Details
| Original language | English |
|---|---|
| Pages (from-to) | 64-79 |
| Number of pages | 16 |
| Journal | BIOFOULING |
| Volume | 39 |
| Issue number | 1 |
| Early online date | 16 Mar 2023 |
| Publication status | Published - 2023 |
Abstract
Biofouling is a major challenge for sustainable shipping, filter membranes, heat exchangers, and medical devices. The development of fouling-resistant coatings requires the evaluation of their effectiveness. Such an evaluation is usually based on the assessment of fouling progression after different exposure times to the target medium (e.g. salt water). The manual assessment of macrofouling requires expert knowledge about local fouling communities due to high variances in phenotypical appearance, has single-image sampling inaccuracies for certain species, and lacks spatial information. Here an approach for automatic image-based macrofouling analysis was presented. A dataset with dense labels prepared from field panel images was made and a convolutional network (adapted U-Net) for the semantic segmentation of different macrofouling classes was proposed. The establishment of macrofouling localization allows for the generation of a successional model which enables the determination of direct surface attachment and in-depth epibiotic studies.
Keywords
- deep learning, environmental monitoring, epibiotic analysis, invasive species, macrofouling, ocean research
ASJC Scopus subject areas
- Agricultural and Biological Sciences(all)
- Aquatic Science
- Immunology and Microbiology(all)
- Applied Microbiology and Biotechnology
- Environmental Science(all)
- Water Science and Technology
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: BIOFOULING, Vol. 39, No. 1, 2023, p. 64-79.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Semantic segmentation for fully automated macrofouling analysis on coatings after field exposure
AU - Krause, Lutz M.K.
AU - Manderfeld, Emily
AU - Gnutt, Patricia
AU - Vogler, Louisa
AU - Wassick, Ann
AU - Richard, Kailey
AU - Rudolph, Marco
AU - Hunsucker, Kelli Z.
AU - Swain, Geoffrey W.
AU - Rosenhahn, Bodo
AU - Rosenhahn, Axel
N1 - Funding Information: The work was funded by ONR N00014-20-12244 (Ruhr University Bochum) and ONR N00014-20-1-2243 (Florida Institute of Technology). The authors are grateful to the Deutsche Forschungsgemeinschaft (DFG) for funding in GRK2376/331085229. The authors thank Labelbox for making their online annotation platform available to us.
PY - 2023
Y1 - 2023
N2 - Biofouling is a major challenge for sustainable shipping, filter membranes, heat exchangers, and medical devices. The development of fouling-resistant coatings requires the evaluation of their effectiveness. Such an evaluation is usually based on the assessment of fouling progression after different exposure times to the target medium (e.g. salt water). The manual assessment of macrofouling requires expert knowledge about local fouling communities due to high variances in phenotypical appearance, has single-image sampling inaccuracies for certain species, and lacks spatial information. Here an approach for automatic image-based macrofouling analysis was presented. A dataset with dense labels prepared from field panel images was made and a convolutional network (adapted U-Net) for the semantic segmentation of different macrofouling classes was proposed. The establishment of macrofouling localization allows for the generation of a successional model which enables the determination of direct surface attachment and in-depth epibiotic studies.
AB - Biofouling is a major challenge for sustainable shipping, filter membranes, heat exchangers, and medical devices. The development of fouling-resistant coatings requires the evaluation of their effectiveness. Such an evaluation is usually based on the assessment of fouling progression after different exposure times to the target medium (e.g. salt water). The manual assessment of macrofouling requires expert knowledge about local fouling communities due to high variances in phenotypical appearance, has single-image sampling inaccuracies for certain species, and lacks spatial information. Here an approach for automatic image-based macrofouling analysis was presented. A dataset with dense labels prepared from field panel images was made and a convolutional network (adapted U-Net) for the semantic segmentation of different macrofouling classes was proposed. The establishment of macrofouling localization allows for the generation of a successional model which enables the determination of direct surface attachment and in-depth epibiotic studies.
KW - deep learning
KW - environmental monitoring
KW - epibiotic analysis
KW - invasive species
KW - macrofouling
KW - ocean research
UR - http://www.scopus.com/inward/record.url?scp=85151168192&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2211.11607
DO - 10.48550/arXiv.2211.11607
M3 - Article
C2 - 36924139
AN - SCOPUS:85151168192
VL - 39
SP - 64
EP - 79
JO - BIOFOULING
JF - BIOFOULING
SN - 0892-7014
IS - 1
ER -