畜禽个体识别技术研究进展

doi:10.16174/j.issn.1673-4645.2024.03.005

摘要/Abstract

摘要： 畜禽个体识别是实现精细化管理、智慧化养殖的重要前提。耳切、耳纹和热铁烙印等是传统人工辨别畜禽个体的方法，存在效率低、个体应激性大等问题，基于无线射频技术的个体识别方法应激程度小，但存在价格昂贵、易脱落、续航时间短等问题。近年来，随着机器视觉与深度学习技术的快速发展，非接触式个体识别方法成为当前研究热点之一。本文在充分梳理现有畜禽个体识别方法的基础上，介绍了典型的接触式个体识别方法及存在的优缺点，并分别阐述了基于图像处理和基于深度学习的2 种非接触式畜禽个体识别方法及优缺点，总结分析了在畜禽个体识别中关于深度学习模型、样本数据量及研究层面等存在的问题和改进策略，提出了相关建议，可为养殖管理人员提供理论依据和技术支撑。

关键词: 畜禽, 机器视觉, 深度学习, 个体识别

中图分类号: S818.9；TP391.41

纪宝锋, 周孟创, 朱芷芫, 陈嘉辉, 朱君, 李斌. 畜禽个体识别技术研究进展[J]. 中国猪业, 2024, 19(3): 47-58.

