| 73 | 0 | 14 |
| 下载次数 | 被引频次 | 阅读次数 |
性能测定是家畜育种的基石，然而，目前的人工测量方法存在费时费力、易受人为因素影响和接触式测量易造成动物应激反应等弊端，进而导致测定规模受限、精度不足、性能覆盖范围窄等问题，难以匹配我国畜牧业规模化、智能化发展趋势，因此研发新型测定技术十分必要。计算机视觉技术是一种非接触、高效、自动化和准确性高的测定方法，为家畜性能测定提供了一种全新的路径，在家畜性能测定中具有广阔前景。本文综述了计算机视觉技术在家畜体尺、体重、体况评分、背膘厚和眼肌面积测定中的研究进展，旨在为家畜智能化发展提供借鉴。
Abstract：Performance testing is the cornerstone for livestock breeding.However,current manual measurement methods are time-consuming,labor-intensive,susceptible to human error,and prone to causing animal stress due to physical contact.These limitations hinder its large-scale implementation,compromise accuracy,and restrict the range of measurable traits,thereby conflicting with the trend toward large-scale and smart farming in China.Therefore,developing novel measurement technologies is essential.Computer vision technology offers a promising non-contact approach characterized by high efficiency,automation,and accuracy for livestock performance measurement.This review summarizes recent advances in the application of computer vision for measuring livestock body dimensions,body weight,body condition score,backfat thickness,and loin eye area,aiming to provide references for the intelligent development of the livestock industry.
[1]Amdi C,Giblin L,Hennessy A A,et al.Feed allowance and maternal backfat levels during gestation influence maternal cortisol levels,milk fat composition and offspring growth[J].JNutr Sci,2013,2:e1.
[2]赵云翔,阳文攀,陶荣佳,等.妊娠期背膘厚对母猪产程及繁殖性能的影响[J].中国畜牧兽医,2019,46(5):1397-1404.
[3]Hoa V B,Seo H W,Seong P N,et al.Back-fat thickness as a primary index reflecting the yield and overall acceptance of pork meat[J].Anim Sci J,2021,92(1):e 13515.
[4]刘望宏,胡军勇,倪德斌,等.人员因素对猪活体测定结果的影响[J].黑龙江畜牧兽医(上半月),2012(5):10-12.
[5]Minagawa H,Ichikawa T.Determining the weight of pigs with image analysis[J].Trans ASAE,1994,37(3):1011-1015.
[6]Kuchida K,Hamaya S,Saito Y,et al.Development of a body dimension method for dairy cattle by computer analysis with video camera[J].Anim Sci Technol,1996,10(67):878-881.
[7]Stajnko D,Brus M,Hocevar M.Estimation of bull live weight through thermo graphically measured body dimensions[J].Comput Electron Agric,2008,61(2):233-240.
[8]Tasdemir S,Urkmez A,Inal S.Determination of body measurements on the Holstein cows using digital image analysis and estimation of live weight with regression analysis[J].Co mput Electron Agric,2011,76(2):189-197.
[9]Marchant J A,Schofield C P,White R P.Pig growth and conformation monitoring using image analysis[J].Anim Sci J,1999,68:141-150.
[10]刘伟.基于深度学习的牛体尺测量方法研究[D].包头:内蒙古科技大学,2020.
[11]刘同海,滕光辉,付为森,等.基于机器视觉的猪体体尺测点提取算法与应用[J].农业工程学报,2013,29(2):161-168.
[12]江杰,周丽娜,李刚.基于机器视觉的羊体体尺测量[J].计算机应用,2014,3(34):846-850.
[13]白明月,薛河儒,姜新华,等.基于拐点的羊体测量点提取及体尺计算[J].内蒙古农业大学学报(自然科学版),2017,38(6):73-78.
[14]Salau J,Haas J H,Junge W,et al.A multi-Kinect cow scanning system:Calculating linear traits from manually marked recordings of Holstein-Friesian dairy cows[J].Bio syst Eng,2017,157:92-98.
[15]Salau J,Haas J H,Junge W,et al.Automated calculation of udder depth and rear leg angle in Holstein-Friesian cows using a multi-Kinect cow scanning system[J].Bio syst Eng,2017,160:154-169.
[16]Pezzuolo A,Guarino M,Sartori L,et al.A feasibility study on the use of a structured light depth-camera for three-dimensional body measurements of dairy cows in free-stall barns[J].Sensors,2018,18(2):673.
[17]Pezzuolo A,Guarino M,Sartori L,et al.On-barn pig weight estimation based on body measurements by a Kinect vl depth camera[J].Comput Electron Agric,2018,148:29-36.
[18]徐金阳,徐爱俊,周素茵,等.基于Kinect相机的猪弯曲体尺测量算法研究[J].东北农业大学学报,2021,52(9):77-85.
[19]司永胜,安露露,刘刚,等.基于Kinect相机的猪体理想姿态检测与体尺测量[J].农业机械学报,2019,50(1):58-65.
[20]Guo H,Ma X,Ma Q,et al.LSSA CAU:An interactive 3d point clouds analysis software for body measurement oflivestock with similar forms of cows or pigs[J].Comput Electron Agric,2017,138:60-68.
[21]Shi S,Yin L,Liang S H,et al.Research on 3D surface reconstruction and body size measurement of pigs based on multiview RGB-D cameras[J].Comput Electron Agric,2020,175:105543.
