Camera Calibration and Relative Pose Estimation from Gravity

Peter Sturm (1) , Long Quan (1)

1 MOVI - Modeling, localization, recognition and interpretation in computer vision

We examine the potential use of gravity for camera calibration and pose estimation purposes. Concretely, objects being launched or dropped follow trajectories dictated by the law of gravity. We examine if video sequences of such trajectories give us exploitable constraints for estimating the imaging geometry. It is shown that it is possible to estimate the infinite homography and the epipolar geometry between pairs of views from this input, from which we can estimate (some) intrinsic parameters and relative pose. There are less singularities compared to approaches that do not use the information that the observed trajectories follow gravity. In this paper, we sketch the geometric principles of our idea and validate them by numerical simulations.

Mots clés: calibration; computational geometry; image sequences; video cameras; video signal processing

Domaines: Synthèse d'image et réalité virtuelle [cs.GR]

Peter Sturm, Long Quan. Camera Calibration and Relative Pose Estimation from Gravity. International Conference on Pattern Recognition (ICPR '00), Sep 2000, Barcelona, Spain. pp.72-75, ⟨10.1109/ICPR.2000.905278⟩. ⟨inria-00525672⟩