Medial features for superpixel segmentation

David Engel, Luciano Spinello, Rudolph Triebel, Roland Siegwart, Heinrich Bulthoff, Cristóbal Curio

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationProceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009
Pages248-252
Number of pages5
Publication statusPublished - 2009 Dec 1
Externally publishedYes
Event11th IAPR Conference on Machine Vision Applications, MVA 2009 - Yokohama, Japan
Duration: 2009 May 202009 May 22

Other

Other11th IAPR Conference on Machine Vision Applications, MVA 2009
CountryJapan
CityYokohama
Period09/5/2009/5/22

Fingerprint

Image segmentation
Computer vision
Seed
Flow fields
Pixels

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Engel, D., Spinello, L., Triebel, R., Siegwart, R., Bulthoff, H., & Curio, C. (2009). Medial features for superpixel segmentation. In Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009 (pp. 248-252)

Medial features for superpixel segmentation. / Engel, David; Spinello, Luciano; Triebel, Rudolph; Siegwart, Roland; Bulthoff, Heinrich; Curio, Cristóbal.

Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. 2009. p. 248-252.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Engel, D, Spinello, L, Triebel, R, Siegwart, R, Bulthoff, H & Curio, C 2009, Medial features for superpixel segmentation. in Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. pp. 248-252, 11th IAPR Conference on Machine Vision Applications, MVA 2009, Yokohama, Japan, 09/5/20.
Engel D, Spinello L, Triebel R, Siegwart R, Bulthoff H, Curio C. Medial features for superpixel segmentation. In Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. 2009. p. 248-252
Engel, David ; Spinello, Luciano ; Triebel, Rudolph ; Siegwart, Roland ; Bulthoff, Heinrich ; Curio, Cristóbal. / Medial features for superpixel segmentation. Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. 2009. pp. 248-252
@inproceedings{ec51ddde27494ea8a74f8324e1a34230,
title = "Medial features for superpixel segmentation",
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.",
author = "David Engel and Luciano Spinello and Rudolph Triebel and Roland Siegwart and Heinrich Bulthoff and Crist{\'o}bal Curio",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9784901122092",
pages = "248--252",
booktitle = "Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009",

}

TY - GEN

T1 - Medial features for superpixel segmentation

AU - Engel, David

AU - Spinello, Luciano

AU - Triebel, Rudolph

AU - Siegwart, Roland

AU - Bulthoff, Heinrich

AU - Curio, Cristóbal

PY - 2009/12/1

Y1 - 2009/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84867851920&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867851920&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84867851920

SN - 9784901122092

SP - 248

EP - 252

BT - Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009

ER -