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
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
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.
Abstract
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.
참고문헌 (23)
- Abadal M, "Jellytoring : Real-time jellyfish monitoring based on deep learning object detection", Sensors, 20, pp.1708~ (2020)[DOI]
- Chang SJ, "Population characteristics of the venomous giant jellyfish, Nemopilema nomurai, found in the Yellow and Northern East China Seas", J Environ Sci Int, 33, pp.87~95 (2024)[DOI]
- Holmboe J, "Fish tracking using detection in Aquaculture : A pilot study", M. S, pp.2023
- Huang J, "Speed", accuracy trade-offs for modern convolutional object detectors, 2017, 7310~7311
- Jia R, "Underwater object detection in marine ranching based on improved YOLOv8", J Mar Sci Eng, 12, pp.55~ (2023)[DOI]
- Kim DY, "A study on direction of industrial utilization for jellyfish in Korea", J Fish Mar Sci Edu, 26, pp.587~596 (2014)[DOI]
- Lee D, "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, pp.1230~1241 (2019)[DOI]
- Lee HY, "Reproduction and feeding behavior of giant jellyfish, Nemopilema nomurai Kishinouye (Scyphozoa: Rhizostomeae)", Ph. D., pp.2010
- Lee KH, "A study on vertical distribution observation of giant jellyfish(Nemopilema nomurai)using acoustical and optical methods", J Kor Soc Fish Tech, 43, pp.355~361 (2007)[DOI]
- Lin TY, "Focal loss for dense object detection", Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), pp.2980~2988 (2017)
- Nawaeathne U, "Comparative analysis of jellyfish classification: A study using YOLOv8and pre-trained models", 2024 International Research Conference on Smart Computing and Systems Engineering (SCSE), pp.1~6 (2024)
- Oh S, "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, pp.351~564 (2021)[DOI]
- Oh S, "Spatiotemporal distribution of giant jellyfish(Nemopilema nomurai)", Water, 14, pp.2883~ (2022)[DOI]
- Oh S, "A three-year comparison of fluctuations in the occurrence of the giant jellyfish(Nemopilema nomurai)", Water, 16, pp.2265~ (2024)[DOI]
- Oh S, "Density estimation of giant jellyfish(Nemopilema nomurai)using a scientific echosounder", J Korean Soc Fish Ocean Technol, 60, pp.18~26 (2024)[DOI]
- Park G, "Realtime detection of benthic marine invertebrates from, underwater images : A comparison between YOLO and transformer models", Korean J Remote Sens, 39, pp.909~919 (2023)[DOI]
- Pham TN, "Improved YOLOv5 based deep learning system for jellyfish detection", IEEE Access, 12, pp.87838~87849 (2024)[DOI]
- Recht B, "Do imageNet classifiers generalize to imageNet?", Proceedings of the 36th International Conference on Machine Learning, pp.5389~5400 (2019)
- Shin HH, "Estimation of moon jellyfish Aurelia Coerulea using hydroacoustic method off the Coast of Tongyeong, Korea", Korean J Fish Aquat Sci, 52, pp.725~734 (2019)[DOI]
- Son YT, "Water masses and frontal structures in winter in the Northern East China Sea", J Korean Soc Oceanog, 8, pp.327~339 (2003)
- Weihong B, "In-situ detection method of jellyfish based on improved fater R-CNN and FP16", IEEE Access, 11, pp.81803~81814 (2023)[DOI]
- Yoon EA, "In Situ acoustic characteristics of the large jellyfish Nemopilema nomurai in the East China Sea", J Kor Soc Fish Tech, 48, pp.256~268 (2012)[DOI]
- Yu WB, "Study on the rDNA characteristics of harmful jellyfishes Aurelia sp. 1 and Nemopilema nomurai in Krea", M.S., pp.2016