HU Jiazhen, SUN Jialong, HUANG Xiaohua, ZHU Guohao, TAO Qiyou, YUAN Taiping, LI Gen, PANG Guoliang, HU Yu, LI Mingyang. A method for estimating quantity of Trachinotus ovatus in marine cage aquaculture based on high-frequency horizontal mechanical scanning sonar image[J]. South China Fisheries Science, 2024, 20(5): 113-125. DOI: 10.12131/20240042
Citation: HU Jiazhen, SUN Jialong, HUANG Xiaohua, ZHU Guohao, TAO Qiyou, YUAN Taiping, LI Gen, PANG Guoliang, HU Yu, LI Mingyang. A method for estimating quantity of Trachinotus ovatus in marine cage aquaculture based on high-frequency horizontal mechanical scanning sonar image[J]. South China Fisheries Science, 2024, 20(5): 113-125. DOI: 10.12131/20240042

A method for estimating quantity of Trachinotus ovatus in marine cage aquaculture based on high-frequency horizontal mechanical scanning sonar image

More Information
  • Received Date: March 05, 2024
  • Revised Date: June 10, 2024
  • Accepted Date: June 23, 2024
  • Available Online: June 25, 2024
  • To estimate the quantity of Trachinotus ovatus in marine cages accurately, a method for estimating the quantity of fish is proposed by using high-frequency horizontal mechanical scanning sonar and deep learning technology. Differentiating water layers and clustering layer by layer to realize counting is the main way of this method, which mainly involves three parts: fish identification, fish cluster and fish quantity fitting. Firstly, high-frequency horizontal mechanical scanning sonar is used to conduct spiral detection on marine cages to obtain fish image information, which is labeled to build training data set of improved CS-YOLOv8s. After training, the CS-YOLOv8s model is used to recognize fish location information in the images. Secondly, the cages are divided into water layers with a water depth spacing of 40 cm, and the identification coordinate data of each water layer are clustered through DBSCAN method to generate fish quantity data of each water layer. Finally, the quantity data of each water layer is fitted with the given quantity of fish in the cage, and the fitting model of fish quantity is established. The results show that in the quantitative experiment of marine cages, the accuracy of this method is 87.14%, and it can achieve a good estimation of the quantity of T. ovatus.

