计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (4): 194-201.doi: 10.11896/jsjkx.240100144

• 计算机图形学&多媒体 • 上一篇    下一篇

基于YOLO-Unet组合网络的牛只个体识别方法研究

周意, 毛宽民   

  1. 华中科技大学机械科学与工程学院 武汉 430074
  • 收稿日期:2024-01-17 修回日期:2024-05-20 出版日期:2025-04-15 发布日期:2025-04-14
  • 通讯作者: 毛宽民(maokm@hust.edu.cn)
  • 作者简介:(zhou_yi1224@hust.edu.cn)
  • 基金资助:
    宁夏回族自治区重点研发计划(2020BBF02016,2021BFH02001)

Research on Individual Identification of Cattle Based on YOLO-Unet Combined Network

ZHOU Yi, MAO Kuanmin   

  1. School of Mechanical Science & Engineering,Huazhong University of Science and Technology,Wuhan 430074,China
  • Received:2024-01-17 Revised:2024-05-20 Online:2025-04-15 Published:2025-04-14
  • About author:ZHOU Yi,born in 2000,postgraduate.His main research interests include computer vision and deep learning.
    MAO Kuanmin,born in 1964,professor,Ph.D supervisor.His main research interests include machine tool dynamics and agricultural mechanization.
  • Supported by:
    Key R&D Program of Ningxia Hui Autonomous Region(2022BBF02016,2021BFH02001).

PDF (PC)

101

摘要： 非接触式牛只个体识别方法在节约识别成本、简化识别流程和提升识别精度方面具有一定的优势,近年来在牛只个体识别领域有了充分的发展。但现有的研究中存在着识别准确率受环境和天气等外部因素影响过大、模型迁移训练困难等问题。针对上述问题,基于YOLO-Unet组合网络提出了包含3个模块的牛只个体识别模型。首先,根据YOLOv5模型构建图像提取模块,用以提取牛只面部图像;随后,采用Unet模型构建背景消去模块,用以去除牛只面部图像背景,以消除环境影响,进而提升模型泛化性能;最后,使用MobileNetV3构建个体分类模块,对经背景消去后的牛只面部图像进行分类。对背景消去模块进行了消融实验,实验结果表明,引入背景消去模块能极大地提升模型泛化性能。引入背景消去模块的模型在测试集上的识别准确率为90.48%,相较于未引入背景消去模块的模型提升了11.99%。

关键词: 牛只个体识别, 深度学习, 目标检测, 语义分割, 目标识别, 泛化能力

Abstract: Non-contact method for cattle individual identification has advantages in cost reduction of identification,simplification of identification process and accurate identification,which has been fully developed in cattle individual identification in recent years.There are some problems in existing research,such as recognition accuracy affected by external factors(environment,weather,etc.) too much and difficult transfer learning.In view of the above problems,a cattle individual identification model with 3 modules based on YOLO-Unet combined network is proposed.Firstly,the image extraction module is constructed by YOLOv5 model to extract cattle facial images.Then,the background removal module is constructed by Unet model to remove the background of cattle facial images for eliminating the environmental impact,so as to improve the model’s generalization ability.Finally,the individual classification module is constructed by MobileNetV3 model to classify the cattle facial images whose background removed.Ablation experiment is performed on the background elimination module.The experimental result shows that the background removal module can greatly improve the model’s generalization ability.The recognition accuracy of the model with background removal module is 90.48%,which is 11.99％ higher than that of the model without background removal module.

Key words: Cattle individual identification, Deep learning, Object detection, Semantic segmentation, Object recognition, Generalization Ability

中图分类号: 

  • TP183
[1]XU B B,WANG W S,GUO L F,et al.A Review and Future Prospects on Cattle Recognition Based on Non-contact Identification[J].Journal of Agricultural Science and Technology,2020,22(7):79-89.
[2]SONG Y F,WANG J,LI J L,et al.Review of individual identification methods for cattle in precision breeding mode[J].Heilongjiang Animal Science and Veterinary Medicine,2021,(22):48-53,148-149.
[3]DU Z W,ZHOU H,LI C Y,et al.Small Object Detection Based on Deep Convolution Neural Networks:A Review[J].Computer Science,2022,49(12):205-218.
[4]YU J Y,DING P C,WANG C.Overview:Application of Convolution Neural Network in Object Detection[J].Computer Science,2018,45(S2):17-26.
[5]HARRIS C G,STEPHENS M.A Combined Corner and Edge Detector[C]//Alvey Vision Conference.1988:1-6.
[6]DALAL N,TRIGGS B.Histograms of oriented gradients forhuman detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’05).IEEE,2005:886-893.
[7]OJALA T,PIETIKAINEN M,MAENPAA T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[8]HEARST M A,DUMAIS S T,OSUNA E,et al.Support vector machines[J].IEEE Intelligent Systems and Their Applications,1998,13(4):18-28.
[9]KUMAR S,TIWARI S,SINGH S K.Face recognition for cattle[C]//2015 Third International Conference on Image Information Processing(ICIIP).IEEE,2015:65-72.
[10]KUMAR S,SINGH S K,DUTTA T,et al.A fast cattle recognition system using smart devices[C]//Proceedings of the 24th ACM International Conference on Multimedia.2016:742-743.
[11]CHEN J J,LIU C X,GAO Y F,et al.Cow recognition algorithm based on improved bag of feature model[J].Journal of Computer Applications,2016,36(8):2346-2351.
[12]CAI C,LI J.Cattle face recognition using local binary pattern descriptor[C]//2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.IEEE,2013:1-4.
[13]YAO L Y,XIONG H,ZHONG Y J,et al.Comparision of cow face detection algorithms based on deep network model[J].Journal of Jiangsu University(Natural Science Edition),2019,40(2):197-202.
[14]CHEN X L,YANG T L,MAI K Z,et al.Holstein cattle face re-identification unifying global and part feature deep network with attention mechanism[J].Animals,2022,12(8):1047.
[15]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.
[16]LIU S F,CHANG R,LI B,et al.Individual Identification of Cattle Based on RGB-D Images[J/OL].Transactions of the Chinese Society for Agricultural Machinery,1-10[2024-01-12]http://kns.cnki.net/kcms/detail/11.1964.s.20230914.1340.019.html.
[17]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:779-788.
[18]HUANG W K,TENG F,WANG Z D,et al.Image Segmentation Based on Deep Learing:A Survey[J].Computer Science,2024,51(2):107-116.
[19]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015:18th International Conference,Munich,Germany,October 5-9,2015,Proceedings,Part III 18.Springer International Publishing,2015:234-241.
[20]HOWARD A,SANDLER M,CHU G,et al.Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:1314-1324.
[21]YANG S N,ZHAO J M,YANG M,et al.Cattle face recognition method based on debiased term SoftMax and compact metric loss function [J].Heilongjiang Animal Science and Veterinary Medicine,2024(4):36-42.
[22]SCHROFF F,KALENICHENKO D,PHILBIN J.Facenet:A unified embedding for face recognition and clustering[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:815-823.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发