Multimodal Feature-Driven Deep Learning for the Prediction of Duck Body Dimensions and Weight

Wenbo Xiao, Qiannan Han, Gang Shu, Guiping Liang, Hongyan Zhang, Song Wang, Zhihao Xu, Weican Wan, Chuang Li, Guitao Jiang () and Yi Xiao ()
Additional contact information
Wenbo Xiao: College of Information and Technology, Hunan Agricultural University, Changsha 410128, China
Qiannan Han: College of Information and Technology, Hunan Agricultural University, Changsha 410128, China
Gang Shu: College of Animal Science and Technology, Sichuan Agricultural University, Chengdu 611130, China
Guiping Liang: College of Information and Technology, Hunan Agricultural University, Changsha 410128, China
Hongyan Zhang: College of Information and Technology, Hunan Agricultural University, Changsha 410128, China
Song Wang: College of Information and Technology, Hunan Agricultural University, Changsha 410128, China
Zhihao Xu: College of Information and Technology, Hunan Agricultural University, Changsha 410128, China
Weican Wan: Institute of Animal Sciences and Veterinary Medicine, Hunan Academy of Agricultural Sciences, Changsha 410131, China
Chuang Li: Institute of Animal Sciences and Veterinary Medicine, Hunan Academy of Agricultural Sciences, Changsha 410131, China
Guitao Jiang: Institute of Animal Sciences and Veterinary Medicine, Hunan Academy of Agricultural Sciences, Changsha 410131, China
Yi Xiao: College of Information and Technology, Hunan Agricultural University, Changsha 410128, China

Agriculture, 2025, vol. 15, issue 10, 1-19

Abstract: Accurate body dimension and weight measurements are critical for optimizing poultry management, health assessment, and economic efficiency. This study introduces an innovative deep learning-based model leveraging multimodal data—2D RGB images from different views, depth images, and 3D point clouds—for the non-invasive estimation of duck body dimensions and weight. A dataset of 1023 Linwu ducks, comprising over 5000 samples with diverse postures and conditions, was collected to support model training. The proposed method innovatively employs PointNet++ to extract key feature points from point clouds, extracts and computes corresponding 3D geometric features, and fuses them with multi-view convolutional 2D features. A Transformer encoder is then utilized to capture long-range dependencies and refine feature interactions, thereby enhancing prediction robustness. The model achieved a mean absolute percentage error (MAPE) of 5.73% and an R 2 of 0.953 across seven morphometric parameters describing body dimensions, and an MAPE of 10.49% with an R 2 of 0.952 for body weight, indicating robust and consistent predictive performance across both structural and mass-related phenotypes. Unlike conventional manual measurements, the proposed model enables high-precision estimation while eliminating the necessity for physical handling, thereby reducing animal stress and broadening its application scope. This study marks the first application of deep learning techniques to poultry body dimension and weight estimation, providing a valuable reference for the intelligent and precise management of the livestock industry with far-reaching practical significance.

Keywords: poultry; weight prediction; body dimension prediction; multimodal fusion; deep learning; point cloud (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/15/10/1021/pdf (application/pdf)
https://www.mdpi.com/2077-0472/15/10/1021/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:15:y:2025:i:10:p:1021-:d:1651827

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().