2019/06/25 by Mohammad Amin Mehralian, Mehralian, Mohammad Amin, Mohsen Soryani +1
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Robotics and Sensor-Based Localization #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1906.10324
openalex publication_date 2019/06/25 · openalex created_date 2022/02/25 · openalex updated_date 2026/07/28
In real-world applications the Perspective-n-Point (PnP) problem should\ngenerally be applied in a sequence of images which a set of drift-prone\nfeatures are tracked over time. In this paper, we consider both the temporal\ndependency of camera poses and the uncertainty of features for the sequential\ncamera pose estimation. Using the Extended Kalman Filter (EKF), a priori\nestimate of the camera pose is calculated from the camera motion model and then\ncorrected by minimizing the reprojection error of the reference points.\nExperimental results, using both simulated and real data, demonstrate that the\nproposed method improves the robustness of the camera pose estimation, in the\npresence of noise, compared to the state-of-the-art.\n