1.华中农业大学信息学院,武汉 430070
2.华电金沙江上游水电开发有限公司叶巴滩分公司,甘孜 627153
3.华中农业大学水产学院,武汉430070
周逸驰,E-mail:zhouyichi28@163.com
郑芳,E-mail:zhengfang@mail.hzau.edu.cn
收稿:2025-07-14,
纸质出版:2026-03-15
移动端阅览
周逸驰,陈彦祥,刘季松,等.基于关键点检测的前臀鮡表型测量与体质量预测[J].华中农业大学学报,2026,45(2):45‐57.
ZHOU Yichi,CHEN Yanxiang,LIU Jisong,et al.Measuring phenotype and predicting body weight of Pareuchiloglanis anteanalis based on keypoint detection[J].Journal of Huazhong Agricultural University,2026,45(02):45-57.
周逸驰,陈彦祥,刘季松,等.基于关键点检测的前臀鮡表型测量与体质量预测[J].华中农业大学学报,2026,45(2):45‐57. DOI: 10.13300/j.cnki.hnlkxb.2026.02.006.
ZHOU Yichi,CHEN Yanxiang,LIU Jisong,et al.Measuring phenotype and predicting body weight of Pareuchiloglanis anteanalis based on keypoint detection[J].Journal of Huazhong Agricultural University,2026,45(02):45-57. DOI: 10.13300/j.cnki.hnlkxb.2026.02.006.
为提高前臀鮡(
Pareuchiloglanis anteanalis
)表型数据获取效率并降低人工测量误差,构建基于关键点检测的表型自动测量与体质量预测方法。采集前臀鮡腹部视角、侧面视角与背部视角图像共951张,采用COCO格式完成关键点标注,并基于关键点坐标计算体长、体高、眼间距等传统体尺及框架距离指标;在相同训练配置下对RTMPOSE、LiteHRNet、YOLOv12n-pose与YOLOv8n-pose进行对比评估。结果显示,YOLOv8n-pose在测试集上的精确率为94.70%,表型测量平均相对误差(mean relative error,MRE)为5.45%,多数表型相对误差控制在10%以内;进一步结合相关性与共线性分析筛选胸鳍基部起点间距离(
X
5
)、胸鳍基部起点到腹鳍基部右端起点距离(
X
7
)、体高(
X
10
)、头长(
X
12
)和眼间距(
X
14
)等表型指标建立体质量多元回归模型,测试集决定系数
R
²为0.97。结果表明,该方法可实现前臀鮡表型的自动化测量与体质量的定量估算。
A method of automatically measuring the phenotype and predicting the body weight of
Pareuchiloglanis anteanalis
based on the keypoint detection was developed to improve the efficiency of obtaining the phenotypic data of
P. anteanalis
and reduce errors caused by manual measurements. 951 images were collected from the ventral,lateral,and dorsal views of
P. anteanalis
.Keypoints were annotated in the COCO format.Traditional body size including body length,body height,and interorbital distance and indexes of frame distance were calculated based on the coordinates of keypoints.RTMPOSE,LiteHRNet,YOLOv12n-pose,and YOLOv8n-pose were comparatively evaluated under the same
configuration of training,and YOLOv8n-pose was determined to be used for the automatic measurement of phenotypic parameters.Results showed that YOLOv8n-pose had a precision of 94.70% on the test set,with mean relative error (MRE) of 5.45% for phenotypic measurements,and the relative error of most phenotypes was controlled within 10%.Key indexes of phenotype including the distance between pectoral-fin origins (
X
5
),the distance from the pectoral-fin base to the right pelvic-fin base (
X
7
),body height (
X
10
),head length (
X
12
),and interorbital distance (
X
14
),were further selected by combining correlation and collinearity analysis to establish a multiple regression model for predicting body-weight,yielding an
R
² of 0.97 on the test set.It is indicated that the proposed method can achieve automated measurement of phenotype and quantitative estimation of body weight of
P. anteanalis
.It will provide data support for monitoring growth and evaluating selective breeding of small sisorid freshwater fishes.
方树淼,许涛清,崔桂华.鮡属 Pareuchiloglanis 鱼类一新种[J].动物分类学报,1984, 9(2):209-211.FANG S M, XU T Q, CUI G H.A new species of the catfish genus Pareuchiloglanis (Pisces:Sisoridae) from China[J].Acta zootaxonomica sinica, 1984, 9(2):209-211 (in Chinese) .
冯云鹏,杨胜保,方善臣,等.野生前臀亲鱼摄食驯化技术探究[J].科学养鱼,2024(5):75-77.FENG Y P,YANG S B,FANG S C,et al.Study on feeding and domestication technology of wild anterior hip parent fish[J].Scientific fish farming,2024(5):75-77 (in Chinese) .
姚景龙,陈毅峰,李堃,等.中华鮡与前臀鮡的形态差异和物种有效性[J].动物分类学报,2006(1):11-17.YAO J L,CHEN Y F,LI K,et al.Morphological variations and species validity of Pareuchiloglanis sinensis and P .anteanalis in southwestern of China[J].Acta zootaxonomica sinica,2006(1):11-17 (in Chinese with English abstract) .
郭奕,黄佳芯,邓博奇,等.改进Mask R-CNN的真实环境下鱼体语义分割[J].农业工程学报,2022,38(23):162-169.GUO Y,HUANG J X,DENG B Q,et al.Semantic segmentation of the fish bodies in real environment using improved Mask-RCNN model[J].Transactions of the CSAE,2022,38(23):162-169 (in Chinese with English abstract) .
