从人工到智能:牛个体识别技术研究进展

doi:10.16431/j.cnki.1671-7236.2023.05.013

摘要/Abstract

摘要： 牛个体识别技术是实现牛的智能测重、体况评分、体型鉴定、行为监测等自动化技术的先决条件,各种用于牛个体识别的设备和方法在不同的时间段被提出。作者首先对不同牛个体识别方法进行分类阐述,介绍了传统识别方法、生物特征识别方法和深度学习方法在牛个体识别中的研究进展,特别是当前深度学习方法在实际应用中的难点,然后详细分析了不同识别方法的优缺点。传统识别方法如耳切、耳纹、热烙等方法,依靠人工对牛进行识别,识别准确率和识别效率低,忽视了动物福利和标记持久性;无线射频识别技术将牛个体识别由人工识别转向了自动识别,提高了识别效率,但数据安全无法得到保障。随着图像识别技术的发展和深度学习方法的崛起,基于生物特征识别方法和深度学习方法的牛个体识别技术实现了非接触、安全高效的牛智能识别,但基于鼻纹印、视网膜血管和虹膜的生物特征识别方法因理想图像获取难度较大,实用性较差。深度学习方法通过深度神经网络学习图像特征,更适用于复杂条件下的图像应用,在真实的牛场养殖环境中具有广泛的应用前景和潜在价值。作者还对比了不同识别方法在各方面的差异,并在此基础上对牛个体识别技术的研究前景进行了展望。

关键词: 牛; 个体识别; 生物特征识别; 深度学习

Abstract: Individual identification technology was the primary requirement of automatic production techniques,including intelligence weighting,body condition scoring,body shape identification,and behavior monitoring.Individual cattle identification methods were categorized and elaborated in current review,that the research progress of different individual cattle identification methods including traditional,biometric,and deep learning methods were introduced,especially the difficulties of applying deep learning method in practice were discussed.Moreover,the advantages and disadvantages of different identification methods were analyzed.Traditional identification methods such as ear notching,ear tattooing,and hot branding identified cattle relies on manual labor,which had low identification accuracy and efficiency,and ignored animal welfare and mark persistence.Radio frequency identification techniques provided an automatic identifying protocol that elevated the efficiency but the data security could not be guaranteed.With the development of image recognition technology and deep learning methods,non-contact,safe and efficient cattle intelligent recognition had been realized with the technology based on biometric recognition and deep learning methods.However,the biometric identification method based on nose print,retinal blood vessels and iris had poor practicability,because the ideal image was difficult to obtain.Based on deep neural networks learning of image features,the deep learning method was more practical and promising in complex dairy farm circumstances.What’s more,different individual identification methods were compared,and the research on individual cattle identification technology was prospected in current review.

Key words: cattle; individual identification; biometric identification; deep learning

中图分类号:

S818.9

彭阳翔, 杨振标, 闫奎友, 王瀚, 呼德, 王尊, 刘宁, 赵连生. 从人工到智能:牛个体识别技术研究进展[J]. 中国畜牧兽医, 2023, 50(5): 1855-1866.

PENG Yangxiang, YANG Zhenbiao, YAN Kuiyou, WANG Han, HU De, WANG Zun, LIU Ning, ZHAO Liansheng. From Artificial to Intelligent:Research Progress of Individual Idendification Technology for Cattle[J]. China Animal Husbandry and Veterinary Medicine, 2023, 50(5): 1855-1866.

