Deep Learning-Based Automated Approach for Determination of Pig Carcass Traits
Animals · 21.08.2024 · 14 (16) · 2421
DOI: 10.3390/ani14162421 ↗Kurz gefasst
Fachartikel in der Zeitschrift Animals, online erschienen am 21.08.2024. Verfasst von Jiacheng Wei und 7 weiteren Autor:innen. Beteiligte Einrichtung: National Key Laboratory of Swine Genetic Improvement and Germplasm Innovation, Jiangxi Agricultural University, Nanchang 330045, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhiyan Zhang, National Key Technology in Agricultural Project, major science and technology research and development projects of the Jiangxi Provincial Department of Science and Technology.
Abstract (Originalsprache)
Pig carcass traits are among the most economically significant characteristics and are crucial for genetic selection in breeding and enhancing the economic efficiency. Standardized and automated carcass phenotyping can greatly enhance the measurement efficiency and accuracy, thereby facilitating the selection and breeding of superior pig carcasses. In this study, we utilized phenotypic images and data from 3912 pigs to propose a deep learning-based approach for the automated determination of pig carcass phenotypic traits. Using the YOLOv8 algorithm, our carcass length determination model achieves an average accuracy of 99% on the test set. Additionally, our backfat segmentation model, YOLOV8n-seg, demonstrates robust segmentation performance, with a Mean IoU of 89.10. An analysis of the data distribution comparing manual and model-derived measurements revealed that differences in the carcass straight length are primarily concentrated between −2 cm and 4 cm, while differences in the carcass diagonal length are concentrated between −3 cm and 2 cm. To validate the method, we compared model measurements with manually obtained data, achieving coefficients of determination (R2) of 0.9164 for the carcass straight length, 0.9325 for the carcass diagonal length, and 0.7137 for the backfat thickness, indicating high reliability. Our findings provide valuable insights into automating carcass phenotype determination and grading in pig production.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- National Key Laboratory of Swine Genetic Improvement and Germplasm Innovation, Jiangxi Agricultural University, Nanchang 330045, China.
- College of Animal Science and National Engineering Research Center for Breeding Swine Industry, South China Agricultural University, Guangzhou 510642, China.
- Key Laboratory of Swine Genetics and Breeding, Ministry of Agriculture, Huazhong Agricultural University, Wuhan 430070, China.
Förderung
- Zhiyan Zhang
- National Key Technology in Agricultural Project
- major science and technology research and development projects of the Jiangxi Provincial Department of Science and Technology
Zitieren
APA
Wei, J., Wu, Y., Tang, X., Liu, J., Huang, Y., Wu, Z., Li, X., & Zhang, Z. (2024). Deep Learning-Based Automated Approach for Determination of Pig Carcass Traits. Animals, 14(16), 2421. https://doi.org/10.3390/ani14162421
Vancouver
Wei J, Wu Y, Tang X, Liu J, Huang Y, Wu Z, et al. Deep Learning-Based Automated Approach for Determination of Pig Carcass Traits. Animals. 2024;14(16):2421. doi:10.3390/ani14162421
BibTeX
@article{Wei2024,
author = {Wei, Jiacheng and Wu, Yan and Tang, Xi and Liu, Jinxiu and Huang, Yani and Wu, Zhenfang and Li, Xinyun and Zhang, Zhiyan},
title = {Deep Learning-Based Automated Approach for Determination of Pig Carcass Traits},
journal = {Animals},
year = {2024},
volume = {14},
number = {16},
pages = {2421},
doi = {10.3390/ani14162421}
}
EUVIMED