MAIA - A machine learning assisted image annotation method for environmental monitoring and exploration
Zurowietz M, Langenkämper D, Hosking B, Ruhl H, Nattkemper TW (2018)
PLoS ONE 13(11): e0207498.
Zeitschriftenaufsatz
| Veröffentlicht | Englisch
Download
Autor*in
Zurowietz, MartinUniBi ;
Langenkämper, DanielUniBi ;
Hosking, Brett;
Ruhl, Henry;
Nattkemper, Tim WilhelmUniBi
Einrichtung
Abstract / Bemerkung
Digital imaging has become one of the most important techniques in environmental monitoring and exploration. In the case of the marine environment, mobile platforms such as autonomous underwater vehicles (AUVs) are now equipped with high-resolution cameras to capture huge collections of images from the seabed. However, the timely evaluation of all these images presents a bottleneck problem as tens of thousands or more images can be collected during a single dive. This makes computational support for marine image analysis essential. Computer-aided analysis of environmental images (and marine images in particular) with machine learning algorithms is promising, but challenging and different to other imaging domains because training data and class labels cannot be collected as efficiently and comprehensively as in other areas. In this paper, we present Machine learning Assisted Image Annotation (MAIA), a new image annotation method for environmental monitoring and exploration that overcomes the obstacle of missing training data. The method uses a combination of autoencoder networks and Mask Region-based Convolutional Neural Network (Mask R-CNN), which allows human observers to annotate large image collections much faster than before. We evaluated the method with three marine image datasets featuring different types of background, imaging equipment and object classes. Using MAIA, we were able to annotate objects of interest with an average recall of 84.1% more than twice as fast as compared to “traditional” annotation methods, which are purely based on software-supported direct visual inspection and manual annotation. The speed gain increases proportionally with the size of a dataset. The MAIA approach represents a substantial improvement on the path to greater efficiency in the annotation of large benthic image collections.
Stichworte
Marine Biology;
Computer Vision;
Remote Sensing;
Machine Learning;
Deep Learning
Erscheinungsjahr
2018
Zeitschriftentitel
PLoS ONE
Band
13
Ausgabe
11
Art.-Nr.
e0207498
Urheberrecht / Lizenzen
ISSN
1932-6203
eISSN
1932-6203
Finanzierungs-Informationen
Open-Access-Publikationskosten wurden durch die Deutsche Forschungsgemeinschaft und die Universität Bielefeld gefördert.
Page URI
https://pub.uni-bielefeld.de/record/2932066
Zitieren
Zurowietz M, Langenkämper D, Hosking B, Ruhl H, Nattkemper TW. MAIA - A machine learning assisted image annotation method for environmental monitoring and exploration . PLoS ONE. 2018;13(11): e0207498.
Zurowietz, M., Langenkämper, D., Hosking, B., Ruhl, H., & Nattkemper, T. W. (2018). MAIA - A machine learning assisted image annotation method for environmental monitoring and exploration . PLoS ONE, 13(11), e0207498. doi:10.1371/journal.pone.0207498
Zurowietz, Martin, Langenkämper, Daniel, Hosking, Brett, Ruhl, Henry, and Nattkemper, Tim Wilhelm. 2018. “MAIA - A machine learning assisted image annotation method for environmental monitoring and exploration ”. PLoS ONE 13 (11): e0207498.
Zurowietz, M., Langenkämper, D., Hosking, B., Ruhl, H., and Nattkemper, T. W. (2018). MAIA - A machine learning assisted image annotation method for environmental monitoring and exploration . PLoS ONE 13:e0207498.
Zurowietz, M., et al., 2018. MAIA - A machine learning assisted image annotation method for environmental monitoring and exploration . PLoS ONE, 13(11): e0207498.
M. Zurowietz, et al., “MAIA - A machine learning assisted image annotation method for environmental monitoring and exploration ”, PLoS ONE, vol. 13, 2018, : e0207498.
Zurowietz, M., Langenkämper, D., Hosking, B., Ruhl, H., Nattkemper, T.W.: MAIA - A machine learning assisted image annotation method for environmental monitoring and exploration . PLoS ONE. 13, : e0207498 (2018).
Zurowietz, Martin, Langenkämper, Daniel, Hosking, Brett, Ruhl, Henry, and Nattkemper, Tim Wilhelm. “MAIA - A machine learning assisted image annotation method for environmental monitoring and exploration ”. PLoS ONE 13.11 (2018): e0207498.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung 4.0 International Public License (CC-BY 4.0):
Volltext(e)
Name
Access Level
Open Access
Zuletzt Hochgeladen
2019-09-06T09:19:02Z
MD5 Prüfsumme
56c2fc1473602bb254805d4e9f1bc1ac
Link(s) zu Volltext(en)
Access Level
Open Access
Daten bereitgestellt von European Bioinformatics Institute (EBI)
2 Zitationen in Europe PMC
Daten bereitgestellt von Europe PubMed Central.
