首页|期刊导航|智慧农业(中英文)|基于三维点云的家畜体尺表型智能测定技术研究进展

基于三维点云的家畜体尺表型智能测定技术研究进展OA

Research Progress on Intelligent Measurement Technologies for Livestock Body-Size Phenotypes Based on 3D Point Clouds

中文摘要英文摘要

[目的/意义]家畜体尺参数是评价生长发育、体况评分、生产性能和遗传改良的重要表型指标.传统人工体尺测量方法效率低、劳动强度大且易引起家畜应激.二维图像方法虽可实现非接触测量,但缺少深度信息,难以准确测量胸围、腹围等围度体尺.三维点云能够表征家畜体表空间结构,为体尺表型测定提供新的非接触式技术途径.本文系统梳理基于三维点云的家畜体尺测量研究进展,为家畜三维表型智能测量与智慧养殖应用提供参考.[进展]三维点云技术能够在保持非接触测量优势的基础上重建家畜三维体型结构,不仅可用于体长、体宽、体高等线性体尺测量,还可支持胸围、腹围、管围等围度体尺测量,以及臀部形态、后躯丰满度和肢蹄结构等局部形态特征提取.本文以猪、牛、羊为主要研究对象,围绕点云采集、预处理、补全、分割、关键点定位和体尺计算等流程,归纳了家畜点云采集传感器与采集方案,梳理了多视角配准、滤波降噪、姿态归一化和点云补全等预处理方法,总结了直接定位关键点和基于点云分割定位关键点两类体尺测量路线.[结论/展望]现有研究表明,基于三维点云的家畜体尺测量在自动化、非接触、高精度体尺表型测定方面具有良好应用前景,但仍面临复杂养殖环境下点云质量不稳定、模型算法适应性与部署能力不足、多物种多姿态数据集匮乏,以及评价标准不统一等问题.未来应重点发展低成本、轻便可靠的点云采集系统,构建并开源多物种、多姿态、多场景家畜点云数据集,发展鲁棒、轻量、可迁移的点云处理与体尺测量方法,并推进其在边缘计算设备和真实养殖场景中的部署应用.同时,应进一步将体尺测量结果与体况评分、局部形态评价、生长发育监测和生产性能分析相结合,推动三维点云体尺测量由几何参数提取向三维表型智能分析拓展,实现精准、实时、高通量的家畜体尺自动测量.

