Abstract

We address the model-to-image registration problem with line features in the following two ways. (a) We present a robust solution to simultaneously recover the camera pose and the three-dimensional-to-two-dimensional line correspondences. With weak pose priors, our approach progressively verifies the pose guesses with a Kalman filter by using a subset of recursively found match hypotheses. Experiments show our method is robust to occlusions and clutter. (b) We propose a new line feature based pose estimation algorithm, which iteratively optimizes the objective function in the object space. Experiments show that the algorithm has strong robustness to noise and outliers and that it can attain very accurate results efficiently.

©2012 Optical Society of America

Relative pose estimation of uncooperative spacecraft using 2D–3D line correspondences

Zibin Liu, Haibo Liu, Zhaokun Zhu, and Junyao Song
Appl. Opt. 60(22) 6479-6486 (2021)

Skeleton body pose tracking from efficient three-dimensional motion estimation and volumetric reconstruction

Zheng Zhang and Hock Soon
Appl. Opt. 51(23) 5686-5697 (2012)

Probabilistic 3D object recognition and pose estimation using multiple interpretations generation

Zhaojin Lu and Sukhan Lee
J. Opt. Soc. Am. A 28(12) 2607-2618 (2011)

Weighted pose estimation method from lines intersecting at a point

Meng Li, Derong Chen, Jiulu Gong, and Changyuan Wang
Appl. Opt. 55(13) 3435-3441 (2016)

Relative pose estimation for multiple cameras using Lie algebra optimization

Yubo Ni, Xiangjun Wang, and Lei Yin
Appl. Opt. 58(11) 2963-2972 (2019)