TY  - JOUR
AB  - 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.
DA  - 2015
DO  - 10.3389/fmars.2015.00020
KW  - Image Footprint Quantification
KW  - Web-based Image Annotation
KW  - Arbitrary Image Collections
KW  - laser point detection
KW  - Annotation Enhancement
KW  - Marine Imaging
KW  - Underwater image analysis
KW  - Remote Sensing Technology
KW  - image processing
KW  - computational learning
KW  - Intelligent systems
KW  - pattern recognition
LA  - eng
PY  - 2015
SN  - 2296-7745
T2  - Frontiers in Marine Science
TI  - DELPHI - fast and adaptive computational laser point detection and visual footprint quantification for arbitrary underwater image collections
UR  - https://nbn-resolving.org/urn:nbn:de:0070-pub-27244313
Y2  - 2024-11-22T02:00:16
ER  -