English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Medial Features for Superpixel Segmentation

MPS-Authors
/persons/resource/persons83902

Engel,  D
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons83839

Bülthoff,  HH
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons83871

Curio,  C
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

Locator

http://www.mva-org.jp/mva2009/
(Table of contents)

Fulltext (public)

MVA-2009-Engel.pdf
(Any fulltext), 3MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Engel, D., Spinello, L., Triebel, R., Siegwart, R., Bülthoff, H., & Curio, C. (2009). Medial Features for Superpixel Segmentation. In Eleventh IAPR Conference on Machine Vision Applications (MVA 2009) (pp. 248-252). Tokyo, Japan: MVA Conference Committee.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-C4F4-3
Abstract
Image segmentation plays an important role in computer vision and human scene perception. Image oversegmentation is a common technique to overcome the problem of managing the high number of pixels and the reasoning among them. Specifically, a local and coherent cluster that contains a statistically homogeneous region is denoted as a superpixel. In this paper we propose a novel algorithm that segments an image into superpixels employing a new kind of shape centered feature which serve as a seed points for image segmentation, based on Gradient Vector Flow fields (GVF) [14]. The features are located at image locations with salient symmetry. We compare our algorithm to state-of-the-art superpixel algorithms and demonstrate a performance increase on the standard Berkeley Segmentation Dataset.