参考文献

[1] 滕光辉. 畜禽设施精细养殖中信息感知与环境调控综述[J]. 智慧农业(中英文), 2019, 1(3):1-12. TENG GH. Information sensing and environment control of precision facility livestock and poultry farming [J]. Smart Agriculture, 2019, 1(3):1-12. [2] 初梦苑, 司永胜, 李前, 等. 家畜体尺自动测量技术研究进展[J].农业工程学报, 2022, 38(13):228-240. CHU MY, SI YS, LI Q, et al. Research advances in the automatic measurement technology for livestock body size [J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(13):228-240. [3] KUMAR S, SINGH SK. Visual animal biometrics: survey[J]. IET Biometrics, 2017, 6(3):139-156． [4] 王军, 姜永增, 郭艳宏. 基于RFID 技术的生猪行为自动监测系统的设计[J]. 农机化研究, 2014(1):108-111. WANG J, JIANG YZ, GUO YH. Design of pig behavior automatic monitoring system based on RFID technology[J]. Journal of Agricultural Mechanization Research, 2014(1):108-111. [5] 刘琪伟, 郭小燕, 李纯斌, 等. 基于改进YOLOv5 的牛个体图像识别方法[J]. 软件工程, 2023, 26(9):42-47,58. LIU QW, GUO XY, LI CB, et al. An improved YOLOv5-based method for image recognition of cattle individual[J]. Software Engineering, 2023, 26(9):42-47,58. [6] 刘奇. 基于机器视觉的苹果分拣系统研究[D]. 西安: 西京学院, 2022. LIU Q. Research on apple sorting systemand method based on machine vision[D]. Xi'an: Xijing University, 2022. [7] 邢永鑫, 孙游东, 王天一. 基于改进SSD 算法对奶牛的个体识别[J]. 计算机工程与应用, 2022, 58(2):208-214. XING YX, SUN YD, WANG TY. Individual recognition of dairy cow based on improved SSD algorithm[J]. Computer Engineering and Applications, 2022, 58(2):208-214. [8] ANDREW W, GREATWOOD C, BURGHARDT T. Fusing animal biometrics with autonomous robotics: drone-based search and individual ID of Friesiancattle[C]//IEEE Winter Applications of Computer Vision Workshops. Virtual, 2020:38-43. [9] 尚诚. 基于深度学习的羊只个体身份识别研究[D]. 杨凌: 西北农林科技大学, 2022. SHANG C. Research on individual identification of goat based on deep learning [D]. Yangling: Northwest A & F University, 2022. [10] 王思懿. 机器视觉在奶牛个体识别中的研究进展[J]. 农业工程技术, 2020, 40(27):55-57. WAGN SY. Research progress of machine vision in individual identification of dairy cows [J]. Agricultural Engineering Technology, 2020, 40(27):55-57. [11] ALLEN A, GOLDEN B, TAYLOR M, et al. Evaluation of retinal imaging technology for the biometric identification of bovine animals in Northern Ireland[J]. Livestock Science, 2008, 116(1-3):42-52. [12] LU Y, HE XF, WEN Y, et al. A new cow identification system based on iris analysis and recognition[J]. International Journal of Biometrics, 2014, 6(1):18. [13] GABER T, THARWAT A, HASSANIEN AE, et al. Biometric cattle identification approach based on Weber's local descriptor and adaBoost classifier [J]. Computers and Electronics in Agriculture, 2016, 122(C):55-66. [14] KUMAR S, TIWARI S, SINGH SK. Face recognition for cattle[C]//Proceedings of the 2015 Third International Conference on Image Information Processing (ICIIP). New York: ACM,2015:65-72. [15] MONTEIRO FC. Automatic cattle identification using graph matching based on local invariant features [C]//International Conference on Image Analysis and Recognition. Cham: Springer, 2016:792-800. [16] YANG H, ZHANG R, ROBINSON P. Human and sheep facial landmarks localisation by triplet interpolated features [J].Computer Vision and Pattern Recognition, 2016. doi: 10.48550/arXiv.1509.04954. [17] 蔡骋, 宋肖肖, 何进荣. 基于计算机视觉的牛脸轮廓提取算法及实现[J]. 农业工程学报, 2017, 33(11):171-177． CAI C, SONG XX, HE JR. Algorithm and realization for cattle face contour extraction based oncomputer vision [J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(11):171-177． [18] AHRENDT P, GREGERSEN T, KARSTOFT H. Development of a real-time computer vision system for tracking loosehoused pigs [J]. Computers & Electronics in Agriculture, 2011, 76(2):169-174. [19] HUANG W, ZHU W, MA C, et al. Identification of group-housed pigs based on Gabor and local binary pattern features [J]. Biosystems Engineering, 2018, 166:90-100. [20] Z HAO K, JIN X, JI J, et al. Individual identification of holstein dairy cows based on detecting and matcahing feature points in body images[J]. Biosystems Engineering, 2019, 181:128-139. [21] CAI C, LI J. Cattle face recognition using local binary pattern descriptor [C]// Asia-Pacific Signal and Information Processing Association 2013 Annual Summit and Conference. Kaohsiung, Taiwan, China, 2013. [22] 杜峥. 