Iterative pose estimation using coplanar feature points
Iterative pose estimation using coplanar feature points
复制标题
DOI：
10.1006/cviu.1996.0037
复制
发表时间：
1996-05-01
影响因子：
4.5
通讯作者：
Davis, LS
中科院分区：
文献类型：
--
作者：
Oberkampf, D;DeMenthon, DF;Davis, LS
本文提出了一种利用四个或多个共面特征点计算摄像机相对于已知目标的位置和姿态的新方法。从缩放的正投影近似开始，该方法迭代地细化多达两个不同的姿态估计，并为每个姿态提供相关联的质量度量。当相机距离与对象深度相比较大时，或者当特征点提取的精度由于图像噪声而较低时，两个姿态的质量度量是相似的，并且两个姿态估计是可用信息的合理解释。相比之下，在存在图像噪声的情况下，使用针对四个共面点的闭合形式姿态解的已知方法对于远处对象不鲁棒，因为它们仅提供两个可能姿态中的一个并且可能选择错误姿态。(C)出版社：Academic Press，Inc.
This paper presents a new method for the computation of the position and orientation of a camera with respect to a known object, using four or more coplanar feature points. Starting with the scaled orthographic projection approximation, this method iteratively refines up to two different pose estimates, and provides an associated quality measure for each pose. When the camera distance is large compared with the object depth, or when the accuracy of feature point extraction is low because of image noise, the quality measures for the two poses are similar, and the two pose estimates are plausible interpretations of the available information. In contrast, known methods using a closed form pose solution for four coplanar points are not robust for distant objects in the presence of image noise because they provide only one of the two possible poses and may choose the wrong pose. (C) 1996 Academic Press, Inc.