Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.5.3.9

Semantic Segmentation of the Habitats of Ecklonia Cava and Sargassum in Undersea Images Using HRNet-OCR and Swin-L Models  

Kim, Hyungwoo (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Jang, Seonwoong (IREM Tech Inc.)
Bak, Suho (Research Institute, IREM Tech Inc.)
Gong, Shinwoo (Bukyeong Ocean Engineering and Consulting Inc.)
Kwak, Jiwoo (AllBigDat Inc.)
Kim, Jinsoo (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Lee, Yangwon (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Publication Information
Korean Journal of Remote Sensing / v.38, no.5_3, 2022 , pp. 913-924 More about this Journal
Abstract
In this paper, we presented a database construction of undersea images for the Habitats of Ecklonia cava and Sargassum and conducted an experiment for semantic segmentation using state-of-the-art (SOTA) models such as High Resolution Network-Object Contextual Representation (HRNet-OCR) and Shifted Windows-L (Swin-L). The result showed that our segmentation models were superior to the existing experiments in terms of the 29% increased mean intersection over union (mIOU). Swin-L model produced better performance for every class. In particular, the information of the Ecklonia cava class that had small data were also appropriately extracted by Swin-L model. Target objects and the backgrounds were well distinguished owing to the Transformer backbone better than the legacy models. A bigger database under construction will ensure more accuracy improvement and can be utilized as deep learning database for undersea images.
Keywords
Undersea image; Semantic segmentation; HRNet-OCR; Swin transformer;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 Qiu, Z., Y. Yao, and M. Zhong, 2019. Underwater sea cucumbers detection based on pruned SSD, Proc. of 2019 IEEE 3rd Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Chongqing, China, Oct. 11-13, pp. 738-742. https://doi.org/10.1109/IMCEC 46724.2019.8983935   DOI
2 Ataner, E., B. Ozdes, G. Ozturk, T.Y.C. Celik, A. Durdu, and H. Terzioglu, 2020. Deep learning methods in unmanned underwater vehicles, Avrupa Bilim ve Teknoloji Dergisi, 345-350. https://doi.org/10.31590/ejosat.804599   DOI
3 Dosovitskiy, A., L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby, 2020, An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, arXiv preprint arXiv:2010.11929. https://arxiv.org/abs/2010.11929
4 FIRA (Korea Fisheries Resources Agency), 2022. Korea Fisheries Resources Agency - Press Release, https://www.fira.or.kr/fira/fira_010201_2.jsp, Accessed on Oct. 3, 2022.
5 Gao, M., Y. Bai, Z. Li, S. Li, B. Zhang, and Q. Chang, 2021. Real-time jellyfish classification and detection based on improved YOLOv3 algorithm, Sensors, 21(23): 8160. https://doi.org/10.3390/s21238160   DOI
6 Lambertini, A., M. Menghini, J. Cimini, A. Odetti, G. Bruzzone, M. Bibuli, E. Mandanici, L. Vittuari, P. Castaldi, M. Caccia, and L. De Marchi, 2022. Underwater drone architecture for marine digital twin: Lessons learned from SUSHI DROP project, Sensors, 22(3): 744. https://doi.org/10.3390/s22030744   DOI
7 LeCun, Y., B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbardm, and L. D. Jackel, 1989. Backpropagation applied to handwritten zip code recognition, Neural Computation, 1(4): 541-551. https://doi.org/10.1162/neco.1989.1.4.541   DOI
8 Liu, Z., Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, 2021. Swin Transformer: Hierarchical vision transformer using shifted windows, arXiv preprint arXiv:2103.14030. https://arxiv.org/abs/2103.14030   DOI
9 MOF (Ministry of Oceans and Fisheries), 2018. Ministry of Oceans and Fisheries - Fishery Information Portal System, https://www.fips.go.kr/, Accessed on Oct. 3, 2022.
10 NIFS (National Institute of Fishery Science), 2011. National Institute of Fishery Science - Research Achievements, https://www.nifs.go.kr/rsh/, Accessed on Oct. 3, 2022.
11 Sun, K., Y. Zhao, B. Jiang, T. Cheng, B. Xiao, D. Liu, Y. Mu, X. Wang, W. Liu, and J. Wang, 2019. High-resolution representations for labeling pixels and regions, arXiv preprint arXiv:1904.04514. https://arxiv.org/abs/1904.04514