Keyframe-based camera tracking methods can reduce error accumulation in that they reduce the number of camera poses to be estimated by selecting a set of keyframes from an image sequence. In this paper, we propose a novel Bayesian filtering framework for keyframe-based camera tracking and 3D mapping. Our Bayesian filtering enables an effective estimation of keyframe poses using all measurements obtained at non keyframe locations, which improves the accuracy of the estimated path. In addition, we discuss the independence problem between the process noise and the measurement noise when employing vision-based motion estimation approaches for the process mo del, and we present a method of ensuring independence despite using a single visual sensor for both the process and measurement models. We demonstrate the performance of the proposed approach in terms of the consistency of the global map and the accuracy of the estimated path.
|저 자||Jungho Kim, Kukjin Yoon, In So Kweon|
|학 회||International Journal of Robotics Research|
Prev Real-time Head Orientation from a Monocular Camera using Deep Neural Network Real-time Head Orientation from a Monocular Camera using Deep Neural Network 2014.09.03by 박재식 Motion Deblurring using Coded Exposure for a Wheeled Mobile R... Next Motion Deblurring using Coded Exposure for a Wheeled Mobile R... 2014.08.25by