.png){kind=icon}
返回
A robust direct linear transformation for camera pose estimation using points
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2023.104883.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Camera pose estimation from 3D points and their 2D projections, known as the perspective-n-point (PnP) problem, is a fundamental task in computer vision. In this paper, we propose a robust direct linear transformation method for the PnP problem. The novelty lies in that a plane constraint based on the pinhole camera model is introduced, and an over-constrained linear equation system is obtained by merging the linear form of both the measured point correspondences and the plane constraint. As a result, our method successfully reduces the minimal number of point correspondences required by the linear solver to 4, and yields a unique solution for 4point, 5-point, and n-point pose estimation. Experiment results, using both synthetic and real data, show that our method is substantially faster, and offers the accuracy and precision comparable with that of state-of-the-art methods.
Keyword:
Perspective-n-point problem (P n P)
Relative position and attitude
Pose estimation
Monocular vision
Vision-based navigation
Computer vision
期刊
IF:
4.2
论文数:
4.1K
被引数:
6.7K
机构
引用论文
RANDOM SAMPLE CONSENSUS - A PARADIGM FOR MODEL-FITTING WITH APPLICATIONS TO IMAGE-ANALYSIS AND AUTOMATED CARTOGRAPHY随机样本共识-模型拟合的范例，可应用于图像分析和自动制图
OAAI
.png){kind=icon}
OAAI分享收藏
分享收藏分享收藏
查看更多内容