AI-powered visual E-monitoring system for cattle health and wealth
The livestock industry is experiencing a major transformation through the integration of artificial intelligence (AI) and advanced visual e-monitoring technologies. This study presents an AI-powered cattle health monitoring system that combines real-time computer vision, edge computing, and mobile a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525005313 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849405297548853248 |
|---|---|
| author | Aung Si Thu Moe Pyke Tin Masaru Aikawa Ikuo Kobayashi Thi Thi Zin |
| author_facet | Aung Si Thu Moe Pyke Tin Masaru Aikawa Ikuo Kobayashi Thi Thi Zin |
| author_sort | Aung Si Thu Moe |
| collection | DOAJ |
| description | The livestock industry is experiencing a major transformation through the integration of artificial intelligence (AI) and advanced visual e-monitoring technologies. This study presents an AI-powered cattle health monitoring system that combines real-time computer vision, edge computing, and mobile applications to enhance animal welfare and farm productivity. The system employs a multi-camera setup, comprising RGB, RGB-D, and ToF depth cameras, strategically deployed across four functional zones of a cattle barn: the milking parlor, return lane, feeding area, and resting space. Through integrated deep learning algorithms, the platform performs key health-related tasks, including ear-tag, body-based, and face-based cattle identification, body condition scoring (BCS), lameness detection, feeding time estimation, and real-time localization. A farm-side desktop application processes live video streams from 22 cameras using multiprocessing, maintaining an average latency of 0.62 s per frame per camera. Captured data are stored in a structured MySQL database and accessed via a RESTful API by a user-side mobile application developed using Flutter and Clean Architecture. Experimental evaluation under continuous 24-hour operation demonstrated the system’s stability and effectiveness in delivering actionable insights. Cattle identification achieved high accuracies: ear-tag 94.00 %, face-based 93.66 %, body-based 92.80 %, and body-color point cloud 99.55 %. The BCS prediction and lameness detection modules achieved average accuracies of 86.21 % and 88.88 %, respectively. Feedback from veterinarians and farm personnel during pilot testing confirmed its usability and practical relevance. While current limitations include computational demands and the need for improved model robustness, the proposed system establishes a scalable, non-invasive framework for intelligent livestock monitoring. It aligns with broader Green and Digital Transformation (GX and DX) initiatives toward sustainable smart farming practices. |
| format | Article |
| id | doaj-art-310dce62fc0a4f9ca8f6d2956cc33369 |
| institution | Kabale University |
| issn | 2772-3755 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-310dce62fc0a4f9ca8f6d2956cc333692025-08-20T03:36:42ZengElsevierSmart Agricultural Technology2772-37552025-12-011210130010.1016/j.atech.2025.101300AI-powered visual E-monitoring system for cattle health and wealthAung Si Thu Moe0Pyke Tin1Masaru Aikawa2Ikuo Kobayashi3Thi Thi Zin4Graduate School of Engineering, University of Miyazaki, 1-1 Gakuen kibanadai-Nishi, Miyazaki, 889-2192, JapanGraduate School of Engineering, University of Miyazaki, 1-1 Gakuen kibanadai-Nishi, Miyazaki, 889-2192, JapanOrganization for Learning and Student Development, University of Miyazaki, 1-1 Gakuen kibanadai-Nishi, Miyazaki, 889-2192, JapanSumiyoshi Livestock Science Station, Field Science Center, Faculty of Agriculture, University of Miyazaki, 1-1 Gakuen kibanadai-Nishi, Miyazaki, 889-2192, JapanGraduate School of Engineering, University of Miyazaki, 1-1 Gakuen kibanadai-Nishi, Miyazaki, 889-2192, Japan; Corresponding author.The livestock industry is experiencing a major transformation through the integration of artificial intelligence (AI) and advanced visual e-monitoring technologies. This study presents an AI-powered cattle health monitoring system that combines real-time computer vision, edge computing, and mobile applications to enhance animal welfare and farm productivity. The system employs a multi-camera setup, comprising RGB, RGB-D, and ToF depth cameras, strategically deployed across four functional zones of a cattle barn: the milking parlor, return lane, feeding area, and resting space. Through integrated deep learning algorithms, the platform performs key health-related tasks, including ear-tag, body-based, and face-based cattle identification, body condition scoring (BCS), lameness detection, feeding time estimation, and real-time localization. A farm-side desktop application processes live video streams from 22 cameras using multiprocessing, maintaining an average latency of 0.62 s per frame per camera. Captured data are stored in a structured MySQL database and accessed via a RESTful API by a user-side mobile application developed using Flutter and Clean Architecture. Experimental evaluation under continuous 24-hour operation demonstrated the system’s stability and effectiveness in delivering actionable insights. Cattle identification achieved high accuracies: ear-tag 94.00 %, face-based 93.66 %, body-based 92.80 %, and body-color point cloud 99.55 %. The BCS prediction and lameness detection modules achieved average accuracies of 86.21 % and 88.88 %, respectively. Feedback from veterinarians and farm personnel during pilot testing confirmed its usability and practical relevance. While current limitations include computational demands and the need for improved model robustness, the proposed system establishes a scalable, non-invasive framework for intelligent livestock monitoring. It aligns with broader Green and Digital Transformation (GX and DX) initiatives toward sustainable smart farming practices.http://www.sciencedirect.com/science/article/pii/S2772375525005313Cattle health monitoring systemMultiple camerasComputer visionAI application platform |
| spellingShingle | Aung Si Thu Moe Pyke Tin Masaru Aikawa Ikuo Kobayashi Thi Thi Zin AI-powered visual E-monitoring system for cattle health and wealth Smart Agricultural Technology Cattle health monitoring system Multiple cameras Computer vision AI application platform |
| title | AI-powered visual E-monitoring system for cattle health and wealth |
| title_full | AI-powered visual E-monitoring system for cattle health and wealth |
| title_fullStr | AI-powered visual E-monitoring system for cattle health and wealth |
| title_full_unstemmed | AI-powered visual E-monitoring system for cattle health and wealth |
| title_short | AI-powered visual E-monitoring system for cattle health and wealth |
| title_sort | ai powered visual e monitoring system for cattle health and wealth |
| topic | Cattle health monitoring system Multiple cameras Computer vision AI application platform |
| url | http://www.sciencedirect.com/science/article/pii/S2772375525005313 |
| work_keys_str_mv | AT aungsithumoe aipoweredvisualemonitoringsystemforcattlehealthandwealth AT pyketin aipoweredvisualemonitoringsystemforcattlehealthandwealth AT masaruaikawa aipoweredvisualemonitoringsystemforcattlehealthandwealth AT ikuokobayashi aipoweredvisualemonitoringsystemforcattlehealthandwealth AT thithizin aipoweredvisualemonitoringsystemforcattlehealthandwealth |