A layered motion representation with occlusion and compact spatial support
2002
Conference Paper
ps
We describe a 2.5D layered representation for visual motion analysis. The representation provides a global interpretation of image motion in terms of several spatially localized foreground regions along with a background region. Each of these regions comprises a parametric shape model and a parametric motion model. The representation also contains depth ordering so visibility and occlusion are rightly included in the estimation of the model parameters. Finally, because the number of objects, their positions, shapes and sizes, and their relative depths are all unknown, initial models are drawn from a proposal distribution, and then compared using a penalized likelihood criterion. This allows us to automatically initialize new models, and to compare different depth orderings.
Author(s): | Fleet, D. J. and Jepson, A. and Black, M. J. |
Book Title: | European Conf. on Computer Vision, ECCV 2002 |
Volume: | 1 |
Pages: | 692-706 |
Year: | 2002 |
Series: | LNCS 2353 |
Editors: | A. Heyden and G. Sparr and M. Nielsen and P. Johansen |
Publisher: | Springer-Verlag |
Department(s): | Perceiving Systems |
Bibtex Type: | Conference Paper (inproceedings) |
Paper Type: | Conference |
Links: |
pdf
|
BibTex @inproceedings{Black:ECCV:2002:2, title = {A layered motion representation with occlusion and compact spatial support}, author = {Fleet, D. J. and Jepson, A. and Black, M. J.}, booktitle = {European Conf. on Computer Vision, ECCV 2002}, volume = {1}, pages = {692-706}, series = {LNCS 2353}, editors = {A. Heyden and G. Sparr and M. Nielsen and P. Johansen}, publisher = {Springer-Verlag }, year = {2002}, doi = {} } |