Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.6.1.26

Semantic Segmentation of the Submerged Marine Debris in Undersea Images Using HRNet Model  

Kim, Daesun (Ocean Policy Institute, Korea Institute of Ocean Science and Technology)
Kim, Jinsoo (Department of Spatial Information Engineering, 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.)
Bae, Jaegu (Major of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Publication Information
Korean Journal of Remote Sensing / v.38, no.6_1, 2022 , pp. 1329-1341 More about this Journal
Abstract
Destroying the marine environment and marine ecosystem and causing marine accidents, marine debris is generated every year, and among them, submerged marine debris is difficult to identify and collect because it is on the seabed. Therefore, deep-learning-based semantic segmentation was experimented on waste fish nets and waste ropes using underwater images to identify efficient collection and distribution. For segmentation, a high-resolution network (HRNet), a state-of-the-art deep learning technique, was used, and the performance of each optimizer was compared. In the segmentation result fish net, F1 score=(86.46%, 86.20%, 85.29%), IoU=(76.15%, 75.74%, 74.36%), For the rope F1 score=(80.49%, 80.48%, 77.86%), IoU=(67.35%, 67.33%, 63.75%) in the order of adaptive moment estimation (Adam), Momentum, and stochastic gradient descent (SGD). Adam's results were the highest in both fish net and rope. Through the research results, the evaluation of segmentation performance for each optimizer and the possibility of segmentation of marine debris in the latest deep learning technique were confirmed. Accordingly, it is judged that by applying the latest deep learning technique to the identification of submerged marine debris through underwater images, it will be helpful in estimating the distribution of marine sedimentation debris through more accurate and efficient identification than identification through the naked eye.
Keywords
Submerged marine debris; Semantic segmentation; Deep learning; HRNet; Optimizer;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 Ronneberger, O., P. Fischer, and T. Brox, 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation, arXiv preprint arXiv:1505.04597. https://doi.org/10.48550/arXiv.1505.04597   DOI
2 Radeta, M., A. Zuniga, N.H. Motlagh, M. Liyanage, R. Freitas, M. Youssef, S. Tarkoma, H. Flores, and P. Nurmi, 2022. Deep Learning and the Oceans, Computer, 55(5): 39-50. https://doi.org/10.1109/MC.2022.3143087   DOI
3 Cheng, Z. and D. Fu, 2020. Remote Sensing Image Segmentation Method based on HRNET, Proc. of IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA, Sep. 26-Oct. 28, pp. 6750-6753. https://doi.org/10.1109/IGARSS39084.2020.9324289   DOI
4 Chin, C., A. Neo, and S. See, 2022. Visual Marine Debris Detection using Yolov5s for Autonomous Underwater Vehicle, Proc. of 2022 IEEE/ACIS 22nd International Conference on Computer and Information Science (ICIS), Zhuhai, China, Jun. 26-28, pp. 22-24. https://doi.org/10.1109/ICIS54925.2022.9882484   DOI
5 Kim, H., M. Kim, and Y. Lee, 2022. Research Trend of the Remote Sensing Image Analysis Using Deep Learning, Korean Journal of Remote Sensing, 38(5-3): 819-834 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2022.38.5.3.2   DOI
6 Jeong, M., N. Kim, M. Park, and H. Yoon, 2021. The Characteristics of the Compositions and Spatial Distributions of Submerged Marine Debris in the East Sea, Journal of the Korean Society of Marine Environment & Safety, 27(2): 295-307 (in Korean with English abstract). https://doi.org/10.7837/kosomes.2021.27.2.295   DOI
7 Li, Y., Y. Chen, G. Liu, and L. Jiao, 2018. A Novel Deep Fully Convolutional Network for PolSAR Image Classification, Remote Sensing, 10(12): 1984. https://doi.org/10.3390/rs10121984   DOI
8 Yaqub, M., J. Feng, M.S. Zia, K. Arshid, K. Jia, Z.U Rehman, and A. Mehmood, 2020. State-of-the-Art CNN Optimizer for Brain Tumor Segmentation in Magnetic Resonance Images, Brain Sciences, 10(7): 427. https://doi.org/10.3390%2Fbrainsci10070427   DOI
9 Kuroda, M., K. Uchida, T. Tokaia, Y. Miyamoto, T. Mukai, K. Imai, K. Shimizu, M. Yagi, Y. Yamanaka, and T. Mituhashi, 2020. The current state of marine debris on the seafloor in offshore area around Japan, Marine Pollution Bulletin, 161(A): 111670. https://doi.org/10.1016/j.marpolbul.2020.111670   DOI
10 Seong, S. and J. Choi, 2021. Semantic Segmentation of Urban Buildings Using a High-Resolution Network (HRNet) with Channel and Spatial Attention Gates, Remote Sensing, 13(16): 3087. https://doi.org/10.3390/rs13163087   DOI
11 KOEM (Korea Marine Environment Management Corporation), 2019. A study on the establishment of the 3rd Master Plan for Marine Debris Management, Korea Marine Environment Management Corporation, Seoul, Korea.
