MuFeSaC: Learning when to use which feature detector

Sreenivas R. Sukumar; David L. Page; Hamparsum Bozdogan; Andreas F. Koschan; Mongi A. Abidi

doi:10.1109/ICIP.2007.4379543

MuFeSaC: Learning when to use which feature detector

Sreenivas R. Sukumar, David L. Page, Hamparsum Bozdogan, Andreas F. Koschan, Mongi A. Abidi

Geospatial Science and Human Security Di

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Interest point detectors are the starting point in image analysis for depth estimation using epipolar geometry and camera ego-motion estimation. With several detectors defined in the literature, some of them outperforming others in a specific application context, we introduce Multi-Feature Sample Consensus (MuFeSaC) as an adaptive and automatic procedure to choose a reliable feature detector among competing ones. Our approach is derived based on model selection criteria that we demonstrate for mobile robot self-localization in outdoor environments consisting of both man-made structures and natural vegetation.

Original language	English
Title of host publication	2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings
Publisher	IEEE Computer Society
Pages	149-152
Number of pages	4
ISBN (Print)	1424414377, 9781424414376
DOIs	https://doi.org/10.1109/ICIP.2007.4379543
State	Published - 2006
Event	14th IEEE International Conference on Image Processing, ICIP 2007 - San Antonio, TX, United States Duration: Sep 16 2007 → Sep 19 2007

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	6
ISSN (Print)	1522-4880

Conference

Conference	14th IEEE International Conference on Image Processing, ICIP 2007
Country/Territory	United States
City	San Antonio, TX
Period	09/16/07 → 09/19/07

Keywords

Feature learning
Interest point detector evaluation
RANSAC

Access to Document

10.1109/ICIP.2007.4379543

Cite this

Sukumar, S. R., Page, D. L., Bozdogan, H., Koschan, A. F., & Abidi, M. A. (2006). MuFeSaC: Learning when to use which feature detector. In 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings (pp. 149-152). Article 4379543 (Proceedings - International Conference on Image Processing, ICIP; Vol. 6). IEEE Computer Society. https://doi.org/10.1109/ICIP.2007.4379543

@inproceedings{76fad3f4ca8447b69ea23e1499ddc028,

title = "MuFeSaC: Learning when to use which feature detector",

abstract = "Interest point detectors are the starting point in image analysis for depth estimation using epipolar geometry and camera ego-motion estimation. With several detectors defined in the literature, some of them outperforming others in a specific application context, we introduce Multi-Feature Sample Consensus (MuFeSaC) as an adaptive and automatic procedure to choose a reliable feature detector among competing ones. Our approach is derived based on model selection criteria that we demonstrate for mobile robot self-localization in outdoor environments consisting of both man-made structures and natural vegetation.",

keywords = "Feature learning, Interest point detector evaluation, RANSAC",

author = "Sukumar, \{Sreenivas R.\} and Page, \{David L.\} and Hamparsum Bozdogan and Koschan, \{Andreas F.\} and Abidi, \{Mongi A.\}",

year = "2006",

doi = "10.1109/ICIP.2007.4379543",

language = "English",

isbn = "1424414377",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "149--152",

booktitle = "2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings",

note = "14th IEEE International Conference on Image Processing, ICIP 2007 ; Conference date: 16-09-2007 Through 19-09-2007",

}

Sukumar, SR, Page, DL, Bozdogan, H, Koschan, AF & Abidi, MA 2006, MuFeSaC: Learning when to use which feature detector. in 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings., 4379543, Proceedings - International Conference on Image Processing, ICIP, vol. 6, IEEE Computer Society, pp. 149-152, 14th IEEE International Conference on Image Processing, ICIP 2007, San Antonio, TX, United States, 09/16/07. https://doi.org/10.1109/ICIP.2007.4379543

MuFeSaC: Learning when to use which feature detector. / Sukumar, Sreenivas R.; Page, David L.; Bozdogan, Hamparsum et al.
2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. IEEE Computer Society, 2006. p. 149-152 4379543 (Proceedings - International Conference on Image Processing, ICIP; Vol. 6).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - MuFeSaC

T2 - 14th IEEE International Conference on Image Processing, ICIP 2007

AU - Sukumar, Sreenivas R.

AU - Page, David L.

AU - Bozdogan, Hamparsum

AU - Koschan, Andreas F.

AU - Abidi, Mongi A.

PY - 2006

Y1 - 2006

N2 - Interest point detectors are the starting point in image analysis for depth estimation using epipolar geometry and camera ego-motion estimation. With several detectors defined in the literature, some of them outperforming others in a specific application context, we introduce Multi-Feature Sample Consensus (MuFeSaC) as an adaptive and automatic procedure to choose a reliable feature detector among competing ones. Our approach is derived based on model selection criteria that we demonstrate for mobile robot self-localization in outdoor environments consisting of both man-made structures and natural vegetation.

AB - Interest point detectors are the starting point in image analysis for depth estimation using epipolar geometry and camera ego-motion estimation. With several detectors defined in the literature, some of them outperforming others in a specific application context, we introduce Multi-Feature Sample Consensus (MuFeSaC) as an adaptive and automatic procedure to choose a reliable feature detector among competing ones. Our approach is derived based on model selection criteria that we demonstrate for mobile robot self-localization in outdoor environments consisting of both man-made structures and natural vegetation.

KW - Feature learning

KW - Interest point detector evaluation

KW - RANSAC

UR - https://www.scopus.com/pages/publications/48149109095

U2 - 10.1109/ICIP.2007.4379543

DO - 10.1109/ICIP.2007.4379543

M3 - Conference contribution

AN - SCOPUS:48149109095

SN - 1424414377

SN - 9781424414376

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 149

EP - 152

BT - 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings

PB - IEEE Computer Society

Y2 - 16 September 2007 through 19 September 2007

ER -

MuFeSaC: Learning when to use which feature detector

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this