参考文献

[1] 孙雨坤,王玉洁,霍鹏举,等.奶牛个体识别方法及其应用研究进展[J].中国农业大学学报,2019,24(12):62-70. SUN Y K,WANG Y J,HUO P J,et al.Research progress on methods and application of dairy cow identification[J].Journal of China Agricultural University,2019,24(12):62-70.(in Chinese)
[2] BROWN-BRANDL T M,ADRION F,MASELVNE J,et al.A review of passive radio frequency identification systems for animal monitoring in livestock facilities[J].Applied Engineering in Agriculture,2019,35(4):579-591.
[3] AWAD A I.From classical methods to animal biometrics:A review on cattle identification and tracking[J].Computers and Electronics in Agriculture,2016,123:423-435.
[4] RUIZ-GARCIA L,LUNADEI L.The role of RFID in agriculture:Applications,limitations and challenges[J].Computers and Electronics in Agriculture,2011,79(1):42-50.
[5] ANDREW W,HANNUNA S,CAMPBELL N,et al.Automatic individual Holstein Friesian cattle identification via selective local coat pattern matching in RGB-D imagery[A].IEEE International Conference on Image Processing[C].2016.
[6] ARSLAN A C,AKAR M,ALAGOZ F.3D cow identification in cattle farms[A].2014 22nd Signal Processing and Communications Applications Conference (SIU)[C].2014.
[7] ANDREW W,GREATWOOD C,BURGHARDT T.Visual localisation and individual identification of Holstein Friesian cattle via deep learning[A].IEEE International Conference on Computer Vision Workshop[C].2017.
[8] THARWAT A,GABER T,HASSANIEN A E.Cattle identification based on muzzle images using gabor features and SVM classifier[A].International Conference on Advanced Machine Learning Technologies and Applications[C].2014.
[9] AHMED S,GABER T,THARWAT A,et al.Muzzle-based cattle identification using speed up Robust feature approach[A].International Conference on Intelligent Networking and Collaborative Systems (INCOS)[C].2015.
[10] KUSAKUNNIRAN W,WIRATSUDAKUL A,CHUACHAN U,et al.Automatic cattle identification based on fusion of texture features extracted from muzzle images[A].2018 IEEE International Conference on Industrial Technology (ICIT)[C].2018.
[11] 王锋,李琦.基于局部不变特征的牛只个体唇纹识别方法研究[J].黑龙江畜牧兽医,2022,65(2):48-52. WANG F,LI Q.Research on recognition method of individual cattle muzzle based on local invariant features[J].Heilongjiang Animal Science and Veterinary Medicine,2022,65(2):48-52.(in Chinese)
[12] 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.
[13] SUN S,YANG S,ZHAO L.Noncooperative bovine iris recognition via SIFT[J].Neurocomputing,2013,120(23):310-317.
[14] LU Y,HE X,WEN Y,et al.A new cow identification system based on iris analysis and recognition[J].International Journal of Biometrics,2014,6(1):18-32.
[15] 魏征.基于全局和局部特征相结合的不完美牛眼虹膜识别技术研究[D].南京:东南大学,2017. WEI Z.Research on imperfect bivine iris recognition based on combination of local features and global features[D].Nanjing:Southeast University,2017.(in Chinese)
[16] KUMAR S,TIWARI S,SINGH S K.Face recognition for cattle[A].2015 Third International Conference on Image Information Processing (ICIIP)[C].2015.
[17] KUMAR S,TIWARI S,SINGH S K.Face recognition of cattle:Can it be done?[J].Proceedings of the National Academy of Sciences,India Section A:Physical Sciences,2016,86(2):137-148.
[18] LI W,JI Z,WANG L,et al.Automatic individual identification of Holstein dairy cows using tailhead images[J].Computers and Electronics in Agriculture,2017,142(Part B):622-631.
[19] OKURA F,IKUMA S,MAKIHARA Y,et al.RGB-D video-based individual identification of dairy cows using gait and texture analyses[J].Computers and Electronics in Agriculture,2019,165(C):104944.
[20] ZHAO K,JIN X,JI J,et al.Individual identification of Holstein dairy cows based on detecting and matching feature points in body images[J].Biosystems Engineering,2019,181:128-139.
[21] WHITTIER J C,DOUBET J,HENRICKSON D,et al.Biological considerations pertaining to use of the retinal vascular pattern for permanent identification of livestock[A].Proceedings of ASAS Western Section Meeting,American Society of Animal Science[C].2003.
[22] PETERSEN W E.The Identification of the bovine by means of nose-prints1[J].Journal of Dairy Science,1922,5(3):249-258.
[23] DAUGMAN J G. High confidence visual recognition of persons by a test of statistical independence[J]. IEEE Transactions on Pattern Analysis&Machine Intelligence, 1993, 15(11):1148-1161.
[24] RANKIN D M,SCOTNEY B W,MORROW P J,et al.Iris recognition failure over time:The effects of texture[J].Pattern Recognition,2012,45(1):145-150.
[25] DAUGMAN J,DOWNING C.No change over time is shown in Rankin et al. "Iris recognition failure over time:The effects of texture"[J].Pattern Recognition,2013,46(2):609-610.
[26] RANKIN D M,SCOTNEY B W,MORROW P J,et al.Iris recognition-The need to recognize the iris as a dynamic biological system:Response to Daugman and Downing[J].Pattern Recognition,2013,46(2):611-612.
