Abstract
This study addresses the need for a more efficient and accurate live pig weight monitoring system in the Indian meat production industry. Conventional methods for measuring pig weights are labor-intensive, prompting the exploration of AI and image processing-based solutions. The research introduces a novel regression-based Convolutional Neural Network (CNN) model trained on a dataset of 1217 images of live pigs, each accompanied by their corresponding weight values. The model demonstrates promising results on the test dataset, with a coefficient of determination (R2) of 0.801, mean absolute error (MAE) of 0.054, and root mean square error (RMSE) of 0.040. Data collection involved a meticulously designed imaging platform to ensure dataset robustness. The proposed model's efficiency is highlighted by its convergence behavior during training and testing, showcasing its ability to accurately predict live pig weights and its potential to revolutionize the Indian meat production industry.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Stygar AH, Kristensen AR (2016) Monitoring growth in finishers by weighing selected groups of pigs—a dynamic approach. J Anim Sci 94(3):1255–1266
Al Ard Khanji MS, Llorente C, Falceto MV, Bonastre C, Mitjana O, Tejedor MT, Plaizier J (2018) Using body measurements to estimate body weight in gilts. J Anim Sci 98(2):362–367
Wang Z, Hou Y, Xu K, Li L (2021) Design and implementation of pig intelligent classification monitoring system based on convolution neural network (CNN). INMATEH-Agric Eng 63(1)
Wang Y, Yang W, Winter P, Walker L (2008) Walk-through weighing of pigs using machine vision and an artificial neural network. Biosyst Eng 100(1):117–125
Wongsriworaphon A, Arnonkijpanich B, Pathumnakul S (2015) An approach based on digital image analysis to estimate the LWs of pigs in farm environments. Comput Electron Agric 115:26–33
Shi C, Teng G, Li Z (2016) An approach of pig weight estimation using a binocular stereo system based on LabVIEW. Comput Electron Agric 129:37–43
Buayai P, Piewthongngam K, Leung CK, Saikaew KR (2019) Semi-automatic pig weight estimation using digital image analysis. Appl Eng Agric 35(4):521–534
Jun K, Kim SJ, Ji HW (2018) Estimating pig weights from images without constraint on posture and illumination. Comput Electron Agric 153:169–176
Pezzuolo A, Milani V, Zhu D, Guo H, Guercini S, Marinello F (2018) On-barn pig weight estimation based on body measurements by structure-from-motion (SfM). Sensors 18(11):3603
Fernandes AFA, Dorea JRR, Valente BD, Fitzgerald R, Herring W, Rosa GJM (2020) Comparison of data analytics strategies in computer vision systems to predict pig body composition traits from 3D images. J Anim Sci 98:1–9
Yu H, Lee K, Morota G (2021) Forecasting dynamic body weight of nonrestrained pigs from images using an RGB-D sensor camera. Transl Anim Sci 5:1–9
Oliveira DAB, Pereira LGR, Bresolin T, Ferreira REP, Dorea JRR (2021) A review of deep learning algorithms for computer vision systems in livestock. Livest Sci 253:104700
Jensen DB, Dominiak KN, Pedersen LJ (2018) Automatic estimation of slaughter pig live weight using convolutional neural networks. In: II International conference on agro bigdata and decision support systems in agriculture
Cang Y, He H, Qiao Y (2019) An intelligent pig weights estimate method based on deep learning in sow stall environments. IEEE Access 7:164867–164875
Gjergji M, de Moraes Weber V, Silva LOC, da Costa Gomes R, De Araújo TLAC, Pistori H, Alvarez M (July, 2020) Deep learning techniques for beef cattle body weight prediction. In: 2020 international joint conference on neural networks (IJCNN). IEEE pp 1–8
He H, Qiao Y, Li X, Chen C, Zhang X (2021) Automatic weight measurement of pigs based on 3D images and regression network. Comput Electron Agric 187:106299
He H, Qiao Y, Li X, Chen C, Zhang X (2021) Optimization on multi-object tracking and segmentation in pigs’ weight measurement. Comput Electron Agric 186:106190
Zhang J, Zhuang Y, Ji H, Teng G (2021) Pig weight and body size estimation using a multiple output regression convolutional neural network: a fast and fully automatic method. Sensors 21(9):3218
Bhoj S, Tarafdar A, Chauhan A, Singh M, Gaur GK (2022) Image processing strategies for pig liveweight measurement: updates and challenges. Comput Electron Agric 193:106693
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Deb, C.K. et al. (2024). Convolution Neural Network (CNN)-Based Live Pig Weight Estimation in Controlled Imaging Platform. In: Sharma, H., Shrivastava, V., Tripathi, A.K., Wang, L. (eds) Communication and Intelligent Systems. ICCIS 2023. Lecture Notes in Networks and Systems, vol 968. Springer, Singapore. https://doi.org/10.1007/978-981-97-2079-8_8
Download citation
DOI: https://doi.org/10.1007/978-981-97-2079-8_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2078-1
Online ISBN: 978-981-97-2079-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)