EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Video-Based Automated Lameness Detection for Dairy Cows

Kamil Szyc iD, Marta Hebda, Kamil Dembiński, Michał Zdunek, Olgierd Unold iD

Sensors · 2025

DOI: 10.3390/s25185771 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Kamil Szyc und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Wrocław University of Science and Technology, 50-370 Wrocław, Poland. Hauptthemen laut MEDLINE: Lameness, Animal, Video Recording, Cattle Diseases. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Polish Agency for Enterprise Development, Wroclaw University of Science and Technology and Polish Agency for Enterprise Development.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Nowadays, the treatment costs associated with lameness rank second among common diseases of cattle. The standard method for detecting lameness is visual observation of the herd by the farmer. However, these methods are time-consuming and labor-intensive and, due to the qualitative nature of the assessment, involve many discrepancies between different human assessors. This study aims to develop fully automated end-to-end methods for the video-based assessment of lameness in dairy cows using data science. For the study, 832 cows with varying degrees of lameness were recorded. The video recordings were then divided into individual frames, where deep learning detected a single cow and its characteristic anatomical points. A custom 7-point locomotion scoring system, inspired by the commonly used 5-level Sprecher (Zinpro) scale, was introduced and evaluated. This scale was used to assess lameness severity based on processed data, which were analyzed using an expert system, machine-learning methods, and a deep-learning approach. Our solution is based on the analysis of the spine curvature, head position, and distance between pairs of legs. The accuracy of detecting binary lameness (healthy vs. lame) through multiple locomotion features approaches expert-level performance, at 0.821 and 0.872, respectively.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lameness, AnimalVideo RecordingCattle DiseasesAnimalsCattleFemaleDeep LearningDairyingLocomotionMachine Learning

Stichwörter der Autor:innen

applied computing in agriculturedairy cattlelameness detectionvideo processingvisual locomotion scoring

Autor:innen und Institutionen

  • Department of Computer Engineering, Wrocław University of Science and Technology, 50-370 Wrocław, Poland.
  • Faculty of Geology, Geophysics, and Environmental Protection, AGH University of Krakow, 30-059 Kraków, Poland.
  • MEGAVET Bolków M. Nowicki & Ł.Oktawiec Spółka Cywilna, 59-420 Bolków, Poland.
  • 7M AMDG Sp. z o.o., 51-361 Wilczyce, Poland.

ORCID-Profile: Kamil Szyc, Olgierd Unold

Förderung

  • Polish Agency for Enterprise Development
  • Wroclaw University of Science and Technology and Polish Agency for Enterprise Development

Zitieren

APA

Szyc, K., Hebda, M., Dembiński, K., Zdunek, M., & Unold, O. (2025). Video-Based Automated Lameness Detection for Dairy Cows. Sensors. https://doi.org/10.3390/s25185771

Vancouver

Szyc K, Hebda M, Dembiński K, Zdunek M, Unold O. Video-Based Automated Lameness Detection for Dairy Cows. Sensors. 2025. doi:10.3390/s25185771

BibTeX
@article{Szyc2025,
  author = {Szyc, Kamil and Hebda, Marta and Dembiński, Kamil and Zdunek, Michał and Unold, Olgierd},
  title = {Video-Based Automated Lameness Detection for Dairy Cows},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25185771}
}
Kostenlos starten →