Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 May 6;21(9):3218.
doi: 10.3390/s21093218.

Pig Weight and Body Size Estimation Using a Multiple Output Regression Convolutional Neural Network: A Fast and Fully Automatic Method

Jianlong Zhang  1   2 , Yanrong Zhuang  1   2 , Hengyi Ji  1   2 , Guanghui Teng  1   2   3
Affiliations

Pig Weight and Body Size Estimation Using a Multiple Output Regression Convolutional Neural Network: A Fast and Fully Automatic Method

Jianlong Zhang et al. Sensors (Basel). .

Abstract

Pig weight and body size are important indicators for producers. Due to the increasing scale of pig farms, it is increasingly difficult for farmers to quickly and automatically obtain pig weight and body size. Due to this problem, we focused on a multiple output regression convolutional neural network (CNN) to estimate pig weight and body size. DenseNet201, ResNet152 V2, Xception and MobileNet V2 were modified into multiple output regression CNNs and trained on modeling data. By comparing the estimated performance of each model on test data, modified Xception was selected as the optimal estimation model. Based on pig height, body shape, and contour, the mean absolute error (MAE) of the model to estimate body weight (BW), shoulder width (SW), shoulder height (SH), hip width (HW), hip width (HH), and body length (BL) were 1.16 kg, 0.33 cm, 1.23 cm, 0.38 cm, 0.66 cm, and 0.75 cm, respectively. The coefficient of determination (R2) value between the estimated and measured results was in the range of 0.9879-0.9973. Combined with the LabVIEW software development platform, this method can estimate pig weight and body size accurately, quickly, and automatically. This work contributes to the automatic management of pig farms.

Keywords: body size; convolutional neural network; deep learning; estimation; pig weight.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Pig weight and back image acquisition system: (a) three-dimensional diagram of system; (b) distribution of weighing sensors; (c) photo of system.
Figure 2
Figure 2
Pig weight and back image acquisition system: (a) data acquisition scheme; (b) software interface.
Figure 3
Figure 3
Specific locations of body size parameters and measurement of body size: (a) specific locations of body size parameters; (b) body size measurement using a measuring stick.
Figure 4
Figure 4
Samples of pig images in various postures.
Figure 5
Figure 5
Image preprocessing process.
Figure 6
Figure 6
Pig weight and body size estimation model and estimate process. DL: dense layer; BW: body weight; SW: shoulder width; SH: shoulder height; HW: hip width; HH: hip height; BL: body length.
Figure 7
Figure 7
Loss change on validation set of each model.
Figure 8
Figure 8
Comparison between measured and estimated BW (a), SW (b), SH (c), HW (d), HH € and BL (f).
Figure 9
Figure 9
Original image (a) and feature maps (b) output from the first convolutional layer of modified Xception.
Figure 10
Figure 10
LabVIEW panel of the pig weight and body size estimation system.
See this image and copyright information in PMC

References

    1. Li D., Li Z. System Analysis and Development Prospect of Unmanned Farming. Trans. Chin. Soc. Agric. Mach. 2020;51:1–12. doi: 10.6041/j.issn.1000-1298.2020.07.001. - DOI
    1. Lee S., Ahn H., Seo J., Chung Y., Park D., Pan S. Practical Monitoring of Undergrown Pigs for IoT-Based Large-Scale Smart Farm. IEEE Access. 2019;7:173796–173810. doi: 10.1109/ACCESS.2019.2955761. - DOI
    1. Amraei S., Abdanan Mehdizadeh S., Salari S. Broiler weight estimation based on machine vision and artificial neural network. Brit. Poult. Sci. 2017;58:200–205. doi: 10.1080/00071668.2016.1259530. - DOI - PubMed
    1. Wang Y., Yang W., Walker L.T., Rababah T.M. Enhancing the accuracy of area extraction in machine vision-based pig weighing through edge detection. Int. J. Agric. Biol. Eng. 2008;1:37–42. doi: 10.3965/j.issn.1934-6344.2008.01.037-042. - DOI
    1. Matthews S.G., Miller A.L., Clapp J., Plötz T., Kyriazakis I. Early detection of health and welfare compromises through automated detection of behavioural changes in pigs. Vet. J. 2016;217:43–51. doi: 10.1016/j.tvjl.2016.09.005. - DOI - PMC - PubMed

LinkOut - more resources