Sow Posture Analysis and Estrus Prediction Using Closed-Circuit Television Cameras
Sow estrus detection is one of the most critical tasks for improving the production performance of pig farms. However, accurately determining the onset of estrus is challenging because it is time consuming to check each sow and their performance, particularly during specific working hours. Moreover,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10411845/ |
| _version_ | 1797323933932847104 |
|---|---|
| author | Sookeun Song Taegeun Kang Kyungtae Lim Konmin Kim Hyunbean Yi |
| author_facet | Sookeun Song Taegeun Kang Kyungtae Lim Konmin Kim Hyunbean Yi |
| author_sort | Sookeun Song |
| collection | DOAJ |
| description | Sow estrus detection is one of the most critical tasks for improving the production performance of pig farms. However, accurately determining the onset of estrus is challenging because it is time consuming to check each sow and their performance, particularly during specific working hours. Moreover, estrus determination criteria are not standardized, as managers rely on their individual experiences. In this study, we proposed a method for predicting sow estrus using deep learning techniques. To detect sows and classify their postures, we used a lightweight deep-learning-based object detection model, You Only Look Once version 5 (YOLOv5). We trained one of the prediction models, Bidirectional Long Short-Term Memory (Bi-LSTM), which is a supervised learning model, using the time series data composed of a combination of each posture and holding time. By setting the ground truth as data from 24 h before the manager’s estrus determination, we achieved an estrus prediction accuracy of 86 %. This study demonstrates the potential of using closed-circuit television (CCTV) footage to predict sow estrus, and the proposed method can contribute to reducing the labor required for sow estrus checks. |
| first_indexed | 2024-03-08T05:35:12Z |
| format | Article |
| id | doaj.art-aa9d5a1e555a49948d117c5bd194158b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T05:35:12Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-aa9d5a1e555a49948d117c5bd194158b2024-02-06T00:01:10ZengIEEEIEEE Access2169-35362024-01-0112174601746610.1109/ACCESS.2024.335723710411845Sow Posture Analysis and Estrus Prediction Using Closed-Circuit Television CamerasSookeun Song0https://orcid.org/0000-0002-7114-2669Taegeun Kang1Kyungtae Lim2Konmin Kim3Hyunbean Yi4Department of Computer Engineering, Hanbat National University, Daejeon, South KoreaDepartment of Computer Engineering, Hanbat National University, Daejeon, South KoreaDepartment of Applied AI, Seoul National University of Science and Technology, Seoul, South KoreaGfarm Alliance Agricultural Company Ltd., Sejong, South KoreaDepartment of Computer Engineering, Hanbat National University, Daejeon, South KoreaSow estrus detection is one of the most critical tasks for improving the production performance of pig farms. However, accurately determining the onset of estrus is challenging because it is time consuming to check each sow and their performance, particularly during specific working hours. Moreover, estrus determination criteria are not standardized, as managers rely on their individual experiences. In this study, we proposed a method for predicting sow estrus using deep learning techniques. To detect sows and classify their postures, we used a lightweight deep-learning-based object detection model, You Only Look Once version 5 (YOLOv5). We trained one of the prediction models, Bidirectional Long Short-Term Memory (Bi-LSTM), which is a supervised learning model, using the time series data composed of a combination of each posture and holding time. By setting the ground truth as data from 24 h before the manager’s estrus determination, we achieved an estrus prediction accuracy of 86 %. This study demonstrates the potential of using closed-circuit television (CCTV) footage to predict sow estrus, and the proposed method can contribute to reducing the labor required for sow estrus checks.https://ieeexplore.ieee.org/document/10411845/Artificial inseminationdeep learningimage recognitionsow estrus predictionsow posture detection |
| spellingShingle | Sookeun Song Taegeun Kang Kyungtae Lim Konmin Kim Hyunbean Yi Sow Posture Analysis and Estrus Prediction Using Closed-Circuit Television Cameras IEEE Access Artificial insemination deep learning image recognition sow estrus prediction sow posture detection |
| title | Sow Posture Analysis and Estrus Prediction Using Closed-Circuit Television Cameras |
| title_full | Sow Posture Analysis and Estrus Prediction Using Closed-Circuit Television Cameras |
| title_fullStr | Sow Posture Analysis and Estrus Prediction Using Closed-Circuit Television Cameras |
| title_full_unstemmed | Sow Posture Analysis and Estrus Prediction Using Closed-Circuit Television Cameras |
| title_short | Sow Posture Analysis and Estrus Prediction Using Closed-Circuit Television Cameras |
| title_sort | sow posture analysis and estrus prediction using closed circuit television cameras |
| topic | Artificial insemination deep learning image recognition sow estrus prediction sow posture detection |
| url | https://ieeexplore.ieee.org/document/10411845/ |
| work_keys_str_mv | AT sookeunsong sowpostureanalysisandestruspredictionusingclosedcircuittelevisioncameras AT taegeunkang sowpostureanalysisandestruspredictionusingclosedcircuittelevisioncameras AT kyungtaelim sowpostureanalysisandestruspredictionusingclosedcircuittelevisioncameras AT konminkim sowpostureanalysisandestruspredictionusingclosedcircuittelevisioncameras AT hyunbeanyi sowpostureanalysisandestruspredictionusingclosedcircuittelevisioncameras |