Robust binocular pose estimation based on pigeon-inspired optimization

In this paper, an accurate and robust pose estimation algorithm for binocular camera systems is proposed based on pigeon-inspired optimization (PIO), which can be easily generalized to estimation for multiple camera systems. In this method, the information of both cameras is completely used, and the poses of them can be determined accurately at the same time. Pigeon-inspired optimization is a new and efficient evolutionary algorithm, which is employed to select the optimal rotation axis in our method. The robustness and high accuracy of the proposed method has been demonstrated by three cases of experiments over some state-of-the-art pose estimation methods.