Abstract
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.
Highlights
Common statements of marine scientists, working with optical image data, currently refer to “drowning in” or being “overrun by” huge amounts of new data coming in
The index i = 0, .., N − 1 runs over all N images of a transect and the index j over the subset of N′ transect images where an expert manually annotated the laser point (LP)
The manually tuned detection system, that was used before DELPHI, resulted in an F-score of 0.86 for T1 and an F-Score of 0.51 for T2
Summary
Common statements of marine scientists, working with optical image data, currently refer to “drowning in” or being “overrun by” huge amounts of new data coming in. This calls for automated methods from computer vision and pattern recognition to guide and support the manual evaluation of those big data vaults (MacLeod and Culverhouse, 2010). DELPHI-adaptive laser point detection of the imaged objects and the area covered This could be the biomass size of occurring biota in habitat studies (Bergmann et al, 2011) or the amount of marine mineral resources in exploration (Schoening et al, 2012b)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
