Institute Homepage
Institute Homepage DE Sign In

Back

Perceiving Systems Conference Paper 1991

Robust dynamic motion estimation over time

pdf video project
Thumb ticker sm headshot2021
Perceiving Systems
Michael Black
Director
Bildschirmfoto 2013 01 14 um 12.06.42

This paper presents a novel approach to incrementally estimating visual motion over a sequence of images. We start by formulating constraints on image motion to account for the possibility of multiple motions. This is achieved by exploiting the notions of weak continuity and robust statistics in the formulation of the minimization problem. The resulting objective function is non-convex. Traditional stochastic relaxation techniques for minimizing such functions prove inappropriate for the task. We present a highly parallel incremental stochastic minimization algorithm which has a number of advantages over previous approaches. The incremental nature of the scheme makes it truly dynamic and permits the detection of occlusion and disocclusion boundaries.

Award: (IEEE Computer Society Outstanding Paper Award)
Author(s): Black, M. J. and Anandan, P.
Links:
Book Title: Proc. Computer Vision and Pattern Recognition, CVPR-91,
Pages: 296-302
Year: 1991
Month: June
Bibtex Type: Conference Paper (inproceedings)
Address: Maui, Hawaii
Award Paper: IEEE Computer Society Outstanding Paper Award
Electronic Archiving: grant_archive

BibTex 

@inproceedings{Black:CVPR:1991,
  title = {Robust dynamic motion estimation over time},
  aword_paper = {IEEE Computer Society Outstanding Paper Award},
  booktitle = {Proc. Computer Vision and Pattern Recognition, CVPR-91,},
  abstract = {This paper presents a novel approach to incrementally estimating visual motion over a sequence of images. We start by formulating constraints on image motion to account for the possibility of multiple motions. This is achieved by exploiting the notions of weak continuity and robust statistics in the formulation of the minimization problem. The resulting objective function is non-convex. Traditional stochastic relaxation techniques for minimizing such functions prove inappropriate for the task. We present a highly parallel incremental stochastic minimization algorithm which has a number of advantages over previous approaches. The incremental nature of the scheme makes it truly dynamic and permits the detection of occlusion and disocclusion boundaries.},
  pages = {296-302},
  address = {Maui, Hawaii},
  month = jun,
  year = {1991},
  slug = {black-cvpr-1991},
  author = {Black, M. J. and Anandan, P.},
  month_numeric = {6}
}