Robust and accurate online pose estimation algorithm via efficient three-dimensional collinearity model

In this study, the authors propose a robust and high accurate pose estimation algorithm to solve the perspective-N-point problem in real time. This algorithm does away with the distinction between coplanar and non-coplanar point configurations, and provides a unified formulation for the configurations. Based on the inverse projection ray, an efficient collinearity model in object-space is proposed as the cost function. The principle depth and the relative depth of reference points are introduced to remove the residual error of the cost function and to improve the robustness and the accuracy of the authors pose estimation method. The authors solve the pose information and the depth of the points iteratively by minimising the cost function, and then reconstruct their coordinates in camera coordinate system. In the following, the optimal absolute orientation solution gives the relative pose information between the estimated three-dimensional (3D) point set and the 3D mode point set. This procedure with the above two steps is repeated until the result converges. The experimental results on simulated and real data show that the superior performance of the proposed algorithm: its accuracy is higher than the state-of-the-art algorithms, and has best anti-noise property and least deviation by the influence of outlier among the tested algorithms.