Welcome to the homepage of the

Mathematical Optimization for Data Science Group

Department of Mathematics and Computer Science, Saarland University, Germany

Higher Order Motion Models and Spectral Clustering

P. Ochs and T. Brox

Abstract:
Motion segmentation based on point trajectories can integrate information of a whole video shot to detect and separate moving objects. Commonly, similarities are defined between pairs of trajectories. However, pairwise similarities restrict the motion model to translations. Non-translational motion, such as rotation or scaling, is penalized in such an approach. We propose to define similarities on higher order tuples rather than pairs, which leads to hypergraphs. To apply spectral clustering, the hypergraph is transferred to an ordinary graph, an operation that can be interpreted as a projection. We propose a specific nonlinear projection via a regularized maximum operator, and show that it yields significant improvements both compared to pairwise similarities and alternative hypergraph projections.
pdf Bibtex Publisher's link Code
Citation:
P. Ochs, T. Brox:
Higher Order Motion Models and Spectral Clustering. [pdf]
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2012.
Bibtex:
@inproceedings{OB12,
  title        = {Higher Order Motion Models and Spectral Clustering},
  author       = {P. Ochs and T. Brox},
  year         = {2012},
  booktitle    = {IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)},
}


MOP Group
©2017-2024
The author is not
responsible for
the content of
external pages.