12 Kandel, I. and M. Castelli, 2020. The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset, ICT Express, 6(4): 312-315. https://doi.org/10.1016/j.icte.2020.04.010   DOI
13 Kim, S., Y. Yang, J. Jeong, M. Song, D. Lee, M. Choi, S. Cha, C. Lee, and H. Kim, 2016. Verification on the Ghost Fishing by Derelict Fishing Gears through the Tank Experiments, The Korean Society for Fisheries and Marine Sciences Education, 28(5): 1258-1265 (in Korean with English abstract). https://doi.org/10.13000/JFMSE.2016.28.5.1258   DOI
14 Kingma, D.P. and J. Ba, 2015. Adam: A Method for Stochastic Optimization, Proc. of 3rd International Conference for Learning Representations, San Diego, CA, USA, May 7-9, pp. 1-15. https://doi.org/10.48550/arXiv.1412.6980   DOI
15 Politikos, D.V., E. Fakiris, A. Davvetas, I.A. Klampanos, and G. Papatheodorou, 2021. Automatic detection of seafloor marine litter using towed camera images and deep learning, Marine Pollution Bulletin, 164: 111974. https://doi.org/10.1016/j.marpolbul.2021.111974   DOI
16 Ruder, S., 2017. An overview of gradient descent optimization algorithms, arXiv preprint arXiv:1609.04747. https://doi.org/10.48550/arXiv.1609.04747   DOI
17 Shinde, P., 2021. Marine Debris Segmentation using Capsule Network (SegCaps), https://norma.ncirl.ie/id/eprint/5220, Accessed on Dec. 14, 2021
18 Xue, B., B. Huang, W. Wei, G. Chen, H. Li, N. Zhao, and H. Zhang, 2021b. An Efficient Deep-Sea Debris Detection Method Using Deep Neural Networks, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 12348-12360. https://doi.org/10.1109/JSTARS.2021.3130238   DOI
19 Wang, T., S. Oh, H. Lee, D. Choi, J. Jang, and M. Kim, 2022. A Study on the Implementation of Real-Time Marine Deposited Waste Detection AI System and Performance Improvement Method by Data Screening and Class Segmentation 7, The Journal of the Convergence on Culture Technology, 8(3): 571-580 (in Korean with English abstract). http://dx.doi.org/10.17703/JCCT.2022.8.3.571   DOI
20 Wu, H., C. Liang, M. Liu, and Z. Wen, 2021. Optimized HRNet for image semantic segmentation, Expert Systems with Applications, 174: 114532. https://doi.org/10.1016/j.eswa.2020.114532   DOI
21 Yang, J. and G. Yang, 2018. Modified Convolutional Neural Network Based on Dropout and the Stochastic Gradient Descent Optimizer, Algorithms, 11(3): 28. https://doi.org/10.3390/a11030028   DOI
22 Xue, B., B. Huang, G. Chen, H. Li, and W. Wei, 2021a. Deep-Sea Debris Identification Using Deep Convolutional Neural Networks, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 8909-8921. https://doi.org/10.1109/JSTARS.2021.3107853   DOI
23 Song, J., Y. Lee, Y. Han, and Y. Park, 2022. Management status and policy direction of submerged marine debris for improvement of port environment in Korea, Open Geosciences, 14(1): 443-552. https://doi.org/ 10.1515/geo-2022-0368   DOI
24 Zhang, J., S. Lin, L. Ding, and L. Bruzzone, 2020. Multi-Scale Context Aggregation for Semantic Segmentation of Remote Sensing Images, Remote Sensing, 12(4): 701. https://doi.org/10.3390/rs12040701   DOI
25 Zhou, X., 2021. An Improved Semantic Segmentation Model for Remote Sensing Images based on HRNet, Proc. of 2021 International Conference on Computer, Remote Sensing and Aerospace (CRSA 2021), Tokyo, Japan, Jul. 23-25, vol. 2006, pp. 1-6. https://doi.org/10.1088/1742-6596/2006/1/012046   DOI
26 Wang, J., K. Sun, T. Cheng, B. Jiang, C. Deng, Y. Zhao, D. Liu, Y. Mu, M. Tan, X. Wang, W. Liu, and B. Xiao, 2019. Deep high-resolution representation learning for visual recognition, arXiv preprint arXiv:198.07919. https://doi.org/10.48550/arXiv.1908.07919   DOI