Detail publikace

Comparison of Appearance-Based and Geometry-Based Bubble Detectors

Originální název

Comparison of Appearance-Based and Geometry-Based Bubble Detectors

Anglický název

Comparison of Appearance-Based and Geometry-Based Bubble Detectors

Jazyk

en

Originální abstrakt

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.

Anglický abstrakt

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.

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",
  annote="
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.",
  address="Springer Verlag",
  booktitle="Proccedings of Internation Conference on Computer Vision and Graphics",
  chapter="111660",
  doi="10.1007/978-3-319-11331-9_73",
  edition="Lecture Notes in Computer Science",
  howpublished="online",
  institution="Springer Verlag",
  year="2014",
  month="october",
  pages="610--617",
  publisher="Springer Verlag",
  type="conference paper"
}