• ISSN 1000-0615
  • CN 31-1283/S
LI Zhijian, ZHANG Yongqi, WU Di, MENG Xiongdong, LI Yantian, ZHANG Lizhen. Quantitative detection method of swimming activity of Litopenaeus vannamei based on improved YOLOv7-tiny[J]. Journal of fisheries of china, 2024, 48(12): 129608. DOI: 10.11964/jfc.20240414443
Citation: LI Zhijian, ZHANG Yongqi, WU Di, MENG Xiongdong, LI Yantian, ZHANG Lizhen. Quantitative detection method of swimming activity of Litopenaeus vannamei based on improved YOLOv7-tiny[J]. Journal of fisheries of china, 2024, 48(12): 129608. DOI: 10.11964/jfc.20240414443

Quantitative detection method of swimming activity of Litopenaeus vannamei based on improved YOLOv7-tiny

Funds: National Key R & D Program of China (2019YFD0900401); Project of Shanghai Collaborative Innovation Center for Aquatic Animal Breed Creation and Green Breeding (2021 Science and Technology 02-12)
More Information
  • Corresponding author:

    ZHANG Lizhen. E-mail: lzzhang@shou.edu.cn

  • Received Date: April 01, 2024
  • Revised Date: May 23, 2024
  • Available Online: November 17, 2024
  • Shrimp is rich in a variety of trace elements and vitamins, and has a substantial nutritional value, it is also be widely recognized as an important ingredient in high-end, well-known cuisine. Among them, the cultural production of Litopenaeus vannamei accounts for about 85% of the total production of shrimp culture, which is an important economic aquaculture object. The active state of L. vannamei reacts its health condition and behavioral situation. Surveying and identifying the activity of L. vannamei is helpful in finding abnormal behavior in aquaculture, to give early warning and take remedial methods promptly, lessen economic losses in aquaculture, and improve the yield and efficiency of aquaculture. Nowadays in the L. vannamei pond aquaculure process, aquaculture personnel often need to monitor the active swimming state of the shrimp by manually pulling the feed tray, then analyzing the overall environment of the aquaculture pond and formulating effective aquaculture breeding strategies. However, due to the complexity of the pond underwater environment, artificial observation experience is limited, so the method of manually observing the active state of L. vannamei has a lot of problems, such as inefficiency limited scope of application, low accuracy, poor real-time performance, high labor intensity and other problems. In order to solve these problems, propose a visual detection method for the activity of L. vannamei based on an improved YOLOv7 tiny network detection model and multi-objective association based on Euclidean distance to quantitatively study the swimming activity status of shrimp. Based on the YOLOv7 tiny network model, the standard convolution was replaced by Conv convolution, and a VoVGSCSPC module was built to replace the original lightweight aggregation module (ELAN-L). The MPDIoU loss function was used instead of the CIoU loss function to reduce the model capacity and improve the model detection accuracy. The position of shrimp in the image was determined by the visual detection results of improved YOLOv7-tiny model and the multi-objective association method based on Euclidean distance, from which the shrimp's swimming displacement, speed and turn angle were calculated to quantify the shrimp's swimming activity status. After validation on the L. vannamei dataset, the results showed that the misdetection rate and omission rate of the improved YOLOv7-tiny model were reduced by 0.62% and 1.05%, respectively, compared with the YOLOv7-tiny model. The inference speed was improved by 17.07%, so the effectiveness of the improved model was verified. Quantitative analysis of the activity of shrimp showed that the more active shrimp corresponded to the higher the activity index value, which was consistent with the actual situation. The study showed that the proposed quantitative detection method could accurately and quickly obtain the swimming activity index, and could efficiently quantify the swimming activity state of L. vannamei on the feed tray, which was of great significance to grasp the health status of L. vannamei and improved the intelligent level of shrimp culture.

  • [1]
    Li J, Xu W K, Deng L M, et al. Deep learning for visual recognition and detection of aquatic animals: a review[J]. Reviews in Aquaculture, 2023, 15(2): 409-433. doi: 10.1111/raq.12726
    [2]
    Bardera G, Owen M A G, Pountney D, et al. The effect of short-term feed-deprivation and moult status on feeding behaviour of the Pacific white shrimp (Litopenaeus vannamei)[J]. Aquaculture, 2019, 511: 734222. doi: 10.1016/j.aquaculture.2019.734222
    [3]
    王克行. 虾蟹类增养殖学[M]. 北京: 中国农业出版社, 1997.

