Title :
Robust depth regularization explicitly constrained by camera motion
Author :
Zarrouati, N. ; Aldea, Emanuel ; Rouchon, Pierre
Author_Institution :
Mines-ParisTech, Paris, France
Abstract :
The objective of our work is to reconstruct the dense structure of a static scene observed by a monocular camera system following a known trajectory. Our main contribution is representated by the proposition of a TV-L1 energy functional that estimates directly the unknown depth field given the camera motion, thus avoiding to estimate as an intermediate step an optical flow field with additional geometric constraints. Our method has two main interests: we highlight a practical minimal parametrization for the given assumptions (static scene, known camera motion) and we solve the resulting variational problem using an efficient, discontinuity preserving formulation.
Keywords :
cameras; image motion analysis; image reconstruction; image sequences; natural scenes; variational techniques; TV-L1 energy functional; camera motion; dense static scene structure reconstruction; depth field; discontinuity preserving formulation; geometric constraints; minimal parametrization; monocular camera system; optical flow field; robust depth regularization; variational problem; Adaptation models; Adaptive optics; Cameras; Observers; Optical imaging; Robustness;
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
Print_ISBN :
978-1-4673-2216-4