Page 208 - 《水产学报》2025年第5期

张士薇，等 水产学报, 2025, 49(5): 059117

下几个核心部分构成：一套可以稳定采集高质 51.
量图像的硬件装置；一个大样本生长表型关键 Cao B X, Kong J, Luo K, et al. Comparison of growth and sur-
特 征 点 标 注 数 据 库 ； 基 于 HRNet 和 Mask R- vival performance among selected population, imported popula-
CNN 等深度学习算法的体尺性状和体表面积预 tion and inbreeding population in Litopenaeus vannamei[J].
测模型，以及体重的线性预测模型；集成硬件 Journal of Fisheries of China, 2015, 39(1): 42-51 (in Chinese).
监测、图像处理、表型测定和数据存储等功能 [ 7 ] Dai P, Li D Y, Sui J, et al. Prediction of meat yield in the
的软件管理系统。与国内外其他研究相比，本 Pacific whiteleg shrimp Penaeus vannamei[J]. Aquaculture,
系统在软硬件集成度、训练样本量、模型预测 2023, 577: 739914.
能力和测量速率等方面具有优势，已在多家凡 [ 8 ] 金烨楠, 龚瑞, 刘向荣, 等. 3 种对虾的图像测量技术与人工测
纳滨对虾育种单位中得到推广应用。 量方法的比较分析 [J]. 水产学报, 2018, 42(11): 1848-1854.

Jin Y N, Gong R, Liu X R, et al. Comparative analysis of image
参考文献 (References)： measurement technology and artificial measurement method

[ 1 ] 农业农村部渔业渔政管理局, 全国水产技术推广总站, 中国 based on three kinds of prawns[J]. Journal of Fisheries of
水产学会. 中国渔业统计年鉴 2024[M]. 北京: 中国农业出版 China, 2018, 42(11): 1848-1854 (in Chinese).
社, 2024. [ 9 ] 罗艳. 基于机器视觉技术的对虾规格检测方法研究 [D]. 杭
Ministry of Agriculture and Rural Affairs of the People’s 州: 浙江大学, 2013.
Republic of China, National Fisheries Technology Extension Luo Y. Detection of shrimp specification based on machine vis-
Center, China Society of Fisheries. China fishery statistical ion[D]. Hangzhou: Zhejiang University, 2013 (in Chinese).
yearbook 2024[M]. Beijing: China Agriculture Press, 2024 (in [10] 林妙玲. 基于机器视觉的虾体位姿和特征点识别 [D]. 杭州:
Chinese). 浙江大学, 2007.
[ 2 ] Zhang C, Guo C Y, Shu K H, et al. Comparative analysis of the Lin M L. Study on identification of shrimp position and feature
growth performance, vitality, body chemical composition and points based on machine vision[D]. Hangzhou: Zhejiang Uni-
economic efficiency of the main cultivated strains of Pacific versity, 2007 (in Chinese).
white shrimp (Litopenaeus vannamei) in coastal areas of [11] Xi M Z, Rahman A, Nguyen C, et al. Smart headset, computer
China[J]. Aquaculture, 2024, 587: 740856. vision and machine learning for efficient prawn farm manage-
[ 3 ] 刘永新, 邵长伟, 侯吉伦, 等. 中国水产育种研究现状与发展 ment[J]. Aquacultural Engineering, 2023, 102: 102339.
建议 [J]. 水产学报, 2023, 47(1): 019605. [12] 龚瑞. 基于计算机视觉的鱼虾识别和形态参数测量 [D]. 厦
Liu Y X, Shao C W, Hou J L, et al. Research status and devel- 门: 厦门大学, 2018.
opment suggestion of China’s aquaculture breeding[J]. Journal Gong R. Fish recognition and morphological parameters meas-
of Fisheries of China, 2023, 47(1): 019605 (in Chinese). urement of prawn based on computer vision[D]. Xiamen: Xia-
[ 4 ] 徐孝栋. 凡纳滨对虾育种群体遗传参数评估 [D]. 大连: 大连 men University, 2018 (in Chinese).
海洋大学, 2014. [13] 秦品发. 基于深度学习的海洋水产育种体型参数测量 [D]. 厦
Xu X D. Genetic parameters of growth and survival for the 门: 厦门大学, 2021.
selective breeding population in Litopenaeus vannamei[D]. Qin P F. Morphological parameters measurement based on deep
Dalian: Dalian Ocean University, 2014 (in Chinese). learning for marine fisheries breeding [D]. Xiamen: Xiamen
[ 5 ] 王兴强, 马甡, 董双林. 凡纳滨对虾生物学及养殖生态学研究 University, 2021 (in Chinese).
进展 [J]. 海洋湖沼通报, 2004(4): 94-100. [14] Li X M, Liu R X, Wang Z, et al. Automatic penaeus monodon
Wang X Q, Ma S, Dong S L. Studies on the biology and cul- larvae counting via equal keypoint regression with smart-
tural ecology of Litopenaeus vannamei: a review[J]. Transac- phones[J]. Animals, 2023, 13(12): 2036.
tions of Oceanology and Limnology, 2004(4): 94-100 (in [15] Zeng J J, Feng M S, Deng Y C, et al. Deep learning to obtain
Chinese). high-throughput morphological phenotypes and its genetic cor-
[ 6 ] 曹宝祥, 孔杰, 罗坤, 等. 凡纳滨对虾选育群体与近交群体、 relation with swimming performance in juvenile large yellow
引进群体生长和存活性能比较 [J]. 水产学报, 2015, 39(1): 42- croaker[J]. Aquaculture, 2024, 578: 740051.

https://www.china-fishery.cn 中国水产学会主办 sponsored by China Society of Fisheries
10