DELPHI - fast and adaptive computational laser point detection and visual footprint quantification for arbitrary underwater image collections

Schoening T, Kuhn T, Bergmann M, Nattkemper TW (2015)
Frontiers in Marine Science 2: 20.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
OA
Autor*in
Schoening, TimmUniBi; Kuhn, Thomas; Bergmann, Melanie; Nattkemper, Tim WilhelmUniBi
Abstract / Bemerkung
Marine researchers continue to create large quantities of benthic images e.g. using AUVs (Autonomous Underwater Vehicles). In order to quantify the size of sessile objects in the images, a pixel-to-centimetre ratio is required for each image, often indirectly provided through a geometric laser point (LP) pattern, projected onto the seafloor. Manual annotation of these LPs in all images is too time-consuming and thus infeasible for nowadays data volumes. Because of the technical evolution of camera rigs, the LP's geometrical layout and colour features vary for different expeditions and projects. This makes the application of one algorithm, tuned to a strictly defined LP pattern, also ineffective. Here we present the web-tool DELPHI, that efficiently learns the LP layout for one image transect / collection from just a small number of hand labelled LPs and applies this layout model to the rest of the data. The efficiency in adapting to new data allows to compute the LPs and the pixel-to-centimetre ratio fully automatic and with high accuracy. DELPHI is applied to two real-world examples and shows clear improvements regarding reduction of tuning effort for new LP patterns as well as increasing detection performance.
Stichworte
Image Footprint Quantification; Web-based Image Annotation; Arbitrary Image Collections; laser point detection; Annotation Enhancement; Marine Imaging; Underwater image analysis; Remote Sensing Technology; image processing; computational learning; Intelligent systems; pattern recognition
Erscheinungsjahr
2015
Zeitschriftentitel
Frontiers in Marine Science
Band
2
Art.-Nr.
20
ISSN
2296-7745
Finanzierungs-Informationen
Open-Access-Publikationskosten wurden durch die Deutsche Forschungsgemeinschaft und die Universität Bielefeld gefördert.
Page URI
https://pub.uni-bielefeld.de/record/2724431

Zitieren

Schoening T, Kuhn T, Bergmann M, Nattkemper TW. DELPHI - fast and adaptive computational laser point detection and visual footprint quantification for arbitrary underwater image collections. Frontiers in Marine Science. 2015;2: 20.
Schoening, T., Kuhn, T., Bergmann, M., & Nattkemper, T. W. (2015). DELPHI - fast and adaptive computational laser point detection and visual footprint quantification for arbitrary underwater image collections. Frontiers in Marine Science, 2, 20. doi:10.3389/fmars.2015.00020
Schoening, T., Kuhn, T., Bergmann, M., and Nattkemper, T. W. (2015). DELPHI - fast and adaptive computational laser point detection and visual footprint quantification for arbitrary underwater image collections. Frontiers in Marine Science 2:20.
Schoening, T., et al., 2015. DELPHI - fast and adaptive computational laser point detection and visual footprint quantification for arbitrary underwater image collections. Frontiers in Marine Science, 2: 20.
T. Schoening, et al., “DELPHI - fast and adaptive computational laser point detection and visual footprint quantification for arbitrary underwater image collections”, Frontiers in Marine Science, vol. 2, 2015, : 20.
Schoening, T., Kuhn, T., Bergmann, M., Nattkemper, T.W.: DELPHI - fast and adaptive computational laser point detection and visual footprint quantification for arbitrary underwater image collections. Frontiers in Marine Science. 2, : 20 (2015).
Schoening, Timm, Kuhn, Thomas, Bergmann, Melanie, and Nattkemper, Tim Wilhelm. “DELPHI - fast and adaptive computational laser point detection and visual footprint quantification for arbitrary underwater image collections”. Frontiers in Marine Science 2 (2015): 20.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T09:18:30Z
MD5 Prüfsumme
b11c26a87dce9da2241278fc105e53c0

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Suchen in

Google Scholar