[Significance]Livestock body-size parameters are important phenotypic indicators for evaluating growth and development,body condition,production performance,genetic evaluation,and breeding selection.Traditional manual measurement is time-consum-ing,labor-intensive,operator-dependent,and may induce stress and safety risks during animal restraint.Although two-dimensional im-aging enables non-contact measurement,its lack of depth information limits the accurate estimation of girth-related traits and local body morphology.By directly describing three-dimensional body-surface structures,point clouds provide a promising basis for auto-mated and objective livestock phenotyping.The aim of this review is to systematically summarize advances in three-dimensional point cloud-based livestock body measurement,to clarify the main technical workflow and methodological routes,to compare their charac-teristics and application scenarios,and to identify key challenges and research priorities for intelligent three-dimensional phenotyping and smart livestock farming.[Progress]Three-dimensional point cloud technology can reconstruct livestock body structures while re-taining the advantages of non-contact measurement.It can be used for measuring linear traits,such as body length,body height,and body width;girth-related traits,including chest girth,abdominal girth,rump girth,and cannon circumference;and local morphological features such as rump shape,hindquarter fullness,and limb and hoof structure.With pigs,cattle,and sheep as the main research ob-jects,this review examines the technical workflow of point cloud acquisition,preprocessing,completion,segmentation,keypoint local-ization,and body-size calculation.Livestock point cloud acquisition sensors and fixed and mobile acquisition schemes are summa-rized.Preprocessing methods,including multi-view registration,filtering and denoising,posture normalization,and point cloud com-pletion,are reviewed.These procedures can reduce background interference,motion distortion,occlusion,data loss,and posture varia-tion,thereby improving measurement consistency.Two technical routes for body-size measurement are discussed.In the first route,an-atomical keypoints are directly localized from RGB images,depth images,or point clouds using geometric features,projection analy-sis,curvature,skeleton models,or deep learning-based detectors.This route is suitable for linear measurements under standardized postures.In the second route,the animal is first segmented into anatomically relevant regions,after which keypoints or measurement sections are identified within the corresponding regions.By narrowing the search space,segmentation-based methods can reduce inter-ference from unrelated body parts and are particularly suitable for variable postures,partial occlusion,and girth-related measurements.After keypoint localization or section determination,linear traits are generally calculated using Euclidean distances,whereas girth traits are estimated through contour extraction,curve fitting,and accumulated curve length.Overall,a development trend from manual annotation and rule-based geometric analysis toward automated methods integrating keypoint detection,point cloud segmentation,re-gional constraints,posture adaptation,and cross-species transfer is identified.[Conclusions and Prospects]Existing studies indicate that three-dimensional point cloud-based livestock body measurement has promising application prospects for automated,non-contact,and high-precision phenotype acquisition.However,several challenges remain,including unstable point cloud quality in complex farming environments;insufficient robustness,transferability,and edge-deployment capability of algorithms;limited multi-species and multi-posture datasets;and inconsistent definitions,annotations,and evaluation metrics.Future research should focus on improving acquisi-tion accuracy,synchronization,and environmental adaptability and developing low-cost,lightweight,and reliable systems.Multimod-al fusion of depth cameras,LiDAR,and RGB images,together with mobile platforms and multi-view acquisition,should be investigat-ed for continuous measurement of group-housed animals.Robust,lightweight,and transferable models should be developed through self-supervised or unsupervised pretraining,semi-supervised learning,transfer learning,model pruning,knowledge distillation,and lightweight feature extraction.Open datasets should cover multiple species,breeds,growth stages,postures,and farming scenarios,ac-companied by unified keypoint definitions,anatomical annotations,data partitions,and error metrics.In addition,body-size measure-ments should be integrated with body condition scoring,local morphological evaluation,growth and development monitoring,produc-tion performance analysis,genetic evaluation,and breeding selection.This will promote the transition from geometric parameter ex-traction to intelligent three-dimensional phenotypic analysis,ultimately achieving accurate,real-time,and high-throughput automatic livestock body measurement for precision feeding and smart livestock farming.

王海燕;李泽晨;曹钜松;黎煊;李嘉位;李国亮;徐学文

华中农业大学信息学院,湖北 武汉 430070,中国||华中农业大学农业农村部智慧养殖技术重点实验室,湖北 武汉 430070,中国华中农业大学信息学院,湖北 武汉 430070,中国华中农业大学信息学院,湖北 武汉 430070,中国华中农业大学农业农村部智慧养殖技术重点实验室,湖北 武汉 430070,中国华中农业大学信息学院,湖北 武汉 430070,中国华中农业大学信息学院,湖北 武汉 430070,中国华中农业大学农业动物遗传育种与繁殖教育部重点实验室,湖北 武汉 430070,中国

农业科技

三维点云点云采集数据处理深度学习家畜体尺测量

3D point cloudpoint cloud acquisitiondata processingdeep learninglivestock body measurement

《智慧农业(中英文)》 2026 (4)

17-34,18

国家重点研发计划项目(2023YFD1300401)中央高校基本科研业务费专项资金项目(2662025XXPY007)多模态人工智能系统全国重点实验室开放课题基金(MAIS2025062) National Key Research and Development Program of China(2023YFD1300401)Fundamental Research Funds for the Central Universities(2662025XXPY007)Open Project Program of the State Key Laboratory of Multimodal Artificial Intelligence Systems(MAIS2025062)

10.12133/j.smartag.SA202605012

评论