Rapid image processing and classification in underwater exploration using advanced high performance computing

Computational underwater image analysis is developing into a mature field of research, with an increasing number of companies, academic groups and researchers showing interest in it. While on the one hand, the basic question is addressed by many groups, how algorithms can be applied to automatically detect and classify objects of interest (OOI) in underwater image footage, on the other hand the questions for efficiency and performance, i.e. the time a computer (or a compute cluster) needs to perform this task, has received much attention yet. In this paper we will show, how nowadays methods for high performance computing like parallelization and GPU computing via CUDA (Compute Unified Device Architecture) can be used to achieve both, image enhancement and segmentation in less than 0.2 sec per image (4224 × 2376 pixel) on average, which paves the way to real time online applications.

[1]  Hubert Staudigel,et al.  Seamount mineral deposits--A source of rare metals for high technology industries , 2010 .

[2]  Kevin E. Kohler,et al.  Coral Point Count with Excel extensions (CPCe): A Visual Basic program for the determination of coral and substrate coverage using random point count methodology , 2006, Comput. Geosci..

[3]  Tim W. Nattkemper,et al.  Ranking Color Correction Algorithms Using Cluster Indices , 2014, 2014 ICPR Workshop on Computer Vision for Analysis of Underwater Imagery.

[4]  Hartmut Bluhm,et al.  Re-establishment of an abyssal megabenthic community after experimental physical disturbance of the seafloor , 2001 .

[5]  Tim W. Nattkemper,et al.  DELPHI—fast and adaptive computational laser point detection and visual footprint quantification for arbitrary underwater image collections , 2015, Front. Mar. Sci..

[6]  Rahul Sharma,et al.  Assessing the distribution and abundance of seabed minerals from seafloor photographic data in the Central Indian Ocean Basin , 2013 .

[7]  Nicola L. Foster,et al.  Quality assurance in the identification of deep-sea taxa from video and image analysis: response to Henry and Roberts , 2014 .

[8]  Tim Wilhelm Nattkemper,et al.  Image-based marine resource exploration and biodiversity assessment with MAMAS (Marine data Asset Management and Analysis System) , 2014 .

[9]  Melanie Bergmann,et al.  HAUSGARTEN: Multidisciplinary Investigations at a Deep-Sea, Long-Term Observatory in the Arctic Ocean , 2005 .

[10]  Autun Purser,et al.  Temporal and spatial benthic data collection via an internet operated Deep Sea Crawler , 2013 .

[11]  Thomas Kuhn,et al.  Application of Hydro-Acoustic and Video Data for the Exploration of Manganese Nodule Fields , 2013 .

[12]  P. Culverhouse,et al.  Do experts make mistakes? A comparison of human and machine identification of dinoflagellates , 2003 .

[13]  NORMAN HOLME.  Resources of the Sea , 1955, Nature.

[14]  Thomas Kuhn,et al.  Seabed Classification Using a Bag-of-Prototypes Feature Representation , 2014, 2014 ICPR Workshop on Computer Vision for Analysis of Underwater Imagery.

[15]  Mariana Arc,et al.  a seamount Mineral Deposits a source of rare Metals for high-techNology iNDustries , 2022 .

[16]  Cindy Lee Van Dover,et al.  Mining seafloor massive sulphides and biodiversity: what is at risk? , 2011 .

[17]  Phil Culverhouse,et al.  Time to automate identification , 2010, Nature.

[18]  J. Gutt,et al.  Semi-Automated Image Analysis for the Assessment of Megafaunal Densities at the Arctic Deep-Sea Observatory HAUSGARTEN , 2012, PloS one.

[19]  Roberto Danovaro,et al.  Ecological restoration in the deep sea: Desiderata , 2014 .

[20]  C. Roman,et al.  Seabed AUV offers new platform for high‐resolution imaging , 2004 .

[21]  Olaf Pfannkuche,et al.  GEOMAR Landers as Long-Term Deep-Sea Observatories , 2003 .

[22]  P. Rona.  Resources of the Sea Floor , 2003, Science.

[23]  Tim W. Nattkemper,et al.  Biigle - Web 2.0 enabled labelling and exploring of images from the Arctic deep-sea observatory HAUSGARTEN , 2009, OCEANS 2009-EUROPE.

[24]  E Guillemot,et al.  Video acquisition, archiving, annotation and analysis: NEPTUNE Canada's real-time georeferenced library of deep sea video , 2010, OCEANS 2010 MTS/IEEE SEATTLE.

[25]  S D Gaines,et al.  From principles to practice: a spatial approach to systematic conservation planning in the deep sea , 2013, Proceedings of the Royal Society B: Biological Sciences.

[26]  Helge J. Ritter,et al.  Large-scale data exploration with the hierarchically growing hyperbolic SOM , 2006, Neural Networks.

[27]  Jörg Ontrup,et al.  Use of machine-learning algorithms for the automated detection of cold-water coral habitats: a pilot study , 2009 .