EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Benchmarking pig detection and tracking under diverse and challenging conditions

Jonathan Henrich, Christian Post, Maximilian Zilke, Parth Shiroya, Emma Chanut, Amir Mollazadeh Yamchi, Ramin Yahyapour, Thomas Kneib, Imke Traulsen

Computers and Electronics in Agriculture · 2026-02 · 241 · 111264

DOI: 10.1016/j.compag.2025.111264 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers and Electronics in Agriculture, 2026-02. Verfasst von Jonathan Henrich und 8 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 104 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Commission, Bundesministerium für Forschung, Technologie und Raumfahrt.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To ensure animal welfare and effective management in pig farming, monitoring individual behavior is a crucial prerequisite. While monitoring tasks have traditionally been carried out manually, advances in machine learning have made it possible to collect individualized information in an increasingly automated way. Central to these methods is the localization of animals across space (object detection) and time (multi-object tracking). Despite extensive research of these two tasks in pig farming, a systematic benchmarking study has not yet been conducted. In this work, we address this gap by curating two datasets: PigDetect for object detection and PigTrack for multi-object tracking. The datasets are based on diverse image and video material from realistic barn conditions, and include challenging scenarios such as occlusions or bad visibility. For object detection, we show that challenging training images improve detection performance beyond what is achievable with randomly sampled images alone. Comparing different approaches, we found that state-of-the-art models offer substantial improvements in detection quality over real-time alternatives. For multi-object tracking, we observed that SORT-based methods achieve superior detection performance compared to end-to-end trainable models. However, end-to-end models show better association performance, suggesting they could become strong alternatives in the future. We also investigate characteristic failure cases of end-to-end models, providing guidance for future improvements. The detection and tracking models trained on our datasets perform well in unseen pens, suggesting good generalization capabilities. This highlights the importance of high-quality training data. The datasets and research code are made publicly available to facilitate reproducibility, re-use and further development. • We developed a diverse and challenging benchmark dataset for pig detection and tracking. • We evaluated state-of-the-art methods, revealing their strengths, weaknesses, and areas for improvement. • Our models generalize well to unseen pens, highlighting the importance of high-quality training data. • Our benchmark datasets enable systematic method comparison and monitoring of capabilities of new methods.

Förderung

  • European Commission
  • Bundesministerium für Forschung, Technologie und Raumfahrt

Zitieren

APA

Henrich, J., Post, C., Zilke, M., Shiroya, P., Chanut, E., Yamchi, A. M., Yahyapour, R., Kneib, T., & Traulsen, I. (2026). Benchmarking pig detection and tracking under diverse and challenging conditions. Computers and Electronics in Agriculture, 241, 111264. https://doi.org/10.1016/j.compag.2025.111264

Vancouver

Henrich J, Post C, Zilke M, Shiroya P, Chanut E, Yamchi AM, et al. Benchmarking pig detection and tracking under diverse and challenging conditions. Computers and Electronics in Agriculture. 2026;241:111264. doi:10.1016/j.compag.2025.111264

BibTeX
@article{Henrich2026,
  author = {Henrich, Jonathan and Post, Christian and Zilke, Maximilian and Shiroya, Parth and Chanut, Emma and Yamchi, Amir Mollazadeh and Yahyapour, Ramin and Kneib, Thomas and Traulsen, Imke},
  title = {Benchmarking pig detection and tracking under diverse and challenging conditions},
  journal = {Computers and Electronics in Agriculture},
  year = {2026},
  volume = {241},
  pages = {111264},
  doi = {10.1016/j.compag.2025.111264}
}
Kostenlos starten →