Automated Cow Body Condition Scoring Using Multiple 3D Cameras and Convolutional Neural Networks

被引:2
作者
Summerfield, Gary I. [1 ]
De Freitas, Allan [1 ]
van Marle-Koster, Este [2 ]
Myburgh, Herman C. [1 ]
机构
[1] Univ Pretoria, Dept Elect Elect & Comp Engn, ZA-0028 Pretoria, South Africa
[2] Univ Pretoria, Dept Anim Sci, ZA-0028 Pretoria, South Africa
关键词
automated cow body condition scoring; convolutional neural network; computer vision; ensemble modelling; sensor fusion; precision livestock; data augmentation; DAIRY-CATTLE; DEPTH;
D O I
10.3390/s23229051
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Body condition scoring is an objective scoring method used to evaluate the health of a cow by determining the amount of subcutaneous fat in a cow. Automated body condition scoring is becoming vital to large commercial dairy farms as it helps farmers score their cows more often and more consistently compared to manual scoring. A common approach to automated body condition scoring is to utilise a CNN-based model trained with data from a depth camera. The approaches presented in this paper make use of three depth cameras placed at different positions near the rear of a cow to train three independent CNNs. Ensemble modelling is used to combine the estimations of the three individual CNN models. The paper aims to test the performance impact of using ensemble modelling with the data from three separate depth cameras. The paper also looks at which of these three cameras and combinations thereof provide a good balance between computational cost and performance. The results of this study show that utilising the data from three depth cameras to train three separate models merged through ensemble modelling yields significantly improved automated body condition scoring accuracy compared to a single-depth camera and CNN model approach. This paper also explored the real-world performance of these models on embedded platforms by comparing the computational cost to the performance of the various models.
引用
收藏
页数:24
相关论文
共 36 条
  • [1] Real Time Apnoea Monitoring of Children Using the Microsoft Kinect Sensor: A Pilot Study
    Al-Naji, Ali
    Gibson, Kim
    Lee, Sang-Heon
    Chahl, Javaan
    [J]. SENSORS, 2017, 17 (02)
  • [2] Potential for estimation of body condition scores in dairy cattle from digital images
    Bewley, J. M.
    Peacock, A. M.
    Lewis, O.
    Boyce, R. E.
    Roberts, D. J.
    Coffey, M. P.
    Kenyon, S. J.
    Schutz, M. M.
    [J]. JOURNAL OF DAIRY SCIENCE, 2008, 91 (09) : 3439 - 3453
  • [3] A Study of Image Upsampling and Downsampling Filters
    Dumitrescu, Dragos
    Boiangiu, Costin-Anton
    [J]. COMPUTERS, 2019, 8 (02)
  • [4] A BODY CONDITION SCORING CHART FOR HOLSTEIN DAIRY-COWS
    EDMONSON, AJ
    LEAN, IJ
    WEAVER, LD
    FARVER, T
    WEBSTER, G
    [J]. JOURNAL OF DAIRY SCIENCE, 1989, 72 (01) : 68 - 78
  • [5] PRINCIPAL DESCRIPTORS OF BODY CONDITION SCORE IN HOLSTEIN COWS
    FERGUSON, JD
    GALLIGAN, DT
    THOMSEN, N
    [J]. JOURNAL OF DAIRY SCIENCE, 1994, 77 (09) : 2695 - 2703
  • [6] Cow Body Shape and Automation of Condition Scoring
    Halachmi, I.
    Polak, P.
    Roberts, D. J.
    Klopcic, M.
    [J]. JOURNAL OF DAIRY SCIENCE, 2008, 91 (11) : 4444 - 4451
  • [7] A new image classification method using CNN transfer learning and web data augmentation
    Han, Dongmei
    Liu, Qigang
    Fan, Weiguo
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2018, 95 : 43 - 56
  • [8] Automated monitoring of dairy cow body condition, mobility and weight using a single 3D video capture device
    Hansen, M. F.
    Smith, M. L.
    Smith, L. N.
    Jabbar, K. Abdul
    Forbes, D.
    [J]. COMPUTERS IN INDUSTRY, 2018, 98 : 14 - 22
  • [9] Handling Imbalanced Datasets for Robust Deep Neural Network-Based Fault Detection in Manufacturing Systems
    Kafunah, Jefkine
    Ali, Muhammad Intizar
    Breslin, John G.
    [J]. APPLIED SCIENCES-BASEL, 2021, 11 (21):
  • [10] Klopcic M., 2011, Body condition scoring of dairy cows