Computer vision enables short- and long-term analysis of Lophelia pertusa polyp behaviour and colour from an underwater observatory.
Osterloff J, Nilssen I, Järnegren J, Van Engeland T, Buhl-Mortensen P, Nattkemper TW., Sci Rep 9(1), 2019
PMID: 31036904
Osterloff J, Nilssen I, Järnegren J, Van Engeland T, Buhl-Mortensen P, Nattkemper TW., Sci Rep 9(1), 2019
PMID: 31036904
On the impact of Citizen Science-derived data quality on deep learning based classification in marine images.
Langenkämper D, Simon-Lledó E, Hosking B, Jones DOB, Nattkemper TW., PLoS One 14(6), 2019
PMID: 31188894
Langenkämper D, Simon-Lledó E, Hosking B, Jones DOB, Nattkemper TW., PLoS One 14(6), 2019
PMID: 31188894
30 References
Daten bereitgestellt von Europe PubMed Central.
AUTHOR UNKNOWN, 2015
BIIGLE 2.0—Browsing and Annotating Large Marine Image Collections
AUTHOR UNKNOWN, 2017
AUTHOR UNKNOWN, 2017
RecoMIA—Recommendations for Marine Image Annotation: Lessons Learned and Future Directions
AUTHOR UNKNOWN, 2016
AUTHOR UNKNOWN, 2016
An evaluation of the error and uncertainty in epibenthos cover estimates from AUV images collected with an efficient, spatially-balanced design.
Monk J, Barrett NS, Peel D, Lawrence E, Hill NA, Lucieer V, Hayes KR., PLoS ONE 13(9), 2018
PMID: 30226871
Monk J, Barrett NS, Peel D, Lawrence E, Hill NA, Lucieer V, Hayes KR., PLoS ONE 13(9), 2018
PMID: 30226871
Comparison of image annotation data generated by multiple investigators for benthic ecology
AUTHOR UNKNOWN, 2016
AUTHOR UNKNOWN, 2016
AUTHOR UNKNOWN, 2014
AUTHOR UNKNOWN, 0
AUTHOR UNKNOWN, 2003
Neural networks and principal component analysis: Learning from examples without local minima
AUTHOR UNKNOWN, 1989
AUTHOR UNKNOWN, 1989
AUTHOR UNKNOWN, 2015
AUTHOR UNKNOWN, 0
Local deep-feature alignment for unsupervised dimension reduction
AUTHOR UNKNOWN, 2018
AUTHOR UNKNOWN, 2018
AUTHOR UNKNOWN, 0
Multimodal Deep Autoencoder for Human Pose Recovery.
Hong C, Yu J, Wan J, Tao D, Wang M., IEEE Trans Image Process 24(12), 2015
PMID: 26452284
Hong C, Yu J, Wan J, Tao D, Wang M., IEEE Trans Image Process 24(12), 2015
PMID: 26452284
Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images.
Xu J, Xiang L, Liu Q, Gilmore H, Wu J, Tang J, Madabhushi A., IEEE Trans Med Imaging 35(1), 2015
PMID: 26208307
Xu J, Xiang L, Liu Q, Gilmore H, Wu J, Tang J, Madabhushi A., IEEE Trans Med Imaging 35(1), 2015
PMID: 26208307
AUTHOR UNKNOWN, 2002
AUTHOR UNKNOWN, 2018
AUTHOR UNKNOWN, 0
AUTHOR UNKNOWN, 0
AUTHOR UNKNOWN, 0
AUTHOR UNKNOWN, 0
AUTHOR UNKNOWN, 0
AUTHOR UNKNOWN, 0
AUTHOR UNKNOWN, 0
AUTHOR UNKNOWN, 2017
Increased fluid flow activity in shallow sediments at the 3 km Long Hugin Fracture in the central North Sea
AUTHOR UNKNOWN, 2018
AUTHOR UNKNOWN, 2018
A new method for ecological surveying of the abyss using autonomous underwater vehicle photography
AUTHOR UNKNOWN, 2014
AUTHOR UNKNOWN, 2014
AUTHOR UNKNOWN, 0
A systematic analysis of performance measures for classification tasks
AUTHOR UNKNOWN, 2009
AUTHOR UNKNOWN, 2009
AUTHOR UNKNOWN, 0
Export
Markieren/ Markierung löschen
Markierte Publikationen
Web of Science
Dieser Datensatz im Web of Science®Quellen
PMID: 30444917
PubMed | Europe PMC
Suchen in