EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cattle Farming Activity Monitoring Using Advanced Deep Learning Approach

Muhammad Asim iD, Bareera Anam iD, Muhammad Nadeem Ali iD, Byung-Seo Kim iD

Sensors · 2026

DOI: 10.3390/s26030785 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Muhammad Asim und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Software & Communications Engineering, Hongik University, Sejong City 30016, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, National Research Foundation (NRF), Korea, Hongik University Innovation Support program Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Technological advancements have significantly improved cattle farming, particularly in sensor-based activity monitoring for health management, estrus detection, and overall herd supervision. However, such a sensor-based monitoring framework often illustrates several issues, such as high cost, animal discomfort, and susceptibility to false measurement. This study introduces a vision-based cattle activity monitoring approach deployed in a commercial Nestlé dairy farm, specifically one that is estrus-focused, where overhead cameras capture unconstrained herd behavior under variable lighting, occlusions, and crowding. A custom dataset of 2956 Images are collected and then annotated into four fine-grained behaviors—standing, lying, grazing, and estrus—enabling detailed analysis beyond coarse activity categories commonly used in prior livestock monitoring studies. Furthermore, computer vision-based deep learning algorithms are deployed on this dataset to classify the aforementioned classes. A comparative analysis of YOLOv8 and YOLOv9 is provided, which clearly illustrates that YOLOv8-L achieved a mAP of 91.11%, whereas YOLOv9-E achieved a mAP of 90.23%.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAnimalsCattleAlgorithmsFemaleDairyingDetection AlgorithmsAgriculture

Stichwörter der Autor:innen

activity monitoringanimal welfarecameradairy cowdeep learningvideo

Autor:innen und Institutionen

  • Department of Software & Communications Engineering, Hongik University, Sejong City 30016, Republic of Korea.

ORCID-Profile: Muhammad Asim, Bareera Anam, Muhammad Nadeem Ali, Byung-Seo Kim

Förderung

  • National Research Foundation of Korea
  • National Research Foundation (NRF), Korea
  • Hongik University Innovation Support program Fund

Zitieren

APA

Asim, M., Anam, B., Ali, M. N., & Kim, B. S. (2026). Cattle Farming Activity Monitoring Using Advanced Deep Learning Approach. Sensors. https://doi.org/10.3390/s26030785

Vancouver

Asim M, Anam B, Ali MN, Kim BS. Cattle Farming Activity Monitoring Using Advanced Deep Learning Approach. Sensors. 2026. doi:10.3390/s26030785

BibTeX
@article{Asim2026,
  author = {Asim, Muhammad and Anam, Bareera and Ali, Muhammad Nadeem and Kim, Byung-Seo},
  title = {Cattle Farming Activity Monitoring Using Advanced Deep Learning Approach},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26030785}
}
Kostenlos starten →