January
2005
Multilevel Spectral Partitioning for Efficient Image Segmentation and Tracking
Authors:
Abstract:
An efficient multilevel method for solving normalized cut image segmentation problems is presented. The method uses the lattice geometry of images to define a set of coarsened graph partitioning problems. This problem hierarchy provides a framework for rapidly estimating the eigenvectors of normalized graph Laplacians. Within this framework, a coarse solution obtained with a standard eigensolver is propagated to increasingly fine problem instances and refined using subspace iterations. Results are presented for image segmentation and tracking problems. The computational cost of the multilevel method is an order of magnitude lower than current sampling techniques and results in more stable image segmentations.
copied = false, 2000);
">
@workshop{Tolliver-2005-9105,
author = {David Tolliver And Simon Baker And Robert Collins},
title = {Multilevel Spectral Partitioning for Efficient Image Segmentation and Tracking},
booktitle = {Proceedings of 7th IEEE Workshops on Applications of Computer Vision (WACV/MOTION '05)},
year = {2005},
month = {January},
pages = {414 - 420},
}
author = {David Tolliver And Simon Baker And Robert Collins},
title = {Multilevel Spectral Partitioning for Efficient Image Segmentation and Tracking},
booktitle = {Proceedings of 7th IEEE Workshops on Applications of Computer Vision (WACV/MOTION '05)},
year = {2005},
month = {January},
pages = {414 - 420},
}