Multilevel Spectral Partitioning for Efficient Image Segmentation and Tracking

January 2005

Multilevel Spectral Partitioning for Efficient Image Segmentation and Tracking

Authors:

David Tolliver, Simon Baker, and Robert Collins

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.
@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},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.