目标3D模型不准确条件下的单目位姿测量
DOI:
作者:
作者单位:

国防科技大学 空天科学学院

作者简介:

通讯作者:

中图分类号:

TP391.4

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目)(12272404),湖南省科技创新计划(No.2023RC3023)


A monocular pose measurement method for inaccurate 3D model of a target
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献()
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    已有单目视觉引导中平台间位姿高精度测量方法需要准确的目标平台3D模型,无法消除3D模型误差给位姿测量带来的影响。针对此问题,本文对目标平台3D模型和位姿进行迭代优化,并提出一种新的单目视觉测量方法:采用稀疏3D关键点集合建模目标平台3D模型,利用序列图像中多视图几何约束信息,将目标稀疏3D关键点集合和6D位姿作为待求解参数,以最小化物方残差建立目标函数,通过求解该最优化问题,迭代优化稀疏3D关键点集合及位姿,通过采用滑动窗口结合关键帧筛选策略,实现实时、在线的高精度单目视觉测量。实验结果表明,通过迭代优化稀疏3D关键点集合及位姿,所提出方法实现了目标平台3D模型不准确条件下实时、在线的高精度单目位姿测量,同时提升目标3D模型精度。

    Abstract:

    In monocular vision-guided high-precision inter-platform pose measurement, existing methods require an accurate 3D model of the target platform and are unable to eliminate the impact of 3D model errors on pose measurement. To address this issue, iterative optimization is performed on the 3D model of the target platform and pose, and a new monocular vision measurement method is proposed. Specifically, the target platform’s 3D model is modeled using a set of sparse 3D keypoints. By leveraging multi-view geometric constraint information in sequential images, the sparse 3D keypoint set of the target and 6D pose are treated as parameters to be solved. An objective function is established to minimize object-space residuals, and through solving this optimization problem, iterative optimization of the sparse 3D keypoint set and pose is achieved. Additionally, a sliding window combined with a keyframe selection strategy is adopted to realize real-time and online high-precision monocular vision measurement. Experimental results demonstrate that, through iterative optimization of the sparse 3D keypoint set and pose, the proposed method achieves real-time, online high-precision monocular pose. measurement under the condition of an inaccurate 3D model of target platform, while simultaneously improving the accuracy of the target’s 3D model.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-05-01
  • 最后修改日期:2025-09-09
  • 录用日期:2024-08-27
  • 在线发布日期: 2025-09-10
  • 出版日期:
文章二维码