Journal of the Korean Society of Marine Environment & Safety (해양환경안전학회지)

The Korean Society of Marine Environment and safety (해양환경안전학회)
권호 표지
DOI QR코드

DOI QR Code

Marine-Life-Detection and Density-Estimation Algorithms Based on Underwater Images and Scientific Sonar Systems

수중영상과 과학어탐 시스템 기반 해양생물 탐지 밀도추정 알고리즘 연구

  • Young-Tae Son (Geosystem Research Corporation) ;
  • Sang-yeup Jin (Geosystem Research Corporation) ;
  • Jongchan Lee (Geosystem Research Corporation) ;
  • Mookun Kim (Geosystem Research Corporation) ;
  • Ju Young Byon (Korea Hydro & Nuclear Power Corporation) ;
  • Hyung Tae Moo (Korea Hydro & Nuclear Power Corporation) ;
  • Choong Hun Shin (Korea Hydro & Nuclear Power Corporation)
  • 손영태 ((주)지오시스템리서치) ;
  • 진상엽 ((주)지오시스템리서치) ;
  • 이종찬 ((주)지오시스템리서치) ;
  • 김무건 ((주)지오시스템리서치) ;
  • 변주영 (한국수력원자력(주)) ;
  • 문형태 (한국수력원자력(주)) ;
  • 신충훈 (한국수력원자력(주))
  • Received : 2024.05.22
  • Accepted : 2024.08.29
  • Published : 2024.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

The aim of this study is to establish a system for the early detection of high-density harmful marine organisms. Considering its accuracy and processing speed, YOLOv8m (You Only Look Once version 8 medium) is selected as a suitable model for real-time underwater image-based object detection. Applying the detection algorithm allows one to detect numerous fish and the occasional occurrence of jellyfish. The average precision, recall rate, and mAP (mean Average Precision) of the trained model are 0.931, 0.881, and 0.948 for the validation data, respectively. Also, the mAP for each class is 0.97 for fish, 0.97 for jellyfish and 0.91 for salpa, all of which exceed 0.9 (90%) for classes demonstrating the excellent performance of the model. A scientific sonar system is used to address the object-detection range and validate the detection results. Additionally, integrating and grid averaging the echo strength allows the detection results to be smoothed in space and time. Mean-volume back-scattering strength values are obtained to reflect the detection variability within the analysis domain. Furthermore, an underwater image-based object (marine lives) detection algorithm, an image-correction technique based on the underwater environmental conditions (including nights), and quantified detection results based on a scientific sonar system are presented, which demonstrate the utility of the detection system in various applications.

본 연구의 목적은 유해 해양생물의 고밀도 출현을 조기에 탐지하기 위한 시스템 구축이다. 수중영상 기반 객체탐지 모델의 정확도와 이미지 처리속도를 고려하여 실시간 적용에 적합한 YOLOv8m을 선정하였다. 영상 데이터를 해양생물 탐지 알고리즘에 적용한 결과 다수의 어류 및 간헐적인 해파리 출현을 탐지하였다. 학습 모델의 검증 데이터에 대한 평균 정밀도는 0.931, 재현율은 0.881, mAP는 0.948로 산출되었다. 또한, 각 클래스별 mAP는 어류 0.970, 해파리 0.970, 살파 0.910로 모든 클래스에서 0.9(90%) 이상으로 산출되어 우수한 성능을 확인하였다. 과학어탐 시스템을 통해 객체의 탐지 범위와 시간에 따른 수중 객체탐지 결과를 확인할 수 있었으며 에코적분 격자평균을 적용하여 시공간축으로 스무딩 처리된 결과를 얻을 수 있었다. 또한, 평균체적후방산란강도 값이 분석 도메인 내 객체탐지 여부에 따른 변동성을 반영하는 것을 확인할 수 있었다. 수중영상 기반 객체(해양생물)탐지 알고리즘, 환경조건(야간 포함)에 따른 수중영상 보정기법, 과학어탐 시스템 기반의 정량화된 탐지결과를 제시하고 향후 다양한 사용처에서의 활용 가능성을 토의하였다.

Keywords

Acknowledgement

본 논문은 한국수력원자력(주)과 (주)지오시스템리서치가 공동으로 수행한 연구결과입니다.

