한국수산과학회지 (Korean Journal of Fisheries and Aquatic Sciences)

  • 제57권5호
  • /
  • Pages.581-588
  • /
  • 2024
  • /
  • 0374-8111(pISSN)
  • /
  • 2287-8815(eISSN)
한국수산과학회 (The Korean Society of Fisheries and Aquatic Science)
권호 표지
DOI QR코드

DOI QR Code

대형 해파리(Nemopilema nomurai) 탐지를 위한 머신러닝 기반 데이터 구축 및 모델 평가

Machine Learning-based Data Construction and Model Evaluation for Monitoring of Giant Jellyfish Nemopilema nomurai

  • 오선영 (국립부경대학교 해양생산관리학부 수산물리학전공) ;
  • 김형태 (국립부경대학교 해양생산관리학부 수산물리학전공) ;
  • 이경훈 (국립부경대학교 해양생산시스템관리학부)
  • Sunyoung Oh (Department of Fisheries Physis, Pukyong National University) ;
  • Hyungtae Kim (Department of Fisheries Physis, Pukyong National University) ;
  • Kyounghoon Lee (Division of Marine Production System Management, Pukyong National University)
  • 투고 : 2024.08.05
  • 심사 : 2024.09.06
  • 발행 : 2024.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In this, we study developed a machine-learning system that can effectively detect giant jellyfish Nemopilema nomurai by collecting videos of their appearances. Surveys were conducted in the East China Sea, South Sea, and Jeju coastal waters, which are presumed to be jellyfish migration routes. Video data were collected using GoPro cameras, and images were extracted at 1 fps to train the YOLOv8 Nano and Medium models. The YOLOv8 Nano model achieved an F1 score of 0.83 with high confidence and maintained high precision in the precision-recall curve, demonstrating its effectiveness in predicting jellyfish occurrences. The YOLOv8 nano model demonstrated excellent reliability and precision, indicating its potential for effective jellyfish detection. However, to improve the performance of the model even further, data from various environments must be collected and additional validations must be performed.

키워드

과제정보

이 논문은 2023년 국립부경대학교 자율창의학술연구비(지속가능한 어업자원평가 향상에 관한 연구, 202407060001)의 지원을 받아 수행되었으며, 본 논문을 사려 깊게 검토하여 주신 심사워원님들과 편집위원님께 감사드립니다.