基于深度学习的学生课堂行为识别与分析系统研究[D]. 邯郸: 河北工程大学, 2023. DU Z. Research on student Classroom behavior recognition and analysis system based on Deep Learning[D]. Handan: Hebei University of Engineering, 2023. [23] KUMAR S, PANDEY A, SATWIK KSR, et al. Deep learning framework for recognition of cattle using muzzle point image pattern[J]. Measurement, 2018, 116:1-17. [24] BARRY B, GONZALES UA, MCDONNELL K, et al. Using muzzle pattern recognition as a biometric approach for cattle identification [J]. Transactions of the Asabe, 2007, 3 (50):1073-1080. [25] AWAD AI, ZAWBAA HM, MAHMOUD HA, et al. A robust cattle identification scheme using muzzle print images[C]// Institute of Electrical and Electronics Engineers, 2013:529-534. [26] HANSEN MF, SMITH ML, SMITH LN, et al. Towards on-farm pig face recognition using convolutional neural networks[J].Computers in Industry, 2018, 98:145-152. [27] MA RSOT M, MEI J, SHAN X, et al. An adaptive pig face recognition approach using convolutional neural networks[J]. Computers and Electronics in Agriculture, 2020, 173:105386. [28] XU B, WANG W, GUO L, et al. Cattle face net: a cattle face identification approach based on retinaface and arc face loss[J]. Computers and Electronics in Agriculture, 2022, 193:106675. [29] 王荣, 史再峰, 高荣华, 等. 多变环境下基于多尺度卷积网络的猪个体识别[J]. 江西农业大学学报, 2020, 42(2):391-400. WANG R, SHI ZF, GAO RH, et al. Individual identification of pigs based on multi-scale convolutional network in a variable environment[J]. Acta Agriculturae Universitatis Jiangxiensis, 2020, 42(2):391-400. [30] 杨蜀秦, 刘杨启航, 王振, 等. 基于融合坐标信息的改进YOLO V4模型识别奶牛面部[J]. 农业工程学报, 2021, 37(15):129-135. YANG SQ, LIU YQH, WANG Z, et al. Improved YOLO V4 model for face recognition of diary cow by fusing coordinate information[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(15):129-135. [31] 朱敏玲, 赵亮亮, 和首杰. CNN 与SVM 和ResNet 相结合的牛脸识别系统模型研究与实现[J]. 重庆理工大学学报(自然科学),2022, 36(7):155-161. ZHU ML, ZHAO LL, HE SJ. Research and realization on cattle face recognition system model based on CNN combined with SVM and ResNet [J]. Journal of Chongqing University of Technology(Natural Science), 2022, 36(7):155-161. [32] JWADE SA, GUZZOMI A, MIAN A. On farm automatic sheep breed classification using deep learning[J]. Computers and Electronics in Agriculture, 2019, 167:105055. [33] HITELMAN A, EDAN Y, GODO A, et al. Biometric identification of sheep via a machine-vision system [J]. Computers and Electronics in Agriculture, 2022, 194:106713. [34] BILLAH M, WANG X, YU J, et al. Real-time goat face recognition using convolutional neural network[J]. Computers and Electronics in Agriculture, 2022, 194:106730. [35] GEFFEN O, YITZHAKY Y, BARCHILON N, et al. A machine vision system to detect and count laying hens in battery cages[J]. Animal (Cambridge, England), 2020, 14(12):2628-2634. [36] 赵春江, 梁雪文, 于合龙, 等. 基于改进YOLO v7-tiny 的笼养鸡/ 蛋自动识别与计数方法研究[J]. 农业机械学报, 2023, 54(7):300-312. ZHAO CJ, LIANG XW, YU HL, et al. Automatic identification and counting method of caged hens and eggs based on improved YOLO v7[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(7):300-312. [37] 金耀, 何秀文, 万世主, 等. 基于YOLO v3 的生猪个体识别方法[J]. 中国农机化学报, 2021, 42(2):178-183. JIN Y, HE XW, WAN SZ, et al. Individual pig identification method based on YOLO v3[J]. Journal of Chinese Agricultural Mechanization, 2021, 42(2):178-183. [38] 宁远霖, 杨颖, 李振波, 等. 基于改进YOLOv5 的复杂跨域场景下的猪个体识别与计数[J]. 农业工程学报, 2022, 38(17):168-175. NING YL, YANG Y, LI ZB, et al. Detecting and counting pig number using improved YOLO v5 in complex scenes [J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(17):168-175. [39] 吴潇, 杨颖, 刘刚, 等. 基于迁移学习和改进ResNet34 的猪个体识别方法[J]. 中国农机化学报, 2023, 44(9):214-221,237. WU X, YANG Y, LIU G, et al. Pig individual recognition method based on transfer learning and improved ResNet34 for real environment [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(9):214-221,237. [40] 赵凯旋, 何东健. 