CLASSIFYING PIG POSES FOR SMART PIGSTIES USING DEEP LEARNING
- Authors
- Jeon, Chanhui; Kim, Haram; Kim, Dongsoo
- Issue Date
- Feb-2024
- Publisher
- ICIC International
- Keywords
- Computer vision; Convolution blok attention module; Convolutional neural network; Objet detetion; Smart pigsty
- Citation
- ICIC Express Letters, Part B: Applications, v.15, no.2, pp 187 - 193
- Pages
- 7
- Journal Title
- ICIC Express Letters, Part B: Applications
- Volume
- 15
- Number
- 2
- Start Page
- 187
- End Page
- 193
- URI
- https://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/49228
- DOI
- 10.24507/icicelb.15.02.187
- ISSN
- 2185-2766
- Abstract
- Pig postures play a crucial role in understanding the behavior and well-being of pigs in a pigsty environment. In this study, we propose a deep learning-based model for pig posture classification to alleviate the time-consuming and costly task of manual inspection. Our model leverages the power of deep learning techniques such as EfficientNet with convolution block attention module to automatically classify pig postures based on image data captured in the pigsty. Through rigorous experimentation, we have demonstrated the effectiveness of our model in accurately classifying various pig postures, achieving an accuracy of 94.73% and an F1 score of 0.91. Our proposed model has the potential to significantly streamline the process of monitoring pig postures in real time, allowing for more efficient and cost-effective management of pig farming operations. This study contributes to the field of animal behavior research by providing an innovative approach to understanding pig postures in a pigsty environment. © 2024 ICIC International.
- Files in This Item
-
Go to Link
- Appears in
Collections - ETC > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.