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.

Download
OA 2.38 MB
Zeitschriftenaufsatz | Veröffentlicht | Englisch
Volltext vorhanden für diesen Nachweis
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.
Erscheinungsjahr
Zeitschriftentitel
PLoS ONE
Band
13
Ausgabe
11
Art.-Nr.
e0207498
eISSN
Finanzierungs-Informationen
Article Processing Charge funded by the Deutsche Forschungsgemeinschaft and the Open Access Publication Fund of Bielefeld University.
PUB-ID

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, 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)
Access Level
OA Open Access
Zuletzt Hochgeladen
2018-12-20T08:26:30Z

Link(s) zu Volltext(en)
Access Level
OA Open Access

1 Zitation 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

30 References

Daten bereitgestellt von Europe PubMed Central.


AUTHOR UNKNOWN, 2015
BIIGLE 2.0—Browsing and Annotating Large Marine Image Collections
AUTHOR UNKNOWN, 2017
RecoMIA—Recommendations for Marine Image Annotation: Lessons Learned and Future Directions
AUTHOR UNKNOWN, 2016
Comparison of image annotation data generated by multiple investigators for benthic ecology
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, 2015

AUTHOR UNKNOWN, 0
Local deep-feature alignment for unsupervised dimension reduction
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
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

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
A new method for ecological surveying of the abyss using autonomous underwater vehicle photography
AUTHOR UNKNOWN, 2014

AUTHOR UNKNOWN, 0
A systematic analysis of performance measures for classification tasks
AUTHOR UNKNOWN, 2009

AUTHOR UNKNOWN, 0

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Quellen

PMID: 30444917
PubMed | Europe PMC

Suchen in

Google Scholar