EKFPnP: Extended Kalman Filter for Camera Pose Estimation in a Sequence of Images
This work addresses camera pose estimation in image sequences for applications like robotics or AR, but it is incremental as it builds on existing EKF and PnP techniques.
The paper tackled the problem of sequential camera pose estimation by incorporating temporal dependencies and feature uncertainties, resulting in improved robustness against noise compared to state-of-the-art methods.
In real-world applications the Perspective-n-Point (PnP) problem should generally be applied in a sequence of images which a set of drift-prone features are tracked over time. In this paper, we consider both the temporal dependency of camera poses and the uncertainty of features for the sequential camera pose estimation. Using the Extended Kalman Filter (EKF), a priori estimate of the camera pose is calculated from the camera motion model and then corrected by minimizing the reprojection error of the reference points. Experimental results, using both simulated and real data, demonstrate that the proposed method improves the robustness of the camera pose estimation, in the presence of noise, compared to the state-of-the-art.