YU C , LIU Y P , HU Z H,et al.Precise segmentation and measurement of inclined fish’s features based on U-Net and fish morphological characteristics[J].Applied engineering in agriculture,2022,38(1):37-48.
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[2025-07-14].https://doi.org/10.1016/j.aquaculture.2022.738847.
SUO F Y,HUANG K W,LING G,et al.Fish keypoints detection for ecology monitoring based on underwater visual intelligence[C]//2020 16th International Conference on Control,Automation,Robotics and Vision (ICARCV).December 13-15,2020.Shenzhen,China.Shenzhen:IEEE,2020:542-547.
KAMPFFMEYER M,SALBERG A B,JENSSEN R.Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). June 26-July 1,2016 ,Las Vegas,NV,USA.Las Vegas:IEEE,2016:680-688.
REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE transactions on pattern analysis and machine intelligence,2017,39(6):1137-1149.
闫党康.基于改进的Mask R-CNN的鱼类识别算法研究[J].计算机与数字工程,2023,51(6):1238-1243.YAN D K.Research on fish recognition algorithm based on improved mask R-CNN[J].Computer & digital engineering,2023,51(6):1238-1243 (in Chinese with English abstract) .
程思奇.基于关键点检测的水下鱼体长度测量技术研究与实现[D].大连:大连海洋大学,2023.CHENG S Q.Research and implementation of fish body length measurement technology based on keypoint detection[D].Dalian:Dalian Ocean University,2023 (in Chinese with English abstract) .
ZHOU S Y,CAI K W,FENG Y H,et al.An accurate detection model of Takifugu rubripes using an improved YOLO-V7 network[J/OL].Journal of marine science and engineering,2023,11(5):1051[2025-07-14].https://doi.org/10.3390/jmse11051051.
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.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 with English abstract) .
KOLAREVIC J,CALDUCH-GINER J,ESPMARK Å M,et al.A novel miniaturized biosensor for monitoring Atlantic salmon swimming activity and respiratory frequency[J/OL].Animals,2021,11(8):2403[2025-07-14].https://doi.org/10.3390/ani11082403.
MURUGAIYAN J S,PALANIAPPAN M,DURAIRAJ T,et al.Fish species recognition using transfer learning techniques[J].International journal of advances in intelligent informatics,2021,7(2):188[2025-07-14].https://doi.org/10.26555/ijain.v7i2.610.
田洁,杨信廷,徐大明,等.基于深度图像的大菱鲆体重估测模型研究[J].中国农业科技导报,2019,21(9):90-96.TIAN J,YANG X T,XU D M,et al.Research on the estimation model of Scophthalmus maximus ’weight based on depth image[J].Journal of agricultural science and technology,2019,21(9):90-96 (in Chinese with English abstract) .
周晖.基于深度学习的鱼类体尺测量研究[D].上海:上海海洋大学,2022.ZHOU H.Research of fish size measurement based on deep learning[D].Shanghai:Shanghai Ocean University,2022 (in Chinese with English abstract) .
HUSSAIN M.YOLOv1 to v8:unveiling each variant,a comprehensive review of YOLO[J].IEEE access, 2024,12:42816-42833.
LI X , WANG W , WU L ,et al.Generalized focal loss:learning qualified and distributed bounding boxes for dense object detection[DB/OL].arXiv, 2006 :2006.04388[2025-07-14].https://doi.org/10.48550/arXiv.2006.04388.
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[2025-07-14].https://doi.org/10.1016/j.compag.2021.106512.
ZHOU Y J,ZHU W G,HE Y H,et al.YOLOv8-based spatial target part recognition[C]//2023 IEEE 3rd International Conference on Information Technology,Big Data and Artificial Intelligence (ICIBA). May 26-28,2023 ,Chongqing,China.Chongqing:IEEE,2023:1684-1687.
JIANG T, LU P, ZHANG L, et al.Rtmpose:Real-time multi-person pose estimation based on mmpose[DB/OL].arXiv,2023:2303.07399[2025-07-14].https://doi.org/10.48550/arXiv.2303.07399.
YU C Q,XIAO B,GAO C X,et al.Lite-HRNet:a lightweight high-resolution network[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).June 20-25,2021.Nashville,TN,USA.Nashville:IEEE,2021:10435-10445.
MAJI D,NAGORI S,MATHEW M,et al.YOLO-pose:enhancing YOLO for multi person pose estimation using object keypoint similarity loss[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).June 19-20,2022.New Orleans,LA,USA.New Orleans:IEEE,2022:2636-2645.
SHAPIRO S S,WILK M B.An analysis of variance test for normality(complete samples)[J].Biometrika,1965,52(3/4):591-611.
GÜMÜŞ E,YILAYAZ A,KANYILMAZ M,et al.Evaluation of body weight and color of cultured European catfish ( Silurus glanis ) and African catfish ( Clarias gariepinus ) using image analysis[J/OL].Aquacultural engineering,2021,93:102147[2025-07-14].https://doi.org/10.1016/j.aquaeng.2021.102147.
翁智,范琦,郑志强.基于二维与三维的无接触式肉牛体尺自动测量方法[J/OL].智慧农业,2024,1-12(2024-08-06)[2025-07-14].http://kns.cnki.net/kcms/detail/10.1681.S.20240517.1017.002.html.WENG Z,FAN Q,ZHENG Z Q.Automatic body size measurement method for beef cattle based on 2D and 3D contactless sensing[J/OL].Smart agriculture,2024,1-12(2024-08-06)[2025-07-14].http://kns.cnki.net/kcms/detail/10.1681.S.20240517.1017.002.html (in Chinese with English abstract) .
0
浏览量
2
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621