基于卷积神经网络的奶牛个体身份识别方法[J]. 农业工程学报, 2015(5):181-187. ZHAO KX, HE DJ. Recognition of individual dairy cattle based on convolutional neural networks[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015(5):181-187. [41] WANG D, TANG J, ZHU W, et al. Dairy goat detection based on faster R-CNN from surveillance video[J]. Computers and Electronics in Agriculture, 2018, 154:443-449. [42] FANG C, HUANG J, CUAN K, et al. Comparative study on poultry target tracking algorithms based on a deep regression network[J]. Biosystems Engineering, 2020, 190:176-183. [43] QIAO Y, SU D, KONG H, et al. BiLSTM-based individual cattle identification for automated precision livestock farming [C]//2020 IEEE 16th International Conference on Automation Science and Engineering (CASE). Piscataway, New Jersey:IEEE, 2020. [44] 钱坤, 李晨瑫, 陈美杉, 等. 基于改进Swin Transformer 的舰船目标实例分割算法[J]. 系统工程与电子技术, 2023, 45(10):3049-3057. QIA N K, LI CX, CHEN MS, et al. Ship target instance segmentation algorithm based on improved swin transformer[J]. Systems Engineering and Electronics, 2023, 45 (10):3049-3057. [45] ALEXEY D, LUCAS B, ALEXANDER K, et al. An image is worth 16X16 words: transformers for image recognition at scale[C]. ICLR, 2021:1-22. [46] 刘浩, 沈雷, 牟家乐, 等. 基于局部特征融合Transformer 的牛身识别算法[J]. 杭州电子科技大学学报(自然科学版), 2023, 43(1):49-55. LIU H, SHEN L, MOU JL, et al. Cow body recognition of transformer based onconvolutional spatial local feature fusion [J]. Journal of Hangzhou Dianzi University (Natural Sciences), 2023, 43(1):49-55. [47] 郑鹏, 沈雷, 刘浩, 等. 基于Vision Transformer 模型的牛脸识别算法[J]. 杭州电子科技大学学报(自然科学版), 2022, 42(6):40-46. SHEN P, SHEN L, LIU H, et al. Cow face recognition algorithm based on vision transformer model [J]. Journal of Hangzhou Dianzi University (Natural Sciences), 2023, 43(1):49-55. [48] LI XP, XIANG YY, LI SQ. Combining convolutional and vision transformer structures for sheep face recognition [J]. Computers and Electronics in Agriculture, 2023, 205:107651. [49] ZHANG XW, XUAN CZ, Ma YH, et al. A high-precision facial recognition method for small-tailed Han sheep based on an optimised vision transformer [J]. Animal : an International Journal of Animal Bioscience, 2023, 17(8):100886. [50] HU HQ, DAI BS, SHEN WZ, et al. Cow identification based on fusion of deep parts features [J]. Biosystems Engineering,2020, 192:245-256. [51] ANDREW W, GREATWOOD C, BURGHARDT T. Aerial animal biometrics: individual Friesian cattle recovery and visual identification via an autonomous UAV with onboard deep inference[C]//In: IEEE, Macau, China, 2019:237-243. [52] LI Z, LEI X, LIU S. A lightweight deep learning model for cattle face recognition [J]. Computers and Electronics in Agriculture, 2022, 195:106848. [53] 司永胜, 肖坚星, 刘刚, 等. 基于MSRCP 与改进YOLO v4 的躺卧奶牛个体识别方法[J]. 农业机械学报, 2023, 54 (1):243-250,262. SI YS, XIAO JX, LIU G, et al. Individual identification method of lying cows based on MSRCP and improved YOLO v4 model [J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(1):243-250,262. [54] WANG Z, LIU T. Two-stage method based on triplet margin loss for pig face recognition[J]. Computers and Electronics in Agriculture, 2022, 194:106737. [55] BONNEAU M, VAYSSADE J, TROUPE W, et al. Outdoor animal tracking combining neural network and time-lapse cameras[J]. Computers and Electronics in Agriculture, 2020, 168:105150. [56] SU Q, TANG J, ZHAI J, et al. Automatic tracking of the dairy goat in the surveillance video[J]. Computers and Electronics in Agriculture, 2021, 187:106254. [57] 易诗, 沈练, 周思尧, 等. 基于增强型Tiny-YOLOv3 模型的野鸡识别方法[J]. 农业工程学报, 2020, 36(13):141-147. YI S, SHEN L, ZHOU SY, et al. Recognition method of pheasant using enhanced tiny-YOLOv3 model[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(13):141-147. [58] 温志强, 冯向萍, 徐静. 基于Mask R-CNN 的马匹面部别征识别及分割方法[J]. 计算机技术与发展, 2021, 31(6):209-215. WEN ZQ, FENG XP, XU J. Recognition and segmentation of horse facial features based on mask R-CNN[J]. Computer Technology and Development, 2021, 31(6):209-215.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed