[1]张瑞红,赵凯旋,姬江涛,等.基于机器学习的奶牛颈环ID自动定位与识别方法[J].南京农业大学学报,2021,44(3):586-595.[doi:10.7685/jnau.202010005]
 ZHANG Ruihong,ZHAO Kaixuan,JI Jiangtao,et al.Automatic location and recognition of cow’s collar ID based on machine learning[J].Journal of Nanjing Agricultural University,2021,44(3):586-595.[doi:10.7685/jnau.202010005]
点击复制

基于机器学习的奶牛颈环ID自动定位与识别方法()
分享到:

《南京农业大学学报》[ISSN:1000-2030/CN:32-1148/S]

卷:
44卷
期数:
2021年3期
页码:
586-595
栏目:
食品与工程
出版日期:
2021-05-10

文章信息/Info

Title:
Automatic location and recognition of cow’s collar ID based on machine learning
作者:
张瑞红 赵凯旋 姬江涛 朱雪峰
河南科技大学农业装备工程学院, 河南 洛阳 471003
Author(s):
ZHANG Ruihong ZHAO Kaixuan JI Jiangtao ZHU Xuefeng
College of Agricultural Engineering, Henan University of Science and Technology, Luoyang 471003, China
关键词:
标牌定位级联检测器多角度检测字符分割字符识别卷积神经网络
Keywords:
label positioningcascade detectormulti-angle detectioncharacter segmentationcharacter recognitionconvolutional neural network
分类号:
TP391.4
DOI:
10.7685/jnau.202010005
摘要:
[目的] 奶牛个体信息的实时感知和行为分析是现代化奶牛精细养殖的必然要求,奶牛个体身份的有效识别是上述目标的前提和基础。基于奶牛生物特征(牛脸、体斑等)图像的无接触识别方法易受外界干扰、算法复杂度高,可识别的样本规模受到限制。因此,本文提出1种基于机器学习的奶牛颈环ID自动定位与识别方法。[方法] 针对奶牛运动造成的颈环ID偏转问题,采用基于梯度方向直方图(HOG)特征的级联检测器结合多角度检测方法实现奶牛标牌的定位;对标牌图像进行图像增强和二值化分割等处理,得到单个字符图像;设计卷积神经网络的结构和参数,训练字符识别模型,从而完成标牌字符的识别。试验数据包括80头奶牛的1 414幅侧视图像,随机选取其中58头奶牛的图像作为训练集,其余22头奶牛的图像作为测试集。[结果] 标牌定位的准确率为96.98%,召回率为80.23%,字符识别模型的准确率为93.35%,连续图像序列中奶牛个体的识别率为95.45%。[结论] 识别模型对光线变化、污渍沾染、旋转角度等具有良好的鲁棒性,具有代替传统动物个体身份识别方法的潜力。
Abstract:
[Objectives] Real-time perception and behavior analysis of individual cow information are the inevitable requirements of modern dairy cow fine breeding. Effective identification of individual cow identity is the premise and basis of the above goals. The contact-free recognition method based on the image of the cow’s biological characteristics(faces,body spots,etc.) is susceptible to external interference and the algorithm complexity is high,and the identifiable sample size is limited. Therefore,this paper proposes a method of automatic location and recognition of cow’s collar ID based on deep learning. [Methods] Aiming at the ID deflection problem of neck ring caused by cow movement,the cascade detector based on histogram of oriented gradient(HOG) feature combined with multi-angle detection method was adopted to realize the localization of cow signs. A single character image was obtained by a series of processing such as image enhancement and binary segmentation. The structure and parameters of the convolutional neural network were designed to train the character recognition model so as to complete the recognition of signage characters. The experimental data included 1 414 side-looking images of 80 cows,of which 58 were randomly selected as the training set and the images of the remaining 22 cows as the test set. [Results] The accuracy of placards was 96.98%,the recall rate was 80.23%,the accuracy of the character recognition model was 93.35%,and the recognition rate of individual cows in continuous image sequences was 95.45%. [Conclusions] The recognition model has good robustness to light change,stain contamination,rotation angle and so on,which has the potential to replace the traditional animal individual identification method.

参考文献/References:

[1] 王海彬,王洪斌,肖建华. 奶牛精细养殖信息技术进展[J]. 中国奶牛,2009(3):15-17. Wang H B,Wang H B,Xiao J H. Advances in information technology of dairy cow fine breeding[J]. China Dairy Cattle,2009(3):15-17(in Chinese).
[2] 何东健,刘冬,赵凯旋. 精准畜牧业中动物信息智能感知与行为检测研究进展[J]. 农业机械学报,2016,47(5):231-244. He D J,Liu D,Zhao K X. Review of perceiving animal information and behavior in precision livestock farming[J]. Transactions of the Chinese Society for Agricultural Machinery,2016,47(5):231-244(in Chinese with English abstract).
[3] Shen W Z,Cheng F,Zhang Y,et al. Automatic recognition of ingestive-related behaviors of dairy cows based on triaxial acceleration[J]. Information Processing in Agriculture,2020,7(3):427-443.
[4] 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.
[5] Yajuvendra S,Lathwal S S,Rajput N,et al. Effective and accurate discrimination of individual dairy cattle through acoustic sensing[J]. Applied Animal Behaviour Science,2013,146(1/2/3/4):11-18.
[6] Cappai M G,Rubiu N G,Nieddu G,et al. Analysis of fieldwork activities during milk production recording in dairy ewes by means of individual ear tag(ET) alone or plus RFID based electronic identification(EID)[J]. Computers and Electronics in Agriculture,2018,144:324-328.
[7] 于啸. 奶牛精量饲喂控制系统的研究[D]. 长春:吉林大学,2016. Yu X. Study on precise feeding control system for dairy cattle[D]. Changchun:Jilin University,2016(in Chinese with English abstract).
[8] 许译丹. 基于射频识别与传感技术的种鹅个体产蛋识别及定位方法研究[D]. 大庆:黑龙江八一农垦大学,2019. Xu Y D. Research on identification and location method of egg laying of individual goose based on RFID and sensing technology[D]. Daqing:Heilongjiang Bayi Agricultural University,2019(in Chinese with English abstract).
[9] Voulodimos A S,Patrikakis C Z,Sideridis A B,et al. A complete farm management system based on animal identification using RFID technology[J]. Computers and Electronics in Agriculture,2010,70(2):380-388.
[10] Chapinal N,Tucker C B. Validation of an automated method to count steps while cows stand on a weighing platform and its application as a measure to detect lameness[J]. Journal of Dairy Science,2012,95(11):6523-6528.
[11] Shen W Z,Hu H Q,Dai B S,et al. Individual identification of dairy cows based on convolutional neural networks[J]. Multimedia Tools and Applications,2020,79:14711-14724.
[12] 何东健,刘建敏,熊虹婷,等. 基于改进YOLO v3模型的挤奶奶牛个体识别方法[J]. 农业机械学报,2020,51(4):250-260. He D J,Liu J M,Xiong H T,et al. Individual identification of dairy cows based on improved YOLO v3[J]. Transactions of the Chinese Society for Agricultural Machinery,2020,51(4):250-260(in Chinese with English abstract).
[13] 丁静,沈明霞,刘龙申,等. 基于机器视觉的断奶仔猪腹泻自动识别方法[J]. 南京农业大学学报,2020,43(5):969-978. DOI:10.7685/jnau.201908003. Ding J,Shen M X,Liu L S,et al. Automatic recognition of diarrhea in weaned piglets based on machine vision[J]. Journal of Nanjing Agricultural University,2020,43(5):969-978(in Chinese with English abstract).
[14] Xia M,Cai C. Cattle face recognition using sparse representation classifier[J]. ICIC Express Letters,Part B:Applications,2012,3:1499-1505.
[15] Bengio Y. Learning deep architectures for AI[J]. Foundations & Trends? in Machine Learning,2009,2(1):1-127.
[16] Kim H T,Choi H L,Lee D W,et al. Recognition of individual Holstein cattle by imaging body patterns[J]. Asian Australasian Journal of Animal Sciences,2005,18(8):1194-1198.
[17] 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 with English abstract).
[18] Bergamini L,Porrello A,Dondona A C,et al. Multi-views embedding for cattle re-identification[C]//2018 14th International Conference on Signal-Image Technology & Internet-Based Systems(SITIS),November 26-29,2018,Las Palmas de Gran Canaria,Spain. IEEE,2018:184-191.
[19] 崔华,张骁,郭璐,等. 多特征多阈值级联AdaBoost行人检测器[J]. 交通运输工程学报,2015,15(2):109-117. Cui H,Zhang X,Guo L,et al. Cascade AdaBoost pedestrian detector with multi-features and multi-thresholds[J]. Journal of Traffic and Transportation Engineering,2015,15(2):109-117(in Chinese with English abstract).
[20] 刘春生. 复杂大背景下交通标志快速鲁棒的检测和识别研究[D]. 济南:山东大学,2016. Liu C S. Research of fast and robust traffic sign detection and recognition in complicated environment[D]. Jinan:Shandong University,2016(in Chinese with English abstract).
[21] Sun Y,Wang X G,Tang X O. Deep convolutional network cascade for facial point detection[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition,June 23-28,2013,Portland,OR,USA. IEEE,2013:3476-3483.
[22] 陈学保. 车牌字符识别算法的研究[D]. 重庆:重庆大学,2013. Chen X B. Research on the algorithm of license plate character recognition[D]. Chongqing:Chongqing University,2013(in Chinese with English abstract).
[23] 张弛,沈明霞,刘龙申,等. 基于机器视觉的新生仔猪目标识别方法研究与实现[J]. 南京农业大学学报,2017,40(1):169-175. DOI:10.7685/jnau.201602017. Zhang C,Shen M X,Liu L S,et al. Newborn piglets recognition method based on machine vision[J]. Journal of Nanjing Agricultural University,2017,40(1):169-175(in Chinese with English abstract).
[24] 周飞燕,金林鹏,董军. 卷积神经网络研究综述[J]. 计算机学报,2017,40(6):1229-1251. Zhou F Y,Jin L P,Dong J. Review of convolutional neural network[J]. Chinese Journal of Computers,2017,40(6):1229-1251(in Chinese with English abstract).
[25] 易超人,邓燕妮. 多通道卷积神经网络图像识别方法[J]. 河南科技大学学报(自然科学版),2017,38(3):41-44. Yi C R,Deng Y N. Image recognition method of multi-channel convolutional neural network[J]. Journal of Henan University of Science & Technology(Natural Science),2017,38(3):41-44(in Chinese with English abstract).
[26] LeCun Y,Bottou L,Bengio Y,et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE,1998,86(11):2278-2324.

备注/Memo

备注/Memo:
收稿日期:2020-10-06。
基金项目:国家自然科学基金项目(32002227);河南省科技攻关项目(192102110089)
作者简介:张瑞红,硕士研究生。
通信作者:姬江涛,教授,博士,主要从事智能农业装备和农业信息化技术研究,E-mail:jjt0907@163.com。
更新日期/Last Update: 1900-01-01