变模型提高了56.55%,比传统的Brown畸变模型提高了74.15%。此外,迭代重建方法的精度提升了9.08%,显示出该方法在实际应用中的有效性。

🎯 应用场景

该研究的潜在应用领域包括机器人视觉、自动驾驶、增强现实等需要高精度三维重建的场景。通过提升立体视觉系统的测量精度,能够在实际应用中实现更为准确的环境感知和物体识别,具有重要的实际价值和未来影响。

📄 摘要(原文)

Depth position highly affects lens distortion, especially in close-range photography, which limits the measurement accuracy of existing stereo vision systems. Moreover, traditional depth-dependent distortion models and their calibration methods have remained complicated. In this work, we propose a minimal set of parameters based depth-dependent distortion model (MDM), which considers the radial and decentering distortions of the lens to improve the accuracy of stereo vision systems and simplify their calibration process. In addition, we present an easy and flexible calibration method for the MDM of stereo vision systems with a commonly used planar pattern, which requires cameras to observe the planar pattern in different orientations. The proposed technique is easy to use and flexible compared with classical calibration techniques for depth-dependent distortion models in which the lens must be perpendicular to the planar pattern. The experimental validation of the MDM and its calibration method showed that the MDM improved the calibration accuracy by 56.55% and 74.15% compared with the Li's distortion model and traditional Brown's distortion model. Besides, an iteration-based reconstruction method is proposed to iteratively estimate the depth information in the MDM during three-dimensional reconstruction. The results showed that the accuracy of the iteration-based reconstruction method was improved by 9.08% compared with that of the non-iteration reconstruction method.