[22]Ling Y,Jimin Z,Caixing L,et al.Point cloud-based pig body size measurement featured by standard and non-standard postures[J].Comput Electron Agric,2022,199:107135.
[23]Hu H,Yu J,Yin L,et al.An improved PointNet++point cloud segmentation model applied to automatic measurement method of pig body size[J].Comput Electron Agric,2023,205:107560.
[24]Mutua F K,Dewey C E,Arimi S M,et al.Prediction of live body weight using length and girth measurements for pigs in rural Western Kenya[J].J Swine Health Prod,2011,19(1):26-33.
[25]Banik S,Naskar S,Pankaj P K,et al.Effect of different body measurements on body weight in Ghungroo pigs[J].Ind J Anim Sci,2012,82(9):1094-1097.
[26]Panda S,Gaur G K,Chauhan A,et al.Accurate assessment of body weights using morphometric measurements in Landlly pigs[J].Trop Anim Health Prod,2021,53(3):362.
[27]Li G,Liu X,Ma Y,et al.Body size measurement and live body weight estimation for pigs based on back surface point clouds[J].Biosyst Eng,2022,218:10-22.
[28]付为森.基于双目视觉的猪体尺检测与体重预估方法研究[D].北京:中国农业大学,2010.
[29]Kongsro J.Estimation of pig weight using a microsoft kinect prototype imaging system[J].Comput Electron Agric,2014,109:32-35.
[30]初梦苑.基于三维重建的奶牛体尺检测与体重预估研究[D].保定:河北农业大学,2020.
[31]郝雪萍.基于图像处理的杜泊羊体重估算模型研究[D].武汉:武汉理工大学,2015.
[32]张凯,王春光,刘涛,等.基于计算机视觉技术育肥猪体重分析研究[J].农机化研究,2017,39(5):32-36.
[33]de Moraes Weber V A,de Lima Weber F,Gomes R D C,et al.Prediction of girolando cattle weight by means of body measurements extracted from images[J].Rev Bras Zootecn,2020,49:e20190110.
[34]Alonso J,Castanon A R,Bahamonde A.Support vector regression to predict carcass weight in beef cattle in advance of the slaughter[J].Comput Electron Agric,2013,91:116-120.
[35]Jensen D B,Dominiak K N,Pedersen L J.Automatic estimation of slaughter pig live weight using convolutional neural networks[Z].Lleida,Spain,2018.
[36]Fernandes AF A,Dorea J R R,Valente B D,et al.Comparison of data analytics strategies in computer vision systems to predict pig body composition traits from 3D images[J].J Anim Sci,2020,98(8):skaa250.
[37]Cang Y,He H,Qiao Y.An intelligent pig weights estimate method based on deep learning in sow stall environments[J].IEEE ACCESS,2019,7:164867-164875.
[38]He H,Qiao Y,Li X,et al.Automatic weight measurement of pigs based on 3D images and regression network[J].Comput Electron Agric,2021,187:106299.
[39]张建龙,冀横溢,滕光辉.基于深度卷积网络的育肥猪体重估测[J].中国农业大学学报,2021,26(8):111-119.
[40]He W,Mi Y,Ding X,et al.Two-stream cross-attention vision Transformer based on RGB-D images for pig weight estimation[J].Comput Electron Agric,2023,212:107986.
[41]Dohmen R,Catal C,Liu Q.Image-based body mass prediction of heifers using deep neural networks[J].Biosyst Eng,2021,204:283-293.
[42]Gj ergji M,de Moraes Weber V,Silva L O C,et al.Deep learning techniques for beef cattle body weight prediction[Z].345 E47TH ST,NEW YORK,NY 10017 USA:20201-8.
[43]刘高杨.基于机器视觉的奶牛体况自动评分方法研究[D].北京:中国农业大学,2021.
[44]Spoliansky R,Edan Y,Parmet Y,et al.Development of aut-omatic body condition scoring using a low-cost 3-dimensional Kinect camera[J].J Dairy Sci,2016,99(9):7714-7725.
[45]He H,Chen C,Zhang W,et al.Body condition scoring network based on improved YOLOX[J].Pattern analysis and applications:PAA,2023,26(3):1071-1087.
[46]李新儒.基于深度学习的奶牛体况评分方法研究[D].合肥:中国科学技术大学,2020.
[47]吴宇峰.基于深度学习的奶牛体况评分方法研究与系统开发[D].北京:中国农业大学,2022.
[48]Haupt R W,Wynn C M,Johnson M R,et al.Noncontact Laser Ultrasound for Biomedical Imaging Applications[J].Lincoln Lab J,2020,1(24):141-164.
[49]申志杰.基于机器视觉的母猪体况评分方法[D].北京:中国农业大学,2018.
[50]张梓鹏.基于计算机视觉的猪活体背膘厚与眼肌面积智能测定技术研究[D].北京:中国农业大学,2024.
基本信息:
DOI：10.19556/j.0258-7033.20250625-06
中图分类号:S818.9
引用信息:
[1]张梓鹏,李谦君,唐黄益,等.计算机视觉技术在家畜性能测定中的应用[J].中国畜牧杂志,2026,62(03):55-61.DOI:10.19556/j.0258-7033.20250625-06.
基金信息:
四川省科技成果转移转化示范项目（2024ZHCG 0109）; 河南省农业良种联合攻关项目（2022020102）; 财政部和农业农村部：国家生猪产业技术体系（CARS-35）
2026-02-02
2026-02-02
2026-02-02