Perceiving Systems, Computer Vision

Multiview Structure from Motion in Trajectory Space

2011

Conference Paper

ps


Most nonrigid objects exhibit temporal regularities in their deformations. Recently it was proposed that these regularities can be parameterized by assuming that the non- rigid structure lies in a small dimensional trajectory space. In this paper, we propose a factorization approach for 3D reconstruction from multiple static cameras under the com- pact trajectory subspace representation. Proposed factor- ization is analogous to rank-3 factorization of rigid struc- ture from motion problem, in transformed space. The benefit of our approach is that the 3D trajectory basis can be directly learned from the image observations. This also allows us to impute missing observations and denoise tracking errors without explicit estimation of the 3D structure. In contrast to standard triangulation based methods which require points to be visible in at least two cameras, our ap- proach can reconstruct points, which remain occluded even in all the cameras for quite a long time. This makes our solution especially suitable for occlusion handling in motion capture systems. We demonstrate robustness of our method on challenging real and synthetic scenarios.

Author(s): Zaheer, Aamer and Akhter, Ijaz and Mohammad, Haris B and Marzban, Shabbir and Khan, Sohaib
Book Title: Computer Vision (ICCV), 2011 IEEE International Conference on
Pages: 2447--2453
Year: 2011

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Organization: IEEE

Links: pdf
project page

BibTex

@inproceedings{zaheer2011multiview,
  title = {Multiview Structure from Motion in Trajectory Space},
  author = {Zaheer, Aamer and Akhter, Ijaz and Mohammad, Haris B and Marzban, Shabbir and Khan, Sohaib},
  booktitle = {Computer Vision (ICCV), 2011 IEEE International Conference on},
  pages = {2447--2453},
  organization = {IEEE},
  year = {2011},
  doi = {}
}