BROWSE
Detail
Conference Paper
Relative Camera Pose Estimation Using Known Vertical Direction and Bearing Measurements
Cited - time in 
Share 
Share
- Authors
- Jae-Hean Kim, Jin Sung Choi
- Issue Date
- 2016-02
- Citation
- Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV) 2016, pp.1-3
- Language
- English
- Type
- Conference Paper
- Abstract
- We propose a novel approach of solving the relative camera pose problem with the information of known vertical direction and 2D structure from motion (SFM) technique. The information of vertical direction can transform cameras into the camera of which vertical axis is parallel with the vertical direction. Moreover, feature point measurements can also be transformed into bearing angles and elevation angles with respect to the ground plane. Then, 2D pose of the camera and 2D positions of point features can be estimated with 2D trifocal tensor method in closed form. After obtaining those estimates, the remained 1D information about camera and point features are estimated easily.
- KSP Keywords
- 2D Trifocal Tensor, 2D structure, Feature Points, Ground Plane(GP), Known Vertical Direction, Novel approach, Relative camera pose estimation, Tensor method, bearing angles, closed-form, point features