EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Health Status Recognition of Yellow-Feathered Broilers in Floor-Rearing Environments via Whole-Body and Comb Feature Fusion

Jialei Xue, Tian Hua iD, Hongliang Guan, Hao Bai, Guobin Chang iD, Bin Li iD

Animals · 17.08.2026 · 16 (16) · 2559

DOI: 10.3390/ani16162559 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 17.08.2026. Verfasst von Jialei Xue und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Information and Artificial Intelligence, Yangzhou University, Yangzhou 225009, China. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Jiangsu agricultural science and technology innovation fund, CARS, Changzhou Modern Agriculture Science and Technology Innovation Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In commercial floor-rearing environments for yellow-feathered broilers, visual screening of broilers with observable health-related abnormalities is challenged by low illumination, individual occlusion, and the limited use of local comb information. This study proposes a two-stage global–local framework for yellow-feathered broilers. Images were collected from one commercial floor-rearing farm; after screening, 1463 images were used for key-region localization, and 2031 samples were constructed for health-status recognition. Samples were labeled as Healthy or Unhealthy by expert consensus according to observable phenotypic characteristics, rather than veterinary-confirmed disease diagnoses. First, a Dual-Target YOLO (DT-YOLO) model localized whole-body and comb regions. Second, a Transformer network integrated features from paired or single available inputs for classification. DT-YOLO achieved a mean Average Precision (mAP) of 97.56% at the 0.5 IoU threshold. For paired whole-body–comb inputs, the proposed classification model achieved an Accuracy of 97.11%, Macro-Precision of 97.38%, Macro-Recall of 96.58%, and Macro-F1 of 96.95%. Under the mixed-input condition, the model maintained an Accuracy of 96.06% and a Macro-F1 of 96.02%. These findings indicate that combining whole-body and comb information can support visual screening of unhealthy broilers under the single-farm floor-rearing conditions represented in the current dataset. Its applicability to other farms, breeds, and management conditions requires independent external validation.

Schlagwörter

Stichwörter der Autor:innen

broiler health monitoringcomputer visiondeep learningfeature fusionfloor-rearing systemtransformeryellow-feathered broiler

Autor:innen und Institutionen

  • College of Information and Artificial Intelligence, Yangzhou University, Yangzhou 225009, China.
  • College of Animal Science and Technology, Yangzhou University, Yangzhou 225009, China.
  • Joint International Research Laboratory of Agriculture and Agri-Product Safety, The Ministry of Education of China, Institutes of Agricultural Science and Technology Development, Yangzhou University, Yangzhou 225009, Ch…

ORCID-Profile: Tian Hua, Guobin Chang, Bin Li

Förderung

  • the Jiangsu agricultural science and technology innovation fund
  • CARS
  • Changzhou Modern Agriculture Science and Technology Innovation Center

Zitieren

APA

Xue, J., Hua, T., Guan, H., Bai, H., Chang, G., & Li, B. (2026). Health Status Recognition of Yellow-Feathered Broilers in Floor-Rearing Environments via Whole-Body and Comb Feature Fusion. Animals, 16(16), 2559. https://doi.org/10.3390/ani16162559

Vancouver

Xue J, Hua T, Guan H, Bai H, Chang G, Li B. Health Status Recognition of Yellow-Feathered Broilers in Floor-Rearing Environments via Whole-Body and Comb Feature Fusion. Animals. 2026;16(16):2559. doi:10.3390/ani16162559

BibTeX
@article{Xue2026,
  author = {Xue, Jialei and Hua, Tian and Guan, Hongliang and Bai, Hao and Chang, Guobin and Li, Bin},
  title = {Health Status Recognition of Yellow-Feathered Broilers in Floor-Rearing Environments via Whole-Body and Comb Feature Fusion},
  journal = {Animals},
  year = {2026},
  volume = {16},
  number = {16},
  pages = {2559},
  doi = {10.3390/ani16162559}
}
Kostenlos starten →