Fast and efficient local features detection for building recognition

Phuong Giang Nguyen; Hans Jørgen Andersen

doi:10.1007/978-3-642-17934-1

Fast and efficient local features detection for building recognition

Phuong Giang Nguyen, Hans Jørgen Andersen

Research output: Contribution to journal › Journal article › Research › peer-review

Abstract

The vast growth of image databases creates many challenges for
computer vision applications, for instance image retrieval and object recognition.
Large variation in imaging conditions such as illumination and geometrical
properties (including scale, rotation, and viewpoint) gives rise to the
need for invariant features; i.e. image features should have minimal differences
under these conditions. Local image features in the form of key points
are widely used because of their invariant properties. In this chapter, we analyze
different issues relating to existing local feature detectors. Based on this
analysis, we present a new approach for detecting and filtering local features.
The proposed approach is tested in a real-life application which supports
navigation in urban environments based on visual information. The study
shows that our approach performs as well as existing methods but with a
significantly lower number of features.

Original language	English
Book series	Studies in Computational Intelligence
Volume	339
Pages (from-to)	87-104
Number of pages	18
ISSN	1860-949X
DOIs	https://doi.org/10.1007/978-3-642-17934-1
Publication status	Published - 2011

Bibliographical note

Published in: Kwasnicka, H. & Jain, L. C. (Eds.): Innovations in Intelligent Image Analysis. ISBN (print): 978-3-642-17933-4, ISBN (electronic): 978-3-642-17934-1

Access to Document

10.1007/978-3-642-17934-1

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@article{daff70fc46b847e2b6c7e713684b53b4,

title = "Fast and efficient local features detection for building recognition",

abstract = "The vast growth of image databases creates many challenges forcomputer vision applications, for instance image retrieval and object recognition.Large variation in imaging conditions such as illumination and geometricalproperties (including scale, rotation, and viewpoint) gives rise to theneed for invariant features; i.e. image features should have minimal differencesunder these conditions. Local image features in the form of key pointsare widely used because of their invariant properties. In this chapter, we analyzedifferent issues relating to existing local feature detectors. Based on thisanalysis, we present a new approach for detecting and filtering local features.The proposed approach is tested in a real-life application which supportsnavigation in urban environments based on visual information. The studyshows that our approach performs as well as existing methods but with asignificantly lower number of features.",

author = "Nguyen, {Phuong Giang} and Andersen, {Hans J{\o}rgen}",

note = "Published in: Kwasnicka, H. & Jain, L. C. (Eds.): Innovations in Intelligent Image Analysis. ISBN (print): 978-3-642-17933-4, ISBN (electronic): 978-3-642-17934-1",

year = "2011",

doi = "10.1007/978-3-642-17934-1",

language = "English",

volume = "339",

pages = "87--104",

journal = "Studies in Computational Intelligence",

issn = "1860-949X",

publisher = "Physica-Verlag",

}

TY - JOUR

T1 - Fast and efficient local features detection for building recognition

AU - Nguyen, Phuong Giang

AU - Andersen, Hans Jørgen

N1 - Published in: Kwasnicka, H. & Jain, L. C. (Eds.): Innovations in Intelligent Image Analysis. ISBN (print): 978-3-642-17933-4, ISBN (electronic): 978-3-642-17934-1

PY - 2011

Y1 - 2011

N2 - The vast growth of image databases creates many challenges forcomputer vision applications, for instance image retrieval and object recognition.Large variation in imaging conditions such as illumination and geometricalproperties (including scale, rotation, and viewpoint) gives rise to theneed for invariant features; i.e. image features should have minimal differencesunder these conditions. Local image features in the form of key pointsare widely used because of their invariant properties. In this chapter, we analyzedifferent issues relating to existing local feature detectors. Based on thisanalysis, we present a new approach for detecting and filtering local features.The proposed approach is tested in a real-life application which supportsnavigation in urban environments based on visual information. The studyshows that our approach performs as well as existing methods but with asignificantly lower number of features.

AB - The vast growth of image databases creates many challenges forcomputer vision applications, for instance image retrieval and object recognition.Large variation in imaging conditions such as illumination and geometricalproperties (including scale, rotation, and viewpoint) gives rise to theneed for invariant features; i.e. image features should have minimal differencesunder these conditions. Local image features in the form of key pointsare widely used because of their invariant properties. In this chapter, we analyzedifferent issues relating to existing local feature detectors. Based on thisanalysis, we present a new approach for detecting and filtering local features.The proposed approach is tested in a real-life application which supportsnavigation in urban environments based on visual information. The studyshows that our approach performs as well as existing methods but with asignificantly lower number of features.

U2 - 10.1007/978-3-642-17934-1

DO - 10.1007/978-3-642-17934-1

M3 - Journal article

SN - 1860-949X

VL - 339

SP - 87

EP - 104

JO - Studies in Computational Intelligence

JF - Studies in Computational Intelligence

ER -

Fast and efficient local features detection for building recognition

Abstract

Bibliographical note

Access to Document

AUB Link

Fingerprint

Cite this