References

  1. Buslaev, A., V. I. Iglovikov, E. Khvedchenya, A. Parinov, M. Druzhinin, and A. A. Kalinin(2020), Albumentations: fast and flexible image augmentations, Information, 11(2), 125.
  2. Dong-A Ilbo(2024), https://www.donga.com/news/It/article/all/20240616/125457370/2.
  3. Fernandes, P. G., F. Gerlotto, D. V. Holliday, O. Nakken, and E. J. Simmonds(2002), Acoustic applications in fisheries science: the ICES contribution.
  4. Jiang, P., D. Ergu, F. Liu, Y. Cai, and B. Ma(2022), A Review of Yolo algorithm developments, Procedia computer science, 199, pp. 1066-1073.
  5. Kang, M., M. Furusawa, and K. Miyashita(2002), Effective and accurate use of difference in mean volume backscattering strength to identify fish and plankton, ICES Journal of Marine Science, 59(4), pp. 794-804.
  6. Kang, D., J. Park, S. K. Jung, and S. Cho(2014), Estimates of acoustic target strength for giant jellyfish Nemopilema nomurai Kishinouye in the coastal Northwest Pacific, ICES Journal of Marine Science, 71(3), pp. 597-603.
  7. Kang, M., Y. -H. Cho, H. La, W. Son, H. Yun, A. Adrianus, and Y. -S. An(2022), The first attempt of utilization of a wideband autonomous acoustic system and its general knowledge on analyzing the wideband acoustic data, Journal of the Korean Society of Fisheries and Ocean Technology, 58(2), pp. 130-140.
  8. KBS(2013), https://news.kbs.co.kr/news/pc/view/view.do?ncd=2732777.
  9. Kim, P., I. Han, W. Oh, Y. -M, Choi, S. Yoon, H. Lee, and K. Lee(2018), Biomass Estimate of Euphausiids Euphausia sp. Using the Two-frequency Difference Method, The Korean Society of Fisheries and Aquatic Science, 51(3), pp. 305-312.
  10. Lee, K. -H., I. -O. Kim, W. -D. Yoon, J. -K. Shin, and H. -C. An(2007), A study on vertical distribution observation of giant jellyfish (Nemopilema nomurai) using acoustical and optical methods, Journal of the Korean Society of Fisheries and Ocean Technology, 43(4), pp. 355-361.
  11. Lee, C. W.(2013), Acoustic scattering characteristics of Moon Jellyfish(Aurelia aurita) in Korea coastal water, Doctoral dissertation, Hanyang University.
  12. Lee, S., S. Kim, J. W. Choi, D. Kang, J. S. Park, and K. Park(2015), Possibility of False Target Signals Induced by Reverberation Due to Internal Waves in Shallow Water, The Journal of the Acoustical Society of Korea, 34(2), pp. 98-107.
  13. MacLennan, D. N.(1990), Acoustical measurement of fish abundance, The Journal of the Acoustical Society of America, 87(1), pp. 1-15.
  14. MacLennan, D. N. P. G., Fernandes, and J. Dalen(2002), A consistent approach to definitions and symbols in fisheries acoustics, ICES Journal of Marine Science, 59(2), pp. 365-369.
  15. McClatchie, S., R. E. Thorne, P. Grimes, and S. Hanchet (2000), Ground truth and target identification for fisheries acoustics, Fisheries research, 47(2-3), pp. 173-191.
  16. Miyashita, K., I. Aoki, K. Seno, K. Taki, and T. Ogishima (1998), Acoustic identification of isada krill, Euphausia pacifica Hansen, off the Sanriku coast, north eastern Japan, Fisheries Oceanography, 6(4), pp. 266-271.
  17. NIFS(2023), https://www.nifs.go.kr/jelly/main.jely.
  18. NIFS(2009), A Study on the Prevention of Harmful Maine Life Jellyfish Damage.
  19. Panetta, K., C. Gao, and S. Agaian(2015), Human-Visual-System-Inspired Underwater Image Quality Measures, IEEE J. Oceanic Engineering, 41(3), pp. 541-551, https://doi.org/10.1109/JOE.2015.2469915
  20. Redmon, J., S. Divvala, R. Girshick, and A. Farhadi(2016), You only look once: Unified, real-time object detection, In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788.
  21. Sato, M., J. K. Horne, S. L. Parker-Stetter, and J. E. Keister (2015), Acoustic classification of coexisting taxa in a coastal ecosystem, Fisheries Research, 172, pp. 130-136.
  22. Shin, H. -H., I. Han, W. Oh, J. Chae, E. Yoon, and K. Lee (2019), Estimation of Moon Jellyfish Aurelia coerulea Using Hydroacoustic Methods off the Coast of Tongyeong, Korea. The Korean Society of Fisheries and Aquatic Science, 52(6), pp. 725-734.
  23. Simmonds, J. and D. N. MacLennan(2008), Fisheries acoustics: theory and practice. John Wiley & Sons.
  24. Stanton, T. K., D. Chu, and P. H. Wiebe(1998), Sound scattering by several zooplankton groups, II. Scattering models, The Journal of the Acoustical Society of America, 103(1), pp. 236-253.
  25. Urick, R. J.(1962), Generalized form of the sonar equations, The Journal of the Acoustical Society of America, 34(5), pp. 547-550.
  26. Wells, M. G., J. Li, B. Flood, Y. Kuai, J. L. Brooks, S. J. Cooke, P. Semcesen and J. D. Midwood(2021), Speed of sound gradients due to summer thermal stratification can reduce the detection range of acoustic fish tags: results from a field study in Hamilton Harbour, Ontario., Canadian Journal of Fisheries and Aquatic Sciences, 78(3), pp. 269-285.
  27. Yang, H., J. Cheng, T. Tang, J. Chen, and G. Li(2023), Acoustic Target Strength of Jellyfish, Nemopilema nomurai, Measured at Multi Frequency and Multi Orientation, Journal of Applied Ichthyology, 2023(1), 6650863.
  28. Yang, M. and A. Sowmya(2015), An Underwater Color Image Quality Evaluation Metric, in IEEE Transactions on Image Processing, Vol. 24, No. 12, pp. 6062-6071, Dec. 2015, doi: 10.1109/TIP.2015.2491020.