  • [1]
    刘伟峰, 张朝晖, 邢文秀, 等. 渔业生产方式创新视角下我国海洋牧场的概念应用与优化路径[J]. 生态经济, 2024, 40(8): 137-144.
    [2]
    袁华荣, 陈丕茂. 广东省海洋牧场发展现状、问题与对策[J]. 广东农业科学, 2022, 49(7): 141-154.
    [3]
    于盟盟, 任娟, 唐华强, 等. 日照市海洋牧场建设现状及思考[J]. 山西农经, 2022(12): 117-119.
    [4]
    吕龙德, 熊莹. 深远海养殖风头劲我国造船业迎重大利好[J]. 广东造船, 2023, 42(3): 6-12.
    [5]
    沈晨, 张培珍, 刘欢, 等. 基于VMD-Hilbert变换的大型网箱养殖鱼群声特性研究[J]. 吉林大学学报(信息科学版), 2023, 41(6): 1054-1062.
    [6]
    刘世晶, 李国栋, 刘晃, 等. 中国水产养殖装备发展现状[J]. 水产学报, 2023, 47(11): 190-203.
    [7]
    王静, 李蔚然, 刘业强, 等. 基于计算机视觉的养殖动物计数方法研究综述[J]. 农业机械学报, 2023, 54(S1): 315-329.
    [8]
    施继军, 施佐帆, 傅荣兵. 舟山“岱衢族”大黄鱼深水网箱养殖技术[J]. 浙江农业科学, 2023, 64(8): 1987-1990.
    [9]
    张涵钰, 李振波, 李蔚然, 等. 基于机器视觉的水产养殖计数研究综述[J]. 计算机应用, 2023, 43(9): 2970-2982.
    [10]
    崔斌. 视觉识别技术在智慧实验室中的应用研究[J]. 信息与电脑(理论版), 2023, 35(8): 172-174.
    [11]
    傅梁著. 基于视觉感知技术的鱼类行为辨别方法研究[D]. 大连: 大连理工大学, 2022: 15.
    [12]
    FENG S X, YANG X T, LIU Y, et al. Fish feeding intensity quantification using machine vision and a lightweight 3D ResNet-GloRe network[J]. Aquac Engin, 2022, 98: 102244. doi: 10.1016/j.aquaeng.2022.102244
    [13]
    YANG L, CHEN Y Y, SHEN T, et al. A BlendMask-VoVNetV2 method for quantifying fish school feeding behavior in industrial aquaculture[J]. Comput Electron Agr, 2023, 211: 108005. doi: 10.1016/j.compag.2023.108005
    [14]
    LAGARDE R, PEYRE J, AMILHAT E, et al. In situ evaluation of European eel counts and length estimates accuracy from an acoustic camera (ARIS)[J]. Knowl Manag Aquat Ec, 2020, 421: 44. doi: 10.1051/kmae/2020037
    [15]
    乐梓予. 基于声学技术有效保护近海渔业资源的探索与建议[J]. 中国水产, 2022(5): 58-60.
    [16]
    彭战飞, 沈蔚, 张进. 基于成像声呐的鱼类长度测量误差与修正模型研究[J]. 南方水产科学, 2023, 19(4): 31-40. doi: 10.12131/20220279
    [17]
    周吉祥, 刘慧敏, 陆凯, 等. 深海ARV在海洋资源调查中的应用及展望[J]. 海洋地质前沿, 2024, 40(2): 93-102.
    [18]
    朱俊, 封磊. 基于声呐图像的鱼群识别与计数方法[J]. 南京理工大学学报, 2023, 47(6): 782-789.
    [19]
    刘慧杰, 王从峰, 刘德富, 等. 双频识别声呐在鱼类资源调查中的应用进展[J]. 三峡大学学报(自然科学版), 2015, 37(3): 7-11.
    [20]
    FENG Y H, WEI Y G, SUN S, et al. Fish abundance estimation from multi-beam sonar by improved MCNN[J]. Aquat Ecol, 2023, 57(4): 895-911. doi: 10.1007/s10452-023-10007-z
    [21]
    田玉先, 冯德军, 张华, 等. 通过小型探鱼无人船探测大型围网养殖区大黄鱼的分布特性[J]. 水产学报, 2022, 46(11): 2084-2096.
    [22]
    JING D X, ZHOU H Y, HAN J, et al. Fish abundance estimation based on an imaging sonar[J]. Appl Acoust, 2019, 38(4): 705-711.
    [23]
    沈蔚, 朱振宏, 张进, 等. 基于双频识别声呐的鱼类目标识别与计数[J]. 渔业现代化, 2020, 47(6): 81-87. doi: 10.3969/j.issn.1007-9580.2020.06.012
    [24]
    周权, 杜浩, 王洁, 等. 基于环境DNA的长江中华鲟分布特征探究[J]. 环境工程技术学报, 2024, 14(1): 71-78.
    [25]
    SUN Y, ZHANG Y H, WANG H Y, et al. SES-YOLOv8n: automatic driving object detection algorithm based on improved YOLOv8[J]. Signal Image Video P, 2024, 18(5): 3983-3992. doi: 10.1007/s11760-024-03003-9
    [26]
    LI Y H, YAO T, PAN Y W, et al. Contextual transformer networks for visual recognition[J]. IEEE T-PAMI, 2023, 45(2): 1489-1500. doi: 10.1109/TPAMI.2022.3164083
    [27]
    ZHAO L, WEI Z J, LI Y T, et al. SEDG-Yolov5: a lightweight traffic sign detection model based on knowledge distillation[J]. Electronics, 2023, 12(2): 305-305. doi: 10.3390/electronics12020305
    [28]
    WU G Q, CAO L Q, TIAN H Y, et al. HY-DBSCAN: a hybrid parallel DBSCAN clustering algorithm scalable on distributed-memory computers[J]. J Parallel Distributed Comput, 2022, 168: 57-69. doi: 10.1016/j.jpdc.2022.06.005
    [29]
    CHEN G, HUANG W X, RONCH A D, et al. BP neural Network-Kalman filter fusion method for unmanned aerial vehicle target tracking[J]. P I Mech Eng C-J Mec, 2023, 237(18): 4203-4212. doi: 10.1177/0954406220983864
    [30]
    HAI T N, NGUYEN M N, PHUNG L D, et al. Anomalies detection in chest X-rays images using faster R-CNN and YOLO[J]. Vietnam J Comput Sci, 2023, 10(4): 499-515. doi: 10.1142/S2196888823500094
    [31]
    CHOI W, CHA Y J. SDDNet: Real-time crack segmentation[J]. IEEE TIE, 2020, 67(9): 8016-8025.
    [32]
    YU C, SHIN Y. SAR ship detection based on improved YOLOv5 and BiFPN[J]. ICT Express, 2024, 10(1): 28-33. doi: 10.1016/j.icte.2023.03.009
    [33]
    DING F. Least squares parameter estimation and multi-innovation least squares methods for linear fitting problems from noisy data[J]. J Comput Appl Math, 2023, 426: 115107. doi: 10.1016/j.cam.2023.115107
    [34]
    SELVARAJ P, KWON O M, LEE S H, et al. Disturbance rejections of polynomial fuzzy systems under equivalent-input-disturbance estimator approach[J]. Fuzzy Set Syst, 2024, 488: 109013. doi: 10.1016/j.fss.2024.109013
    [35]
    雍李明, 张语克, 赵丽媛, 等. 中华白海豚生态学研究进展[J]. 生物多样性, 2023, 31(5): 145-160.
    [36]
    陈凯骅, 陈海洋, 李惠东, 等. 码头声波驱鱼技术的研究与应用[J]. 电力科技与环保, 2020, 36(3): 60-62.
    [37]
    朱振宏. 基于成像声呐的鱼类资源评估关键技术研究[D]. 上海: 上海海洋大学, 2021: 46-52.
    [38]
    荆丹翔, 周晗昀, 韩军, 等. 基于成像声呐DIDSON的水域内鱼群数量估计方法[J]. 应用声学, 2019, 38(4): 705-711.
    [39]
    崔智强, 祝捍皓, 宋伟华, 等. 一种基于前视声呐的养殖网箱内鱼群数量评估方法[J]. 渔业现代化, 2023, 50(4): 107-117. doi: 10.3969/j.issn.1007-9580.2023.04.013
  • Related Articles

