Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 37 min ago
Peer-reviewedCC BYAnimals : an open access journal from MDPI

Vision-Based Detection of Estrus-Related Interaction Behavior in Hanwoo Cattle Using Lightweight YOLO Models.

  • Usama Hanif1
  • Dae-Yeong Kang2
  • Mohammad Ismail1
  • Pirlepesov Daniyar Maratovich2
  • Seong-Hun Kim2
  • Hyeon-Tae Kim3
  1. 1Department of Bio-Systems Engineering, Gyeongsang National University, Jinju 52828, Republic of Korea.
  2. 2Department of Smart Farm, Gyeongsang National University, Jinju 52828, Republic of Korea.
  3. 3Department of Bio-Industrial Machinery Engineering, Institute of Smart Space Agriculture (ISSA), Gyeongsang National University, Jinju 52828, Republic of Korea.
Read full textPDFDOICite

Abstract

Timely estrus detection determines reproductive efficiency in Hanwoo cattle, yet visual observation is increasingly difficult as herd sizes grow and standing behavior becomes less consistently expressed. Fixed farm cameras offer a non-invasive alternative, but mounting, chin-resting and sniffing involve two overlapping animals and occur rarely, complicating automated detection. This study evaluated how annotation strategy, augmentation policy and detector choice affect detection of these cues. A surveillance dataset of 846 red-green-blue (RGB) frames, containing 200 estrus-interaction instances against 2180 posture instances, was recorded at a commercial farm. Three annotation strategies, partial bounding-box label (PBL), full single bounding-box label (FSBL) and full dual bounding-box label (FDBL), were combined with three augmentation stages and three lightweight detectors (YOLOv5n, YOLOv8n, YOLO11n), giving 27 configurations. Rare-class performance varied approximately twice as widely as overall performance and depended more on annotation and augmentation than on detector family. PBL maximized sensitivity (recall 0.718), FSBL maximized localization quality (average precision, AP50 0.798) and overall accuracy (mean average precision, mAP50 0.864), and FDBL preserved relational context (recall 0.700, AP50 0.775). Annotation and augmentation should be selected according to whether the purpose is screening candidate interactions or supporting expert confirmation. Detections represent a behavioral proxy, not physiological confirmation of estrus.

Related

  1. A lightweight privacy-aware federated vision transformer for tomato leaf disease classification
    Debangana Ram, Manasi Gyanchandani, Akhtar Rasool +1
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textPlant biologyCrossref
  2. Detection of Frustration-related Operant Behavior in Rats via Machine Learning Methods
    J. Wang, A. S. Babu, B. Nguyen +4
    bioRxivPreprintCC BYFull textZoology & animal behaviourbioRxiv
  3. MambaSeed: A lightweight Mamba-based hybrid vision network for tomato leaf disease recognition
    XueShen Wang, Heng Zhang, Yayong Chen +4
    PLOS OnePeer-reviewedCC BY 4.0Full textPlant biologyPLOS
  4. Lightweight frequency-aware hybrid vision transformer for fine-grained plant disease recognition
    Kun Li, Li Dong, Jing Qian +3
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Full textPlant biologyCrossrefPMC
  5. LTK-YOLO: Lightweight Keypoint Detection for Robotic Tea Bud Picking
    Xiaomei Yi, Zekai Zheng, Hao Liang +3
    Plants (Basel, Switzerland)Peer-reviewedCC BYFull textPlant biologyEurope PMC

Cite

BibTeXRIS
BibTeX
@article{hanif2026visionbased,
  title = {{Vision-Based Detection of Estrus-Related Interaction Behavior in Hanwoo Cattle Using Lightweight YOLO Models.}},
  author = {Usama Hanif and Dae-Yeong Kang and Mohammad Ismail and Pirlepesov Daniyar Maratovich and Seong-Hun Kim and Hyeon-Tae Kim},
  journal = {Animals : an open access journal from MDPI},
  year = {2026},
  month = sep,
  doi = {10.3390/ani16193054},
  url = {https://europepmc.org/article/MED/42883023},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Vision-Based Detection of Estrus-Related Interaction Behavior in Hanwoo Cattle Using Lightweight YOLO Models.
AU  - Usama Hanif
AU  - Dae-Yeong Kang
AU  - Mohammad Ismail
AU  - Pirlepesov Daniyar Maratovich
AU  - Seong-Hun Kim
AU  - Hyeon-Tae Kim
PY  - 2026
DA  - 2026/09/28
JO  - Animals : an open access journal from MDPI
DO  - 10.3390/ani16193054
UR  - https://europepmc.org/article/MED/42883023
AB  - Timely estrus detection determines reproductive efficiency in Hanwoo cattle, yet visual observation is increasingly difficult as herd sizes grow and standing behavior becomes less consistently expressed. Fixed farm cameras offer a non-invasive alternative, but mounting, chin-resting and sniffing involve two overlapping animals and occur rarely, complicating automated detection. This study evaluated how annotation strategy, augmentation policy and detector choice affect detection of these cues. A surveillance dataset of 846 red-green-blue (RGB) frames, containing 200 estrus-interaction instances against 2180 posture instances, was recorded at a commercial farm. Three annotation strategies, partial bounding-box label (PBL), full single bounding-box label (FSBL) and full dual bounding-box label (FDBL), were combined with three augmentation stages and three lightweight detectors (YOLOv5n, YOLOv8n, YOLO11n), giving 27 configurations. Rare-class performance varied approximately twice as widely as overall performance and depended more on annotation and augmentation than on detector family. PBL maximized sensitivity (recall 0.718), FSBL maximized localization quality (average precision, AP50 0.798) and overall accuracy (mean average precision, mAP50 0.864), and FDBL preserved relational context (recall 0.700, AP50 0.775). Annotation and augmentation should be selected according to whether the purpose is screening candidate interactions or supporting expert confirmation. Detections represent a behavioral proxy, not physiological confirmation of estrus.
SN  - 2076-2615
ER  -