Using deep learning to accurately detect sow vulva size in a group pen with a single camera
Journal of Animal Science · 03.01.2024 · 102
DOI: 10.1093/jas/skad407 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Animal Science, online erschienen am 10.12.2023. Verfasst von Shen-Chang Chang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Southern Region Branch, Taiwan Livestock Research Institute, Ministry of Agriculture, Pingtung 91247, Taiwan. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
This paper presents a non-contact method for the detection of changes in sow vulva size in a group pen. The traditional approach to estrus detection is manually pressing down on the back of the sow to elicit standing responses; however, this method causes undue distress for sows not in estrus. When a sow is in estrus, the vulva is red and swollen due to the presence of endocrine. Monitoring changes in vulva size to detect estrus with as little impact on the sow as possible is the focus of this study. This is achieved using a single camera combined with a deep learning framework. Our approach comprises two steps: vulva detection and vulva size conversion. Images of sows of Yorkshire, Landrace, and Duroc breeds were collected in group housing, and the vulva was detected through artificial markers and the network architecture of YOLO v4. Based on the internal and external parameters of the camera, the detected size was converted into millimeters and the results of manual measurement (MM) and automatic calculation combined to calculate the size of the vulva. Analysis of the calculated size compared with MM indicates that the object recognition rate of the system exceeds 97.06%, with a size error of only + 1.70 to −4.47 mm and high-calculation efficiency (>2.8 frames/s). Directions for future research include the automatic detection of pig width.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Southern Region Branch, Taiwan Livestock Research Institute, Ministry of Agriculture, Pingtung 91247, Taiwan.
- Department of Animal Science, National Pingtung University of Science and Technology, Pingtung 91201, Taiwan.
- Bachelor of Program in Scientific Agriculture, National Pingtung University of Science and Technology, Pingtung 91201, Taiwan.
ORCID-Profile: Chia-Ying Chang
Zitieren
APA
Chang, S. C., Wu, X. R., Kuan, H. Y., Peng, S. Y., & Chang, C. Y. (2024). Using deep learning to accurately detect sow vulva size in a group pen with a single camera. Journal of Animal Science, 102. https://doi.org/10.1093/jas/skad407
Vancouver
Chang SC, Wu XR, Kuan HY, Peng SY, Chang CY. Using deep learning to accurately detect sow vulva size in a group pen with a single camera. Journal of Animal Science. 2024;102. doi:10.1093/jas/skad407
BibTeX
@article{Chang2024,
author = {Chang, Shen-Chang and Wu, Xin-Ru and Kuan, Hao-Yuan and Peng, Shao-Yu and Chang, Chia-Ying},
title = {Using deep learning to accurately detect sow vulva size in a group pen with a single camera},
journal = {Journal of Animal Science},
year = {2024},
volume = {102},
doi = {10.1093/jas/skad407}
}
EUVIMED