    [1]NIU Yingyue, OU Youjun, LAN Junnan, WEN Jiufu, LI Jia'er, LI Junwei, ZHOU Hui. Structure and early development of gill tissue in artificially cultured Eleutheronema tetradactylum[J]. South China Fisheries Science, 2020, 16(5): 108-114. DOI: 10.12131/20200028
    [2]OU Youjun, LI Jia'er, AI Li, WANG Wen, LI Liudong. Early development of squamation for Oplegnathus fasciatus[J]. South China Fisheries Science, 2016, 12(5): 112-117. DOI: 10.3969/j.issn.2095-0780.2016.05.014
    [3]LI Yuhu, SONG Qinqin, ZHANG Zhihuai, HUANG Hao, ZHOU Hailong, XIANG Jianhai. Analysis of growth and development rules and growth curve fitting of Litopenaeus vannamei[J]. South China Fisheries Science, 2015, 11(1): 89-95. DOI: 10.3969/j.issn.2095-0780.2015.01.013
    [4]XIONG Hualong, YAO Junjie, AN Miao, WANG Jinna, JIANG Zuoyu. Effects of glucose and vitamin C on early development of Puan silve crucian carp (Carassius auratus gibelio)[J]. South China Fisheries Science, 2014, 10(6): 88-92. DOI: 10.3969/j.issn.2095-0780.2014.06.013
    [5]OU Youjun, LI Jia′er, AI Li, XIE Jing. Early development and growth of larval, juvenile and young Oplegnathus fasciatus reared in pond in Guangdong Province[J]. South China Fisheries Science, 2014, 10(6): 66-71. DOI: 10.3969/j.issn.2095-0780.2014.06.009
    [6]CAI Wenchao, OU Youjun, LI Jia′er, SUN Peng. Development of immune organs at early stages of Trachinotus ovatus[J]. South China Fisheries Science, 2012, 8(5): 39-45. DOI: 10.3969/j.issn.2095-0780.2012.05.006
    [7]CHEN Zigui, XIAO Shu, PAN Ying, YU Ziniu. Comparison of early development and growth of Hong Kong oyster (Crassostrea hongkongensis) families[J]. South China Fisheries Science, 2011, 7(6): 40-46. DOI: 10.3969/j.issn.2095-0780.2011.06.007
    [8]CAI Wenchao, QU Youjun. Toxicity of Cu2+to fish during early developmental stages: a review[J]. South China Fisheries Science, 2009, 5(5): 75-79. DOI: 10.3969/j.issn.1673-2227.2009.05.014
    [9]LIU Qi, OU Youjun. Present status on feeding behavior studies in early development of fishes[J]. South China Fisheries Science, 2006, 2(1): 71-75.
    [10]SUN Qinghai, SHI Weide, SUN Jianzhang. Morphological studies on the early development of Miichthys miiuy[J]. South China Fisheries Science, 2005, 1(6): 8-17.
  • Cited by

    Periodical cited type(2)

    1. 杨立,蒙庆米,白天泉,李嘉尧,姚俊杰,马兰. 海拔对稻田金背鲤肠道结构、消化酶活性和肠道菌群的影响. 华南农业大学学报. 2024(06): 898-907 .
    2. 马兰,蒙庆米,李嘉尧,秦国兵,姚俊杰,王秀龙,杨立. 稻田增加沟坑对金背鲤肠道结构、消化酶活性及微生物群落的影响. 华南农业大学学报. 2024(06): 889-897 .

    Other cited types(0)

Catalog

    Article views (1165) PDF downloads (61) Cited by(2)
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return