    Wang K X. Shrimp and crab enrichment[M]. Beijing: China Agriculture Press, 1997. (in Chinese).
    [4]
    Álvarez-Ellacuría E A, Palmer M, Catalán I A, et al. Image-based, unsupervised estimation of fish size from commercial landings using deep learning[J]. ICES Journal of Marine Science, 2020, 77(4): 1330-1339. doi: 10.1093/icesjms/fsz216
    [5]
    曾庆婷, 于赫男, 林小涛, 等. 氨氮胁迫下凡纳滨对虾运动行为与能量分配模式变化[J]. 中国水产科学, 2016, 23(1): 198-206.

    Zeng Q T, Yu H N, Lin X T, et al. Effects of ammonia-nitrogen on locomotor performance and the energy budget of Litopenaeus vannamei[J]. Journal of Fishery Sciences of China, 2016, 23(1): 198-206 (in Chinese).
    [6]
    Xi M Z, Rahman A, Nguyen C, et al. Smart headset, computer vision and machine learning for efficient prawn farm management[J]. Aquacultural Engineering, 2023, 102: 102339. doi: 10.1016/j.aquaeng.2023.102339
    [7]
    李钊丞, 项盛羽, 沈梦庭, 等. 南美白对虾快速游动发声特征及其信息利用研究[J]. 水生生物学报, 2023, 47(6): 997-1006. doi: 10.7541/2023.2022.0303

    Li Z C, Xiang S Y, Shen M T, et al. Acoustic characteristics of fast swimming and its information utilization for Litopenaeus vannamei[J]. Acta Hydrobiologica Sinica, 2023, 47(6): 997-1006 (in Chinese). doi: 10.7541/2023.2022.0303
    [8]
    Nontarit C, Kondo T, Khamkaew W, et al. Shrimp-growth estimation based on ResNeXt for an automatic feeding-tray lifting system used in shrimp farming[C]//IEEE. Proceedings of the 2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP). Chiang Mai: IEEE, 2022: 1-6.
    [9]
    裴凯洋, 张胜茂, 樊伟, 等. 基于计算机视觉的鱼类视频跟踪技术应用研究进展[J]. 海洋渔业, 2022, 44(5): 640-647.

    Pei K Y, Zhang S M, Fan W, et al. Research progress of fish video tracking application based on computer vision[J]. Marine Fisheries, 2022, 44(5): 640-647 (in Chinese).
    [10]
    袁永明, 施珮. 基于图像处理的鱼群运动监测方法研究[J]. 南方水产科学, 2018, 14(5): 109-114. doi: 10.3969/j.issn.2095-0780.2018.05.014