[27] HU H,DAI B,SHEN W,et al.Cow identification based on fusion of deep parts features[J].Biosystems Engineering,2020,192(C):245-256.
[28] GAO J,BURGHARDT T,ANDREW W,et al.Towards self-supervision for video identification of individual Holstein-Friesian cattle:The cows 2021 dataset[J].arXiv Preprint arXiv:2021,2105:01938.
[29] LI G,ERICKSON G E,XIONH Y.Individual beef cattle identification using muzzle images and deep learning techniques[J].Animals,2022,12(11):1453-1453.
[30] 邢永鑫,吴碧巧,吴松平,等.基于卷积神经网络和迁移学习的奶牛个体识别[J].激光与光电子学进展,2021,58(16):503-511. XING Y X,WU B Q,WU S P,et al.Individual cow recognition based on convolution neural network and transfer learning[J].Laser&Optoelectronics Progress,2021,58(16):503-511.(in Chinese)
[31] 宋肖肖.牛脸特征点检测的研究与实现[D].杨凌:西北农林科技大学,2017. SONG X X.Research and implemention of cattle face feature points detection[D].Yangling:Northwest A&F University,2017.(in Chinese)
[32] SHEN W,HU H,DAI B,et al.Individual identification of dairy cows based on convolutional neural networks[J].Multimedia Tools and Applications,2020,79(21):14711-14724.
[33] 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,2015,31(5):181-187. ZHAO K X,HE D J.Recognition of individual dairy cattle based on convolutional neural networks[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(5):181-187.(in Chinese)
[34] BELLO R W,TALIB A Z H,MOHAMED A S A B.Deep belief network approach for recognition of cow using cow nose image pattern[J].Walailak Journal of Science and Technology,2021,18(5):8984.
[35] LI S,FU L,SUN Y,et al.Individual dairy cow identification based on lightweight convolutional neural network.[J].PLoS One,2021,16(11):e0260510.
[36] WENG Z,MENG F,LIU S,et al.Cattle face recognition based on a two-branch convolutional neural network[J].Computers and Electronics in Agriculture,2022,196:106871.
[37] 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 M L,ZHAO L L,HE S J.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.(in Chinese)
[38] ANDREW W,GREATWOOD C,BURGHARDT T.Fusing animal biometrics with autonomous robotics:Drone-based search and individual ID of Friesian cattle[A].2020 IEEE Winter Applications of Computer Vision Workshops[C].2020.
[39] QIAO Y,SU D,KONG H,et al.Individual cattle identification using a deep learning based framework[J].IFAC-Papers Online,2019,52(30):318-323.
[40] ANDREW W,GAO J,MULLAN S,et al.Visual identification of individual Holstein-Friesian cattle via deep metric learning[J].Computers and Electronics in Agriculture,2021,185:106133.
[41] QIAO Y,CLARK C,LOMAX S,et al.Automated individual cattle identification using video data:A unified deep learning architecture approach[J].Frontiers in Animal Science,2021,2:759147.
[42] 李昊玥,陈桂芬,裴傲.基于改进Mask R-CNN的奶牛个体识别方法研究[J].华南农业大学学报,2020,41(6):161-168. LI H Y,CHEN G F,PEI A.Research on individual recognition of dairy cows based on improved Mask R-CNN[J].Journal of South China Agricultural University,2020,41(6):161-168.(in Chinese)
[43] 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 S Q,LIU Y Q H,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.(in Chinese)
[44] HOU H,SHI W,GUO J,et al.Cow rump identification based on lightweight convolutional neural networks[J].Information,2021,12(9):361.
[45] CHEN S,WANG S,ZUO X,et al.Angus cattle recognition using deep learning[A].2020 25th International Conference on Pattern Recognition[C].2021.
[46] DULAL R,ZHENG L,KABIR M A,et al.Automatic cattle identification using YOLO v5 and mosaic augmentation:A comparative analysis[J].arXiv Preprint arXiv,2022,2210:11939.
[47] CHEN X,YANG T,MAI K,et al.Holstein cattle face re-identification unifying global and part feature deep network with attention mechanism[J].Animals,2022,12(8):1047.
[48] DAC H H,GONZALEZ V C,LIPOVETZKY N,et al.Livestock Identification using deep learning for traceability[J].Sensors,2022,22(21):8256.
[49] XIAO J,LIU G,WANG K,et al.Cow identification in free-stall barns based on an improved Mask R-CNN and an SVM[J].Computers and Electronics in Agriculture,2022,194:106738.
[50] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[51] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].2014.
[52] GIRSHICK R.Fast R-CNN[A].Proceedings of the IEEE International Conference on Computer Vision[C].2015.
[53] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-time object detection with region proposal networks[A].Conference and Workshop on Neural Information Processing Systems[C].2016.
[54] HE K,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[A].Proceedings of the IEEE International Conference on Computer Vision[C].2017.
[55] 秦立峰,张晓茜,董明星,等.基于多特征融合相关滤波的运动奶牛目标提取[J].农业机械学报,2021,52(11):244-252. QING L F,ZHANG X Q,DONG M X,et al.Target extraction of moving cows based on multi-feature fusion correlation filtering[J].Transactions of the Chinese Society of Agricultural Machinery,2021,52(11):244-252.(in Chinese)