| Citation: |
ZHANG Shiwei, DAI Ping, GAO Guangchun, MENG Xianhong, LUO Kun, SUI Juan, TAN Jian, FU Qiang, CAO Jiawang, CHEN Baolong, LI Xupeng, QIANG Guangfeng, XING Qun, QI Yunhui, KONG Jie, LUAN Sheng. Development and application of a deep learning algorithm-based growth phenotypes measurement system of the Pacific white shrimp (Litopenaeus vannamei)[J]. Journal of fisheries of china. DOI: 10.11964/jfc.20240714612
|
To address the low efficiency and high error rates associated with manual measurement of growth phenotypes in the Pacific white shrimp (Litopenaeus vannamei), this study developed a dedicated image acquisition box capable of capturing standardized, high-quality side-view images of the shrimp. Utilizing this system, a High-Resolution Network (HRNet) model was employed to identify nine key feature points of the shrimp, enabling the measurement of traits such as body length. Additionally, a Mask Region Convolutional Neural Network (Mask R-CNN) model was utilized for shrimp contour segmentation to calculate body surface area. Regression models incorporating body length and body surface area were subsequently developed to predict body weight. An integrated image processing and data management software was also developed to establish a precise measurement system for the growth phenotypes of L. vannamei. The study found that the HRNet model achieved recognition rates exceeding 98% for all nine feature points, with rates exceeding 99% for seven points. The true values of body length and abdominal segment length were measured using two methods: manual measurement with a ruler and measurement from manually tagged feature points in the images. The predictive accuracy of body length and abdominal segment length was calculated to be 0.91–0.97 and 0.91–0.93, respectively, with average relative errors of 1.39%-4.63% and 2.46%-4.59%. Evaluation against manually segmented shrimp body contours showed that the Mask R-CNN model predicted body surface area with an accuracy of 0.98 and an average relative error of 1.73%. Regression models incorporating variables such as body length, body surface area, and gender were developed to predict body weight, achieving accuracies above 0.94, with the model incorporating both body length and body surface area achieving the highest prediction accuracy (0.97). These results demonstrate that computer vision technology combined with deep learning algorithms can accurately measure growth phenotypes, such as body length and body surface area, and predict body weight L. vannamei. This study provides an efficient tool for the accurate and rapid measurement of growth phenotypes in L. vannamei.
| [1] |
农业农村部渔业渔政管理局, 全国水产技术推广总站, 中国水产学会. 中国渔业统计年鉴 2024[M]. 北京: 中国农业出版社, 2024.
Ministry of Agriculture and Rural Affairs of the People’s Republic of China, National Fisheries Technology Extension Center, China Society of Fisheries. China fishery statistical yearbook 2024[M]. Beijing: China Agriculture Press, 2024 (in Chinese).
|
| [2] |
Zhang C, Guo C Y, Shu K H, et al. Comparative analysis of the growth performance, vitality, body chemical composition and economic efficiency of the main cultivated strains of Pacific white shrimp (Litopenaeus vannamei) in coastal areas of China[J]. Aquaculture, 2024, 587: 740856. doi: 10.1016/j.aquaculture.2024.740856
|
| [3] |
刘永新, 邵长伟, 侯吉伦, 等. 中国水产育种研究现状与发展建议[J]. 水产学报, 2023, 47(1): 019605.
Liu Y X, Shao C W, Hou J L, et al. Research status and development suggestion of China’s aquaculture breeding[J]. Journal of Fisheries of China, 2023, 47(1): 019605 (in Chinese).
|
| [4] |
徐孝栋. 凡纳滨对虾育种群体遗传参数评估[D]. 大连: 大连海洋大学, 2014.
Xu X D. Genetic parameters of growth and survival for the selective breeding population in Litopenaeus vannamei[D]. Dalian: Dalian Ocean University, 2014 (in Chinese).
|
| [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进展[J]. 海洋湖沼通报, 2004(4): 94-100. doi: 10.3969/j.issn.1003-6482.2004.04.016
Wang X Q, Ma S, Dong S L. Studies on the biology and cultural ecology of Litopenaeus vannamei: a review[J]. Transactions of Oceanology and Limnology, 2004(4): 94-100 (in Chinese). doi: 10.3969/j.issn.1003-6482.2004.04.016
|
| [6] |
曹宝祥, 孔杰, 罗坤, 等. 凡纳滨对虾选育群体与近交群体、引进群体生长和存活性能比较[J]. 水产学报, 2015, 39(1): 42-51.
Cao B X, Kong J, Luo K, et al. Comparison of growth and survival performance among selected population, imported population and inbreeding population in Litopenaeus vannamei[J]. Journal of Fisheries of China, 2015, 39(1): 42-51 (in Chinese).
|
| [7] |
Dai P, Li D Y, Sui J, et al. Prediction of meat yield in the Pacific whiteleg shrimp Penaeus vannamei[J]. Aquaculture, 2023, 577: 739914. doi: 10.1016/j.aquaculture.2023.739914
|
| [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 measurement technology and artificial measurement method based on three kinds of prawns[J]. Journal of Fisheries of China, 2018, 42(11): 1848-1854 (in Chinese).
|
| [9] |
罗艳. 基于机器视觉技术的对虾规格检测方法研究[D]. 杭州: 浙江大学, 2013.
Luo Y. Detection of shrimp specification based on machine vision[D]. Hangzhou: Zhejiang University, 2013 (in Chinese).
|
| [10] |
林妙玲. 基于机器视觉的虾体位姿和特征点识别[D]. 杭州: 浙江大学, 2007.
Lin M L. Study on identification of shrimp position and feature points based on machine vision[D]. Hangzhou: Zhejiang University, 2007 (in Chinese).
|
| [11] |
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
|
| [12] |
龚瑞. 基于计算机视觉的鱼虾识别和形态参数测量[D]. 厦门: 厦门大学, 2018.
Gong R. Fish recognition and morphological parameters measurement of prawn based on computer vision[D]. Xiamen: Xiamen University, 2018 (in Chinese).
|
| [13] |
秦品发. 基于深度学习的海洋水产育种体型参数测量[D]. 厦门: 厦门大学, 2021.
Qin P F. Morphological parameters measurement based on deep learning for marine fisheries breeding [D]. Xiamen: Xiamen University, 2021 (in Chinese).
|
| [14] |
Li X M, Liu R X, Wang Z, et al. Automatic penaeus monodon larvae counting via equal keypoint regression with smartphones[J]. Animals, 2023, 13(12): 2036. doi: 10.3390/ani13122036
|
| [15] |
Zeng J J, Feng M S, Deng Y C, et al. Deep learning to obtain high-throughput morphological phenotypes and its genetic correlation with swimming performance in juvenile large yellow croaker[J]. Aquaculture, 2024, 578: 740051. doi: 10.1016/j.aquaculture.2023.740051
|
| [16] |
Li H R, Zheng R, Jiang W X, et al. Fish length estimation based on stereo vision and keypoint detection[C]//IEEE. Proceedings of 2024 36th Chinese Control and Decision Conference. Xi'an: IEEE, 2024: 1747-1752.
|
| [17] |
Yu C, Fan X, Hu Z H, et al. Segmentation and measurement scheme for fish morphological features based on Mask R-CNN[J]. Information Processing in Agriculture, 2020, 7(4): 523-534. doi: 10.1016/j.inpa.2020.01.002
|
| [18] |
Freitas M V, Lemos C G, Ariede R B, et al. High-throughput phenotyping by deep learning to include body shape in the breeding program of pacu (Piaractus mesopotamicus)[J]. Aquaculture, 2023, 562: 738847. doi: 10.1016/j.aquaculture.2022.738847
|
| [19] |
王禹莎, 王家迎, 辛瑞, 等. 基于计算机视觉的大黄鱼体尺、体重性状表型测量装置开发和应用[J]. 水产学报, 2023, 47(1): 019516.
Wang Y S, Wang J Y, Xin R, et al. Application of computer vision in morphological and body weight measurements of large yellow croaker (Larimichthys crocea)[J]. Journal of Fisheries of China, 2023, 47(1): 019516 (in Chinese).
|
| [20] |
Russell B C, Torralba A, Murphy K P, et al. LabelMe: a database and web-based tool for image annotation[J]. International Journal of Computer Vision, 2008, 77(1): 157-173.
|
| [21] |
Rothschild C, Aflalo E D, Kedem I, et al. Computer vision system for counting crustacean larvae by detection[J]. Smart Agricultural Technology, 2023, 5: 100289. doi: 10.1016/j.atech.2023.100289
|
| [22] |
Solahudin M, Slamet W, Dwi A S. Vaname (Litopenaeus vannamei) shrimp fry counting based on image processing method[J]. IOP Conference Series: Earth and Environmental Science, 2018, 147: 012014. doi: 10.1088/1755-1315/147/1/012014
|
| [23] |
甘露. 计算机视觉技术在虾蟹类养殖中的应用[J]. 黑龙江水产, 2024, 43(3): 334-336. doi: 10.3969/j.issn.1674-2419.2024.03.022
Gan L. Application of computer vision technology in shrimp and crab culture[J]. Northern Chinese Fisheries, 2024, 43(3): 334-336 (in Chinese). doi: 10.3969/j.issn.1674-2419.2024.03.022
|
| [24] |
李道亮, 刘畅. 人工智能在水产养殖中研究应用分析与未来展望[J]. 智慧农业(中英文), 2020, 2(3): 1-20.
Li D L, Liu C. Recent advances and future outlook for artificial intelligence in aquaculture[J]. Smart Agriculture, 2020, 2(3): 1-20 (in Chinese).
|
| [25] |
吴雯岑, 赵辉, 刘伟文, 等. 精密视觉测量中照明对图像质量的影响[J]. 上海交通大学学报, 2009, 43(6): 931-934,939. doi: 10.3321/j.issn:1006-2467.2009.06.018
Wu W C, Zhao H, Liu W W, et al. Effects of illumination on image quality in precision vision measurement[J]. Journal of Shanghai Jiaotong University, 2009, 43(6): 931-934,939 (in Chinese). doi: 10.3321/j.issn:1006-2467.2009.06.018
|
| [26] |
李婵, 万晓霞, 谢伟, 等. 照明光源对多光谱图像采集精度影响的研究[J]. 激光杂志, 2016, 37(12): 44-47.
Li C, Wan X X, Xie W, et al. Effects of light source on multispectral image acquisition accuracy[J]. Laser Journal, 2016, 37(12): 44-47 (in Chinese).
|
| [27] |
龚聪, 徐杜. 光源强度变化对图像检测精度的影响及其解决方法[J]. 科学技术与工程, 2014, 14(13): 236-239. doi: 10.3969/j.issn.1671-1815.2014.13.047
Gong C, Xu D. Impact and solution of light source intensity changes to image measuring precision[J]. Science Technology and Engineering, 2014, 14(13): 236-239 (in Chinese). doi: 10.3969/j.issn.1671-1815.2014.13.047
|
| [28] |
洪辰, 刘子豪, 汪许倩, 等. 基于形态学特征的对虾完整性识别方法构建[J]. 食品安全质量检测学报, 2021, 12(22): 8666-8673.
Hong C, Liu Z H, Wang X Q, et al. Construction of completeness recognition method for shrimp (Litopenaeus vannamei) based on morphological characteristics[J]. Journal of Food Safety and Quality, 2021, 12(22): 8666-8673 (in Chinese).
|
| [29] |
Ghasemi-Varnamkhasti M, Goli R, Forina M, et al. Application of image analysis combined with computational expert approaches for shrimp freshness evaluation[J]. International Journal of Food Properties, 2016, 19(10): 2202-2222. doi: 10.1080/10942912.2015.1118386
|
| [30] |
高丽杰, 信文雪. 基于深度学习的光照不均匀图像识别系统设计[J]. 信息与电脑, 2023, 35(9): 25-27. doi: 10.3969/j.issn.1003-9767.2023.09.008
Gao L J, Xin W X. Design of illumination uneven image recognition system based on deep learning[J]. Information & Computer, 2023, 35(9): 25-27 (in Chinese). doi: 10.3969/j.issn.1003-9767.2023.09.008
|
| [31] |
Yu X J, Wang J P, Wen S T, et al. A deep learning based feature extraction method on hyperspectral images for nondestructive prediction of TVB-N content in Pacific white shrimp (Litopenaeus vannamei)[J]. Biosystems Engineering, 2019, 178: 244-255. doi: 10.1016/j.biosystemseng.2018.11.018
|
| [32] |
唐扬, 孟小菲, 沈瑞福, 等. 凡纳滨对虾家系选育的研究与应用[J]. 水产科学, 2018, 37(4): 555-563.
Tang Y, Meng X F, Shen R F, et al. Research and application of family selective breeding in culture of Pacific white shrimp Litopenaeus vannamei[J]. Fisheries Science, 2018, 37(4): 555-563 (in Chinese).
|
| [33] |
陈松林, 徐文腾, 卢昇, 等. 水产育种生物技术发展战略研究[J]. 中国工程科学, 2023, 25(4): 214-226. doi: 10.15302/J-SSCAE-2023.07.023
Chen S L, Xu W T, Lu S, et al. Development strategy for aquatic breeding biotechnology[J]. Strategic Study of CAE, 2023, 25(4): 214-226 (in Chinese). doi: 10.15302/J-SSCAE-2023.07.023
|
| [34] |
孔杰, 栾生, 谭建, 等. 对虾选择育种研究进展[J]. 中国海洋大学学报, 2020, 50(9): 81-97.
Kong J, Luan S, Tan J, et al. Progress of study on penaeid shrimp selective breeding[J]. Periodical of Ocean University of China, 2020, 50(9): 81-97 (in Chinese).
|
| [35] |
Sun K, Xiao B, Liu D, et al. Deep high-resolution representation learning for human pose estimation[C]//IEEE. Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 5693-5703.
|
| [36] |
杨爱萍, 田鑫, 杨炳旺, 等. 基于多特征融合的单幅水下图像清晰化[J]. 天津大学学报(自然科学与工程技术版), 2018, 51(10): 1031-1041.
Yang A P, Tian X, Yang B W, et al. Single underwater image sharpening based on multi-feature fusion[J]. Journal of Tianjin University (Science and Technology Edition), 2018, 51(10): 1031-1041 (in Chinese).
|
| [37] |
徐岩, 孙美双. 基于多特征融合的卷积神经网络图像去雾算法[J]. 激光与光电子学进展, 2018, 55(3): 031012.
Xu Y, Sun M S. Convolution neural network image defogging based on multi-feature fusion[J]. Laser & Optoelectronics Progress, 2018, 55(3): 031012 (in Chinese).
|
| [38] |
Zhou H, Kim S H, Kim S C, et al. Size estimation for shrimp using deep learning method[J]. Smart Media Journal, 2023, 12(3): 112-119.
|
| [39] |
鲍镇宁, 于洋, 李富花. 基于Faster R-CNN的对虾生长性状表型高通量测定技术的建立及应用[J]. 水生生物学报, 2023, 47(10): 1576-1584. doi: 10.7541/2023.2022.0490
Bao Z N, Yu Y, Li F H. The establishment and application of a fast phenotypic determination technique based on Faster R-CNN for growth traits in shrimp[J]. Acta Hydrobiologica Sinica, 2023, 47(10): 1576-1584 (in Chinese). doi: 10.7541/2023.2022.0490
|
| [40] |
何志鹏, 巩高瑞, 熊阳, 等. 基于计算机视觉的黄颡鱼表型特征测量和体重预测模型研究[J]. 水生生物学报, 2024, 48(7): 1149-1158. doi: 10.7541/2024.2023.0254
He Z P, Gong G R, Xiong Y, et al. A phenotypic measurement and weight prediction model of Pelteobagrus fulvidraco based on computer vision[J]. Acta Hydrobiologica Sinica, 2024, 48(7): 1149-1158 (in Chinese). doi: 10.7541/2024.2023.0254
|
| [41] |
Redmon J, Divvala S, Girshick R, et al. You Only Look Once: unified, real-time object detection[C]//IEEE. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 779-788.
|
| [42] |
宋自根, 张佳彬, 覃学标, 等. 一种基于Mask-RCNN图像分割的头足类动物角质颚色素沉积量化方法[J]. 渔业现代化, 2021, 48(5): 70-78. doi: 10.3969/j.issn.1007-9580.2021.05.010
Song Z G, Zhang J B, Qin X B, et al. A Mask-RCNN based quantification method for pigmentation of cephalopod beaks[J]. Fishery Modernization, 2021, 48(5): 70-78 (in Chinese). doi: 10.3969/j.issn.1007-9580.2021.05.010
|
| [43] |
He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//IEEE. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
|
| [44] |
Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//IEEE. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 2117-2125.
|
| [45] |
He K M, Gkioxari G, Dollár P, et al. Mask R-CNN[C]//IEEE. Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 2961-2969.