    Yuan Y M, Shi P. Study on fish movement monitoring method based on image processing[J]. South China Fisheries science, 2018, 14(5): 109-114 (in Chinese). doi: 10.3969/j.issn.2095-0780.2018.05.014
    [11]
    Morimoto T, Zin T T, Itami T. A study on abnormal behavior detection of infected shrimp[C]//IEEE. Proceedings of the 2018 IEEE 7th Global Conference on Consumer Electronics (GCCE). Nara: IEEE, 2018: 291-292.
    [12]
    de Oliveira Barreiros M, de Oliveira Dantas D, de Oliveira Silva L C, et al. Zebrafish tracking using YOLOv2 and Kalman filter[J]. Scientific Reports, 2021, 11(1): 3219. doi: 10.1038/s41598-021-81997-9
    [13]
    Wageeh Y, Mohamed H E D, Fadl A, et al. YOLO fish detection with Euclidean tracking in fish farms[J]. Journal of Ambient Intelligence and Humanized Computing, 2021, 12(1): 5-12. doi: 10.1007/s12652-020-02847-6
    [14]
    Sun L Q, Wang B N, Yang P, et al. Water quality parameter analysis model based on fish behavior[J]. Computers and Electronics in Agriculture, 2022, 203: 107500. doi: 10.1016/j.compag.2022.107500
    [15]
    Chahid A, N’Doye I, Majoris J E, et al. Fish growth trajectory tracking using Q-learning in precision aquaculture[J]. Aquaculture, 2022, 550: 737838. doi: 10.1016/j.aquaculture.2021.737838
    [16]
    Wang H, Zhang S, Zhao S L, et al. Real-time detection and tracking of fish abnormal behavior based on improved YOLOV5 and SiamRPN++[J]. Computers and Electronics in Agriculture, 2022, 192: 106512. doi: 10.1016/j.compag.2021.106512
    [17]
    Li X, Hao Y F, Zhang P, et al. A novel automatic detection method for abnormal behavior of single fish using image fusion[J]. Computers and Electronics in Agriculture, 2022, 203: 107435. doi: 10.1016/j.compag.2022.107435
    [18]
    Yamaguchi M,Nontarit C, Kondo T, et al. Accuracy Improvement of the Shrimp-size Estimation Method for an Automatic Feeding-tray Lifting System Used in Shrimp Farming[C]//IEEE. Proceedings of the 2023 20th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON). Nakhon Phanom: IEEE, 2023: 1-5.
    [19]
    Suarez P L, Sappa A, Carpio D, et al. Deep learning based shrimp classification[C]//Proceedings of the International Symposium on Visual Computing. Cham: Springer International Publishing, 2022: 36-45
    [20]
    Fan K J, Su W H. Applications of fluorescence spectroscopy, RGB- and MultiSpectral imaging for quality determinations of white meat: a review[J]. Biosensors, 2022, 12(2): 76. doi: 10.3390/bios12020076
    [21]
    Li H, Li J, Wei H, et al. Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles[J]. arXiv preprint arXiv: 2206.02424, 2022.
    [22]
    Ma S L, Xu Y. MPDIoU: a loss for efficient and accurate bounding box regression[J]. arXiv preprint arXiv: 2307.07662, 2023.
    [23]
    Zhao X Q, Yan S, Gao Q. An algorithm for tracking multiple fish based on biological water quality monitoring[J]. IEEE Access, 2019, 7: 15018-15026. doi: 10.1109/ACCESS.2019.2895072
    [24]
    王金鹏, 周佳良, 张跃跃, 等. 基于优选YOLOv7模型的采摘机器人多姿态火龙果检测系统[J]. 农业工程学报, 2023, 39(8): 276-283. doi: 10.11975/j.issn.1002-6819.202208031

    Wang J P, Zhou J L, Zhang Y Y, et al. Multi-pose dragon fruit detection system for picking robots based on the optimal YOLOv7 model[J]. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(8): 276-283 (in Chinese). doi: 10.11975/j.issn.1002-6819.202208031
    [25]
    Hu W C, Chen L B, Yu P J, et al. A deep learning-based white shrimp body length and bait detection methodology for turbid underwater aquaculture environment[C]//IEEE. Proceedings of the 2023 5th International Conference on Computer Communication and the Internet (ICCCI). Fujisawa: IEEE, 2023: 60-65.
    [26]
    李为, 荣宽, 覃丽蓉, 等. 水产动物行为及其在渔业中的应用研究进展[J]. 水生生物学报, 2021, 45(5): 1171-1180. doi: 10.7541/2021.2020.305

    Li W, Rong K, Qin L R, et al. Research progress of aquatic animal behavior and its application in fisheries[J]. Acta Hydrobiologica Sinica, 2021, 45(5): 1171-1180 (in Chinese). doi: 10.7541/2021.2020.305
    [27]
    李娜. 基于机器视觉的虾体活力状态检测方法研究[D]. 唐山: 华北理工大学, 2021.

    Li N. Study on detection method of shrimp body vitality based on machine vision[D]. Tangshan: North China University of Science and Technology, 2021 (in Chinese).
    [28]
    汪峰. 基于计算机视觉的虾苗活力分析研究[D]. 上海: 上海海洋大学, 2022.

    Wang F. Research on the vitality analysis of shrimp fry based on computer vision[D]. Shanghai: Shanghai Ocean University, 2022 (in Chinese).
    [29]
    张沛东, 张秀梅, 李健. 对虾的行为生态学研究进展I. 对虾的行为习性[J]. 应用生态学报, 2006, 17(1): 127-130. doi: 10.3321/j.issn:1001-9332.2006.01.026

    Zhang P D, Zhang X M, Li J, et al. Research advances in behavioral ecology of penaeid shrimps I. Behavior of penaeid shrimps[J]. Chinese Journal of Applied Ecology, 2006, 17(1): 127-130 (in Chinese). doi: 10.3321/j.issn:1001-9332.2006.01.026

Catalog

    Article views (237) PDF downloads (49) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return