참고문헌

  1. Abadal M, Frau A, Hinz H and Cid Y. 2020. Jellytoring: Real-time jellyfish monitoring based on deep learning object detection. Sensors 20, 1708. http://dx.doi.org/10.3390/s20061708.
  2. Chang SJ and Ki JS. 2024. Population characteristics of the venomous giant jellyfish, Nemopilema nomurai, found in the Yellow and Northern East China Seas. J Environ Sci Int 33, 87-95. https://doi.org/10.5322/JESI.2024.33.1.87.
  3. Holmboe J. 2023. Fish tracking using detection in Aquaculture: A pilot study. M.S Thesis, Norwegian University of Life Sciences, Trondheim, Norway.
  4. Huang J, Rathod V, Sun C, Zhu M, Korattikara A, Fathi A, Fischer I, Wojna Z, Song Y, Guadarrama S and Murphy K. 2017. Speed/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7310-7311.
  5. Jia R, Lv B, Chen J, Liu H, Cao L and Liu M. 2023. Underwater object detection in marine ranching based on improved YOLOv8. J Mar Sci Eng 12, 55. https://doi.org/10.3390/jmse12010055.
  6. Kim DY, Lee JS and Kim DH. 2014. A study on direction of industrial utilization for jellyfish in Korea. J Fish Mar Sci Edu 26, 587-596. https://doi.org/10.13000/JFMSE.2014.26.3.587.
  7. Lee D, Han I, Chae J, Yoon W, Yang Y, Kim D and Lee K. 2019. Analysis of the advantage and disadvantage of harmful jellyfish's damage reduvion devices strategy types in the beach. The J Fish Mar Sci Edu 31, 1230-1241. https://doi.org/10.13000/JFMSE.2019.8.31.4.1230.
  8. Lee HY. 2010. Reproduction and feeding behavior of giant jellyfish, Nemopilema nomurai Kishinouye (Scyphozoa: Rhizostomeae). Ph. D. Thesis, Pukyong National University, Busan, Korea.
  9. Lee KH, Kim IO, Yoon WD, Shin JK and An HC. 2007. A study on vertical distribution observation of giant jellyfish (Nemopilema nomurai) using acoustical and optical methods. J Kor Soc Fish Tech 43, 355-361. https://doi.org/10.3796/KSFT.2007.43.4.355.
  10. Lin TY, Goyal P, Girshick R, He K and Dollar P. 2017. Focal loss for dense object detection. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), 2980-2988.
  11. Nawaeathne U, Kumari H and Kumari H. 2024. Comparative analysis of jellyfish classification: A study using YOLOv8 and pre-trained models. In: 2024 International Research Conference on Smart Computing and Systems Engineering (SCSE), Colombo, Sri Lanka, 1-6. http://dx.doi.org/10.1109/SCSE61872.2024.10550783.
  12. Oh S, Kim KY, Lim WA, Park G, Oh H, Oh W and Lee K. 2021. Vertical distribution of giant jellyfish (Nemopilema nomurai) in the coastal waters of Korea and its correlation analysis by survey method. J Koran Soc Fish Ocean Technol 57, 351-564. https://doi.org/10.3796/KSFOT.2021.57.4.351.
  13. Oh S, Kim KY, Oh HJ, Park G, Oh W and Lee K. 2022. Spatiotemporal distribution of giant jellyfish (Nemopilema nomurai). Water 14, 2883. https://doi.org/10.3390/w14182883.
  14. Oh S, Kim KY, Youn SH, Lee S, Park G, Oh W and Lee K. 2024. A three-year comparison of fluctuations in the occurrence of the giant jellyfish (Nemopilema nomurai). Water 16, 2265. https://doi.org/10.3390/w16162265.
  15. Oh S, Kim KY, Youn SH, Lee S, Park G, Oh W and Lee K. 2024. Density estimation of giant jellyfish (Nemopilema nomurai) using a scientific echosounder. J Korean Soc Fish Ocean Technol 60, 18-26. https://doi.org/10.3796/KSFOT.2024.60.1.018.
  16. Park G, Bak S, Jang S, Gong S, Kwak J and Lee Y. 2023. Realtime detection of benthic marine invertebrates from, underwater images: A comparison between YOLO and transformer models. Korean J Remote Sens 39, 909-919. https://doi.org/10.7780/kjrs.2023.39.5.3.3.
  17. Pham TN, Nguyen VH, Kwon KR, Kim JH and Huh JH. 2024. Improved YOLOv5 based deep learning system for jellyfish detection. IEEE Access 12, 87838-87849. http://dx.doi.org/10.1109/ACCESS.2024.3405452.
  18. Recht B, Roelofs R, Schmidt L and Shankar V. 2019. Do imageNet classifiers generalize to imageNet?. In: Proceedings of the 36th International Conference on Machine Learning. Long Beach, CA, U.S.A., 5389-5400.
  19. Shin HH, Han I, Oh W, Chae J, Yoon E and Lee K. 2019. Estimation of moon jellyfish Aurelia Coerulea using hydroacoustic method off the Coast of Tongyeong, Korea. Korean J Fish Aquat Sci 52, 725-734. https://doi.org/10.5657/KFAS.2019.0725.
  20. Son YT, Lee SH, Lee JC and Kim JC. 2003. Water masses and frontal structures in winter in the Northern East China Sea. J Korean Soc Oceanog 8, 327-339.
  21. Weihong B, Yun J, Jiaxin L, LingLing S, Guangwei F and Wa J. 2023. In-situ detection method of jellyfish based on improved fater R-CNN and FP16. IEEE Access 11, 81803-81814. http://dx.doi.org/10.1109/ACCESS.2023.3300655.
  22. Yoon EA, Hwang DJ, Shin HH, Gwak DS and Cha CP. 2012. In Situ acoustic characteristics of the large jellyfish Nemopilema nomurai in the East China Sea. J Kor Soc Fish Tech 48, 256-268. http://dx.doi.org/10.3796/KSFT.2012.48.3.256.
  23. Yu WB. 2016. Study on the rDNA characteristics of harmful jellyfishes Aurelia sp.1 and Nemopilema nomurai in Krea. M.S. Thesis, Sangmyung University, Seoul, Korea.