|
| [46] |
Prajapati S D, Ujjania N C. Study on length weight relationship and condition factor of whiteleg shrimp Litopenaeus vannamei (Boone, 1931) cultured in earthen pond, Khambhat (Gujarat)[J]. International Journal of Fauna and Biological Studies, 2021, 8(1): 67-70. doi: 10.22271/23940522.2021.v8.i1b.792
|
| [47] |
李玉虎, 张志怀, 宋芹芹, 等. 凡纳滨对虾新品系体形性状对其体质量的影响[J]. 热带生物学报, 2014, 5(4): 307-311. doi: 10.3969/j.issn.1674-7054.2014.04.001
Li Y H, Zhang Z H, Song Q Q, et al. Effect of growth traits on body weight of the new breeds of Litopenaeus vannamei[J]. Journal of Tropical Biology, 2014, 5(4): 307-311 (in Chinese). doi: 10.3969/j.issn.1674-7054.2014.04.001
|
| [1] | XIANG Kun, SUN Haofeng, XU Yuqing, PEI Luowei, ZHAO Jian, YE Zhangying. Advances in the production and removal of off-flavors in Recirculating Aquaculture Systems (RAS) for the cultivation of freshwater fish[J]. Journal of fisheries of china, 2024, 48(12): 129501. DOI: 10.11964/jfc.20240814642 |
| [2] | OU Liguo, LAN Zhenfeng, LIU Bilin, CHEN Xinjun, CHEN Yong. Automatic extraction of contour features of fish morphology based on computer vision[J]. Journal of fisheries of china, 2024, 48(12): 129106. DOI: 10.11964/jfc.20201212549 |
| [3] | XU Ankang, HUANG Liuyi, YOU Xinxing, BI Chunwei, HE Shuyue, XU Xinle, WANG Xiao. 3D reconstruction of fish based on binocular vision: a case study of Scomberomorus niphonius[J]. Journal of fisheries of china, 2024, 48(12): 129105. DOI: 10.11964/jfc.20240114331 |
| [4] | CAO Shuhua, WEI Maole, LI Yongren, HUANG Bowen, XIN Lusheng, BAI Changming, WANG Chongming. Construction of and polymerizing characterization witheukaryotic expression system for Ostreid herpesvirus 1 structural proteins[J]. Journal of fisheries of china, 2024, 48(5): 059407. DOI: 10.11964/jfc.20240214373 |
| [5] | ZHAO Wenwu, CHEN Peng, ZHAO Yue, FANG Hai, ZHAO Yongfeng. Analysis of measures to enhance the influence of fishery scientific journals[J]. Journal of fisheries of china, 2023, 47(12): 129116. DOI: 10.11964/jfc.20231014210 |
| [6] | DING Xiaoyu, LI Zhentong, DUAN Pengfei, QIU Yishu, WANG Xinyi, LI Linlin, WANG Linna, LIU Yang, LI Wensheng, WANG Qingbin, ZHAO Xia, TIAN Yongsheng, LI Shengzhong. Effects of long-term cryopreservation on ultrastructure and enzyme activity of Epinephelus lanceolatus sperm[J]. Journal of fisheries of china, 2023, 47(7): 079605. DOI: 10.11964/jfc.20221113796 |
| [7] | HU Yixuan, LIU Ying, REN Xiaozhong, LI Meng, BI Chunwei. Numerical study on optimization of inlet system of square arc angle aquaculture tank based on flow pattern[J]. Journal of fisheries of china, 2023, 47(5): 059516. DOI: 10.11964/jfc.20211213244 |
| [8] | WANG Yusha, WANG Jiaying, XIN Rui, KE Qiaozhen, JIANG Pengxin, ZHOU Tao, XU Peng. Application of computer vision in morphological and body weight measurements of large yellow croaker (Larimichthys crocea)[J]. Journal of fisheries of china, 2023, 47(1): 019516. DOI: 10.11964/jfc.20220813656 |
| [9] | JIN Yenan, GONG Rui, LIU Xiangrong, ZENG Xiangxiang, MAO Yong. Comparative analysis of image measurement technology and artificial measurement method based on three kinds of prawns[J]. Journal of fisheries of china, 2018, 42(11): 1848-1854. DOI: 10.11964/jfc.20170910971 |
| [10] | ZHANG Kai, YU Deguang, XIE Jun, WANG Guangjun, YU Ermeng, GONG Wangbao, LI Zhifei, WEI Nan, XIA Yun, WANG Cuicui, LIU Banghui. Emergy evaluation of largemouth bass (Micropterus salmoides) aquaculture system in the Pearl River Delta, China[J]. Journal of fisheries of china, 2017, 41(9): 1424-1433. DOI: 10.11964/jfc.20160310324 |
DownLoad: