Přístupnostní navigace
E-application
Search Search Close
Publication detail
STROKINA, N. JURÁNEK, R. EEROLA, T. ZEMČÍK, P. KÄLVIÄINEN, H. LENSU, L.
Original Title
Comparison of Appearance-Based and Geometry-Based Bubble Detectors
Type
conference paper
Language
English
Original 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.
Keywords
Detection of Bubbles,
Authors
STROKINA, N.; JURÁNEK, R.; EEROLA, T.; ZEMČÍK, P.; KÄLVIÄINEN, H.; LENSU, L.
RIV year
2014
Released
8. 10. 2014
Publisher
Springer Verlag
Location
Warsaw
ISBN
978-3-319-11330-2
Book
Proccedings of Internation Conference on Computer Vision and Graphics
Edition
Lecture Notes in Computer Science
Pages from
610
Pages to
617
Pages count
8
BibTex
@inproceedings{BUT111660, author="Nataliya {Strokina} and Roman {Juránek} and Tuomas {Eerola} and Pavel {Zemčík} and Heikki {Kälviäinen} and Lasse {Lensu}", title="Comparison of Appearance-Based and Geometry-Based Bubble Detectors", booktitle="Proccedings of Internation Conference on Computer Vision and Graphics", year="2014", series="Lecture Notes in Computer Science", volume="8671", pages="610--617", publisher="Springer Verlag", address="Warsaw", doi="10.1007/978-3-319-11331-9\{_}73", isbn="978-3-319-11330-2" }