Faculty of Information Technology, BUT

Publication Details

Comparison of Appearance-Based and Geometry-Based Bubble Detectors

STROKINA Nataliya, JURÁNEK Roman, EEROLA Tuomas, ZEMČÍK Pavel, KÄLVIÄINEN Heikki and LENSU Lasse. Comparison of Appearance-Based and Geometry-Based Bubble Detectors. In: Proccedings of Internation Conference on Computer Vision and Graphics. Lecture Notes in Computer Science, vol. 8671. Warsaw: Springer Verlag, 2014, pp. 610-617. ISBN 978-3-319-11330-2.
Czech title
Porovnání detektorů bublin založených na vzhledu a na geometrii
Type
conference paper
Language
english
Authors
Strokina Nataliya (TUT)
Juránek Roman, Ing., Ph.D. (DCGM FIT BUT)
Eerola Tuomas, doc., Ph.D. (LUT)
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT)
Kälviäinen Heikki, prof. (LUT)
Lensu Lasse (TUT)
Keywords
Detection of Bubbles, 
Abstract

Bubble detection is a complicated tasks since varying lighting conditions changes considerably the appearance of bubbles in liquid. The two common techniques to detect circular objects such as bubbles, the geometry-based and appearance-based approaches, have their advantages and weaknesses. The geometry-based methods often fail to detect small blob-like bubbles that do not match the used geometrical model, and appearance-based approaches are vulnerable to appearance changes caused by, e.g., illumination. In this paper, we compare a geometry-based concentric circular arrangements (CCA) and appearance-based sliding window methods as well as their combinations in terms of bubble detection, gas volume computation, and size distribution estimation. The best bubble detection performance was achieved with the sliding window method whereas the most precise volume estimate was produced by the CCA method. The combination of the two approaches gave only a minor advantage compared to the base methods.
Published
2014
Pages
610-617
Proceedings
Proccedings of Internation Conference on Computer Vision and Graphics
Series
Lecture Notes in Computer Science
Volume
8671
Conference
International Conference on Computer Vision and Graphics 2014, PJIIT - Polish-Japanese Institute of Information Technology, PL
ISBN
978-3-319-11330-2
Publisher
Springer Verlag
Place
Warsaw, PL
DOI
BibTeX
@INPROCEEDINGS{FITPUB10736,
   author = "Nataliya Strokina and Roman Jur\'{a}nek and Tuomas Eerola and Pavel Zem\v{c}\'{i}k and Heikki K\"{a}lvi\"{a}inen and Lasse Lensu",
   title = "Comparison of Appearance-Based and Geometry-Based Bubble Detectors",
   pages = "610--617",
   booktitle = "Proccedings of Internation Conference on Computer Vision and Graphics",
   series = "Lecture Notes in Computer Science",
   volume = 8671,
   year = 2014,
   location = "Warsaw, PL",
   publisher = "Springer Verlag",
   ISBN = "978-3-319-11330-2",
   doi = "10.1007/978-3-319-11331-9\_73",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10736"
}
Back to top