计算机视觉的PNP问题的最优解
Optimal Solutions of the PNP Problem in Computer Vision
-
摘要: 本文讨论了计算机视觉的PNP(Perspective-N-Point)问题:根据观察到的n个已知 特征点的象点求解被观察物体相对于相机的三维运动参数.由于象噪声,该问题本质上是非 线性最优化问题.本文导出一个闭式解,并提出若干克服象噪声影响的方法.仿真试验的结 果表明本文的方法有很好的应用前景.Abstract: This paper gives a comprehensive treatment of the PNP (Perspective-N-Point) problem in computer vision: find the 3-D motion parameters of a viewed object relative to a camera from the observed image points of n known feature points. This problem is essentially one of nonlinear optimization due to the image noise. In this paper, a closed-form solution is developed, and several methods to combat the image noise are presented. The simulation results show that the approaches given in this paper hold great promise in application.
-
Key words:
- Computer vision /
- PNP problem /
- motion parameters /
- RS decomposition /
- camera array
-
计量
- 文章访问数: 4661
- HTML全文浏览量: 315
- PDF下载量: 1112
- 被引次数: 0